CN115580680A - Call restriction method, device, system, electronic equipment and storage medium - Google Patents
Call restriction method, device, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115580680A CN115580680A CN202110686147.0A CN202110686147A CN115580680A CN 115580680 A CN115580680 A CN 115580680A CN 202110686147 A CN202110686147 A CN 202110686147A CN 115580680 A CN115580680 A CN 115580680A
- Authority
- CN
- China
- Prior art keywords
- call
- abnormal number
- suspected abnormal
- suspected
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000002159 abnormal effect Effects 0.000 claims abstract description 323
- 238000000605 extraction Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 238000001228 spectrum Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 4
- 239000006185 dispersion Substances 0.000 claims description 4
- 230000003993 interaction Effects 0.000 description 15
- 238000004891 communication Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 230000005236 sound signal Effects 0.000 description 6
- 230000008451 emotion Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The application discloses a call restriction method, a device, a system, an electronic device and a storage medium, wherein the method comprises the following steps: under the condition that call connection is established with a suspected abnormal number, playing first voice information, wherein the first voice information is used for inquiring historical call intention of the suspected abnormal number; under the condition that second voice information of the suspected abnormal number is obtained, determining abnormal type information of the suspected abnormal number according to the second voice information; determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number; and performing call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate. According to the embodiment of the application, the timeliness of call limitation on the abnormal number can be improved.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a system, an electronic device, and a storage medium for call restriction.
Background
With the development of communication technology, the frequency of receiving unknown calls by people is higher and higher, and among the unknown calls, abnormal calls aiming at cheating, promotion, harassment and the like are not lacked, so that great interference is brought to the life of people. At present, an operator can acquire a suspected abnormal number according to the reporting information of a user, analyze the calling behavior of the suspected abnormal number according to an existing strategy, and store the abnormal number in an internet tag library to perform calling limitation on the abnormal number under the condition that the suspected abnormal number is determined to be the abnormal number. However, the user has a long period from the time of receiving the incoming call to the time of reporting the suspected abnormal number, to the time of studying and judging the suspected abnormal number by the operator, and finally to the time of limiting the call, which results in poor timeliness of limiting the call of the abnormal number.
Disclosure of Invention
The embodiment of the application provides a call restriction method, a call restriction device, a call restriction system, electronic equipment and a storage medium, which can improve timeliness of call restriction on abnormal numbers.
In a first aspect, an embodiment of the present application provides a call barring method, including:
under the condition that call connection is established with a suspected abnormal number, playing first voice information, wherein the first voice information is used for inquiring historical call intention of the suspected abnormal number;
under the condition that second voice information of the suspected abnormal number is obtained, determining abnormal type information of the suspected abnormal number according to the second voice information;
determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number;
and performing call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
In a second aspect, an embodiment of the present application provides a call restriction apparatus, including:
the system comprises a playing module, a processing module and a processing module, wherein the playing module is used for playing first voice information under the condition that call connection is established with a suspected abnormal number, and the first voice information is used for inquiring the historical call intention of the suspected abnormal number;
the first determining module is used for determining the abnormal type information of the suspected abnormal number according to the second voice information under the condition that the second voice information of the suspected abnormal number is obtained;
the second determining module is used for determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number;
and the limiting module is used for carrying out call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
In a third aspect, an embodiment of the present application provides a call restriction system, including an outbound management device, a media bridge device, a voice control device, and a call control device;
the outbound management device is to: establishing call connection with the suspected abnormal number;
the media bridging means is for: playing first voice information, acquiring second voice information of the suspected abnormal number, and forwarding the second voice information to the voice control device, wherein the first voice information is used for inquiring the historical calling intention of the suspected abnormal number;
the voice control device is used for: according to the second voice information, determining abnormal type information of the suspected abnormal number, and sending the abnormal type information of the suspected abnormal number to the call control device;
the call control device is configured to: and controlling the call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number.
In a fourth aspect, an embodiment of the present application provides an electronic device, including: a processor, and a memory storing computer program instructions;
the processor reads and executes the computer program instructions to implement the call restriction method of the first aspect.
In a fifth aspect, the present application provides a computer storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the call restriction method according to the first aspect.
