CN114222302A

CN114222302A - Calling method and device for abnormal call, electronic equipment and storage medium

Info

Publication number: CN114222302A
Application number: CN202111515690.0A
Authority: CN
Inventors: 张烜峰; 冯大航; 陈孝良
Original assignee: Beijing SoundAI Technology Co Ltd
Current assignee: Beijing SoundAI Technology Co Ltd
Priority date: 2021-12-13
Filing date: 2021-12-13
Publication date: 2022-03-22
Anticipated expiration: 2041-12-13
Also published as: CN114222302B

Abstract

The disclosure provides a calling method, a calling device, electronic equipment and a storage medium for abnormal calls, and belongs to the technical field of communication. In the embodiment of the disclosure, the identity information and the abnormal content information claimed by the initiator are extracted from the first call record of the abnormal call event of the target object, and then the event type of the abnormal call event is determined according to the abnormal content information, so that when the call dissuasion is subsequently performed on the target object, the voice robot is controlled to play the voice data containing the identity information and the event type.

Description

Calling method and device for abnormal call, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a method and an apparatus for calling an abnormal call, an electronic device, and a storage medium.

Background

In recent years, the rapid development of information technology brings many benefits to people, and also promotes new risks, such as telecommunication phishing. Dissuading the owner in the face of telecommunication phishing has become an important means of preventing such problems. The dissuading means dissuading the owner by making a call to the owner and making a call with the owner when the owner receives a suspected fraud call, thereby avoiding the risk of being fraudulently.

At present, in the process of dissuading from the host, the voice robot is generally used for dissuading from the conversation, and specifically, the voice robot is controlled to carry out the conversation with the host according to a fixed and single conversation template. Therefore, the voice robot is more mechanized during conversation, so that the owner is difficult to trust, and the conversation success rate is reduced.

Disclosure of Invention

The embodiment of the disclosure provides a calling method, a calling device, electronic equipment and a storage medium for abnormal calls, which can improve the trust of a user, and further improve the possibility of complete answering of the user, thereby ensuring the dissuading effect of calls. The technical scheme comprises the following steps.

In one aspect, a calling method for abnormal calls is provided, and the method includes:

extracting the identity information claimed by an initiator of the abnormal call event and the abnormal content information of the abnormal call event from a first call record of the abnormal call event of a target object;

determining the event type of the abnormal call event based on the abnormal content information, wherein the event type represents the abnormal type generated by the abnormal call event;

and initiating a call request to the target object, and controlling the voice robot to play target voice data in response to the target object accepting the call request, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal call event and the event type.

In some embodiments, extracting the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event of the target object includes:

based on an identity information base, extracting the identity information claimed by the initiator from the text information of the first call record, wherein the identity information base is used for storing various types of identity information;

and extracting abnormal content information of the abnormal call event from the text information of the first call record based on an abnormal content information base, wherein the abnormal content information base is used for storing various types of abnormal content information.

In some embodiments, the target voice data further comprises identity information of the target object;

before initiating a call request to the target object, the method further comprises:

and in response to the target object having the abnormal call event, determining the identity information of the target object.

In some embodiments, the target voice data also includes identity information of the object from which the call request originated.

In some embodiments, before initiating the call request to the target object, the method further comprises:

determining audio characteristic information of the target object based on the first call record of the abnormal call event, wherein the audio characteristic information is used for representing emotional characteristics and gender characteristics of the target object;

determining a target tone color matched with the audio characteristic information;

after initiating a call request to the target object, the method further comprises:

and responding to the target object to accept the call request, and controlling the voice robot to play the target voice data by adopting the target tone.

In some embodiments, after controlling the voice robot to play the target voice data, the method further comprises:

responding to the target object to interrupt the call, and performing audio recognition on a second call record of the voice robot and the target object to obtain text information of the second call record;

and performing semantic recognition on the text information of the second call record to obtain call interruption information of the second call record, wherein the call interruption information is used for indicating the reason of call interruption.

and responding to the abnormal interruption of the call, and after the target duration is separated, re-initiating the call request to the target object.

performing audio recognition on the voice robot and a second communication record of the target object to obtain text information of the second communication record;

and performing semantic recognition on the text information of the second call record to obtain call effect information of the second call record, wherein the call effect information is used for indicating the dissuading effect generated by the call.

In some embodiments, after obtaining the call effect information of the second call record, the method further includes:

and if the call effect information recorded by the second call is used for indicating that the call dissuasion fails, converting the voice robot into artificial voice.

and sending a short message prompt to the target object, wherein the short message prompt is used for prompting that the call is to be initiated to the target object.

based on the event type of the abnormal call event, acquiring a conversation template related to the event type, wherein the conversation template comprises a plurality of conversation contents related to the event type;

and controlling the voice robot to communicate with the target object based on the conversation template in response to the target object accepting the call request.

In one aspect, a calling device for abnormal calls is provided, and the device includes:

the extraction module is used for extracting the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event of the target object;

the determining module is used for determining the event type of the abnormal call event based on the abnormal content information, wherein the event type represents the abnormal type generated by the abnormal call event;

and the calling module is used for initiating a calling request to the target object, responding to the target object to accept the calling request, and controlling the voice robot to play target voice data, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal communication event and the event type.

In some embodiments, the extraction module is to:

the determining module is further configured to:

In some embodiments, the determining module is further configured to:

the calling module is further configured to:

In some embodiments, the apparatus further comprises an identification module to:

In some embodiments, the call module is further configured to:

In some embodiments, the apparatus further comprises a conversion module to:

In some embodiments, the apparatus further comprises a sending module to:

In some embodiments, the apparatus further comprises an acquisition module to:

the calling module is further configured to:

In one aspect, an electronic device is provided and includes one or more processors and one or more memories having at least one program code stored therein, the program code being loaded and executed by the one or more processors to implement the call method for abnormal calls.

