WO2016180222A1

WO2016180222A1 - Abnormal call determination method and device

Info

Publication number: WO2016180222A1
Application number: PCT/CN2016/080163
Authority: WO
Inventors: 王进
Original assignee: 中兴通讯股份有限公司
Priority date: 2015-07-24
Filing date: 2016-04-25
Publication date: 2016-11-17
Also published as: CN106714178A

Abstract

Disclosed are an abnormal call determination method and device. The method comprises: when a mobile terminal is in a call state, acquiring voiceprint characteristic information about voice data of a call end corresponding to the mobile terminal; determining whether the voiceprint characteristic information matches a pre-stored voiceprint sample; and when the voiceprint characteristic information successfully matches the pre-stored voiceprint sample, determining that the current call is an abnormal call. The technical solution realizes that a current call is determined as an abnormal call by means of voiceprint characteristic information about a call end, so that when the ID of the call end constantly changes, the case where the call is abnormal can also be identified by means of the voiceprint characteristic information about the call end, thereby increasing the accuracy of abnormal call identification.

Description

Abnormal call determination method and device

Technical field

This document relates to, but is not limited to, the field of communications, and in particular, to an abnormal call determination method and apparatus.

Background technique

At present, mobile terminals mainly use abnormality calls based on caller ID (identification or identity) and user crowdsourcing. For example, if the ID of an incoming call (caller number, etc.) is registered as a tag such as "fraud", a corresponding prompt message is displayed during the call to prompt the user to be vigilant. However, the way to identify an abnormal call such as a fraudulent call in this way is based on the incoming call ID (or outgoing ID), and the abnormal call can quickly change the ID (changing the number or performing the number camouflage, etc.). ), which in turn leads to the inability to accurately identify abnormal calls using this identification method.

Summary of the invention

The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.

The embodiment of the invention provides an abnormal call determination method and device, which can accurately identify an abnormal call when the call end ID changes.

An abnormal call determination method provided by an embodiment of the present invention includes the following steps:

Acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state;

Determining whether the voiceprint feature information matches a pre-stored voiceprint sample;

When the voiceprint feature information is successfully matched with the pre-stored voiceprint sample, it is determined that the current call is an abnormal call.

Optionally, the step of acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state includes:

When the mobile terminal is in a call state, periodically collecting voice data of the call terminal;

Extracting voiceprint feature information corresponding to the voice data.

When the mobile terminal is in a call state, determining whether the contact identifier of the call terminal meets a preset condition;

And acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call terminal meets the preset condition.

Optionally, the preset condition includes: the contact identifier of the call end is a service number, the contact identifier is a special sequence number, or the mobile terminal cannot display a contact identifier of the call end.

Optionally, after the step of determining whether the voiceprint feature information matches a pre-stored voiceprint sample, the method further includes:

When the voiceprint feature information matches the pre-stored voiceprint sample is unsuccessful, and the current call ends, a markup interface including a markup option is displayed;

When receiving a markup instruction triggered by the user based on the markup option, marking the voiceprint feature information based on the markup instruction;

The pre-stored voiceprint sample is updated based on the recorded voiceprint feature information.

The embodiment of the present invention further provides an abnormal call determining apparatus, where the abnormal call determining apparatus includes:

An acquiring module, configured to acquire voiceprint feature information of voice data of a call end corresponding to the mobile terminal when the mobile terminal is in a call state;

Determining a module, configured to determine whether the voiceprint feature information matches a pre-stored voiceprint sample;

a determining module, configured to: when the voiceprint feature information is successfully matched with the pre-stored voiceprint sample, Determines that the current call is an abnormal call.

Optionally, the obtaining module includes:

The collecting unit is configured to periodically collect voice data of the calling terminal when the mobile terminal is in a call state;

The extracting unit is configured to extract the voiceprint feature information corresponding to the voice data.

Optionally, the obtaining module includes:

a determining unit, configured to determine, when the mobile terminal is in a call state, whether the contact identifier of the calling terminal meets a preset condition;

And an acquiring unit, configured to acquire voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call terminal meets a preset condition.