According to the call limiting method, the call limiting device, the call limiting system, the electronic equipment and the storage medium, call connection is established with the suspected abnormal number, voice interaction is carried out with the suspected abnormal number to obtain the historical call intention of the suspected abnormal number, so that the abnormal type of the suspected abnormal number is determined, and then call limitation can be carried out on the suspected abnormal number according to the abnormal type of the suspected abnormal number. Therefore, on one hand, the attribute of the suspected abnormal number can be determined in a short time, and the abnormal number can be subjected to call limitation, so that the timeliness of the call limitation on the abnormal number can be improved; on the other hand, different strategies can be adopted for carrying out call restriction on abnormal numbers of different abnormal types, so that the flexibility and the adaptability of call restriction on the abnormal numbers can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a call restriction system provided by some embodiments of the present application;
fig. 2 is a flow chart of a call restriction method provided in some embodiments of the present application;
fig. 3 is a flowchart illustrating a call restriction method according to another embodiment of the present application;
FIG. 4 is a schematic diagram of a call restriction device according to some embodiments of the present application;
fig. 5 is a schematic hardware structure diagram of a call limiting device according to some embodiments of the present application.
Detailed Description
Features of various aspects and exemplary embodiments of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
In order to solve the problem of the prior art, embodiments of the present application provide a call restriction method, device, system, electronic device, and computer storage medium.
The following first describes a call restriction system provided in an embodiment of the present application.
Fig. 1 is a schematic diagram illustrating a call restriction system 100 according to an embodiment of the present application.
As shown in fig. 1, the call restriction system 100 includes an outbound management device 101, a media bridge device 102, a voice control device 103, and a call control device 104;
the outbound management device 101 is used for establishing call connection with a suspected abnormal number;
the media bridge device 102 is configured to play first voice information, acquire second voice information of the suspected abnormal number, and forward the second voice information to the voice control device, where the first voice information is used to inquire a historical call intention of the suspected abnormal number;
the voice control device 103 is configured to determine, according to the second voice information, abnormal type information of the suspected abnormal number, and send the abnormal type information of the suspected abnormal number to the call control device;
the call control device 104 is configured to control a call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number.
The call barring system 100 according to the embodiment of the present application can establish a communication connection with the carrier communication network a. Specifically, after obtaining the suspected abnormal number, the outbound management device 101 may establish an outbound signaling with the operator communication network a, so as to establish a call connection with the suspected abnormal number. The media bridging device 102 may be connected to a media gateway of the carrier communication network a, and after the outbound management device 101 establishes call connection with the suspected abnormal number, play the voice information of the historical call intention for inquiring the suspected abnormal number to the suspected abnormal number, and receive the voice information of the suspected abnormal number in real time.
The media bridge device 102 may also forward the received voice message from the suspected abnormal number to the voice control device 103. The voice control device 103 may analyze the received voice information, determine the abnormal type information of the suspected abnormal number, and send the determination result to the call control device 104.
The voice interaction between the call restriction system 100 and the suspected abnormal number may be one or more rounds, and during the multiple rounds of conversation, the voice control device 103 may generate the voice interaction information of the next round according to the analysis result of the voice information. The voice control device 103 may also determine whether the opposite party has finished speaking by using a pre-trained meta information extraction model, and control the media bridge device 102 to play the next round of voice information after the opposite party has finished speaking.
The call control device 104 may predict the number of calls of the suspected abnormal number in the next time period according to the type information of the suspected abnormal number, and determine the target call completing rate of the suspected abnormal number according to the preset maximum call volume of the corresponding abnormal type in the next time period. In addition, the call control device 104 may perform call restriction on the suspected abnormal number according to the abnormal type information of the abnormal number. Call restriction may be achieved by restricting the call completion rate of the abnormal number to not exceed a target call completion rate.
The call restriction system provided by the embodiment of the application acquires the historical call intention of the suspected abnormal number by establishing call connection with the suspected abnormal number and performing voice interaction with the suspected abnormal number so as to determine the abnormal type of the suspected abnormal number, and then performs call restriction on the suspected abnormal number according to the abnormal type of the suspected abnormal number. Therefore, on one hand, the attribute of the suspected abnormal number can be determined in a short time, and the abnormal number can be subjected to call limitation, so that the timeliness of the call limitation on the abnormal number can be improved; on the other hand, different strategies can be adopted for carrying out call restriction on abnormal numbers of different abnormal types, so that the flexibility and the adaptability of call restriction on the abnormal numbers can be improved.
The call restriction system provided in the embodiment of the present application may be used to execute the call restriction method of the present application, and the call restriction method of the present application is described below.
Fig. 2 is a flowchart illustrating a call restriction method according to an embodiment of the present application.
As shown in fig. 2, the method may include the steps of:
step 201: under the condition that call connection is established with a suspected abnormal number, playing first voice information, wherein the first voice information is used for inquiring historical call intention of the suspected abnormal number;
step 202: under the condition that second voice information of the suspected abnormal number is obtained, determining abnormal type information of the suspected abnormal number according to the second voice information;
step 203: determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number;
step 204: and performing call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
The suspected abnormal number related to the application can be a number with the following characteristics:
the suspected abnormal numbers call a plurality of numbers in unit time, have high frequency and are intensively distributed in a certain time period; the called parties are scattered, and the correlation among all the called numbers is small; the correlation between the suspected abnormal number and the called party is usually weak, namely the historical conversation relationship is few, and the number of the suspected abnormal number which is used as a calling party to initiate a call is usually far greater than the number of the suspected abnormal number which is used as a called party; the call duration of the call dialed by the suspected abnormal number is usually short, and the probability of the called party hanging up is high; in addition, the suspected abnormal number may also include a number reported by the user.