In one aspect, a computer-readable storage medium having at least one program code stored therein is provided, the program code being loaded and executed by a processor to implement the call method for abnormal calls.

In one aspect, a computer program product is provided, and the computer program product includes computer program code stored in a computer readable storage medium, and a processor of an electronic device reads the computer program code from the computer readable storage medium, and executes the computer program code, so that the electronic device executes the above-mentioned call method for an abnormal call.

According to the technical scheme provided by the embodiment of the disclosure, the identity information and the abnormal content information claimed by the initiator are extracted from the first call record of the abnormal call event of the target object, and the event type of the abnormal call event is further determined according to the abnormal content information, so that when the target object is subsequently discouraging in call, the voice robot is controlled to play the voice data containing the identity information and the event type.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.

Fig. 1 is a schematic diagram of an implementation environment of a calling method for an abnormal call according to an embodiment of the present disclosure;

fig. 2 is a flowchart of a calling method for abnormal calls according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a calling method for abnormal calls according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a calling device for abnormal calls according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a server according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the present disclosure more apparent, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

The calling method aiming at the abnormal call related to the embodiment of the disclosure can be applied to the scenes of telecommunication network fraud. In some embodiments, when the owner receives a suspected fraud call, the calling method for abnormal calls provided by the embodiments of the disclosure can be adopted to initiate a call to the owner to communicate with the owner to dissuade the owner, thereby avoiding the risk of being fraudulently.

Fig. 1 is a schematic diagram of an implementation environment of a calling method for an abnormal call according to an embodiment of the present disclosure, and referring to fig. 1, the implementation environment includes: a first electronic device 101.

The first electronic device 101 may be provided as a server, and may specifically be a background server of a communication management platform, where the communication management platform is provided with functions of monitoring a call event and initiating a call to the outside. In the embodiment of the present disclosure, the first electronic device 101 is configured to extract, from a first call record of an abnormal call event of a target object, identity information claimed by an initiator of the abnormal call event and abnormal content information of the abnormal call event, determine an event type of the abnormal call event based on the abnormal content information, initiate a call request to the target object, and in response to the target object accepting the call request, control the voice robot to play target voice data including the identity information and the event type.

The server may be an independent physical server, a server cluster or a distributed file system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data and artificial intelligence platform, and the like. Optionally, the number of the servers may be more or less, and the embodiment of the disclosure does not limit this. Of course, the server may also include other functional servers in order to provide more comprehensive and diversified services.

In some embodiments, the implementation environment further comprises: a second electronic device 102.

The second electronic device 102 may be provided as a terminal, and particularly, a terminal operated by a manager (hereinafter, referred to as a management terminal). In some embodiments, the second electronic device 102 has associated therewith a communication management platform. In the embodiment of the present disclosure, the second electronic device 102 is configured to provide a visual interface of the communication management platform, so that the manager can view the analysis.

The first electronic device 101 and the second electronic device 102 may be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiment of the present disclosure.

In some embodiments, the terminal is at least one of a smartphone, a smartwatch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop portable computer, and the like. A terminal may refer to one of a plurality of terminals, and this embodiment is only illustrated by a terminal. Those skilled in the art will appreciate that the number of terminals described above may be greater or fewer.

Fig. 2 is a flowchart of a calling method for abnormal calls according to an embodiment of the present disclosure, which is executed by a first electronic device, with reference to fig. 2, and includes the following steps.

201. The first electronic equipment extracts the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event of the target object.

202. The first electronic equipment determines the event type of the abnormal call event based on the abnormal content information, wherein the event type represents the abnormal type of the abnormal call event.

203. The first electronic equipment initiates a call request to the target object, and controls the voice robot to play target voice data in response to the target object accepting the call request, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal call event and the event type.

In the embodiment of the present disclosure, the first electronic device may be provided as a server, and the second electronic device may be provided as a management terminal. The following describes a procedure of a call with a server as an execution agent. Fig. 3 is a flowchart of a calling method for abnormal calls provided by an embodiment of the present disclosure, and referring to fig. 3, the method includes the following steps.

301. The server extracts the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event of the target object.

The target object refers to a target user, and the target user may be any user. In the embodiment of the present disclosure, the target user is used to refer to a user who has occurred an abnormal call event, which refers to a call event that has a security problem, such as a fraudulent call. In some embodiments, the server is provided with functionality to monitor incoming call records for the user. In an alternative embodiment, if the server detects an abnormal incoming call of the target object, the server triggers and executes a step of extracting the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event, for example, the abnormal incoming call may be an outbound call.

The first call record is a call record of an abnormal call event, and is used for recording event information of the abnormal call event, such as call audio, mobile phone numbers of both parties of the call, call time, locations of both parties of the call, and the like. The identity information is used to indicate the identity claimed by the originator of the abnormal call event. In some embodiments, the identity information is in the form of an identity key, which is a key related to an identity, e.g., xx people. The initiator refers to an object that initiates the abnormal call event, and may also be referred to as a caller. Understandably, if the initiator is a fraudster, the purported identity of the initiator is the identity spoofed by the initiator. The abnormal content information is used for representing abnormal content generated in the abnormal call event. In some embodiments, the anomalous content information is in the form of risk keywords, which are keywords related to risk, e.g., winnings, money transfers, and the like. It should be understood that the risk mentioned in the embodiments of the present disclosure refers to a fraud risk. In some embodiments, the keyword is presented as a word, or a piece of text. In some embodiments, the number of identity keywords and risk keywords mentioned above is one or more, respectively.

In some embodiments, the server performs audio recognition on the first call record to obtain text information of the first call record; based on an identity information base, extracting the identity information claimed by the initiator from the text information of the first call record, wherein the identity information base is used for storing various types of identity information; and extracting abnormal content information of the abnormal call event from the text information of the first call record based on an abnormal content information base, wherein the abnormal content information base is used for storing various types of abnormal content information. In an alternative embodiment, the server performs the above-mentioned audio identification and information extraction process based on the call audio in the first call record, and accordingly, the text information of the first call record refers to the text information of the call audio of the first call record.

