[go: up one dir, main page]

CN115766939A - Method and system for screening abnormal call access of voice platform - Google Patents

Method and system for screening abnormal call access of voice platform Download PDF

Info

Publication number
CN115766939A
CN115766939A CN202211456576.XA CN202211456576A CN115766939A CN 115766939 A CN115766939 A CN 115766939A CN 202211456576 A CN202211456576 A CN 202211456576A CN 115766939 A CN115766939 A CN 115766939A
Authority
CN
China
Prior art keywords
call
abnormal
voice
call request
access
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.)
Pending
Application number
CN202211456576.XA
Other languages
Chinese (zh)
Inventor
李晋源
王晓鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Information Center of Yunnan Power Grid Co Ltd
Original Assignee
Information Center of Yunnan Power Grid Co Ltd
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 Information Center of Yunnan Power Grid Co Ltd filed Critical Information Center of Yunnan Power Grid Co Ltd
Priority to CN202211456576.XA priority Critical patent/CN115766939A/en
Publication of CN115766939A publication Critical patent/CN115766939A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Telephonic Communication Services (AREA)

Abstract

The invention belongs to the technical field of voice communication, and particularly relates to a method and a system for screening abnormal access of voice platform communication. The method comprises the steps of receiving a call request instruction accessed by a voice initiating terminal, and acquiring corresponding abnormal access identification according to call request number information, wherein the abnormal access identification comprises the steps of performing abnormal identification on the call request instruction through a number static abnormal analysis model, or performing abnormal identification on a voice call after the call request instruction is connected through a dynamic connection abnormal identification model, and performing abnormal identification on the accessed call according to a preset abnormal access rule. The call request instruction and the voice call after being connected are respectively subjected to abnormity identification by combining the number static abnormity analysis model and the dynamic connection abnormity identification model, the access identification effect for call abnormity is high by a double identification mode, the accuracy for call abnormity access screening is high, and the processing efficiency for the voice platform communication service is improved even if the processing efficiency is not high.

Description

一种语音平台通话异常接入的筛选方法及系统A method and system for screening abnormal call access of a voice platform

技术领域technical field

本发明属于语音通话技术领域,具体涉及一种语音平台通话异常接入的筛选方法及系统。The invention belongs to the technical field of voice calls, and in particular relates to a screening method and system for abnormal call access on a voice platform.

背景技术Background technique

近年来,随着互联网技术以及通信技术的飞速发展,基于语音平台的通话功能在各个行业的应用越来越广泛,比如可实现多人同时通话,提高沟通效率,或者能推进基于AI技术的智能语音平台的应用和智能化扩展,使得语音平台在应用过程中需进行优化更新。In recent years, with the rapid development of Internet technology and communication technology, the call function based on the voice platform is more and more widely used in various industries. The application and intelligent expansion of the voice platform make the voice platform need to be optimized and updated during the application process.

在基于语音平台的多人或多终端进行通话接入时,参与通话过程的用户越多,语音平台转发的数据量越大,从而影响语音平台通话过程的通话质量和通话处理效率。而其中存在通话异常接入的情况,在不加以筛选的情况下,拨打次数频繁的通信业务将严重影响和延误语音平台针对语音接入的处理效率,对语音平台的通话接入造成极其恶劣的影响。When multiple people or terminals based on the voice platform perform call access, the more users participating in the call process, the greater the amount of data forwarded by the voice platform, which affects the call quality and call processing efficiency of the voice platform call process. However, there are cases of abnormal call access. Without screening, frequent communication services will seriously affect and delay the processing efficiency of the voice platform for voice access, causing extremely bad impact on the call access of the voice platform. Influence.

发明内容Contents of the invention

有鉴于此,本发明提供了一种语音平台通话异常接入的筛选方法及系统,通过结合号码静态异常分析模型和动态接通异常识别模型分别对通话请求指令和接通后的语音通话进行异常识别,能够解决语音平台在不加以筛选严重影响和延误语音平台针对语音接入的处理效率,对语音平台的通话接入造成极其恶劣的影响的问题。In view of this, the present invention provides a method and system for screening abnormal call access of a voice platform, by combining the static abnormal analysis model of the number and the dynamic abnormal connection identification model to respectively detect the abnormal call request instruction and the connected voice call. Identification can solve the problem that the voice platform will seriously affect and delay the voice access processing efficiency of the voice platform if it is not screened, and have an extremely bad impact on the call access of the voice platform.

本发明至少一个方案提供了一种语音平台通话异常接入的筛选方法,应用于语音平台,所述该方法包括:At least one solution of the present invention provides a method for screening abnormal call access of a voice platform, which is applied to a voice platform, and the method includes:

接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息;receiving a call request instruction accessed by a voice initiating terminal, wherein the call request instruction includes call request number information;

根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别;Obtain the corresponding abnormal access identification according to the call request number information, and the abnormal access identification includes abnormal identification of the call request instruction through the number static abnormal analysis model, or abnormal identification of the call through the dynamic connection abnormal identification model The voice call after the request command is connected is abnormally identified, wherein the number static abnormality analysis model is used to perform abnormal identification on the call request number information contained in the call request command according to the pre-stored abnormal number log data, and the dynamic connection abnormality identification The model is used to identify abnormal access to the call request command according to the audio data of the voice call;

按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。According to the preset abnormal access rules, abnormal identification is performed on the call after the voice initiation terminal corresponding to the call request instruction is connected.

可选的,所述语音平台通话异常接入的筛选方法还包括:Optionally, the screening method for abnormal call access of the voice platform further includes:

获取语音发起终端的历史基础信息和语音发起终端的历史通话信息;Obtain the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal;

根据所述语音发起终端的历史基础信息和所述语音发起终端的历史通话信息获取所述通话请求被标记的号码静态分析标签,以及所述通话请求指令对应的语音动态分析标签;Obtaining the number static analysis tag marked with the call request and the voice dynamic analysis tag corresponding to the call request instruction according to the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal;

根据所述号码静态分析标签和所述语音动态分析标签遍历预存异常号码日志数据,确定所述通话请求指令是否接入异常。According to the number static analysis tag and the voice dynamic analysis tag, traversing the pre-stored abnormal number log data to determine whether the call request instruction is abnormal.