For better understanding of the call restriction method provided by the present application, the call restriction method of the embodiment of the present application is described below with reference to the call restriction system of fig. 1:
in step 201, the outbound management device may initiate a call instruction after acquiring the suspected abnormal number, and establish a call connection with the suspected abnormal number.
The first voice information is judged and generated by the voice control device according to the conversation scene and the voice information from the media bridging device. The voice control apparatus can judge the voice information and the dialogue scene through natural language processing. The voice control device controls the media bridging device to play the first voice message. The first voice information contains information for inquiring the historical call intention of the suspected abnormal number, which may include promotion, advertisement, fraud, harassment, and the like.
In some embodiments, the outbound management device obtains a suspected abnormal number and initiates a call instruction to the suspected abnormal number, and establishes a call connection with the suspected abnormal number. After the call connection with the suspected abnormal number is established, the voice control device controls the media bridging device to play voice information to perform voice interaction with the suspected abnormal number, and the voice interaction can be one or more turns according to the conversation scene. The voice control device may control a playing timing of the first voice information, the first voice information may be played when the call starts, or an appropriate timing may be selected to be played according to a scenario of voice interaction, which is not limited in this application. For example, before sending the first voice message, the voice control device controls the media bridging device to play the voice message to inquire whether a suspected abnormal number has been called in the historical calling time or inquire the identity of the historical calling person, and the like, and after one or more rounds of conversation, the first voice message is played according to the interaction scene.
In step 202, the second voice message is sent by the suspected abnormal number, which is a response message of the suspected abnormal number to the first voice message played by the media bridge device, and may include historical call intention information of the suspected abnormal number. For example: voice messages with keywords or meanings such as telemarketing, advertising, harassment, etc. Further, the second speech information may also be long-time unacknowledged, chaotic or meaningless speech information. According to the response condition of the suspected abnormal number, the voice control device can control the media bridging device to send the first voice message again or for multiple times.
The voice control device carries out semantic recognition on the second voice information, and determines the abnormal type of the abnormal number according to the information contained in the recognition result.
Semantic analysis is divided into word-level speech analysis and sentence-level speech analysis. The basic task of word-level semantic analysis is to perform semantic disambiguation and determine the specific meaning of an ambiguous word in context. The basic task of sentence-level speech analysis is semantic role labeling, the structure of a sentence is analyzed in units of sentences, the relationship between each component in the sentence and a predicate is researched with a predicate as the center, and the relationship is described by semantic roles. Semantic analysis can recognize the structure of a sentence and the word sense of each word in the sentence to determine the meaning of text contained in voice information, and convert natural language which can be understood by human into language which can be understood by a computer.
In the embodiment of the present application, the voice control apparatus may determine the type information of the suspected abnormality number by semantic analysis of the meaning of the word and the sentence. For example: the voice control device can determine the type of the suspected abnormal number according to the keyword obtained by semantic recognition, such as word information of 'insurance', 'house buying', 'car buying', 'card transaction' and the like, and label the type; the voice control device can also determine and label the abnormal number type according to the meaning information of sentences such as 'do you want to travel abroad recently', 'do you need to report for learning class', and the like.
The voice control device determines the abnormal type of the suspected abnormal number according to the semantic analysis result of the voice information of the suspected abnormal number, so that the suspected abnormal number is determined to be an abnormal number. The anomaly types for suspected anomaly numbers may include types of promotions, advertisements, fraud, harassment, and the like.
In the embodiment of the application, the media bridging device acquires the second voice information from the suspected abnormal number and sends the second voice information to the voice control device in the voice interaction process with the suspected abnormal number. The voice control device carries out semantic analysis on the received voice information, determines the abnormal type of the suspected abnormal number according to the semantic content of the second voice information obtained by the semantic analysis, and can also determine the abnormal type of the abnormal number according to the conditions that call connection is established but no response is given for a long time and disordered or nonsense voice is disordered or meaningless.
In step 203, the voice control device may send the abnormal number type information of the suspected abnormal number to the call barring device, and the call barring device may determine the target call completing rate of the suspected abnormal number according to a preset rule.
Call completion rate is the percentage value of the number of calls made by the telephone exchange to the total number of calls made by the subscriber. And setting the target call completing rate of the suspected abnormal number by the call control device according to the abnormal type information of the suspected abnormal number.