Optionally, the abnormal call determining apparatus further includes:

a display module, configured to display a markup interface including a markup option when the voiceprint feature information is unsuccessful in matching the pre-stored voiceprint sample, and the current call ends;

a marking module, configured to perform a marking operation on the voiceprint feature information based on the marking instruction upon receiving a marking instruction triggered by the user based on the marking option;

The update module is configured to update the pre-stored voiceprint sample based on the marked voiceprint feature information.

In the embodiment of the present invention, when the mobile terminal is in a call state, the voiceprint feature information of the voice data corresponding to the call end of the mobile terminal is obtained, and then when the acquired voiceprint feature information and the pre-stored voiceprint sample are successfully matched, the current determination is performed. The call is an abnormal call; the voice call characteristic information of the call end is used to determine that the current call is an abnormal call, so that when the call end ID is constantly changing, the voice call feature information can also identify that the call is abnormal, and the abnormal call recognition is improved. accuracy.

Other aspects will be apparent upon reading and understanding the drawings and detailed description.

BRIEF abstract

1 is a schematic flow chart of a first embodiment of an abnormal call determination method according to the present invention;

2 is a schematic flowchart of a refinement of a first embodiment of a step of acquiring voiceprint feature information according to the present invention;

3 is a schematic flow chart of a second embodiment of the step of acquiring voiceprint feature information according to the present invention;

4 is a schematic flow chart of a second embodiment of an abnormal call determination method according to the present invention;

FIG. 5 is a schematic diagram of functional modules of a first embodiment of an abnormal call determining apparatus according to the present invention; FIG.

6 is a schematic diagram of a refinement function module of the first embodiment of the acquisition module of FIG. 5;

7 is a schematic diagram of a refinement function module of the second embodiment of the acquisition module of FIG. 5;

FIG. 8 is a schematic diagram of functional modules of a second embodiment of an abnormal call determining apparatus according to the present invention.

Embodiments of the invention

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the invention provides an abnormal call determination method.

1 is a schematic flowchart of a first embodiment of a method for determining an abnormal call according to the present invention. The execution body of the method may be a mobile terminal.

In this embodiment, the abnormal call determination method includes:

Step S10: Acquire voiceprint feature information of voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state;

Acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state, wherein the voice data of the call end is the downlink voice of the communication channel of the current call, and of course, obtaining more accurate voiceprint feature information The voice data can be sampled according to the preset sampling time to obtain voiceprint feature information.

Step S20, determining whether the voiceprint feature information matches a pre-stored voiceprint sample;

Comparing the obtained voiceprint feature information with the voiceprint samples pre-stored in the voiceprint sample library to determine whether the voiceprint feature information matches the pre-stored voiceprint sample, of course, according to the voiceprint feature information, pre-set reliability, and Pre-stored sounds matching the voiceprint feature information in the voiceprint sample library by preset thresholds, etc. The sample of the embossing pattern, when the at least one pre-stored voiceprint sample is found, the voiceprint feature information is successfully matched with the pre-stored voiceprint sample.

Step S30, determining that the current call is an abnormal call when the voiceprint feature information is successfully matched with the pre-stored voiceprint sample. The pre-stored voiceprint sample is a voiceprint sample of an abnormal call.

When the voiceprint feature information matches the pre-stored voiceprint sample, that is, if at least one pre-stored voiceprint sample in the voiceprint sample library is the same or similar to the voiceprint feature information, it is determined that the current call is an abnormal call. Of course, you can continue to judge or determine the type of abnormal call, such as harassing calls, sales calls, or fraudulent calls, and output corresponding prompt information according to the corresponding call type; or you can directly output prompts when determining that the current call is abnormal. The information includes: a label, an instruction for controlling the vibration of the mobile terminal, a voice, a voice, and/or a video, and the prompting information is sent to remind the user that the current call is an abnormal call.

In this embodiment, when the mobile terminal is in a call state, the voiceprint feature information of the voice data corresponding to the call end of the mobile terminal is obtained, and then the current call is determined when the acquired voiceprint feature information and the pre-stored voiceprint sample are successfully matched. It is an abnormal call; it realizes that the current call is an abnormal call through the voiceprint feature information of the call end, so that when the call end ID is constantly changing, the voice call feature information can also identify that the call has an abnormality, thereby improving the accuracy of the abnormal call recognition. Sex, which in turn can reduce unnecessary losses for users.