可选的,所述语音平台通话异常接入的筛选方法还包括:Optionally, the screening method for abnormal call access of the voice platform further includes:

根据所述语音发起终端的历史基础信息和所述语音发起终端的历史通话信息获取所述通话请求指令对应的历史通话平均时长数据和历史通话频次数据;Obtain historical call average duration data and historical call frequency data corresponding to the call request instruction according to the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal;

根据所述历史通话平均时长数据和历史通话频次数据进行异常接入判断,确定所述通话请求指令对应的通话请求号码信息是否为异常号码。Perform abnormal access judgment according to the historical call average duration data and historical call frequency data, and determine whether the call request number information corresponding to the call request instruction is an abnormal number.

可选的,所述语音平台通话异常接入的筛选方法还包括:Optionally, the screening method for abnormal call access of the voice platform further includes:

获取参与接入所述语音平台的语音发起终端的通话请求,基于存储的通话日志中筛选分离预先存储的异常号码的通话请求;Obtain the call request of the voice originating terminal participating in the access to the voice platform, and screen and separate the call request of the pre-stored abnormal number based on the stored call log;

为筛选后的每个所述话请求选定至少一个所述语音平台的受话终端作为接入终端;Selecting at least one call-receiving terminal of the voice platform as an access terminal for each of the screened call requests;

基于所述受话终端的请求队列进行所述通话请求的时序排列,响应所述通话请求并接通所述语音发起终端进行音频通话;Carrying out the chronological arrangement of the call requests based on the request queue of the called terminal, responding to the call request and connecting the voice initiating terminal for an audio call;

根据预设的异常接入规则从音频通话日志中筛选出异常号码,其中,所述音频通话的时长小于预设通话阈值且在预设时间内呼叫次数大于呼叫阈值的语音发起终端的通话请求标记为异常接入,并将发起通话请求的号码标记为异常号码。According to the preset abnormal access rules, abnormal numbers are screened out from the audio call log, wherein the call request mark of the voice originating terminal whose duration of the audio call is less than the preset call threshold and the number of calls within the preset time is greater than the call threshold It is an abnormal access, and the number that initiates the call request is marked as an abnormal number.

可选的,按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别,具体包括:Optionally, according to the preset abnormal access rules, abnormal identification is performed on the call after the voice initiation terminal corresponding to the call request instruction is connected, specifically including:

将所述通话请求指令接入所述号码静态异常分析模型,获取号码异常接入值;和/或,Connecting the call request instruction to the number static abnormality analysis model to obtain an abnormal number access value; and/or,

将所述通话请求指令接入所述动态接通异常识别模型,获取通话异常评估值;Connecting the call request instruction to the dynamic connection abnormality identification model to obtain a call abnormality evaluation value;

根据所述号码异常接入值和/或所述通话异常评估值,获取异常接入识别结果,且当所述异常接入识别结果指示所述通话请求指令为异常时,对所述通话请求指令进行拦截,并将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。Obtain an abnormal access identification result according to the abnormal number access value and/or the abnormal call evaluation value, and when the abnormal access identification result indicates that the call request instruction is abnormal, execute the call request instruction Intercepting, and adding the call request number information corresponding to the call request instruction into the abnormal number log data.

可选的,所述语音平台通话异常接入的筛选方法还包括:Optionally, the screening method for abnormal call access of the voice platform further includes:

根据所述号码异常接入值判断所述通话请求指令是否异常;judging whether the call request instruction is abnormal according to the abnormal access value of the number;

若判断结果指示所述通话请求指令不异常,则为所述通话请求指令选定至少一个所述语音平台的受话终端作为接入终端,响应所述通话请求并接通所述语音发起终端进行音频通话,音频通话数据接入所述动态接通异常识别模型;If the judgment result indicates that the call request instruction is not abnormal, then select at least one called terminal of the voice platform as an access terminal for the call request instruction, respond to the call request and connect the voice initiating terminal to proceed Audio call, the audio call data is connected to the dynamic abnormal connection identification model;

若判断结果指示所述通话请求指令异常,则对所述通话请求指令进行拦截,并将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。If the judgment result indicates that the call request command is abnormal, intercept the call request command, and add the call request number information corresponding to the call request command to the abnormal number log data.

可选的,所述语音平台通话异常接入的筛选方法还包括:Optionally, the screening method for abnormal call access of the voice platform further includes:

根据所述通话异常评估值判断所述通话请求指令是否异常;judging whether the call request instruction is abnormal according to the evaluation value of the call abnormality;

若判断结果指示所述通话请求指令不异常,则将所述通话请求指令对应的通话请求号码信息加入白名单;否则,将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。If the judgment result indicates that the call request instruction is not abnormal, add the call request number information corresponding to the call request instruction to the white list; otherwise, add the call request number information corresponding to the call request instruction to the abnormal number log data.

可选的,当所述通话请求指令是通过电信运营商进行通话接入行为时,所述号码静态分析标签包括以下至少一项:Optionally, when the call request instruction is a call access behavior through a telecom operator, the number static analysis tag includes at least one of the following:

所述语音发起终端的进网试用标识、所述语音发起终端的IMEI信息、所述通话请求指令携带的通话请求号码信息、所述通话请求指令对应的筛选结果信息。The network access trial identifier of the voice initiating terminal, the IMEI information of the voice initiating terminal, the call request number information carried in the call request instruction, and the screening result information corresponding to the call request instruction.

可选的,当所述通话请求指令是通过电信运营商进行通话接入行为时,所述语音动态分析标签和所述历史通话平均时长数据和历史通话频次数据包括以下至少一项:Optionally, when the call request instruction is a call access behavior through a telecom operator, the voice dynamic analysis tag and the historical call average duration data and historical call frequency data include at least one of the following:

所述语音发起终端通过语音平台接入的通话序列、所述语音发起终端在预设时长内完成同一通话请求号码信息的拨号通话频次、所述语音发起终端单次语音通话的时长。The call sequence that the voice initiating terminal accesses through the voice platform, the frequency of dialing calls that the voice initiating terminal completes the same call request number information within a preset time period, and the duration of a single voice call of the voice initiating terminal.