The call completing rate of the target call of the suspected abnormal number can be set according to the abnormal type of the abnormal number; or setting according to the historical calling frequency of the abnormal number in the abnormal type and the comparison between the abnormal number and other numbers with the same abnormal type; the abnormal number type may be set according to conditions such as a ratio of the abnormal number type to all abnormal number types, which is not limited in the present application. The target call completion rate of the different types of abnormal numbers can be managed by managing the call completion times thereof in the next period. For example: the number of call completion times of a telemarketing type number in the next period may be set to 2, the number of call completion times of an advertisement type number in the next period to 1, the number of call completion times of a nuisance number in the next period to 0, and the like. The number of times of call completion can be set according to the actual service condition of the abnormal number, which is not limited in the present application.
In step 204, the call control device may perform call restriction on the suspected abnormal number according to the target call completing rate corresponding to the abnormal type of the suspected abnormal number, so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
According to the call limiting method in the embodiment of the application, the call connection is established with the suspected abnormal number, and the voice interaction is carried out with the suspected abnormal number to obtain the historical call intention of the suspected abnormal number, so that the abnormal type of the suspected abnormal number is determined, and then the call limitation can be carried out on the suspected abnormal number according to the abnormal type of the suspected abnormal number. Therefore, on one hand, the attribute of the suspected abnormal number can be determined in a short time, and the abnormal number can be subjected to call limitation, so that the timeliness of the call limitation on the abnormal number can be improved; on the other hand, different strategies can be adopted for carrying out call restriction on abnormal numbers of different abnormal types, so that the flexibility and the adaptability of carrying out call restriction on the abnormal numbers can be improved.
Optionally, after the call connection is established with the suspected abnormal number and before the first voice message is played, the method further includes:
converting the acquired voice information of the suspected abnormal number into a first frequency spectrum;
identifying a meta-information tag of the first spectrum using a pre-trained meta-information extraction model;
and determining the first voice information according to the meta-information tag.
In this embodiment, the media bridge device receives the voice information in the current session with the suspected abnormal number, and sends the voice information to the voice control device. The voice control device converts the voice information from the media bridging device into a first frequency spectrum. The first spectrum may be, for example, a Log domain spectrum. The first spectrum may be used as input data for a pre-trained meta-information extraction model. The meta information extraction model is used for extracting meta information tags of the voice information.
The voice control apparatus may determine the first voice information content conforming to the current dialog scenario based on the meta information tag value. In addition, the voice control device may select voice information that conforms to the current dialog scenario according to a preset rule based on the meta information tag and the current number of rounds of voice interaction, and send the voice information to the media bridge device. After receiving the voice information from the voice control device, the media bridging device can play the voice information to the suspected abnormal number, so that continuous voice interaction is realized, and the individuation of the voice interaction is enhanced.
Before determining the first speech information, the speech control apparatus generates and trains a meta information extraction model in advance. The main function of the meta-information extraction model is to extract meta-information tags of the voice information. The meta-information tag may include information such as mood, emotion, sentence pattern, etc. of the speech information in the speech sample, and may further include information such as gender, region, age, etc. of the speaker.
The meta information extraction model is generated as follows:
firstly, an audio signal feature extraction algorithm is designed based on the recognition mechanism of human auditory sense and brain, and then modeling is carried out on the audio signal features, tone and emotion labels based on a Long Short-Term Memory network (LSTM). The detailed process is as follows:
firstly, pre-emphasis processing is carried out on a Log domain frequency spectrum converted from voice information: the spectrum is filtered using the following algorithm, where x is the speech sample spectrum.
H(x)＝1-μx -1 (1)
Then frame windowing is carried out on the filtered frequency spectrum: 512 samples are windowed every 30 ms. The window length adopts the following algorithm, wherein n is the nth adopted interval, and L is the frame length.
The fourier transform is performed on the energy distribution over the spectrum, and the algorithm is as follows, where N is the number of fourier transform points and x (N) is the audio signal in the nth window.
The audio energy information is mapped onto the Mel scale using a Mel filter bank to fit the hearing habits of the human ear, and the mapping formula is as follows, where f is frequency.
And performing decorrelation and dimensionality reduction on the filtered audio signal by using discrete cosine transform to generate audio signal features which can be used for modeling. The algorithm is as follows:
c (n) is the nth order feature vector. n ranges from 1 to 12.