In an alternative embodiment, taking the form of identity information as an identity keyword, the identity information base is used for storing a plurality of identity keywords as an example, and the process of extracting the identity keyword by the server is as follows: performing word segmentation on the text information of the first call record to obtain a plurality of candidate keywords included in the text information, performing similarity matching based on the plurality of candidate keywords and a plurality of identity keywords included in the identity information base, selecting at least one candidate keyword matched with any one identity keyword included in the identity information base, and determining the selected at least one candidate keyword as the identity keyword claimed by the initiator.

In an optional embodiment, taking the abnormal content information as a risk keyword, taking the abnormal content information base as an example for storing a plurality of risk keywords, the process of extracting the risk keywords by the server is as follows: the method includes the steps of segmenting words of text information of the first call record to obtain a plurality of candidate keywords included in the text information, conducting similarity matching based on the candidate keywords and a plurality of risk keywords included in the abnormal content information base, selecting at least one candidate keyword matched with any one risk keyword included in the abnormal content information base, and determining the selected at least one candidate keyword as the risk keyword.

The similarity matching is a process of judging whether two keywords are matched or not based on the similarity between the two keywords. In some embodiments, the similarity is cosine similarity, for example, the cosine similarity of two keywords is calculated based on their feature vectors.

In the above embodiment, by setting the identity information base and the abnormal content information base, and based on the keywords included in the identity information base and the abnormal content information base, the matched keywords in the text information of the first call record are extracted, so that the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event are obtained, and the efficiency and the accuracy of extracting the identity information and the abnormal content information are improved.

In some embodiments, the server employs Natural Language Processing (NLP) technology to extract the identity information claimed by the originator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event. Among them, the natural language processing technology is a technology for studying a language problem of human interaction with a computer.

In some embodiments, the server extracts the identity keyword claimed by the initiator of the abnormal call event and the risk keyword from the first call record of the abnormal call event by using a keyword extraction technology provided in a natural language processing technology. In an alternative embodiment, the server employs a keyword extraction technique based on statistical features to perform the above-mentioned keyword extraction process. For example, the Term Frequency-inverse Document Frequency (TF-IDF) technology is a keyword extraction method that refers to the rarity of keywords, and thus, in the application scenario of telecommunication network fraud, the Term Frequency-inverse Document Frequency technology is adopted, and the accuracy of keyword extraction can be further improved. In another alternative embodiment, the server performs the above process of extracting keywords based on a deep learning technique. Among them, deep learning is an algorithm that gradually extracts higher-level features from an original input based on a plurality of processing layers including a complex structure or composed of multiple nonlinear transformations. For example, the above process of extracting the keywords is performed by using a Deep Neural Network, wherein the Deep Neural Network may be a Convolutional Neural Network (CNN) or a Deep Neural Network (Deep Neural Network, DNN) or other Neural networks.

In the embodiment, the process of extracting the keywords is executed by adopting a natural language processing technology, so that the efficiency and the accuracy of extracting the identity information and the abnormal content information are improved.

In other embodiments, the server further extracts other identity information of the initiator of the abnormal call event from the first call record of the abnormal call event, for example, a mobile phone number of the initiator, a location of the initiator, and the like. Therefore, the extracted information amount is increased, so that when the subsequent call is dissuaded, richer identity information of the initiator is referred to obtain the confidence of the user, and the call success rate of the user is improved.

302. The server determines the event type of the abnormal call event based on the abnormal content information, wherein the event type represents the abnormal type generated by the abnormal call event.

In the disclosed embodiment, the event type can also be understood as a fraud type. Illustratively, the event types include impersonation, impersonation of a charger customer service, impersonation of a campus loan, impersonation of a credit card loan, general type, hog killing, and so forth. The embodiment of the present disclosure does not limit the specific setting of the event type.

Two ways of determining the event type of the abnormal call event are provided below, and the corresponding procedures are shown in (302A) and (302B).

(302A) In some embodiments, the process of the server determining the event type of the abnormal call event is: the server adopts a natural language processing technology to carry out semantic recognition on the extracted abnormal content information to obtain the event type of the abnormal call event.

In some embodiments, the server performs semantic recognition by using the first semantic recognition model, and the corresponding process is as follows: and the server inputs the extracted abnormal content information into a first semantic recognition model, and performs semantic recognition on the extracted abnormal content information through the first semantic recognition model to obtain the event type of the abnormal call event.

Wherein, semantic recognition refers to recognizing the meaning of a word, a word or a text. The first semantic recognition model is used for recognizing the event type of the abnormal call event. In some embodiments, the first semantic identification model is a multi-classification model.

In some embodiments, the first semantic recognition model is derived based on deep neural network training. Taking the example that the first semantic recognition model is obtained based on deep neural network training, the first semantic recognition model comprises an input layer, a convolutional layer, a pooling layer, a full-link layer and an output layer. The input layer is used for inputting the abnormal content information acquired by the server into the first semantic recognition model and converting the input information into a digital matrix so that the first semantic recognition model can perform a subsequent operation process; the convolution layer is used for performing convolution operation on the matrix generated by the input layer, local features are extracted based on the result of the convolution operation, and the first semantic recognition model can comprise one or more convolution layers; the pooling layer is used for quantizing the feature extraction values obtained by the convolutional layer to obtain a matrix with a smaller dimension so as to further extract the features, and the first semantic recognition model can comprise one or more pooling layers; the full connection layer is used for integrating the extracted local features into complete features through a weight matrix and calculating the event type based on the complete features; the output layer is used for acquiring the event type output by the full connection layer and outputting the event type as the event type of the abnormal call event.