本发明又一个方案,还提供了一种语音平台通话异常接入的筛选系统,用于执行上述语音平台通话异常接入的筛选方法,所述语音平台通话异常接入的筛选系统包括:Yet another solution of the present invention also provides a screening system for abnormal call access of the voice platform, which is used to perform the above screening method for abnormal call access of the voice platform. The screening system for abnormal call access of the voice platform includes:

指令接收模块,用于接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息;An instruction receiving module, configured to receive a call request instruction for voice initiation terminal access, wherein the call request instruction includes call request number information;

异常接入识别模块,用于根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别;The abnormal access identification module is used to obtain the corresponding abnormal access identification according to the call request number information, and the abnormal access identification includes abnormal identification of the call request instruction through the number static abnormal analysis model, or through the dynamic access The call exception identification model performs abnormal identification on the voice call after the call request instruction is connected, wherein the number static abnormal analysis model is used to perform abnormal identification on the call request number information contained in the call request instruction according to the pre-stored abnormal number log data , the dynamic abnormal connection identification model is used to identify the abnormal access of the call request instruction according to the audio data of the voice call;

通话异常识别模块,用于按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。The call abnormal identification module is used to identify abnormal calls after the voice initiation terminal corresponding to the call request instruction is connected according to the preset abnormal access rules.

本发明其中一方案还提供了一种计算机设备,包括存储器和处理器,所述存储器存储有计算机程序,所述处理器执行所述计算机程序时实现语音平台通话异常接入的筛选方法的步骤。One solution of the present invention also provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the method for screening abnormal call access of the voice platform are realized.

本发明还包括一种存储介质,存储有计算机程序,所述计算机程序被处理器执行时实现语音平台通话异常接入的筛选方法的步骤。The present invention also includes a storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method for screening abnormal call access of the voice platform are realized.

本发明提供的技术方案,具有如下有益效果:The technical scheme provided by the invention has the following beneficial effects:

本发明提供的技术方案在接收语音发起终端接入的通话请求指令后,根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。通过结合号码静态异常分析模型和动态接通异常识别模型分别对通话请求指令和接通后的语音通话进行异常识别,通过双重识别的方式针对通话异常接入识别效果高,针对通话异常接入筛选的精确度高,针对即便不具有有利于提高了语音平台通信业务的处理效率。The technical solution provided by the present invention obtains the corresponding abnormal access identification according to the information of the call request number after receiving the call request instruction of the voice-initiated terminal access, and the abnormal access identification includes identifying the abnormal access through the static abnormal analysis model of the number. Abnormal identification of the call request instruction, or abnormal identification of the voice call after the call request instruction is connected through the dynamic connection abnormal identification model, and the voice initiation terminal corresponding to the call request instruction according to the preset abnormal access rules The calls after access are identified abnormally. By combining the number static abnormality analysis model and the dynamic connection abnormality recognition model, the call request instruction and the connected voice call are respectively identified abnormally, and the double recognition method is highly effective in identifying abnormal call access, and screening for abnormal call access The accuracy is high, and it is beneficial to improve the processing efficiency of the communication service of the voice platform even if it does not.

附图说明Description of drawings

附图用来提供对本发明的进一步理解,并且构成说明书的一部分,与本发明的实施例一起用于解释本发明,并不构成对本发明的限制。在附图中:The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the description, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the attached picture:

图1为本发明一个实施例中一种语音平台通话异常接入的筛选方法的流程图。FIG. 1 is a flow chart of a method for screening abnormal call access of a voice platform in an embodiment of the present invention.

图2为本发明一个实施例中一种语音平台通话异常接入的筛选方法中标签分析确定是否接入异常的流程图。FIG. 2 is a flow chart of label analysis to determine whether access is abnormal in a method for screening abnormal call access of a voice platform in an embodiment of the present invention.

图3为本发明一个实施例中一种语音平台通话异常接入的筛选方法中通话时长及频次判断是否接入异常的流程图。Fig. 3 is a flow chart of judging whether the access is abnormal by the call duration and frequency in a method for screening abnormal call access of the voice platform in an embodiment of the present invention.

图4为本发明一个实施例中一种语音平台通话异常接入的筛选方法中基于异常接入规则筛选异常号码的流程图。FIG. 4 is a flow chart of screening abnormal numbers based on abnormal access rules in a method for screening abnormal call access on a voice platform in an embodiment of the present invention.

图5为本发明一个实施例中一种语音平台通话异常接入的筛选方法中受话终端进行音频通话处理的流程图。FIG. 5 is a flow chart of audio call processing by a called terminal in a method for screening abnormal call access on a voice platform in an embodiment of the present invention.

图6为本发明一个实施例中一种语音平台通话异常接入的筛选方法中双重处理的架构图。FIG. 6 is an architecture diagram of dual processing in a method for screening abnormal call access of a voice platform in an embodiment of the present invention.

图7为本发明一个实施例中一种语音平台通话异常接入的筛选系统的系统框图。Fig. 7 is a system block diagram of a screening system for abnormal call access of a voice platform in an embodiment of the present invention.

具体实施方式Detailed ways

为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

本发明提供的一种语音平台通话异常接入的筛选方法及系统,使用户不需要专注于逐一翻阅查找所需可接入语音通话对象,只需要通过语音方式调用所需可接入语音通话对象的标签功能,就能在语音终端设备快速显示出用户所需的目标图形,提高了目标可接入语音通话对象的显示效率,简化了所需可接入语音通话对象的显示流程。The present invention provides a method and system for screening abnormal call access of a voice platform, so that users do not need to focus on searching for the required accessible voice call objects one by one, but only need to call the required accessible voice call objects through voice The tag function can quickly display the target graphics required by the user on the voice terminal device, which improves the display efficiency of the target accessible voice call objects, and simplifies the display process of the required accessible voice call objects.

为了便于理解本申请的以下实施例,以下将参考附图对本申请的以下实施例进行详细描述。In order to facilitate understanding of the following embodiments of the present application, the following embodiments of the present application will be described in detail below with reference to the accompanying drawings.

在本申请的一些实施例中,所述终端设备可以是语音发起终端的电子设备,该电子设备包括但不局限于智能手机、个人电脑、移动电话、带有通话功能的虚拟现实设备和可穿戴设备等中的一种或几种的组合;其中,个人电脑包括但不局限于平板电脑、台式电脑、笔记本、上网本、掌上电脑等PC设备中的一种或几种的组合;在本申请的一些实施例中,“用户”可代指使用终端设备的人或物,例如使用终端设备的人或物,如机械臂等。In some embodiments of the present application, the terminal device may be an electronic device that initiates a voice terminal, and the electronic device includes but is not limited to a smart phone, a personal computer, a mobile phone, a virtual reality device with a call function, and a wearable One or a combination of several devices; among them, personal computers include but are not limited to tablet computers, desktop computers, notebooks, netbooks, palmtop computers, and other PC devices; one or a combination of several of them; In some embodiments, "user" may refer to a person or thing using a terminal device, for example, a person or thing using a terminal device, such as a robot arm.