An LSTM model based on a Recurrent Neural Network (RNN) is modeled by using the characteristics of the audio signal obtained by processing, wherein,
node model of RNN:
h i ＝σ(W xh x i +W hh h t-1 +b h ) (6)
nodal model of LSTM:
c t ＝f t c t-1 +i t tanh(W wc x t +W hc h t-1 +b c ) (7)
RNN-LSTM connectivity layer model:
h t ＝o t tanh(c t ) (8)
and then, inputting the audio characteristic vector and labels such as tone, emotion and the like into the model established in the process, and training to obtain a prediction model.
And finally, packaging the algorithm steps and the prediction model into a meta-information extraction module.
In the process of building the meta-information extraction model, in order to weaken the specific semantic content characteristics and enable the meta-information extraction model to realize the judgment of emotion and mood independently of the specific semantic content, an encoding-decoding model (Encoder-Decoder) is used for optimizing the meta-information extraction model.
Firstly, converting each section of voice sample into a text section by using a general voice recognition algorithm, and performing word segmentation to further generate semantic features such as word vectors and the like.
Secondly, defining a semantic content function as F (x), a meta-information extraction function as G (x), and constructing reconstruction functions F and G corresponding to F and G. If the overall reconstruction function S is set, the following models can be established based on extraction and reconstruction:
f(x)＝c (9)
g(x)＝m (10)
S(F(f(x)),G(g(x)))＝x (11)
and then, training the model by using a deep neural network, and obtaining g as an optimized meta-information extraction function after parameter fitting. The model module corresponding to the function can recognize the meta-information of the voice sample under the condition of eliminating the influence of semantic content as much as possible.
In an embodiment of the application, the voice control device extracts the meta-information tag through a pre-trained meta-information extraction model, and selects appropriate dialogue voice information and first voice information according to the meta-information tag and the dialogue scene. The voice control device weakens the semantic content characteristics by using the meta-information extraction model, can realize the judgment of emotion and tone independent of specific semantic content, and improves the interactivity with suspected abnormal numbers. The call restriction system enhances the individuation of voice interaction information by acquiring the meta-information tag of the voice information, is beneficial to acquiring the voice information which is more in line with expectation, and can better cope with various application scenes.
Optionally, the determining, according to the abnormal type information of the suspected abnormal number, a target call completing rate of the suspected abnormal number includes:
predicting the calling times of the suspected abnormal number in the next time period by using a pre-trained calling time prediction model;
and determining the target call completing rate of the suspected abnormal number in the next time interval according to the predicted calling times and the preset maximum calling quantity of the number of the abnormal type to which the suspected abnormal number belongs in the next time interval.
In this embodiment, after the voice control device determines the abnormal type of the suspected abnormal number, the call control device may predict the number of calls of the suspected abnormal number in the next time period by using a pre-trained call number prediction model, and determine the target call completing rate of the suspected abnormal number according to the maximum call volume preset for the abnormal type.
The call limiting device predicts the number of calls of the suspected abnormal number in the next time period, and the duration of the next time period can be flexibly set or adjusted according to needs.
The maximum call volume of a suspected abnormal number of a certain abnormal type in the next time period refers to the maximum connection times of the call of the suspected abnormal number in the next time period. The target call completing rate is the ratio of the maximum allowable call volume of the suspected abnormal number type in the next time interval to the predicted call times.
In the embodiment, the call restriction device can adaptively adjust the target call completing rate of the abnormal number according to the preset rule aiming at the real-time application scene, thereby enhancing the flexibility and the adaptive capacity of call restriction.
Optionally, the call number prediction model is obtained by training through the following steps: the method comprises the steps of obtaining complaint quantity of various abnormal numbers in a first preset time period and calling characteristic indexes of various abnormal numbers in a second preset time period, and generating characteristic matrixes of various suspected abnormal numbers, wherein the calling characteristic indexes comprise at least one of calling frequency, dispersion, calling interval, call completing rate and calling duration;
and training to obtain the calling frequency prediction model based on the LASSO regression model and the feature matrixes of the various abnormal numbers.
As an example, for each type of suspected abnormal number, the complaint amount of the previous day and the indexes of the calling frequency, dispersion, average calling interval, call completing rate, average calling duration and the like of the previous hour are obtained and calculated, and a number feature matrix is generated. And training based on the LASSO regression model and the abnormal number characteristic matrix to obtain a calling frequency prediction model.
The LASSO (Least absolute shrinkage and selection operator) method is a compression estimation method with the idea of reducing a variable set. By constructing a penalty function, the coefficients of the variables can be compressed and some regression coefficients can be changed into 0, so that the purpose of variable selection is achieved.
Optionally, the training to obtain the call frequency prediction model based on the LASSO regression model and the feature matrices of the various abnormal numbers includes:
the following cost function is configured:
wherein M is the number of various abnormal numbers, p is the number of calling characteristic indexes, and x ij Is a feature matrix, w j Is a characteristic coefficient;
taking the calling frequency of each type of abnormal number in the second preset time period as a dependent variable, and taking calling characteristic indexes except the calling frequency as independent variables for training;
and taking the model with the lowest value of the cost function as the call frequency prediction model.