Referring to FIG. 2, FIG. 2 is a schematic diagram showing the refinement process of the first embodiment of the step of acquiring voiceprint feature information according to the present invention.

A first embodiment of the refinement process of step S10 of the present invention is proposed based on the first embodiment. In this embodiment, step S10 includes:

Step S11, when the mobile terminal is in a call state, periodically collect voice data of the call end;

When the mobile terminal makes a call, the voice data of the call end is collected periodically, that is, the duration of the voice data collected periodically is a fixed duration.

Step S12, extracting voiceprint feature information corresponding to the voice data.

In this embodiment, the voice data may be sampled and extracted based on the preset sampling frequency. Corresponding voiceprint feature information, of course, in order to obtain more accurate voiceprint feature information, the voiceprint feature information obtained by sampling may be filtered or processed or processed accordingly.

In this embodiment, the voice data of the call end is periodically collected when the mobile terminal is in a call state, and the voiceprint feature information corresponding to the voice data is extracted, so that the obtained voiceprint feature information is more accurate, and thus When the voiceprint feature information matches the pre-stored voiceprint sample, it can more accurately determine whether the voiceprint feature information matches the pre-stored voiceprint sample, thereby further improving the accuracy of the abnormal call recognition.

Referring to FIG. 3, FIG. 3 is a schematic diagram of a refinement process of a second embodiment of the step of acquiring voiceprint feature information according to the present invention.

A second embodiment of the refinement process of step S10 of the present invention is proposed based on the first embodiment. In this embodiment, step S10 includes:

Step S13: When the mobile terminal is in a call state, determine whether the contact identifier of the call terminal meets a preset condition;

The preset condition includes: the contact identifier of the call end is the service number, the contact identifier of the call end is a special sequence number, or the mobile terminal cannot display the contact identifier of the call end. Of course, the preset condition may also include that the contact identifier of the call end is not The identifier in the mobile terminal address book or the contact, that is, the contact identifier of the call end does not match the number in the mobile terminal address book or the contact; the contact identifier of the call end is the service number, and the contact identifier of the call end is a special serial number. When the mobile terminal cannot display the contact identifier of the call end or the contact identifier of the call end is not the number in the mobile terminal address book or the contact, the call state of the mobile terminal satisfies the preset condition.

When the user makes a call through the mobile terminal, it is determined whether the contact identifier of the current call end meets the preset condition.

In step S14, when the contact identifier of the call end meets the preset condition, the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal is obtained.

When the contact identifier of the call end meets the preset condition, the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal is obtained, wherein the voice data of the call end is the downlink voice of the communication channel in the current call, and then may be according to the preset sampling time. Sampling voice data to obtain voiceprint features Information to obtain more accurate voiceprint feature information.

In this embodiment, when the mobile terminal is in a call state, and it is determined that the contact identifier of the call end meets the preset condition, the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal is obtained, and the contact at the call end is realized. The voiceprint feature information is obtained when the identifier meets the preset condition, and the voiceprint feature information is obtained when the caller identifier is the mobile terminal communication information or the contact number, thereby further improving the accuracy of the abnormal call recognition.

Referring to FIG. 4, FIG. 4 is a schematic flowchart diagram of a second embodiment of an abnormal call determination method according to the present invention.

The second embodiment of the abnormal call determination method of the present invention is proposed based on the foregoing embodiment. In this embodiment, the abnormal call determination method further includes:

Step S40, when the voiceprint feature information and the pre-stored voiceprint sample match unsuccessfully, and the current call ends, displaying a markup interface including a markup option;

When the voiceprint feature information is not successfully matched with the pre-stored voiceprint sample, and the current call ends, a markup interface including a markup option is displayed, prompting the user whether to select the phone number of the call end, and the user can click or touch the mark interface. The markup option triggers the markup instruction.

Step S50, when receiving a marking instruction triggered by the user based on the marking option, marking the voiceprint feature information based on the marking instruction;

Upon receiving the marking instruction triggered by the marking option of the marking interface, the mobile terminal performs the corresponding marking operation according to the marking instruction according to the voiceprint characteristic information of the calling end, for example, marking the voiceprint characteristic information as a fraudulent telephone, a sales call or a harassing telephone. Wait.