图1是根据本申请一示例性实施例示出的一种语音平台通话异常接入的筛选方法的流程图。参阅图1所示,本申请的该实施例提供了一种语音平台通话异常接入的筛选方法,该方法应用于语音平台;该方法包括如下步骤:Fig. 1 is a flow chart of a method for screening abnormal call access on a voice platform according to an exemplary embodiment of the present application. Referring to shown in Fig. 1, this embodiment of the present application provides a kind of screening method of voice platform call abnormal access, and this method is applied to voice platform; This method comprises the following steps:

S1:接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息;S1: Receive a call request instruction accessed by a voice-initiating terminal, wherein the call request instruction includes call request number information;

S2:根据所述通话请求号码信息获取对应的异常接入识别;S2: Obtain a corresponding abnormal access identification according to the call request number information;

S3:按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。S3: According to the preset exception access rule, abnormal identification is performed on the call after the voice initiating terminal corresponding to the call request instruction is connected.

其中,在步骤S2中,在对异常接入识别时,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别。Wherein, in step S2, when identifying abnormal access, the abnormal access identification includes abnormal identification of the call request command through the number static abnormal analysis model, or abnormal identification of the call request command through the dynamic connection abnormal identification model. After the request command is connected, the voice call is abnormally identified.

其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别。Wherein, the number static abnormality analysis model is used to identify the abnormality of the call request number information included in the call request instruction according to the pre-stored abnormal number log data, and the dynamic connection abnormality recognition model is used to identify the call request according to the audio data of the voice call. Instructions for abnormal access identification.

在本实施例中,所述终端设备上安装有的每一种软件均在所述语音终端设备定义有用于进行交互进而触发相应软件操作的可接入语音通话对象。其中,软件可接入语音通话对象既包括有文字对象,也包括非文字对象。所述可接入语音通话对象包括用于进行交互进而触发软件操作的图形、图像和图形/图像与文字相结合中的一种或多种可接入语音通话对象。In this embodiment, each type of software installed on the terminal device defines an accessible voice call object for interaction and triggering corresponding software operations on the voice terminal device. Among them, the software can access voice communication objects include both text objects and non-text objects. The accessible voice communication object includes one or more types of accessible voice communication objects in graphic, image, and combination of graphic/image and text for interaction and triggering software operation.

在本实施例中,参见图2所示,所述语音平台通话异常接入的筛选方法还包括步骤S101-步骤S103:In this embodiment, as shown in FIG. 2 , the screening method for abnormal call access of the voice platform further includes step S101-step S103:

S101、获取语音发起终端的历史基础信息和语音发起终端的历史通话信息;S101. Obtain historical basic information of the voice initiating terminal and historical call information of the voice initiating terminal;

S102、根据所述语音发起终端的历史基础信息和所述语音发起终端的历史通话信息获取所述通话请求被标记的号码静态分析标签,以及所述通话请求指令对应的语音动态分析标签;S102. According to the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal, obtain the number static analysis tag marked with the call request, and the voice dynamic analysis tag corresponding to the call request instruction;

S103、根据所述号码静态分析标签和所述语音动态分析标签遍历预存异常号码日志数据,确定所述通话请求指令是否接入异常。S103. Traverse the pre-stored abnormal number log data according to the number static analysis tag and the voice dynamic analysis tag, and determine whether the call request instruction is abnormal.

在本实施例中,根据语音发起终端对应的历史基础信息和历史通话信息进行对当前通话请求指令标记号码静态分析标签,当接通时,根据通话内容进行标记语音动态分析标签,然后根据两种标签查询存储的异常号码日志数据,确定当前的通话请求指令是否存在接入异常行为,以判断从过异常接入行为或无异常接入行为的语音发起终端此次的接入是否正常。In this embodiment, according to the historical basic information and historical call information corresponding to the voice initiating terminal, the current call request instruction is marked with a static analysis tag for the number. The tag queries the stored abnormal number log data to determine whether there is an abnormal access behavior in the current call request command, so as to judge whether the access of the voice-initiating terminal with abnormal access behavior or no abnormal access behavior is normal this time.

在一些实施例中,参见图3所示,所述语音平台通话异常接入的筛选方法还包括:In some embodiments, as shown in FIG. 3 , the method for screening abnormal call access of the voice platform further includes:

步骤S201、根据所述语音发起终端的历史基础信息和所述语音发起终端的历史通话信息获取所述通话请求指令对应的历史通话平均时长数据和历史通话频次数据;Step S201, according to the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal, obtaining the historical call average duration data and historical call frequency data corresponding to the call request instruction;

步骤S202、根据所述历史通话平均时长数据和历史通话频次数据进行异常接入判断,确定所述通话请求指令对应的通话请求号码信息是否为异常号码。Step S202: Perform abnormal access judgment according to the historical call average duration data and historical call frequency data, and determine whether the call request number information corresponding to the call request instruction is an abnormal number.

在本实施例中,在进行异常接入判断时,还根据历史通话平均时长数据和历史通话频次数据进行判断,当在规定时间内历史通话频次数据或拨号频次超出预设阈值,以及历史通话平均时长数据小于预设通话时间阈值,进行判断为异常号码,可归类为频繁拨号的骚扰电话,该通话请求号码信息被标记为异常号码。In this embodiment, when judging abnormal access, the judgment is also made based on the historical call average duration data and historical call frequency data. If the duration data is less than the preset call time threshold, it is judged as an abnormal number, which can be classified as a frequently dialed nuisance call, and the call request number information is marked as an abnormal number.