In this embodiment, on the basis of the LASSO regression model, the cost function is designed by comprehensively considering the feature consistency of the abnormal number. For each type of abnormal type, the calling frequency in the previous period is used as a dependent variable, other characteristic indexes are used as independent variable training models, and the model with the lowest price function is replaced by the optimal model. Finally, a calling frequency prediction model of each abnormal number is obtained.
In order to better understand the call restriction method of the embodiment of the present application, a specific example of a call restriction method is provided below.
As shown in fig. 3, the call restriction method includes:
step 301: the outbound management device acquires the suspected abnormal number and establishes call connection with the suspected abnormal number;
step 302: the voice control device instructs the media bridging device to play voice information to inquire whether a suspected abnormal number carries out historical calling or not and to inquire a historical calling intention;
step 303: the operator communication network sends the voice information of the suspected abnormal number to the media bridging device;
step 304: the media bridging device sends the received voice information to the voice control device;
step 305: the voice control device converts voice information into a first frequency spectrum, and uses a pre-trained meta-information extraction model to identify a meta-information label of the first frequency spectrum;
step 306: the voice control device selects a voice file according with the current conversation scene according to the meta information label and the current conversation turns, and sends the voice file to the media bridging device;
step 307: after receiving the voice file, the media bridging device plays the voice information;
step 308: after the historical calling intention of the suspected abnormal number is collected, the voice control device determines the abnormal type information of the suspected abnormal number according to the historical calling intention of the suspected abnormal number;
step 309: the call control device determines a target call completing rate of the suspected abnormal number according to the abnormal type of the suspected abnormal number, and performs call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
In summary, the call restriction method in the embodiment of the present application establishes a call connection with the suspected abnormal number, and performs voice interaction with the suspected abnormal number to obtain a historical call intention of the suspected abnormal number, so as to determine the abnormal type of the suspected abnormal number, and then performs call restriction on the suspected abnormal number according to the abnormal type of the suspected abnormal number. Therefore, on one hand, the attribute of the suspected abnormal number can be determined in a short time, and the abnormal number can be subjected to call limitation, so that the timeliness of the call limitation on the abnormal number can be improved; on the other hand, different strategies can be adopted for carrying out call restriction on abnormal numbers of different abnormal types, so that the flexibility and the adaptability of call restriction on the abnormal numbers can be improved.
Fig. 4 is a schematic structural diagram of a call restriction device according to an embodiment of the present application. As shown in fig. 4, the call restriction apparatus 400 includes:
a playing module 401, configured to play first voice information when call connection is established with a suspected abnormal number, where the first voice information is used to inquire a historical call intention of the suspected abnormal number;
a first determining module 402, configured to determine, according to second voice information of the suspected abnormal number, abnormal type information of the suspected abnormal number when the second voice information of the suspected abnormal number is obtained;
a second determining module 403, configured to determine, according to the abnormal type information of the suspected abnormal number, a target call completing rate of the suspected abnormal number;
a limiting module 404, configured to perform call limitation on the suspected abnormal number, so that a call completing rate of the suspected abnormal number does not exceed the target call completing rate.
Optionally, the call limiting apparatus 400 further includes:
the conversion module is used for converting the acquired voice information of the suspected abnormal number into a first frequency spectrum;
the identification module is used for identifying the meta-information label of the first frequency spectrum by using a pre-trained meta-information extraction model;
and the third determining module is used for determining the first voice information according to the meta-information tag.
Optionally, the second determining module 403 includes:
the prediction unit is used for predicting the calling times of the suspected abnormal number in the next time period by using a pre-trained calling time prediction model;
and the determining unit is used for determining the target call completing rate of the suspected abnormal number in the next time interval according to the predicted calling times and the preset maximum call volume of the number of the abnormal type to which the suspected abnormal number belongs in the next time interval.
Optionally, the call limiting apparatus 400 further includes a training module for training the call number prediction model, where the training module includes:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the complaint quantity of various abnormal numbers in a first preset time interval and the calling characteristic index of various abnormal numbers in a second preset time interval and generating a characteristic matrix of various suspected abnormal numbers, and the calling characteristic index comprises at least one of calling frequency, dispersion, calling interval, call completing rate and calling duration;
and the training unit is used for training to obtain the calling frequency prediction model based on the LASSO regression model and the characteristic matrixes of the various abnormal numbers.