The first semantic recognition model adopted by the embodiment of the disclosure is a trained model. In some embodiments, the server obtains a plurality of abnormal content samples and event types of the plurality of abnormal content samples, and performs model training based on the plurality of abnormal content samples and the event types of the plurality of abnormal content samples to obtain the first semantic identification model. Specifically, the training process of the first semantic recognition model comprises the following steps: in the first iteration process, respectively inputting the plurality of abnormal content samples into an initial model to obtain a type training result of the first iteration process; determining a loss function based on the type training result of the first iteration process and the event type of the abnormal content sample, and adjusting model parameters in the initial model based on the loss function; taking the model parameters after the first iteration adjustment as model parameters of the second iteration, and then carrying out the second iteration; and repeating the iteration process for a plurality of times, in the Nth process, taking the model parameters after the N-1 th iteration adjustment as new model parameters, carrying out model training until the training meets the target condition, and acquiring the model corresponding to the iteration process meeting the target condition as the first semantic recognition model. Wherein N is a positive integer and is greater than 1. Optionally, the target condition met by training is that the number of training iterations of the initial model reaches a target number, which may be a preset number of training iterations; alternatively, the target condition met by the training may be that the loss value meets a target threshold condition, such as a loss value less than 0.00001. The embodiments of the present disclosure are not limited thereto.

In the embodiment, the event type of the abnormal call event is determined by using the semantic recognition model, the event type of the abnormal call event can be determined quickly, the event type with higher accuracy can be determined, and the accuracy of determining the event type is improved while the efficiency of determining the event type is improved.

(302B) In some embodiments, the process of the server determining the event type of the abnormal call event is: the server determines an event type corresponding to the abnormal content information based on the abnormal content information and a first corresponding relation, and determines the determined event type as the event type of the abnormal call event, wherein the first corresponding relation comprises multiple types of abnormal content information and corresponding event types.

In an optional embodiment, the server performs similarity matching based on the abnormal content information in the multiple types of abnormal content information included in the first corresponding relationship, determines the abnormal content information matched with the abnormal content information, and determines an event type corresponding to the matched abnormal content information as the event type of the abnormal call event.

In this embodiment, the event type of the abnormal call event is determined based on the abnormal content information in the first call record of the abnormal call event and the first corresponding relationship, so that the event type of the abnormal call event can be determined quickly, and the efficiency of determining the event type is improved.

The step 301 is a process of simultaneously extracting the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event from the first call record of the abnormal call event, and in other embodiments, the server can further extract the abnormal content information from the first call record of the abnormal call event, determine the event type of the abnormal call event based on the abnormal content information, and then extract the identity information claimed by the initiator from the text information of the first call record based on the identity information base corresponding to the event type (or the multiple types of identity information corresponding to the event type in the identity information base). Therefore, the event type is determined firstly, the identity information is extracted, and the identity information is extracted by using the identity information base corresponding to the event type, so that the processing content of the server is greatly reduced, and the processing efficiency of the server is improved.

The above steps 301 to 302 are for example to trigger execution of extracting abnormal content information and determining an event type when an abnormal call event of a target object is detected, and to explain a scenario, in other embodiments, a server determines whether the abnormal call event occurs in response to an abnormal call event occurring in the target object, and executes the above steps 301 to 302 when the abnormal call event occurs, and does not need to execute the above steps 301 to 302 when the abnormal call event does not occur. In some embodiments, the server adopts an abnormal recognition model to determine whether the abnormal call event is abnormal, and the corresponding process is as follows: the server inputs the call audio of the first call record into the abnormal recognition model, and judges whether the abnormal call event is abnormal or not through the abnormal recognition model to obtain an abnormal recognition result of the abnormal call event. The abnormal recognition model is used for judging whether the abnormal call event generates abnormality or not. In some embodiments, the anomaly identification model is a binary model. Therefore, the problem that server resources are wasted due to the fact that the server executes the steps under the condition that the abnormal call event cannot be abnormal is solved by judging whether the abnormal call event occurs.

303. The server determines audio characteristic information of the target object based on the first call record of the abnormal call event, wherein the audio characteristic information is used for representing emotional characteristics and gender characteristics of the target object.

In some embodiments, the audio feature information comprises emotional feature information and gender feature information, wherein the emotional feature information is used for characterizing an emotional type of the target object, and the gender feature information is used for characterizing a gender type of the target object. In some embodiments, the audio feature information is in the form of a feature vector.

In some embodiments, the process of the server determining the gender feature information is: the server extracts the audio basic features of the target object based on the call audio of the first call record, wherein the audio basic features comprise volume, tone quality, tone color, spectrum features and the like, the extracted audio basic features are input into a gender identification model, and the gender of the target object is identified through the gender identification model to obtain gender feature information of the target object. The gender identification model is used for identifying the gender of the target object. In some embodiments, the gender identification model is a two-classification model.

In some embodiments, the emotional characteristic information is determined based on the dialog mood of the target object, for example, the volume of the dialog is high or low, the speech rate of the dialog is, and the corresponding process is: the server extracts the audio basic features of the target object based on the call audio of the first call record, inputs the extracted audio basic features into a first emotion recognition model, and recognizes the emotion of the target object through the first emotion recognition model to obtain the emotion feature information of the target object. In still other embodiments, the emotional characteristic information is determined based on the emotional text of the target object, for example, the text containing the target emotional words, such as the text containing satisfaction or happiness, or the text containing anger or annoyance, and the corresponding process is: and the server inputs the text information of the first call record into a second emotion recognition model, and the emotion of the target object is recognized through the second emotion recognition model to obtain the emotion characteristic information of the target object.