在一些实施例中,参见图4所示,所述语音平台通话异常接入的筛选方法还包括:In some embodiments, as shown in FIG. 4, the method for screening abnormal call access of the voice platform further includes:

步骤S301、获取参与接入所述语音平台的语音发起终端的通话请求,基于存储的通话日志中筛选分离预先存储的异常号码的通话请求;Step S301. Obtain call requests from voice originating terminals participating in accessing the voice platform, and screen and separate pre-stored call requests of abnormal numbers based on stored call logs;

步骤S302、为筛选后的每个所述话请求选定至少一个所述语音平台的受话终端作为接入终端;Step S302, selecting at least one called terminal of the voice platform as an access terminal for each of the screened voice requests;

步骤S303、基于所述受话终端的请求队列进行所述通话请求的时序排列,响应所述通话请求并接通所述语音发起终端进行音频通话;Step S303, performing a sequence arrangement of the call requests based on the request queue of the called terminal, responding to the call request and connecting the voice initiating terminal for an audio call;

步骤S304、根据预设的异常接入规则从音频通话日志中筛选出异常号码,其中,所述音频通话的时长小于预设通话阈值且在预设时间内呼叫次数大于呼叫阈值的语音发起终端的通话请求标记为异常接入,并将发起通话请求的号码标记为异常号码。Step S304: Filter out the abnormal numbers from the audio call log according to the preset abnormal access rules, wherein the duration of the audio call is less than the preset call threshold and the number of calls within the preset time is greater than the call threshold of the voice originating terminal The call request is marked as an abnormal access, and the number that initiates the call request is marked as an abnormal number.

在一些实施例中,按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别,具体包括:In some embodiments, abnormal identification is performed on the call after the voice initiation terminal corresponding to the call request instruction is accessed according to the preset abnormal access rules, specifically including:

将所述通话请求指令接入所述号码静态异常分析模型,获取号码异常接入值;和/或将所述通话请求指令接入所述动态接通异常识别模型,获取通话异常评估值;Connecting the call request instruction to the number static abnormal analysis model to obtain a number abnormal access value; and/or connecting the call request instruction to the dynamic connection abnormal identification model to obtain a call abnormal evaluation value;

根据所述号码异常接入值和/或所述通话异常评估值,获取异常接入识别结果,且当所述异常接入识别结果指示所述通话请求指令为异常时,对所述通话请求指令进行拦截,并将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。Obtain an abnormal access identification result according to the abnormal number access value and/or the abnormal call evaluation value, and when the abnormal access identification result indicates that the call request instruction is abnormal, execute the call request instruction Intercepting, and adding the call request number information corresponding to the call request instruction into the abnormal number log data.

在一些实施例中,参见图5所示,所述语音平台通话异常接入的筛选方法还包括:In some embodiments, as shown in FIG. 5, the method for screening abnormal call access of the voice platform further includes:

步骤S401、根据所述号码异常接入值判断所述通话请求指令是否异常;Step S401, judging whether the call request instruction is abnormal according to the abnormal access value of the number;

步骤S402、若判断结果指示所述通话请求指令不异常,则为所述通话请求指令选定至少一个所述语音平台的受话终端作为接入终端,响应所述通话请求并接通所述语音发起终端进行音频通话,音频通话数据接入所述动态接通异常识别模型;Step S402, if the judgment result indicates that the call request command is not abnormal, select at least one called terminal of the voice platform as an access terminal for the call request command, respond to the call request and connect the voice Initiating the terminal to conduct an audio call, and accessing the audio call data to the dynamic abnormal connection identification model;

步骤S403、若判断结果指示所述通话请求指令异常,则对所述通话请求指令进行拦截,并将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。Step S403, if the judgment result indicates that the call request command is abnormal, intercept the call request command, and add the call request number information corresponding to the call request command to the abnormal number log data.

在一些实施例中,参见图1至图6所示,所述语音平台通话异常接入的筛选方法还包括:In some embodiments, referring to FIGS. 1 to 6 , the method for screening abnormal call access of the voice platform further includes:

根据所述通话异常评估值判断所述通话请求指令是否异常;judging whether the call request instruction is abnormal according to the evaluation value of the call abnormality;

若判断结果指示所述通话请求指令不异常,则将所述通话请求指令对应的通话请求号码信息加入白名单;否则,将所述通话请求指令对应的通话请求号码信息加入异常号码日志数据。If the judgment result indicates that the call request instruction is not abnormal, add the call request number information corresponding to the call request instruction to the white list; otherwise, add the call request number information corresponding to the call request instruction to the abnormal number log data.

当所述通话请求指令是通过电信运营商进行通话接入行为时,所述号码静态分析标签包括以下至少一项:所述语音发起终端的进网试用标识、所述语音发起终端的IMEI信息、所述通话请求指令携带的通话请求号码信息、所述通话请求指令对应的筛选结果信息。When the call request instruction is a call access behavior through a telecom operator, the number static analysis tag includes at least one of the following: the network access trial identifier of the voice initiating terminal, the IMEI information of the voice initiating terminal, The call request number information carried by the call request instruction, and the screening result information corresponding to the call request instruction.

当所述通话请求指令是通过电信运营商进行通话接入行为时,所述语音动态分析标签和所述历史通话平均时长数据和历史通话频次数据包括以下至少一项:所述语音发起终端通过语音平台接入的通话序列、所述语音发起终端在预设时长内完成同一通话请求号码信息的拨号通话频次、所述语音发起终端单次语音通话的时长。When the call request instruction is a call access behavior through a telecom operator, the voice dynamic analysis tag and the historical call average duration data and historical call frequency data include at least one of the following: The call sequence accessed by the platform, the frequency of dialing the same call request number information by the voice initiating terminal within a preset time period, and the duration of a single voice call by the voice initiating terminal.

在进行异常接入识别时,可以通过获取参与接入所述语音平台的语音发起终端的通话请求,基于存储的通话日志中筛选分离预先存储的异常号码的通话请求;然后,为筛选后的每个所述话请求选定至少一个所述语音平台的受话终端作为接入终端;基于所述受话终端的请求队列进行所述通话请求的时序排列,响应所述通话请求并接通所述语音发起终端进行音频通话;根据预设的异常接入规则从音频通话日志中筛选出异常号码,其中,所述音频通话的时长小于预设通话阈值且在预设时间内呼叫次数大于呼叫阈值的语音发起终端的通话请求标记为异常接入,并将发起通话请求的号码标记为异常号码。When performing abnormal access identification, the call request of the pre-stored abnormal number can be screened and separated based on the stored call log by acquiring the call request of the voice originating terminal participating in the access to the voice platform; then, for each screened call request Select at least one called terminal of the voice platform as an access terminal for each of the speech requests; perform the sequence arrangement of the call requests based on the request queue of the called terminal, respond to the call request and connect the The voice initiating terminal conducts an audio call; screens out abnormal numbers from the audio call log according to preset abnormal access rules, wherein the duration of the audio call is less than the preset call threshold and the number of calls within the preset time is greater than the call threshold The call request of the voice initiating terminal is marked as an abnormal access, and the number that initiates the call request is marked as an abnormal number.