Optionally, the training unit is specifically configured to:
the following cost function is configured:
wherein M is the number of various abnormal numbers, p is the number of calling characteristic indexes, and x ij Is a feature matrix, w j Is a characteristic coefficient;
taking the calling frequency of each type of abnormal number in the second preset time period as a dependent variable, and taking calling characteristic indexes except the calling frequency as independent variables for training;
and taking the model with the lowest cost function value as the calling time prediction model.
Each module/unit in the apparatus shown in fig. 4 has a function of implementing each step in fig. 2 to fig. 3, and can achieve the corresponding technical effect, and for brevity, no further description is provided herein.
Fig. 5 shows a hardware structure diagram of an electronic device provided in an embodiment of the present application.
As shown in fig. 5, the electronic device may include a processor 501 and a memory 502 storing computer program instructions.
Specifically, the processor 501 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
Specifically, the processor 501 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement the embodiments of the present Application.
In one example, the Memory 502 may be a Read Only Memory (ROM). In one example, the ROM can be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.
The memory 502 may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform operations described with reference to the call restriction methods according to embodiments of the application.
The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the call restriction methods in the above embodiments, and achieve the corresponding technical effects achieved by the method/step executed in the example shown in fig. 2, which are not described herein again for brevity.
In one example, the electronic device can also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 to complete communication therebetween.
The communication interface 503 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and the non-mobile electronic devices described above.
The electronic device may execute the call restriction method in the embodiment of the present application, thereby implementing the call restriction method described in conjunction with fig. 2 to 3.
In addition, in combination with the call restriction method in the foregoing embodiments, the embodiments of the present application may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the call restriction methods in the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (11)
1. A method for call barring, comprising:
under the condition that call connection is established with a suspected abnormal number, playing first voice information, wherein the first voice information is used for inquiring historical call intention of the suspected abnormal number;
under the condition that second voice information of the suspected abnormal number is obtained, determining abnormal type information of the suspected abnormal number according to the second voice information;
determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number;
and performing call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
2. The method of claim 1, wherein after establishing a call connection with the suspected abnormal number and before playing the first voice message, the method further comprises:
converting the acquired voice information of the suspected abnormal number into a first frequency spectrum;
identifying a meta-information tag of the first spectrum using a pre-trained meta-information extraction model;
and determining the first voice information according to the meta-information tag.
3. The method according to claim 1, wherein the determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number comprises:
predicting the calling times of the suspected abnormal number in the next time period by using a pre-trained calling time prediction model;
and determining the target call completing rate of the suspected abnormal number in the next time interval according to the predicted calling times and the preset maximum calling quantity of the number of the abnormal type to which the suspected abnormal number belongs in the next time interval.
4. The method of claim 3, wherein the call number prediction model is trained by:
the method comprises the steps of obtaining complaint quantity of various abnormal numbers in a first preset time period and calling characteristic indexes of various abnormal numbers in a second preset time period, and generating characteristic matrixes of various suspected abnormal numbers, wherein the calling characteristic indexes comprise at least one of calling frequency, dispersion, calling interval, call completing rate and calling duration;
and training to obtain the calling frequency prediction model based on the LASSO regression model and the feature matrixes of the various abnormal numbers.
5. The method of claim 4, wherein the training of the call times prediction model based on the LASSO regression model and the feature matrices of the classes of abnormal numbers comprises:
the following cost function is configured:
wherein M is the number of various abnormal numbers, p is the number of calling characteristic indexes, and x ij Is a feature matrix, w j Is a characteristic coefficient;
taking the calling frequency of each type of abnormal number in the second preset time period as a dependent variable, and taking calling characteristic indexes except the calling frequency as independent variables for training;
and taking the model with the lowest value of the cost function as the call frequency prediction model.
6. A call restriction device, comprising:
the system comprises a playing module, a processing module and a processing module, wherein the playing module is used for playing first voice information under the condition that call connection is established with a suspected abnormal number, and the first voice information is used for inquiring the historical call intention of the suspected abnormal number;
the first determining module is used for determining the abnormal type information of the suspected abnormal number according to the second voice information under the condition that the second voice information of the suspected abnormal number is obtained;
the second determining module is used for determining the target call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number;
and the limiting module is used for carrying out call limitation on the suspected abnormal number so that the call completing rate of the suspected abnormal number does not exceed the target call completing rate.
7. A call restriction system is characterized by comprising an outbound management device, a media bridging device, a voice control device and a call control device;
the outbound management device is to: establishing call connection with the suspected abnormal number;
the media bridging device is to: playing first voice information, acquiring second voice information of the suspected abnormal number, and forwarding the second voice information to the voice control device, wherein the first voice information is used for inquiring the historical calling intention of the suspected abnormal number;
the voice control device is used for: determining abnormal type information of the suspected abnormal number according to the second voice information, and sending the abnormal type information of the suspected abnormal number to the call control device;
the call control device is configured to: and controlling the call completing rate of the suspected abnormal number according to the abnormal type information of the suspected abnormal number.