The emotion recognition model is used for recognizing the emotion type of the target object, wherein the first emotion recognition model is used for recognizing the emotion type of the target object based on the audio basic characteristics of the target object, and the second emotion recognition model is used for recognizing the emotion type of the target object based on the text information of the first call record. In some embodiments, the above-mentioned emotion recognition model is a two-classification model, for example, whether the emotion of the target subject is stable or not, or a multi-classification model, for example, whether the emotion of the target subject is impatient, confused or calm, or the like. In other embodiments, the server may further determine emotional characteristic information of the target object by combining the audio basic characteristic of the target object and the text information of the first call record, and take, as an example, probability values of various emotion types of the recognition result output by the emotion recognition model, the corresponding process is as follows: and the server adds the probability values of various emotion types output by the first emotion recognition model and the probability values of various emotion types output by the second emotion recognition model, and determines the emotion type with the maximum sum of the probability values as the emotion type of the target object, so that the emotion characteristic information of the target object is obtained. Of course, the server may also input the audio basic feature of the target object and the text information of the first call record into a third emotion recognition model, and recognize the emotion type of the target object based on the audio basic feature of the target object and the text information of the first call record through the third emotion recognition model to obtain the emotion feature information of the target object. And the third emotion recognition model is used for recognizing the emotion type of the target object based on the audio basic features of the target object and the text information of the first call record.

In the embodiment, the emotion type of the target object is determined by adopting the emotion recognition model, the emotion type of the target object can be determined quickly, the emotion type with higher accuracy can be determined, and the emotion type determining accuracy is improved while the emotion type determining efficiency is improved.

304. The server determines a target timbre that matches the audio feature information.

In some embodiments, the server determines a tone color corresponding to the audio feature information based on the audio feature information and a second corresponding relationship, and determines the determined tone color as a target tone color matching with the audio feature information, wherein the first corresponding relationship comprises a plurality of audio feature information and corresponding tone colors.

For example, assuming that the audio feature information indicates that the target object is panic-female, a formal male tone may be selected as the target tone; assuming that the audio feature information indicates that the target object is impatient-male, a soft female timbre may be selected as the target timbre.

In the embodiment, different types of timbres are preset, and then the timbres of corresponding types are automatically allocated to the target object based on different audio characteristics of the target object, so that the timbres according with the real situation of the target object are adopted for call dissuasion in the following, the possibility of complete answering of a user can be improved, and the call dissuasion effect is improved.

It should be noted that, steps 301 to 302 are processes in which the server determines the event type of the abnormal call event, and steps 303 to 304 are processes in which the server selects the target tone matched with the target object, where the above-mentioned embodiment takes as an example a process in which the server determines the event type of the abnormal call event first and then selects the target tone matched with the target object, and describes the scenario, while in other embodiments, the server can also select the target tone matched with the target object first and then determine the event type of the abnormal call event, or the server can also execute a process in which the server selects the target tone matched with the target object while determining the event type of the abnormal call event. The embodiment of the present disclosure does not limit the execution sequence of steps 301 to 302 and steps 303 to 304.

It should be further noted that steps 303 to 304 are optional steps, and in other embodiments, after the server performs steps 301 to 302, step 305 is performed without performing steps 303 to 304.

305. The server sends a short message prompt to the target object, wherein the short message prompt is used for prompting that a call is to be initiated to the target object.

In some embodiments, the server is provided with a text messaging capability, e.g., the server sends a text message prompt to the target object using an outbound channel provided by an authority (e.g., anti-fraud center) to prompt that a call will be placed to the target object. Illustratively, a short message prompt is used to prompt an official manager that a call is to be placed to the target object. Therefore, the user can know that a call is available later by sending the short message prompt in advance, so that the user generates basic trust, and the success rate of subsequent calls is improved.

It should be noted that, in steps 301 to 305, the server sequentially determines the event type of the abnormal call event, selects a target tone color matched with the target object, and then executes a process of sending the short message prompt to the target object, and in other embodiments, the server may further execute the process of sending the short message prompt to the target object and then execute the process of selecting the target tone color matched with the target object after determining the event type of the abnormal call event, that is, after executing steps 301 to 302, step 305 is executed first, and then steps 303 to 304 are executed, or the server may further execute the process of sending the short message prompt to the target object while executing the process of selecting the target tone color matched with the target object, that is, while executing steps 303 to 304, step 305 is executed. The execution sequence of steps 303 to 304 and 305 is not limited in the embodiment of the present disclosure.

It should be noted that step 305 is an optional step, and in other embodiments, after the server performs steps 301 to 304, step 306 is performed without performing step 305.

306. The server initiates a call request to the target object.

Wherein, the call request is initiated to the target object, that is, the call request is initiated to the terminal of the target object. In some embodiments, the server initiates a call request to the terminal of the target object based on the mobile phone number of the target object recorded by the first call record.

307. And the server responds to the target object to accept the call request, and controls the voice robot to play target voice data by adopting the target tone, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal call event and the event type.

Wherein the target voice data is used for indicating the event subject of the abnormal call event. The target voice data is generated based on the identity information claimed by the initiator of the abnormal call event and the event type of the abnormal call event. In some embodiments, the server is preset with a voice template of the target voice data, in an identity information field of the voice template, the identity information claimed by the initiator of the abnormal call event is added, and in an event type field of the voice template, the event type of the abnormal call event is added, so as to generate the target voice data.

In the above embodiment, when the call dissuasion is performed on the target object, the voice robot is controlled to play the voice data containing the identity information and the event type, so that the trust of the user can be improved by stating the related information in the abnormal call event occurring in the target object, the possibility of complete answering of the user is further improved, the owner can complete the anti-fraud investigation and the related dissuasion in a more matched manner, and the effect of call dissuasion is ensured.

In the above embodiments, the example is to play the voice data including the identity information and the event type, in still other embodiments, the target voice data further includes the identity information of the target object, accordingly, in step 301, the server further determines the identity information of the target object in response to the target object having the abnormal call event, and further in step 307, in response to the target object receiving the call request, further controls the voice robot to play the voice data including the identity information and the event type and simultaneously play the voice data including the identity information of the target object. In other embodiments, the target voice data further includes identity information of the object from which the call request originated. Therefore, when the target object receives the call request, the voice data containing the identity information of the target object or the voice data containing the identity information of the object initiating the call request are played, so that the trust sense of the user can be improved, and the possibility of complete answering of the user is further improved.