其中,响应所述通话请求并接通所述语音发起终端进行音频通话,还包括环境噪声识别下的语音检测,具体为:获取所述音频通话时语音发起终端用户发出的语音信号;对所述的语音信号进行噪音识别,若所述的语音信号中包含语音噪声,则利用预设的噪声分类模型确定所述语音噪声对应的噪声类别;基于所述噪声类别,确定所述语音噪声对应的降噪处理策略,并利用所述降噪处理策略对所述语音噪声进行降噪处理。Wherein, responding to the call request and connecting the voice initiating terminal for an audio call also includes voice detection under environmental noise recognition, specifically: acquiring a voice signal sent by the voice initiating terminal user during the audio call; Perform noise recognition on the speech signal, if the speech signal contains speech noise, then use the preset noise classification model to determine the noise category corresponding to the speech noise; based on the noise category, determine the noise reduction corresponding to the speech noise Noise processing strategy, and use the noise reduction processing strategy to perform noise reduction processing on the speech noise.

在一些实施例中,针对异常接入,进行处理操作可以为:根据筛选筛选分离的异常号码的通话请求进行异常接入分类及呼叫转移,接入所述语音平台的接续处理终端;根据所述异常号码的属性信息以及常接入分类信息对异常接入的通话请求实施直接拦截、防骚扰语音提示、话务提示接通或业务回拨警告。In some embodiments, for abnormal access, the processing operation may be: perform abnormal access classification and call transfer according to the call request of the abnormal number separated by screening, and access the connection processing terminal of the voice platform; according to the Attribute information of abnormal numbers and regular access classification information implement direct interception of abnormal access call requests, anti-harassment voice prompts, traffic prompts to connect or business callback warnings.

如图7所示,在本发明的一个实施例中提供了一种语音平台通话异常接入的筛选系统包括指令接收模块100、异常接入识别模块200以及通话异常识别模块300。As shown in FIG. 7 , an embodiment of the present invention provides a screening system for abnormal call access of a voice platform, including an instruction receiving module 100 , an abnormal access identification module 200 and an abnormal call identification module 300 .

其中,所述指令接收模块100用于接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息。Wherein, the instruction receiving module 100 is configured to receive a call request instruction accessed by a voice initiating terminal, wherein the call request instruction includes call request number information.

所述异常接入识别模块200用于根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别。The abnormal access identification module 200 is used to obtain corresponding abnormal access identification according to the call request number information, and the abnormal access identification includes abnormal identification of the call request instruction through a static number abnormal analysis model, or through The dynamic connection abnormal identification model performs abnormal identification on the voice call after the call request instruction is connected, wherein the number static abnormal analysis model is used to analyze the call request number information contained in the call request instruction according to the pre-stored abnormal number log data Abnormal identification, the dynamic connection abnormal identification model is used to identify abnormal access to the call request instruction according to the audio data of the voice call.

所述通话异常识别模块300用于按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。The call abnormal identification module 300 is configured to identify abnormal calls after the voice initiation terminal corresponding to the call request instruction is accessed according to preset abnormal access rules.

其中,语音平台通话异常接入的筛选系统在执行时采用如前述的一种语音平台通话异常接入的筛选方法的步骤,因此,本实施例中对语音平台通话异常接入的筛选系统的运行过程不再详细介绍。Wherein, the screening system for the abnormal call access of the voice platform adopts the steps of the screening method for the abnormal call access of the voice platform as mentioned above during execution. Therefore, in this embodiment, the operation of the screening system for the abnormal call access of the voice platform The process will not be described in detail.

在本发明的一个实施例中还提供了一种计算机设备,包括存储器和处理器,存储器中存储有计算机程序,该处理器执行计算机程序时实现上述各方法实施例中的步骤,该方法包括如下步骤:In one embodiment of the present invention, a computer device is also provided, including a memory and a processor, and a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. The method includes the following step:

接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息;receiving a call request instruction accessed by a voice initiating terminal, wherein the call request instruction includes call request number information;

根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别;Obtain the corresponding abnormal access identification according to the call request number information, and the abnormal access identification includes abnormal identification of the call request instruction through the number static abnormal analysis model, or abnormal identification of the call through the dynamic connection abnormal identification model The voice call after the request command is connected is abnormally identified, wherein the number static abnormality analysis model is used to perform abnormal identification on the call request number information contained in the call request command according to the pre-stored abnormal number log data, and the dynamic connection abnormality identification The model is used to identify abnormal access to the call request command according to the audio data of the voice call;

按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。According to the preset abnormal access rules, abnormal identification is performed on the call after the voice initiation terminal corresponding to the call request instruction is connected.

在本发明的一个实施例中还提供了一种存储介质,其上存储有计算机程序,该计算机程序被处理器执行时实现上述各方法实施例中的步骤,该方法包括如下步骤:In one embodiment of the present invention, a storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented, and the method includes the following steps:

接收语音发起终端接入的通话请求指令,其中,所述通话请求指令包括通话请求号码信息;receiving a call request instruction accessed by a voice initiating terminal, wherein the call request instruction includes call request number information;

根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,其中,所述号码静态异常分析模型用于根据预存异常号码日志数据对通话请求指令包含的通话请求号码信息进行异常识别,所述动态接通异常识别模型用于根据语音通话的音频数据对通话请求指令进行异常接入识别;Obtain the corresponding abnormal access identification according to the call request number information, and the abnormal access identification includes abnormal identification of the call request instruction through the number static abnormal analysis model, or abnormal identification of the call through the dynamic connection abnormal identification model The voice call after the request instruction is connected is abnormally identified, wherein the number static abnormality analysis model is used to perform abnormal identification on the call request number information contained in the call request instruction according to the pre-stored abnormal number log data, and the dynamic connection abnormality identification The model is used to identify abnormal access to the call request command according to the audio data of the voice call;

按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。According to the preset abnormal access rules, abnormal identification is performed on the call after the voice initiation terminal corresponding to the call request instruction is connected.