Step S60, updating the pre-stored voiceprint sample based on the marked voiceprint feature information.

The marked voiceprint feature information is added to the pre-stored voiceprint sample to update the voiceprint sample, and the index information corresponding to the marking operation and the index of the voiceprint feature information can be established to facilitate subsequent query matching.

In this embodiment, the marking option can be displayed on the call interface. For example, when the voiceprint feature information and the pre-stored voiceprint sample are unsuccessful, the marking option is displayed on the call interface or the marking option of the call interface is activated, and then the execution continues. In step S50 and step S60, the update of the pre-stored voiceprint sample is implemented.

In this embodiment, when the voiceprint feature information does not match the pre-stored voiceprint sample and the current call ends, the voiceprint feature information is marked, and the pre-stored voiceprint sample is updated based on the labeled voiceprint feature information. The update of the pre-stored voiceprint samples enriches the pre-stored voiceprint samples, further improving the accuracy of abnormal call recognition.

The embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the above method.

The embodiment of the invention further provides an abnormal call determination device.

Referring to FIG. 5, FIG. 5 is a schematic diagram of functional modules of a first embodiment of an abnormal call determining apparatus according to the present invention.

In this embodiment, the abnormal call determining apparatus includes:

The obtaining module 10 is configured to acquire voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state;

When the mobile terminal is in a call state, the acquiring module 10 acquires the voiceprint feature information of the voice data of the call terminal corresponding to the mobile terminal, where the voice data of the call end is the downlink voice of the communication channel of the current call, and of course, the acquisition module 10 obtains The voiceprint feature information is more accurate, and the voice data can be sampled according to the preset sampling time to obtain voiceprint feature information.

The determining module 20 is configured to determine whether the voiceprint feature information matches a pre-stored voiceprint sample; the pre-stored voiceprint sample is a voiceprint sample of an abnormal call;

The determining module 20 is configured to compare the acquired voiceprint feature information with the voiceprint samples pre-stored in the voiceprint sample library, and determine whether the voiceprint feature information matches the pre-stored voiceprint sample, and of course, according to the voiceprint feature information. Pre-set voiceprint samples matching the voiceprint feature information in the voiceprint sample library, pre-set reliability and preset thresholds, and sound tone feature information and pre-stored voice patterns when at least one pre-stored voiceprint sample is found This match was successful.

The determining module 30 is configured to determine that the current call is an abnormal call when the voiceprint feature information is successfully matched with the pre-stored voiceprint sample.

The determining module 30 is configured to set the voiceprint when the voiceprint feature information matches the pre-stored voiceprint sample. When at least one pre-stored voiceprint sample in the sample library is the same or similar to the voiceprint feature information, it is determined that the current call is an abnormal call. Of course, you can continue to judge or determine the type of abnormal call, such as harassing calls, sales calls, or fraudulent calls, and output corresponding prompt information according to the corresponding call type; or you can directly output prompts when determining that the current call is abnormal. The information includes: a label, an instruction for controlling the vibration of the mobile terminal, a voice, a voice, and/or a video, and the prompting information is sent to remind the user that the current call is an abnormal call.

In this embodiment, when the mobile terminal is in a call state, the obtaining module 10 is configured to acquire voiceprint feature information of the voice data corresponding to the call end of the mobile terminal, and the determining module 20 is configured to determine the acquired voiceprint feature information and the pre-stored sound. When the pattern matching is successful, the determining module 30 is configured to determine that the current call is an abnormal call, and the voiceprint feature information of the calling end is used to determine that the current call is an abnormal call, so that when the call end ID changes continuously, the voiceprint feature can also be adopted. The information identifies that the call is abnormal, improves the accuracy of the abnormal call recognition, and thus can reduce unnecessary loss of the user.

Referring to FIG. 6, FIG. 6 is a schematic diagram of a refinement function module of the first embodiment of the acquisition module of FIG. 5.