Further, the server controls the voice robot to play voice data containing the verification prompt in response to receiving the target audio data of the target object. The target audio data refers to audio for questioning the object that initiated the call request, such as audio containing a questioning word. The verification prompt is used for prompting the user to perform inquiry based on the mobile phone number of the object initiating the call request so as to ensure the security of the call request.

In some embodiments, after determining the event type of the abnormal call event, the server further obtains a dialog template associated with the event type based on the event type of the abnormal call event, where the dialog template includes a plurality of dialog contents associated with the event type, and after initiating a call request to the target object, the server further controls the voice robot to talk with the target object based on the dialog template in response to the target object accepting the call request. So, through setting up the dialogue template of multiple incident type in advance, and then to different incident scenes, can directly call corresponding dialogue template and use, can realize big batch, the dialogue of polymorphic type, can carry out the response of different talk to the chat content of owner's difference for voice robot can talk more in a flexible way, has improved human-computer interaction efficiency, has ensured the effect of dissuading, has promoted the dissuading rate.

The above steps 301 to 307 are to initiate a call to the target object to dissuade the call from the target object after detecting the abnormal call event of the target object, so as to avoid the risk of fraud. Further, after the call is ended, the following implementation can be made, see step 308 to step 309.

308. And the server responds to the end of the call, and performs audio recognition on the second call record of the voice robot and the target object to obtain text information of the second call record.

The second call record is a call record of a call event between the voice robot and the target object, and is used for recording event information of the call event, such as call audio, mobile phone numbers of both parties, call time, locations of both parties, and the like.

In some embodiments, the server is provided with an audio-to-text converter, and the audio recognition is performed on the call audio recorded by the second call through the audio-to-text converter to obtain the text information recorded by the second call. The text information of the second call record refers to the text information of the call audio of the second call record.

309. And the server carries out semantic recognition on the text information of the second call record to obtain the call effect information of the second call record, wherein the call effect information is used for indicating the dissuading effect generated by the call.

In some embodiments, the call effect information is used to indicate whether the call is dissuaded successfully or is used to indicate the level of dissuading effect of the call, e.g., good, and bad.

In some embodiments, the server performs semantic recognition by using the second semantic recognition model, and the corresponding process is as follows: the server inputs the text information of the second call record into a second semantic recognition model, and performs semantic recognition on the text information of the second call record through the second semantic recognition model to obtain the call effect information of the second call record.

Wherein the second semantic recognition model is used for recognizing the call effect (namely the dissuasion effect) of the second call record. Taking the example that the call effect information is used for indicating whether the call is dissuaded successfully or not, the second semantic recognition model is a binary model; taking the call effect information used for indicating the level of dissuasion effect of the call as an example, the second semantic identification model is a multi-classification model.

In some embodiments, the second semantic recognition model is based on deep neural network training. With respect to the model structure and the training process of the second semantic recognition model, refer to the model structure and the training process of the first semantic recognition model in step 302, and are not described in detail.

310. And if the call effect information recorded by the second call is used for indicating that the call dissuasion fails, the server converts the voice robot into artificial voice.

In this embodiment, when the dissuading effect of this call is poor, the manual speech can be automatically converted, so that manual dissuading can be performed subsequently, the flexibility of call dissuading is improved, and the effect of call dissuading is improved.

It should be noted that the steps 308 to 310 are optional steps. In other embodiments, the server does not need to perform the above steps 308 to 310 after the call is ended.

It should be understood that during the conversation between the voice robot and the target object, there may be a case of call interruption, and in this case, there can be other implementation manners:

(1) in some embodiments, the server responds to the target object interrupting the call, and performs audio recognition on a second call record of the voice robot and the target object to obtain text information of the second call record; and performing semantic recognition on the text information of the second call record to obtain call interruption information of the second call record, wherein the call interruption information is used for indicating the reason of call interruption.

In some embodiments, the server performs semantic recognition by using a third semantic recognition model, and the corresponding process is as follows: the server inputs the text information of the second call record into a third semantic recognition model, and performs semantic recognition on the text information of the second call record through the third semantic recognition model to obtain call interruption information of the second call record.

And the third semantic recognition model is used for recognizing the call interruption reason of the second call record. In some embodiments, the third semantic identification model is a multi-classification model. In some embodiments, the third semantic recognition model is based on deep neural network training. Regarding the model structure and the training process of the third semantic recognition model, refer to the model structure and the training process of the first semantic recognition model in step 302, and are not described in detail.

In this embodiment, when the user hangs up the call autonomously, the call interruption information is identified to clarify the reason of the call interruption, so that the subsequent manual dissuasion can be smoothly implemented.

In some embodiments, the server adds a target status tag to the second call record in response to the target object interrupting the call, the target status tag being used to indicate that the user hangs up the call autonomously. Further, the server also sends the call information of the call between the voice robot and the target object to the management terminal, wherein the call information comprises the call audio of the second call record, the text information of the second call record and the target state label, and correspondingly, the management terminal receives the call information sent by the server and displays the call information of the call. Further optionally, the management terminal responds to the target status label for indicating the user to hang up the phone autonomously, and displays a manual call prompt for prompting manual initiation of a call request. At this time, the manager may operate on the management terminal based on the call information of the call to trigger the management terminal to initiate a call request to the target object, and then perform a call with the target object to perform manual dissuasion if the target object accepts the call request. Further, after the call with the target object is ended, the manager can operate on the management terminal, the result obtained by manually discouraging at this time is recorded into the management terminal, and accordingly the management terminal responds to the recording operation, obtains the recorded processing result, and sends the recorded processing result to the server.