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,所述的计算机程序可存储于一非易失性计算机可读取存储介质中,该计算机程序在执行时,可包括如上述各方法的实施例的流程。其中,本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和易失性存储器中的至少一种。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile memory and volatile memory.

另外,本申请的一部分可被应用为计算机程序产品,例如计算机程序指令,当其被计算机执行时,通过该计算机的操作,可以调用或提供根据本申请的方法和/或技术方案。而调用本申请的方法的程序指令,可能被存储在固定的或可移动的记录介质中,和/或通过广播或其他信号承载媒体中的数据流而被传输,和/或被存储在根据所述程序指令运行的计算机设备的工作存储器中。In addition, a part of the present application can be applied as a computer program product, such as a computer program instruction. When it is executed by a computer, the method and/or technical solution according to the present application can be invoked or provided through the operation of the computer. The program instructions for invoking the method of the present application may be stored in a fixed or removable recording medium, and/or transmitted through a data stream in a broadcast or other signal-carrying medium, and/or stored in a in the working memory of the computer device on which the program instructions described above are executed.

综上所述,本发明提供的技术方案在接收语音发起终端接入的通话请求指令后,根据所述通话请求号码信息获取对应的异常接入识别,所述异常接入识别包括通过号码静态异常分析模型对所述通话请求指令进行异常识别,或者通过动态接通异常识别模型对所述通话请求指令接通后的语音通话进行异常识别,按照预设的异常接入规则对所述通话请求指令对应的语音发起终端接入后的通话进行异常识别。通过结合号码静态异常分析模型和动态接通异常识别模型分别对通话请求指令和接通后的语音通话进行异常识别,通过双重识别的方式针对通话异常接入识别效果高,针对通话异常接入筛选的精确度高,针对即便不具有有利于提高了语音平台通信业务的处理效率。To sum up, the technical solution provided by the present invention obtains the corresponding abnormal access identification according to the information of the call request number after receiving the call request instruction of the voice-initiated terminal access, and the abnormal access identification includes static abnormality of the number. The analysis model performs abnormal identification on the call request instruction, or performs abnormal identification on the voice call after the call request instruction is connected through the dynamic connection abnormal identification model, and performs abnormal identification on the call request instruction according to the preset abnormal access rules. Abnormalities are identified for calls after the corresponding voice-initiating terminal is connected. By combining the number static abnormality analysis model and the dynamic connection abnormality recognition model, the call request instruction and the connected voice call are respectively identified abnormally, and the double identification method is highly effective in identifying abnormal call access, and screening for abnormal call access The accuracy is high, and it is beneficial to improve the processing efficiency of the communication service of the voice platform even if it does not.

以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.

Claims (10)

1. A method for screening abnormal call access of a voice platform is characterized by being applied to the voice platform and comprising the following steps:
receiving a call request instruction accessed by a voice initiating terminal, wherein the call request instruction comprises call request number information;
acquiring corresponding abnormal access identification according to the call request number information, wherein the abnormal access identification comprises abnormal identification of the call request instruction through a number static abnormal analysis model or abnormal identification of the voice call after the call request instruction is connected through a dynamic connection abnormal identification model, the number static abnormal analysis model is used for performing abnormal identification on the call request number information contained in the call request instruction according to pre-stored abnormal number log data, and the dynamic connection abnormal identification model is used for performing abnormal access identification on the call request instruction according to the audio data of the voice call;
and performing exception identification on the call after the voice initiating terminal corresponding to the call request instruction is accessed according to a preset exception access rule.
2. The method for screening abnormal access of voice platform call according to claim 1, wherein the method for screening abnormal access of voice platform call further comprises:
acquiring historical basic information of a voice initiating terminal and historical call information of the voice initiating terminal;
acquiring a number static analysis label marked by the call request and a voice dynamic analysis label corresponding to the call request instruction according to the historical basic information of the voice initiating terminal and the historical call information of the voice initiating terminal;
and determining whether the call request instruction is accessed abnormally according to the number static analysis label and the voice dynamic analysis label traversing pre-stored abnormal number log data.
3. The method for screening abnormal call access of a voice platform according to claim 2, wherein the method for screening abnormal call access of a voice platform further comprises:
acquiring historical call average duration data and historical call frequency data corresponding to the call request instruction according to historical basic information of the voice initiating terminal and historical call information of the voice initiating terminal;
and performing abnormal access judgment according to the historical call average duration data and the historical call frequency data, and determining whether the call request number information corresponding to the call request instruction is an abnormal number.
4. The method for screening abnormal access of voice platform call according to any one of claims 1-3, wherein the method for screening abnormal access of voice platform call further comprises:
acquiring a call request of a voice initiating terminal participating in accessing the voice platform, and screening and separating the call request of a pre-stored abnormal number based on a stored call log;
selecting at least one called terminal of the voice platform as an access terminal for each screened voice request;
performing time sequence arrangement of the call request based on a request queue of the called terminal, responding to the call request and connecting the voice initiating terminal to perform audio call;
and screening abnormal numbers from the audio call logs according to a preset abnormal access rule, wherein the call request of the voice initiating terminal of which the audio call duration is less than a preset call threshold and the call frequency is more than the call threshold within a preset time is marked as abnormal access, and the number of the call initiating request is marked as an abnormal number.
5. The method for screening abnormal access of voice platform calls according to claim 4, wherein the method for performing abnormal recognition on the call after the access of the voice initiating terminal corresponding to the call request instruction according to a preset abnormal access rule specifically comprises:
accessing the call request instruction to the number static anomaly analysis model to obtain a number anomaly access value; and/or the presence of a gas in the atmosphere,
accessing the call request instruction into the dynamic connection abnormity identification model to obtain a call abnormity evaluation value;
and acquiring an abnormal access identification result according to the number abnormal access value and/or the call abnormal evaluation value, intercepting the call request command when the abnormal access identification result indicates that the call request command is abnormal, and adding call request number information corresponding to the call request command into abnormal number log data.
6. The method for screening abnormal access of voice platform call according to claim 5, wherein the method for screening abnormal access of voice platform call further comprises:
judging whether the call request instruction is abnormal or not according to the number abnormal access value;
if the judgment result indicates that the call request instruction is not abnormal, selecting at least one receiving terminal of the voice platform as an access terminal for the call request instruction, responding to the call request and connecting the voice initiating terminal to carry out audio call, wherein audio call data are accessed into the dynamic connection abnormal recognition model;
if the judgment result indicates that the call request instruction is abnormal, intercepting the call request instruction, and adding call request number information corresponding to the call request instruction into abnormal number log data.
7. The method for screening abnormal access of voice platform call according to claim 6, wherein the method for screening abnormal access of voice platform call further comprises:
judging whether the call request instruction is abnormal or not according to the call abnormal evaluation value;
if the judgment result indicates that the call request instruction is not abnormal, adding call request number information corresponding to the call request instruction into a white list; and if not, adding the call request number information corresponding to the call request instruction into abnormal number log data.
8. The method for screening abnormal access of voice platform call according to claim 2, wherein when the call request instruction is a call access behavior through a telecom operator, the number static analysis tag includes at least one of the following items:
the network access trial identification of the voice initiating terminal, the IMEI information of the voice initiating terminal, the call request number information carried by the call request instruction and the screening result information corresponding to the call request instruction.
9. The method for screening abnormal call access of a voice platform according to claim 3, wherein when the call request command is a call access behavior performed by a telecom operator, the voice dynamic analysis tag and the historical average call duration data and the historical call frequency data include at least one of the following:
the voice initiating terminal completes the dialing conversation frequency of the same conversation request number information in a preset time length and the time length of single voice conversation of the voice initiating terminal through a conversation sequence accessed by a voice platform.
10. A screening system for abnormal access of voice platform call, which is used for executing the screening method for abnormal access of voice platform call of any one of claims 1 to 9, and the screening system for abnormal access of voice platform call comprises:
the instruction receiving module is used for receiving a call request instruction accessed by a voice initiating terminal, wherein the call request instruction comprises call request number information;
an abnormal access identification module, configured to obtain corresponding abnormal access identification according to the call request number information, where the abnormal access identification includes performing abnormal identification on the call request command through a number static abnormal analysis model, or performing abnormal identification on a voice call after the call request command is connected through a dynamic connection abnormal identification model, where the number static abnormal analysis model is configured to perform abnormal identification on call request number information included in the call request command according to pre-stored abnormal number log data, and the dynamic connection abnormal identification model is configured to perform abnormal access identification on the call request command according to audio data of the voice call;
and the call abnormity identification module is used for carrying out abnormity identification on the call after the voice initiating terminal corresponding to the call request instruction is accessed according to a preset abnormity access rule.
CN202211456576.XA 2022-11-21 2022-11-21 Method and system for screening abnormal call access of voice platform Pending CN115766939A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211456576.XA CN115766939A (en) 2022-11-21 2022-11-21 Method and system for screening abnormal call access of voice platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211456576.XA CN115766939A (en) 2022-11-21 2022-11-21 Method and system for screening abnormal call access of voice platform