8. The system of claim 7, wherein the voice control device is further configured to:
performing model training on the voice information forwarded by the media bridging device to generate a meta-information extraction model;
determining the first speech information using the meta-information extraction model;
and sending the determined first voice information to the media bridging device.
9. The system according to claim 7, wherein the call control means is pre-configured with a call number prediction model;
the call control device is specifically configured to:
predicting the calling times of the suspected abnormal number in the next time period by using the calling time prediction model;
and determining the target call completing rate of the suspected abnormal number in the next time interval according to the predicted calling times and the preset maximum calling quantity of the number of the abnormal type to which the suspected abnormal number belongs in the next time interval.
10. An electronic device, comprising: a processor, and a memory storing computer program instructions;
the processor reads and executes the computer program instructions to implement the call restriction method of any one of claims 1 to 5.
11. A computer storage medium having computer program instructions stored thereon which, when executed by a processor, implement the call restriction method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686147.0A CN115580680A (en) | 2021-06-21 | 2021-06-21 | Call restriction method, device, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686147.0A CN115580680A (en) | 2021-06-21 | 2021-06-21 | Call restriction method, device, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115580680A true CN115580680A (en) | 2023-01-06 |
Family
ID=84579484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110686147.0A Pending CN115580680A (en) | 2021-06-21 | 2021-06-21 | Call restriction method, device, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115580680A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104735272A (en) * | 2013-12-24 | 2015-06-24 | 中国移动通信集团贵州有限公司 | Crank call interception method and system |
| CN111064850A (en) * | 2019-12-18 | 2020-04-24 | 上海欣方智能系统有限公司 | System and method for realizing prevention, control and reminding of crank calls based on communication network |
| CN111901473A (en) * | 2020-09-04 | 2020-11-06 | 中国平安人寿保险股份有限公司 | Incoming call processing method, device, equipment and storage medium |
-
2021
- 2021-06-21 CN CN202110686147.0A patent/CN115580680A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104735272A (en) * | 2013-12-24 | 2015-06-24 | 中国移动通信集团贵州有限公司 | Crank call interception method and system |
| CN111064850A (en) * | 2019-12-18 | 2020-04-24 | 上海欣方智能系统有限公司 | System and method for realizing prevention, control and reminding of crank calls based on communication network |
| CN111901473A (en) * | 2020-09-04 | 2020-11-06 | 中国平安人寿保险股份有限公司 | Incoming call processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107222865B (en) | Communication swindle real-time detection method and system based on suspicious actions identification | |
| US10262195B2 (en) | Predictive and responsive video analytics system and methods | |
| CN110910901B (en) | Emotion recognition method and device, electronic equipment and readable storage medium | |
| AU2021231850B2 (en) | Systems and methods of speaker-independent embedding for identification and verification from audio | |
| CN109977202A (en) | A kind of intelligent customer service system and its control method | |
| CN101262524A (en) | Rubbish voice filtration method and system | |
| CN110188361A (en) | Speech intention recognition methods and device in conjunction with text, voice and emotional characteristics | |
| CN114338623B (en) | Audio processing method, device, equipment and medium | |
| CN107995370A (en) | Call control method, device and storage medium and mobile terminal | |
| CN104410973A (en) | Recognition method and system for tape played phone fraud | |
| CN1714390B (en) | Speech recognition device and method | |
| CN110489519B (en) | Session method based on session prediction model and related products | |
| CN115662431A (en) | Voice robot communication method and device adopting high-generalization multitask intention recognition | |
| CN110556114B (en) | Speaker identification method and device based on attention mechanism | |
| CN115580680A (en) | Call restriction method, device, system, electronic equipment and storage medium | |
| CN115659217A (en) | Fraud recognition model training method and device, electronic equipment and storage medium | |
| US11606461B2 (en) | Method for training a spoofing detection model using biometric clustering | |
| CN112687293A (en) | Intelligent agent training method and system based on machine learning and data mining | |
| CN113539275B (en) | Method, device and storage medium for determining speech technology | |
| CN113314103A (en) | Illegal information identification method and device based on real-time speech emotion analysis | |
| Militani et al. | A speech quality classifier based on signal information that considers wired and wireless degradations | |
| US20240233709A1 (en) | Systems and methods of speaker-independent embedding for identification and verification from audio | |
| CN116564294A (en) | Training method and device for noise identification model | |
| CN118301618A (en) | Anti-telecommunication phishing dissuading processing method based on big data | |
| CN117577107A (en) | Method, device and equipment for matching discouraging strategy based on voice dialogue information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |