CN105721660B - Harassing call recognition methods and system - Google Patents
Harassing call recognition methods and system Download PDFInfo
- Publication number
- CN105721660B CN105721660B CN201610076781.1A CN201610076781A CN105721660B CN 105721660 B CN105721660 B CN 105721660B CN 201610076781 A CN201610076781 A CN 201610076781A CN 105721660 B CN105721660 B CN 105721660B
- Authority
- CN
- China
- Prior art keywords
- call
- value
- advance
- incoming
- harassing
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/66—Substation equipment, e.g. for use by subscribers with means for preventing unauthorised or fraudulent calling
- H04M1/663—Preventing unauthorised calls to a telephone set
Abstract
The present invention provides a kind of harassing call recognition methods and system, wherein method includes:Incoming call analyzing step, parses incoming call, to obtain incoming information analysis result, wherein incoming information analysis result includes user behavior information and call natural language processing information;Step is calculated, user behavior information and call natural language processing information are respectively calculated, first is obtained and comments value and second to comment value in advance in advance;Determination step is commented value and second to comment value in advance, to obtain handling result, and handling result is matched with default label, obtains judgement result in advance according to preset algorithm processing first.The method automatically can carry out incoming call to judge whether incoming call is harassing call by analyzing user behavior, to reduce the energy and time that user handles harassing call, also can avoid user and harassed, swindle and threaten by harassing call.
Description
Technical field
The present invention relates to natural language processing field more particularly to a kind of harassing call recognition methods and systems.
Background technology
Currently, while people enjoy mobile communication and offer convenience, the puzzlement of harassing call is also often suffered from, very much
User can be connected to the harassing call of cheat or sales force etc., receive such phone and waste time and have fooled risk.
Thus there is an urgent need for a kind of method judged automatically Stranger Calls number, judge whether the incoming call is harassing and wrecking electricity
Words, and the corresponding prompt message of client can be given, client decides whether to receive calls according to prompt message.
Invention content
A kind of harassing call recognition methods of present invention offer and system, can to solve none of these methods in the prior art
Automatically to incoming call judged to identify whether be harassing call the technical issues of.
One aspect of the present invention provides a kind of harassing call recognition methods, including:
Incoming call analyzing step, parses incoming call, to obtain incoming information analysis result, wherein incoming information parses
As a result include user behavior information and call natural language processing information;
Step is calculated, user behavior information and call natural language processing information are respectively calculated, it is pre- to obtain first
Value and second is commented to comment value in advance;
Determination step comments value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result, and will place
Reason result is matched with default label, obtains judgement result.
Further, calculating step includes:
Preset value is assigned to user behavior information, and to the duration of call, voice frequency, the dialing etc. in user behavior information
It waits for that duration and active number dialing telephone call are handled, value is commented in advance to obtain first.
Further, determination step includes:
Handling result is obtained according to preset formula D=x*A+y*B, wherein x is the first pre- weight for commenting value, and y is second pre-
The weight of value, A is commented to comment value, B to comment value in advance for second in advance for first.
Further, calculating step further includes:
User's communication content is monitored, call voice is obtained;
Call voice is converted into text;
Using natural language processing technique to text-processing, obtains second and comment value in advance.
Further, before analyzing step of sending a telegram here, further include:
Step is prejudged, incoming number is prejudged, is prejudged as a result, it includes harassing call and not true to prejudge result
It is two kinds fixed;
If it is uncertain to prejudge result, transfers electric analyzing step and execute.
Further, determination step further includes after obtaining handling result:
Judge that incoming call is harassing call, doubtful harassing call or non-harassing call according to handling result, and provides the user with
Corresponding prompt message;
If incoming call is harassing call, incoming call labeled as harassing call and is stored to database.
Another aspect of the present invention provides a kind of harassing call identifying system, including:
Incoming call parsing module obtains incoming information analysis result, wherein carry out telecommunications for receiving incoming information and parsing
Breath analysis result includes user behavior information and call natural language processing information;
Computing module obtains for being respectively calculated to user behavior information and call natural language processing information
One comments value and second to comment value in advance in advance;
Determination module, for commenting value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result, and
Handling result is matched with default label, obtains judgement result.