Publications (1)

Publication Number Publication Date
CN115766939A true CN115766939A (en) 2023-03-07

Family

ID=85333668

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211456576.XA Pending CN115766939A (en) 2022-11-21 2022-11-21 Method and system for screening abnormal call access of voice platform

Country Status (1)

Country Link
CN (1) CN115766939A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119135430A (en) * 2024-10-09 2024-12-13 华润电力技术研究院有限公司 Business request scenario determination method, device, computer equipment, medium and product

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109639913A (en) * 2019-01-03 2019-04-16 中国联合网络通信集团有限公司 A kind of automatic speech harassing and wrecking number processing method, apparatus and system
CN111654866A (en) * 2020-05-29 2020-09-11 北京合力思腾科技股份有限公司 Method, device and computer storage medium for preventing mobile communication from fraud
CN114881711A (en) * 2022-07-11 2022-08-09 荣耀终端有限公司 Method for carrying out anomaly analysis based on request behavior and electronic equipment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109639913A (en) * 2019-01-03 2019-04-16 中国联合网络通信集团有限公司 A kind of automatic speech harassing and wrecking number processing method, apparatus and system
CN111654866A (en) * 2020-05-29 2020-09-11 北京合力思腾科技股份有限公司 Method, device and computer storage medium for preventing mobile communication from fraud
CN114881711A (en) * 2022-07-11 2022-08-09 荣耀终端有限公司 Method for carrying out anomaly analysis based on request behavior and electronic equipment

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119135430A (en) * 2024-10-09 2024-12-13 华润电力技术研究院有限公司 Business request scenario determination method, device, computer equipment, medium and product

Similar Documents

Publication Publication Date Title
US20140244249A1 (en) System and Method for Identification of Intent Segment(s) in Caller-Agent Conversations
CN103514075B (en) The method and apparatus that monitoring api function is called in the terminal
US9148506B2 (en) Method and system for processing application logs
US8180646B2 (en) System and method for implementing voice print-based priority call routing
WO2021189257A1 (en) Malicious process detection method and apparatus, electronic device, and storage medium
CN110519810B (en) Service relay switching method, terminal equipment, storage medium and device
US7992156B1 (en) Determining the address of a system call table to perform antivirus tasks in a computer
US10902147B2 (en) System and method for performing screen capture-based sensitive information protection within a call center environment
CN115766939A (en) Method and system for screening abnormal call access of voice platform
US9191513B1 (en) System and method for dynamic job allocation based on acoustic sentiments
US11321151B2 (en) Automated troubleshooting system and method for performing an action on a user device
JP7140358B2 (en) Reception work support system, reception work support method, and program
US8452841B2 (en) Text chat for at-risk customers
CN112069832A (en) Quality inspection method, quality inspection device and computer readable storage medium for voice call
US10341491B1 (en) Identifying unreported issues through customer service interactions and website analytics
US10924611B2 (en) Voice recognition system and call evaluation setting method
CN115052037B (en) Client detection method, device, storage medium and equipment
CN110245848A (en) The methods of risk assessment and device of program code
CN109040645B (en) Audio and video file transcription method and device, storage medium and server
CN107766232A (en) A kind of plug-in management method and device
CN116128081A (en) Mobile network service quality processing method, device, equipment and storage medium
CN107621903B (en) Double-touch-screen equipment and response control method thereof
CN114143770A (en) Service recommendation method and device based on different-network mobile phone numbers
CN109918222A (en) The dump analysis method and system of application program
CN110473522B (en) Method for accurately analyzing short voice fragments

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20230307