A first embodiment of the refinement function module of the acquisition module 10 of the present invention is provided based on the first embodiment. In this embodiment, the acquisition module 10 includes:

The collecting unit 21 is configured to periodically collect voice data of the calling terminal when the mobile terminal is in a call state;

The extracting unit 22 is configured to extract voiceprint feature information corresponding to the voice data.

In this embodiment, the extracting unit 12 is configured to extract the voiceprint feature information corresponding to the voice data by sampling the voice data based on the preset sampling frequency. Of course, in order to obtain more accurate voiceprint feature information, the voiceprint obtained by the sampling may be obtained. The feature information is subjected to corresponding calculation or processing such as filtering.

In this embodiment, when the mobile terminal is in a call state, the collecting unit 11 is configured to periodically collect the voice data of the calling end, and the extracting unit 12 is configured to extract the voiceprint feature information corresponding to the voice data, so that the obtained voiceprint is obtained. The feature information is more accurate, so that when determining whether the voiceprint feature information matches the pre-stored voiceprint sample, it is possible to more accurately determine whether the voiceprint feature information matches the pre-stored voiceprint sample, thereby further improving the abnormal call recognition. accuracy.

Referring to FIG. 7, FIG. 7 is a schematic diagram of a refinement function module of the second embodiment of the acquisition module of FIG. 5.

A second embodiment of the refinement function module of the acquisition module 10 of the present invention is proposed based on the first embodiment. In this embodiment, the acquisition module 10 includes:

The determining unit 13 is configured to determine, when the mobile terminal is in a call state, whether the contact identifier of the calling terminal meets a preset condition;

When the user makes a call through the mobile terminal, the determining unit 13 determines whether the contact identifier of the current calling terminal satisfies the preset condition.

The obtaining unit 14 is configured to acquire the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call terminal meets the preset condition.

The obtaining unit 14 is configured to obtain voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call end meets the preset condition, where the voice data of the call end is the downlink voice of the communication channel in the current call, and then The voice data may be sampled according to a preset sampling time to obtain voiceprint feature information to obtain more accurate voiceprint feature information.

In this embodiment, when the mobile terminal is in a call state, and the determining unit 13 is configured to determine that the contact identifier of the call end meets the preset condition, the obtaining unit 14 is configured to acquire the voiceprint feature of the voice data of the call end corresponding to the mobile terminal. The information is obtained by acquiring the voiceprint feature information when the contact identifier of the call end meets the preset condition, and avoids obtaining the voiceprint feature information when the call end identifier is the mobile terminal communication information or the contact number, thereby further improving the abnormal call. The accuracy of the identification.

Referring to FIG. 8, FIG. 8 is a schematic diagram of a functional module of a second embodiment of an abnormal call determining apparatus according to the present invention. Figure.

The second embodiment of the abnormal call determining apparatus of the present invention is proposed based on the above embodiment. In this embodiment, the abnormal call determining apparatus further includes:

The display module 40 is configured to display, when the voiceprint feature information is matched with the pre-stored voiceprint sample, an unsuccessful manner, and when the current call ends, display a mark interface including a mark option;

When the voiceprint feature information is not successfully matched with the pre-stored voiceprint sample and the current call ends, the display module 40 displays a markup interface including a markup option, prompting the user whether to select the phone number of the caller, and the user can click or touch the mark The markup option of the interface triggers the markup instruction.

The marking module 50 is configured to, when receiving a marking instruction triggered by the user based on the marking option, perform marking operation on the voiceprint feature information based on the marking instruction;

The marking module 50 is configured to perform a corresponding marking operation on the voiceprint feature information of the calling terminal according to the marking instruction when receiving the marking instruction triggered by the marking option of the marking interface, for example, marking the voiceprint feature information as fraudulent telephone, promotion Phone or harassing calls, etc.

The update module 60 is configured to update the pre-stored voiceprint samples based on the marked voiceprint feature information.

In this embodiment, when the voiceprint feature information does not match the pre-stored voiceprint sample and the current call ends, the marking module 50 is set to mark the voiceprint feature information, and the update module 60 is set to be based on the voiceprint feature after the marking. The information updates the pre-stored voiceprint samples, which realizes the update of the pre-stored voiceprint samples, enriches the pre-stored voiceprint samples, and further improves the accuracy of abnormal call recognition.