(2) In other embodiments, the server re-initiates the call request to the target object after the target duration interval in response to the abnormal interruption of the call.

The abnormal call interruption may be call interruption caused by poor network or network delay. The target time period is a predetermined fixed time period, such as 10 minutes.

In the embodiment, under the condition that the call is interrupted due to external reasons such as network abnormality and the like, the call is automatically rebroadcast after a period of time, so that the flexibility of external call dissuasion is improved, and the call dissuasion effect is further improved.

All the above optional technical solutions may be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.

Fig. 4 is a schematic structural diagram of a calling device for abnormal calls according to an embodiment of the present disclosure, and referring to fig. 4, the device includes:

an extracting module 401, configured to extract, from a first call record of an abnormal call event of a target object, identity information claimed by an initiator of the abnormal call event and abnormal content information of the abnormal call event;

a determining module 402, configured to determine an event type of the abnormal call event based on the abnormal content information, where the event type represents an abnormal type generated by the abnormal call event;

and the calling module 403 is configured to initiate a call request to the target object, and in response to the target object accepting the call request, control the voice robot to play target voice data, where the target voice data includes the identity information claimed by the initiator of the abnormal call event and the event type.

In some embodiments, the extraction module 401 is configured to:

the determining module 402 is further configured to:

In some embodiments, the determining module 402 is further configured to:

the calling module 403 is further configured to:

In some embodiments, the calling module 403 is further configured to:

In some embodiments, the apparatus further comprises a conversion module to:

In some embodiments, the apparatus further comprises a sending module to:

In some embodiments, the apparatus further comprises an acquisition module to:

the calling module 403 is further configured to:

It should be noted that: in the calling device for abnormal calls provided in the above embodiments, only the division of the functional modules is illustrated when a call is made, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the electronic device may be divided into different functional modules to complete all or part of the functions described above. In addition, the calling device for abnormal calls and the calling method for abnormal calls provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

The electronic device in the embodiment of the present disclosure may be provided as a terminal, and fig. 5 is a schematic structural diagram of a terminal 500 provided in the embodiment of the present disclosure. The terminal 500 may be: smart devices, tablets, laptops or desktops. Terminal 500 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, and the like.

In general, the terminal 500 includes: a processor 501 and a memory 502.

The processor 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 501 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 501 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, processor 501 may also include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning.

Memory 502 may include one or more computer-readable storage media, which may be non-transitory. Memory 502 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 502 is used to store at least one program code for execution by the processor 501 to implement the call method for abnormal calls provided by the management terminal in the method embodiments of the present disclosure.

In some embodiments, the terminal 500 may further optionally include: a peripheral interface 503 and at least one peripheral. The processor 501, memory 502 and peripheral interface 503 may be connected by a bus or signal lines. Each peripheral may be connected to the peripheral interface 503 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 504, display screen 505, camera assembly 506, audio circuitry 507, positioning assembly 508, and power supply 509.

The peripheral interface 503 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 501 and the memory 502. In some embodiments, the processor 501, memory 502, and peripheral interface 503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 501, the memory 502, and the peripheral interface 503 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 504 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 504 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 504 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 504 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 504 may further include NFC (Near Field Communication) related circuits, which are not limited by this disclosure.

The display screen 505 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 505 is a touch display screen, the display screen 505 also has the ability to capture touch signals on or over the surface of the display screen 505. The touch signal may be input to the processor 501 as a control signal for processing. At this point, the display screen 505 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display screen 505 may be one, disposed on the front panel of the terminal 500; in other embodiments, the display screens 505 may be at least two, respectively disposed on different surfaces of the terminal 500 or in a folded design; in other embodiments, the display 505 may be a flexible display disposed on a curved surface or a folded surface of the terminal 500. Even more, the display screen 505 can be arranged in a non-rectangular irregular figure, i.e. a shaped screen. The Display screen 505 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 506 is used to capture images or video. Optionally, camera assembly 506 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 506 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

Audio circuitry 507 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 501 for processing, or inputting the electric signals to the radio frequency circuit 504 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 500. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 501 or the radio frequency circuit 504 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, audio circuitry 507 may also include a headphone jack.

The positioning component 508 is used for positioning the current geographic Location of the terminal 500 for navigation or LBS (Location Based Service). The Positioning component 508 may be a Positioning component based on the united states GPS (Global Positioning System), the chinese beidou System, the russian graves System, or the european union's galileo System.

Power supply 509 is used to power the various components in terminal 500. The power source 509 may be alternating current, direct current, disposable or rechargeable. When power supply 509 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 500 also includes one or more sensors 510. The one or more sensors 510 include, but are not limited to: acceleration sensor 511, gyro sensor 512, pressure sensor 513, fingerprint sensor 514, optical sensor 515, and proximity sensor 516.

The acceleration sensor 511 may detect the magnitude of acceleration on three coordinate axes of the coordinate system established with the terminal 500. For example, the acceleration sensor 511 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 501 may control the display screen 505 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 511. The acceleration sensor 511 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 512 may detect a body direction and a rotation angle of the terminal 500, and the gyro sensor 512 may cooperate with the acceleration sensor 511 to acquire a 3D motion of the user on the terminal 500. The processor 501 may implement the following functions according to the data collected by the gyro sensor 512: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

The pressure sensor 513 may be disposed on a side frame of the terminal 500 and/or underneath the display screen 505. When the pressure sensor 513 is disposed on the side frame of the terminal 500, a user's holding signal of the terminal 500 may be detected, and the processor 501 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 513. When the pressure sensor 513 is disposed at the lower layer of the display screen 505, the processor 501 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 505. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 514 is used for collecting a fingerprint of the user, and the processor 501 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 514, or the fingerprint sensor 514 identifies the identity of the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, the processor 501 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings, etc. The fingerprint sensor 514 may be disposed on the front, back, or side of the terminal 500. When a physical button or a vendor Logo is provided on the terminal 500, the fingerprint sensor 514 may be integrated with the physical button or the vendor Logo.

The optical sensor 515 is used to collect the ambient light intensity. In one embodiment, the processor 501 may control the display brightness of the display screen 505 based on the ambient light intensity collected by the optical sensor 515. Specifically, when the ambient light intensity is high, the display brightness of the display screen 505 is increased; when the ambient light intensity is low, the display brightness of the display screen 505 is reduced. In another embodiment, processor 501 may also dynamically adjust the shooting parameters of camera head assembly 506 based on the ambient light intensity collected by optical sensor 515.

A proximity sensor 516, also referred to as a distance sensor, is typically disposed on the front panel of the terminal 500. The proximity sensor 516 is used to collect the distance between the user and the front surface of the terminal 500. In one embodiment, when the proximity sensor 516 detects that the distance between the user and the front surface of the terminal 500 gradually decreases, the processor 501 controls the display screen 505 to switch from the bright screen state to the dark screen state; when the proximity sensor 516 detects that the distance between the user and the front surface of the terminal 500 becomes gradually larger, the display screen 505 is controlled by the processor 501 to switch from the breath screen state to the bright screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 5 is not intended to be limiting of terminal 500 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

The electronic device in the embodiment of the present disclosure may be provided as a server, and fig. 6 is a schematic structural diagram of a server provided in the embodiment of the present disclosure, where the server 600 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where at least one program code is stored in the one or more memories 602, and is loaded and executed by the one or more processors 601 to implement the call method for the abnormal call executed by the server in the various method embodiments described above. Of course, the server 600 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 600 may also include other components for implementing the functions of the device, which is not described herein again.

In an exemplary embodiment, a computer readable storage medium, such as a memory including program code, which is executable by a processor to perform the call method for an abnormal call in the above embodiments is also provided. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided, which includes computer program code stored in a computer readable storage medium, from which a processor of an electronic device reads the computer program code, and executes the computer program code, so that the electronic device performs the above-mentioned call method for an abnormal call.

In some embodiments, the computer program according to the embodiments of the present disclosure may be deployed to be executed on one electronic device, or on a plurality of electronic devices located at one site, or on a plurality of electronic devices distributed at a plurality of sites and interconnected by a communication network, and the plurality of electronic devices distributed at the plurality of sites and interconnected by the communication network may constitute a block chain system.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by hardware associated with program code, and the program may be stored in a computer readable storage medium, where the above mentioned storage medium may be a read-only memory, a magnetic or optical disk, etc.

The foregoing is considered as illustrative of the embodiments of the disclosure and is not to be construed as limiting thereof, and any modifications, equivalents, improvements and the like made within the spirit and principle of the disclosure are intended to be included within the scope of the disclosure.

Claims

1. A calling method for abnormal calls is characterized by comprising the following steps:

determining an event type of the abnormal call event based on the abnormal content information, wherein the event type represents an abnormal type generated by the abnormal call event;

initiating a call request to the target object, responding to the call request accepted by the target object, and controlling the voice robot to play target voice data, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal call event and the event type.

2. The method of claim 1, wherein the extracting, from the first call record of the abnormal call event of the target object, the identity information claimed by the initiator of the abnormal call event and the abnormal content information of the abnormal call event comprises:

3. The method of claim 1, wherein the target speech data further comprises identity information of the target object;

before the call request is initiated to the target object, the method further includes:

and responding to the abnormal call event of the target object, and determining the identity information of the target object.

4. The method of claim 3, wherein the target voice data further comprises identity information of an object from which the call request originated.

5. The method of claim 1, wherein prior to initiating the call request to the target object, the method further comprises:

after the call request is initiated to the target object, the method further comprises:

6. The method of claim 1, wherein after controlling the voice robot to play the target voice data, the method further comprises:

responding to the interruption of the call of the target object, and performing audio recognition on a second call record of the voice robot and the target object to obtain text information of the second call record;

7. The method of claim 1, wherein after controlling the voice robot to play the target voice data, the method further comprises:

and responding to abnormal interruption of the call, and after the target duration is separated, re-initiating the call request to the target object.

8. The method of claim 1, wherein after controlling the voice robot to play the target voice data, the method further comprises:

9. The method of claim 8, wherein after obtaining the call effect information of the second call record, the method further comprises:

10. The method of claim 1, wherein prior to initiating the call request to the target object, the method further comprises:

and sending a short message prompt to the target object, wherein the short message prompt is used for prompting that a call is to be initiated to the target object.

11. The method of claim 1, wherein prior to initiating the call request to the target object, the method further comprises:

based on the event type of the abnormal call event, acquiring a conversation template associated with the event type, wherein the conversation template comprises a plurality of conversation contents associated with the event type;

and responding to the target object to accept the call request, and controlling the voice robot to talk with the target object based on the dialogue template.

12. A calling device for abnormal calls, the device comprising:

the extraction module is used for extracting the identity information claimed by an initiator of the abnormal call event and the abnormal content information of the abnormal call event from a first call record of the abnormal call event of a target object;

and the calling module is used for initiating a calling request to the target object, responding to the target object to accept the calling request, and controlling the voice robot to play target voice data, wherein the target voice data comprises the identity information claimed by the initiator of the abnormal call event and the event type.

13. An electronic device, comprising one or more processors and one or more memories having at least one program code stored therein, the program code being loaded and executed by the one or more processors to implement the method for calling for an abnormal call as claimed in any one of claims 1 to 11.

14. A computer-readable storage medium having at least one program code stored therein, the program code being loaded and executed by a processor to implement the method for calling for an abnormal call according to any one of claims 1 to 11.

15. A computer program product, characterized in that the computer program product comprises computer program code, which is stored in a computer-readable storage medium, from which a processor of an electronic device reads the computer program code, the processor executing the computer program code, causing the electronic device to execute the call method for an abnormal call according to any one of claims 1 to 11.