One of ordinary skill in the art will appreciate that all or a portion of the above steps may be performed by a program to instruct related hardware, such as a processor, which may be stored in a computer readable storage medium, such as a read only memory, disk or optical disk. Wait. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the above embodiment may be implemented in the form of hardware, for example, by an integrated circuit to implement its corresponding function, It can be implemented in the form of a software function module, for example, by a processor executing a program/instruction stored in a memory to implement its corresponding function. The invention is not limited to any specific form of combination of hardware and software.

The above is only an alternative embodiment of the present invention, and thus does not limit the scope of the invention, and the equivalent structure or equivalent process transformation made by using the specification and the drawings of the present invention, or directly or indirectly applied to other related technologies. The fields are all included in the scope of patent protection of the present invention.

Industrial applicability

The above technical solution enables an abnormal call to be recognized when the caller ID is constantly changing, and the accuracy of abnormal call recognition is improved.

Claims

An abnormal call determination method, the abnormal call determination method comprising the following steps:

Acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state;

Determining whether the voiceprint feature information matches a pre-stored voiceprint sample;

When the voiceprint feature information is successfully matched with the pre-stored voiceprint sample, it is determined that the current call is an abnormal call.
The abnormal call determination method according to claim 1, wherein the step of acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state comprises:

When the mobile terminal is in a call state, periodically collecting voice data of the call terminal;

Extracting voiceprint feature information corresponding to the voice data.
The abnormal call determination method according to claim 1, wherein the step of acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the mobile terminal is in a call state comprises:

When the mobile terminal is in a call state, determining whether the contact identifier of the call terminal meets a preset condition;

And acquiring the voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call terminal meets the preset condition.
The abnormal call determination method according to claim 3, wherein the preset condition comprises:

The contact identifier of the call end is a service number, the contact identifier is a special serial number, or the mobile terminal cannot display the contact identifier of the call end.
The abnormal call determination method according to any one of claims 1 to 4, further comprising:

After the step of determining whether the voiceprint feature information matches the pre-stored voiceprint sample, the matching of the voiceprint feature information with the pre-stored voiceprint sample is unsuccessful, and when the current call ends, displaying the flag option is displayed. Tag interface

When receiving a markup instruction triggered by the user based on the markup option, marking the voiceprint feature information based on the markup instruction;

The pre-stored voiceprint sample is updated based on the recorded voiceprint feature information.
An abnormal call determining device, the abnormal call determining device comprising:

An acquiring module, configured to acquire voiceprint feature information of voice data of a call end corresponding to the mobile terminal when the mobile terminal is in a call state;

Determining a module, configured to determine whether the voiceprint feature information matches a pre-stored voiceprint sample;

The determining module is configured to determine that the current call is an abnormal call when the voiceprint feature information is successfully matched with the pre-stored voiceprint sample.
The abnormal call determination apparatus according to claim 6, wherein the acquisition module comprises:

The collecting unit is configured to periodically collect voice data of the calling terminal when the mobile terminal is in a call state;

The extracting unit is configured to extract the voiceprint feature information corresponding to the voice data.
The abnormal call determination apparatus according to claim 6, wherein the acquisition module comprises:

a determining unit, configured to determine, when the mobile terminal is in a call state, whether the contact identifier of the calling terminal meets a preset condition;

And an acquiring unit, configured to acquire voiceprint feature information of the voice data of the call end corresponding to the mobile terminal when the contact identifier of the call terminal meets a preset condition.
The abnormal call determining apparatus according to claim 8, wherein said preset condition comprises:

The contact identifier of the call end is a service number, the contact identifier is a special serial number, or the mobile terminal cannot display the contact identifier of the call end.
The abnormal call determining device according to any one of claims 6 to 9, wherein the abnormal call determining device further comprises:

a display module, configured to display a markup interface including a markup option when the voiceprint feature information is unsuccessful in matching the pre-stored voiceprint sample, and the current call ends;

a marking module, configured to perform a marking operation on the voiceprint feature information based on the marking instruction upon receiving a marking instruction triggered by the user based on the marking option;

The update module is configured to update the pre-stored voiceprint sample based on the marked voiceprint feature information.