Further, computing module is specifically used for:
Preset value is assigned to user behavior information, and to the duration of call, voice frequency, the dialing etc. in user behavior information
It waits for that duration and active number dialing telephone call are handled, value is commented in advance to obtain first.
Further, determination module is specifically used for:
Handling result is obtained according to preset formula D=x*A+y*B, wherein x is the first pre- weight for commenting value, and y is second pre-
The weight of value, A is commented to comment value, B to comment value in advance for second in advance for first.
Further, computing module is additionally operable to:
User's communication content is monitored, call voice is obtained;
Call voice is converted into text;
Using natural language processing technique to text-processing, obtains second and comment value in advance.
Harassing call recognition methods provided by the invention and system, are parsed by the incoming information to reception, are obtained
User behavior information and call natural language processing information, and to user behavior information and call natural language processing information difference
It is calculated, obtains first and comment value and second to comment value in advance in advance;Value and second is commented to comment value in advance in advance according to preset algorithm processing first, with
Handling result is obtained, and handling result is matched with default label, obtains judgement result.The method can be by user's row
Judged for information and call natural language processing information, to determine whether incoming call is harassing call, to reduce at user
The energy and time of harassing call is managed, while avoiding user from being harassed, swindle by harassing call and threatening.
Description of the drawings
The invention will be described in more detail below based on embodiments and refering to the accompanying drawings.Wherein:
Fig. 1 is the flow diagram according to the harassing call recognition methods of the embodiment of the present invention one;
Fig. 2 is the flow diagram according to the harassing call recognition methods of the embodiment of the present invention two;
Fig. 3 is the structural schematic diagram according to the harassing call identifying system of the embodiment of the present invention three;
Fig. 4 is the structural schematic diagram according to the harassing call identifying system of the embodiment of the present invention four.
In the accompanying drawings, identical component uses identical reference numeral.Attached drawing is not drawn according to actual ratio.
Specific implementation mode
The present invention will be further described with reference to the accompanying drawings.
A kind of harassing call recognition methods of present invention offer and system, can to solve none of these methods in the prior art
Automatically to incoming call judged to identify whether be harassing call the technical issues of.
Embodiment one
The executive agent of the present embodiment is harassing call identifying system.
Fig. 1 is according to the flow diagram of the harassing call recognition methods of the embodiment of the present invention one, as shown in Figure 1, this hair
A kind of bright harassing call recognition methods of offer, including:
Incoming call analyzing step 11, parses incoming call, to obtain incoming information analysis result, wherein incoming information solution
Analysis result includes user behavior information and call natural language processing information.
Specifically, user behavior information includes the information of user's communication behavior, such as the duration of call, voice frequency, dialing
Waiting time and active number dialing telephone call etc., these information can be obtained from the database of mobile phone, or be disturbed from support mobile phone
It disturbs and is obtained in the database of the server of phone identification, do not limited herein.Call natural language processing information includes that user is logical
Content is talked about, in the case where user authorizes agreement to monitor dialog context, dialog context is supervised using mobile phone software
It listens, and dialog context is stored into mobile phone database, or support in the database of server of mobile phone harassing call identification.
Step 12 is calculated, user behavior information and call natural language processing information are respectively calculated, obtain first
Value and second is commented to comment value in advance in advance.
Specifically, being calculated using user behavior information, obtain first and comment value in advance, is believed using call natural language processing
Breath is calculated, and is obtained second and is commented value in advance.
Determination step 13 comments value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result, and will
Handling result is matched with default label, obtains judgement result.
Specifically, comment value and second to comment value to be handled according to preset algorithm in advance in advance by first, handling result is obtained, at this
Reason result is a numerical value, which is matched with default label, that is, judges that handling result is fallen in default label
In which interval range, to know that incoming call is harassing call, doubtful harassing call or non-harassing call, judgement result is to disturb
Disturb one in phone, doubtful harassing call or non-harassing call.Default label concretely numerical intervals, if default label is set
It sets there are two threshold value, then available three numerical intervals, such as first threshold value are 0.4, second threshold value is 0.8, then presets
Three numerical intervals of label are respectively the first interval less than 0.4, are more than 0.4 and are less than 0.8 second interval and more than 0.8
3rd interval, and for falling the handling result in first interval, judgement result is harassing call, falls the processing in second interval
As a result, judgement result is doubtful harassing call, the handling result in 3rd interval is fallen, judgement result is non-harassing call.If
A threshold value is arranged in default label, then 2 numerical intervals are can get, if it is 0.4 that the threshold value, which is arranged, then pre- bidding at this time
The two values section of label is respectively the first interval less than 0.4 and the second interval more than 0.4, falls the processing in first interval
As a result, judgement result is harassing call or doubtful harassing call, the handling result in second interval is fallen, judgement result is non-harassing and wrecking
Phone.It is above-mentioned handling result to be fallen in the different judgement of the acquisition in different sections as a result, be carried out according to actual conditions flexible
Variation, only citing illustrates herein, does not limit.
Harassing call recognition methods provided by the invention, is parsed by the incoming information to reception, obtains user's row
For information and call natural language processing information, and to user behavior information and call natural language processing information count respectively
It calculates, obtains first and comment value and second to comment value in advance in advance;Value and second is commented to comment value in advance in advance according to preset algorithm processing first, to be located
Reason as a result, and handling result is matched with default label, obtain judge result.The method can be by user behavior information
Judged with call natural language processing information, i.e., according to user's once judgement to the incoming call behavioural information, is come to determine
Whether electricity is harassing call, handles the energy and time of harassing call to reduce user, while avoiding user by harassing and wrecking electricity
Harassing and wrecking, swindle and threatening of words etc..
Embodiment two
Fig. 2 is according to the flow diagram of the harassing call recognition methods of the embodiment of the present invention two, as shown in Fig. 2, this hair
A kind of bright harassing call recognition methods of offer, including:
Step 10 is prejudged, incoming number is prejudged, is prejudged as a result, the anticipation result includes harassing call
With uncertain two kinds;If the anticipation result is uncertain, the execution of electric analyzing step 11 is transferred.
Specifically, can be prejudged by retrieving incoming number in the database, prejudged as a result, prejudging result packet
It includes harassing call and does not know two kinds, for database dedicated for storing harassing call number, which is storable in mobile phone sheet
In ground storage, it may also set up in the server, after receiving incoming call, which be sent in database, in data
It is retrieved in library, if existing to the record that the incoming number is harassing call in database, then anticipation result is harassing and wrecking electricity
Words directly provide the prompt that the incoming call is harassing call to user at this time, if not retrieving the incoming number in database, that
It is uncertain to prejudge result, illustrates to also need to further to judge the incoming number, transfers electric analyzing step at this time
11 execute.
Incoming call analyzing step 11, parses incoming call, to obtain incoming information analysis result, wherein incoming information solution
Analysis result includes user behavior information and call natural language processing information.
For details, reference can be made to the records of corresponding steps in embodiment one for this step.
Step 12 is calculated, user behavior information and call natural language processing information are respectively calculated, obtain first
Value and second is commented to comment value in advance in advance.
Further, this step specifically includes:
Step 121, preset value is assigned to user behavior information, and to the duration of call in user behavior information, call frequency
Rate, dialing waiting time and active number dialing telephone call are handled, and value is commented in advance to obtain first.
Specifically, preset value is an input parameter value, it, can be by user's row when analyzing user behavior information
The relationship of value is commented to pass through in advance with first for the duration of call, voice frequency, dialing waiting time and the active number dialing telephone call in information
Expression formula calculates.Include the progress such as the duration of call, voice frequency, active number dialing telephone call and dialing waiting time to user behavior
Analysis, if the duration of call is more than 5 minutes, can regard as non-harassing call, and the duration of call can regard as harassing and wrecking electricity less than 30 seconds
Words, the duration of call can regard as doubtful harassing call between 30 seconds and 5 minutes, and the specific period can be flexibly arranged, herein
It does not limit.If voice frequency is higher, such as more than 5 times, non-harassing call can be regarded as, if number of pass times is no more than 2 times, can be recognized
It is set to harassing call, voice frequency can regard as doubtful harassing call between 2 times to 5 times, lead to if user has actively to dial
Words record can regard as non-harassing call more than 3 times, if active number dialing telephone call record only has 1 time, can regard as harassing call,
Active number dialing telephone call is recorded between 1 time to 3 times, can regard as doubtful harassing call.It is, of course, also possible to by the duration of call,
Voice frequency, active number dialing telephone call are judged that judgment method is flexible and changeable after being combined, details are not described herein, as long as will
User behavior includes the judgment method that the duration of call, voice frequency and active number dialing telephone call are included, and is protected in the present invention
Within the scope of.Such as it is that respective weight, the power is arranged in the duration of call, voice frequency, dialing waiting time and active number dialing telephone call
Weight can embody the influence that each information pair first in user behavior information comments value in advance, and preset value at this time is the weighted value, is passed through
The expression formula for the relationship that the duration of call, voice frequency, dialing waiting time and active number dialing telephone call comment value in advance with first, calculating obtains
It obtains first and comments value in advance.
Further, this step further includes specifically:
Step 122, user's communication content is monitored, obtains call voice;Call voice is converted into text;It utilizes
Natural language processing technique obtains second and comments value in advance to text-processing.
Natural language processing is computer science and an important directions in artificial intelligence field.It, which is studied, realizes
The various theoretical and methods of effective communication are carried out between people and computer by natural language.Since its research is related to nature language
Speech, i.e. people's language used in everyday, so it has inseparable relationship with philological research.It melts linguistics, calculates
In one, purpose is exactly the system that structure can effectively realize natural language communication for machine science, mathematics, statistics.By certainly
This technology of right Language Processing, can make machine have the ability for understanding natural language.
Incoming call is answered specifically, the premise that this step is able to carry out is user, and agrees to harassing call identification
System monitors user's communication content.The call voice listened to is converted into text by harassing call identifying system, then
Content of text is analyzed using natural language processing technique, can specifically pass through a large amount of trained language material and scene pair
Text is handled, and value is commented in advance to obtain second.
Further, if user to incoming call answered, but there is no agree to harassing call identifying system to
Family dialog context is monitored, then the dialog context of the incoming call is obtained from database, it is written to convert call voice
This, then analyzes content of text using natural language processing technique, value is commented in advance to obtain second, if in database
The dialog context of the incoming call is not stored, then second pre- to comment value be 0.
Further, step 122 further includes storing call voice into database, which can be data in mobile phone
Library, or support in the database of server of mobile phone harassing call identification.Dialog context is carried out to be disagreed in user
When monitoring, dialog context is obtained from database, and value is commented in advance to calculate acquisition second.
Determination step 13 comments value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result, and will
Handling result is matched with default label, obtains judgement result.
Further, this step specifically includes step 131:Handling result is obtained according to preset formula D=x*A+y*B,
In, it is the second pre- weight for commenting value that x comments the weight of value, y for first in advance, and A comments value, B to comment value in advance for second in advance for first.
Specifically, D is the handling result of incoming call, while considering the effect of user behavior information and user's communication content, two
The respective importance of person can be embodied by weight, then can be corresponding if stressing influence of the user behavior information to handling result
Increase first comment the weight x of value in advance, if stressing influence of the dialog context to result, the second pre- power for commenting value can be increased accordingly
The value of weight y, x and y can be configured according to actual conditions, x and y can be such as disposed as to the value less than 1, and sum of the two is 1.
Certainly, weight x and y can also be obtained by the model training in semantic understanding, more accurately to sentence to harassing call
It is disconnected.
Further, in this step after step 131, further include step 132:Judge that incoming call is to disturb according to handling result
Phone, doubtful harassing call or non-harassing call are disturbed, and provides the user with corresponding prompt message;If incoming call is harassing call,
Then incoming call labeled as harassing call and is stored to database.
Specifically, if it is determined that the result is that harassing call, can prompt user's " incoming call is harassing call ", user oneself is allowed to select
Whether answer, also can directly automatically hang up and be handled without waiting for user, if it is determined that the result is that doubtful harassing call, can prompt to use
Family " incoming call is doubtful harassing call ", allows user oneself to choose whether to answer, if it is determined that result is non-harassing call, can also not have to
Prompt is provided, directly user is waited for answer.
Certainly, if incoming call is harassing call, in order to constantly update the data library, incoming call can be labeled as harassing call
And store in database, when next time receives the incoming call again, can directly it be found in the database, it need not be using
A series of judgement can know the incoming call for harassing call.It is, of course, also possible to be carried out to non-harassing call and doubtful harassing call
It marks and stores into database, details are not described herein.
Harassing call recognition methods provided by the invention, is parsed by the incoming information to reception, obtains user's row
For information and call natural language processing information, and to user behavior information and call natural language processing information count respectively
It calculates, obtains first and comment value and second to comment value in advance in advance;Value and second is commented to comment value in advance in advance according to preset algorithm processing first, to be located
Reason as a result, and handling result is matched with default label, obtain judge result.The method can be by user behavior information
Judged with call natural language processing information, i.e., according to user's once judgement to the incoming call behavioural information, is come to determine
Whether electricity is harassing call, handles the energy and time of harassing call to reduce user, while avoiding user by harassing and wrecking electricity
Harassing and wrecking, swindle and threatening of words etc..
Embodiment three
The present embodiment is device embodiment, to execute above-mentioned harassing call recognition methods.
Fig. 3 is according to the structural schematic diagram of the harassing call identifying system of the embodiment of the present invention three, as shown in figure 3, this hair
A kind of bright harassing call identifying system of offer, including:Incoming call parsing module 21, computing module 22 and determination module 23.
Wherein, incoming call parsing module 21 obtains incoming information analysis result for receiving incoming information and parsing, wherein
Incoming information analysis result includes user behavior information and call natural language processing information;
Computing module 22 is obtained for being respectively calculated to user behavior information and call natural language processing information
First comments value and second to comment value in advance in advance;
Determination module 23, for commenting value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result,
And match handling result with default label, obtain judgement result.
The present embodiment is device embodiment corresponding with embodiment of the method one, and specific details can be found in retouching in embodiment one
It states, details are not described herein.
Harassing call identifying system provided by the invention, by sending a telegram here, parsing module 21 solves the incoming information of reception
Analysis, acquisition user behavior information and call natural language processing information, and to user behavior information and led to using computing module 22
Words natural language processing information is respectively calculated, and is obtained first and is commented value and second to comment value in advance in advance;Finally by determination module 23
First value and second is commented to comment value in advance in advance according to preset algorithm processing, to obtain handling result, and by handling result and default label
It is matched, obtains judgement result.This system can be by sentencing user behavior information and call natural language processing information
It is disconnected, i.e., according to user's once judgement to the incoming call behavioural information, to determine whether incoming call is harassing call, to reduce user
The energy and time of harassing call is handled, while avoiding user from being harassed, swindle by harassing call and threatening.
Example IV
The present embodiment is the supplementary explanation carried out on the basis of embodiment three.
Fig. 4 is according to the structural schematic diagram of the harassing call identifying system of the embodiment of the present invention four, as shown in figure 4, this hair
A kind of bright harassing call identifying system of offer, including:Prejudge module 20, incoming call parsing module 21, computing module 22 and judgement mould
Block 23.
Wherein, module 20 is prejudged, for being prejudged to incoming number, is prejudged as a result, it includes disturbing to prejudge result
It disturbs phone and does not know two kinds;If anticipation result is uncertain, triggering incoming call parsing module 21.
Incoming call parsing module 21 obtains incoming information analysis result for receiving incoming information and parsing, wherein incoming call
Information analysis result includes user behavior information and call natural language processing information.
Computing module 22 is obtained for being respectively calculated to user behavior information and call natural language processing information
First comments value and second to comment value in advance in advance.
Further, computing module 22 is specifically used for:
Preset value is assigned to user behavior information, and to the duration of call, voice frequency, the dialing etc. in user behavior information
It waits for that duration and active number dialing telephone call are handled, value is commented in advance to obtain first.
Further, computing module 22 is specifically additionally operable to:
User's communication content is monitored, call voice is obtained;Call voice is converted into text;Utilize natural language
Treatment technology obtains second and comments value in advance to text-processing.
Determination module 23, for commenting value and second to comment value in advance in advance according to preset algorithm processing first, to obtain handling result,
And match handling result with default label, obtain judgement result.
Further, determination module 23 is specifically used for:
Handling result is obtained according to preset formula D=x*A+y*B, wherein x is the first pre- weight for commenting value, and y is second pre-
The weight of value, A is commented to comment value, B to comment value in advance for second in advance for first.
The present embodiment is device embodiment corresponding with embodiment of the method two, and specific details can be found in retouching in embodiment two
It states, details are not described herein.
Although by reference to preferred embodiment, invention has been described, the case where not departing from the scope of the present invention
Under, various improvement can be carried out to it and can replace component therein with equivalent.Especially, as long as there is no structures to rush
Prominent, items technical characteristic mentioned in the various embodiments can be combined in any way.The invention is not limited in texts
Disclosed in specific embodiment, but include all technical solutions fallen within the scope of the appended claims.
Claims (8)
1. a kind of harassing call recognition methods, which is characterized in that including:
Incoming call analyzing step, parses incoming call, to obtain incoming information analysis result, wherein incoming information analysis result
Including user behavior information and call natural language processing information;
Step is calculated, the user behavior information and the call natural language processing information are respectively calculated, acquisition the
One comments value and second to comment value in advance in advance;
Determination step comments value and described second to comment value in advance in advance according to preset algorithm processing described first, to obtain handling result, and
The handling result is matched with default label, obtains judgement result;
Wherein, determination step includes:
Handling result is obtained according to preset formula D=x*A+y*B, wherein x is the described first pre- weight for commenting value, and y is described the
The two pre- weights for commenting value, A comment value, B to comment value in advance for described second in advance for described first.
2. harassing call recognition methods according to claim 1, which is characterized in that calculating step includes:
Preset value is assigned to user behavior information, and to the duration of call, voice frequency, the dialing etc. in the user behavior information
It waits for that duration and active number dialing telephone call are handled, value is commented in advance to obtain first.
3. harassing call recognition methods according to claim 1, which is characterized in that calculating step further includes:
User's communication content is monitored, call voice is obtained;
The call voice is converted into text;
Using natural language processing technique to the text-processing, obtains described second and comment value in advance.
4. according to any harassing call recognition methods of claim 1-3, which is characterized in that incoming call analyzing step it
Before, further include:
Step is prejudged, incoming number is prejudged, is prejudged as a result, the anticipation result includes harassing call and not true
It is two kinds fixed;
If the anticipation result is uncertain, turns the incoming call analyzing step and execute.
5. harassing call recognition methods according to claim 4, which is characterized in that the determination step is obtaining processing knot
After fruit, further include:
Judge that incoming call is harassing call, doubtful harassing call or non-harassing call according to the handling result, and provides the user with
Corresponding prompt message;
If the incoming call is harassing call, the incoming call labeled as harassing call and is stored to database.
6. a kind of harassing call identifying system, which is characterized in that including:
Incoming call parsing module obtains incoming information analysis result for receiving incoming information and parsing, wherein incoming information solution
Analysis result includes user behavior information and call natural language processing information;
Computing module is obtained for being respectively calculated to the user behavior information and the call natural language processing information
Obtain first comments value and second to comment value in advance in advance;
Determination module, for commenting value and described second to comment value in advance in advance according to preset algorithm processing described first, to obtain processing knot
Fruit, and the handling result is matched with default label, obtain judgement result;
Wherein, determination module is specifically used for:
Handling result is obtained according to preset formula D=x*A+y*B, wherein x is the described first pre- weight for commenting value, and y is described the
The two pre- weights for commenting value, A comment value, B to comment value in advance for described second in advance for described first.
7. harassing call identifying system according to claim 6, which is characterized in that computing module is specifically used for:
To the user behavior information assign preset value, and in the user behavior information the duration of call, voice frequency, dial
Number waiting time and active number dialing telephone call are handled, and value is commented in advance to obtain described first.
8. harassing call identifying system according to claim 6, which is characterized in that computing module is additionally operable to:
User's communication content is monitored, call voice is obtained;
The call voice is converted into text;
Using natural language processing technique to the text-processing, obtains described second and comment value in advance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610076781.1A CN105721660B (en) | 2016-02-03 | 2016-02-03 | Harassing call recognition methods and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610076781.1A CN105721660B (en) | 2016-02-03 | 2016-02-03 | Harassing call recognition methods and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105721660A CN105721660A (en) | 2016-06-29 |
CN105721660B true CN105721660B (en) | 2018-09-11 |
Family
ID=56155639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610076781.1A Active CN105721660B (en) | 2016-02-03 | 2016-02-03 | Harassing call recognition methods and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105721660B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106331390B (en) * | 2016-11-23 | 2019-04-30 | 杭州东信北邮信息技术有限公司 | A kind of method and system identifying swindle number based on communicating data |
CN108271158A (en) * | 2016-12-31 | 2018-07-10 | 中国移动通信集团辽宁有限公司 | Call processing method and system |
CN106878528A (en) * | 2017-01-23 | 2017-06-20 | 北京思特奇信息技术股份有限公司 | A kind of disturbance incoming call SMS interception method and system based on block chain technology |
CN107765700A (en) * | 2017-10-01 | 2018-03-06 | 上海量科电子科技有限公司 | Use householder method, system and the aircraft of mobile terminal |
CN108366173A (en) * | 2018-01-05 | 2018-08-03 | 腾讯科技(深圳)有限公司 | A kind of phone recognition methods, relevant device and system |
US10477021B1 (en) | 2018-11-29 | 2019-11-12 | Capital One Services, Llc | Systems for detecting harassing communication |
CN111343330A (en) * | 2019-03-29 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Smart phone |
CN112151070B (en) * | 2019-06-26 | 2023-05-05 | 杭州海康威视数字技术股份有限公司 | Voice detection method and device and electronic equipment |
US11582344B2 (en) * | 2019-08-16 | 2023-02-14 | Kingstar Technologies, Inc. | Displaying a textual message based on configuration of the user equipment |
CN111930808B (en) * | 2020-09-16 | 2021-05-07 | 浙江鹏信信息科技股份有限公司 | Method and system for improving blacklist accuracy by using key value matching model |
CN113766069B (en) * | 2021-09-06 | 2023-08-18 | 中国银行股份有限公司 | Harassment call interception method and device |
CN114339639B (en) * | 2021-12-27 | 2023-05-12 | 中国电信股份有限公司 | Call identification method, device, storage medium and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7552054B1 (en) * | 2000-08-11 | 2009-06-23 | Tellme Networks, Inc. | Providing menu and other services for an information processing system using a telephone or other audio interface |
CN104618554A (en) * | 2014-12-18 | 2015-05-13 | 惠州Tcl移动通信有限公司 | Method and terminal for automatically saving unknown caller number by recognizing voice content |
CN104717674A (en) * | 2014-12-02 | 2015-06-17 | 北京奇虎科技有限公司 | Number attribute recognition method and device, terminal and server |
-
2016
- 2016-02-03 CN CN201610076781.1A patent/CN105721660B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7552054B1 (en) * | 2000-08-11 | 2009-06-23 | Tellme Networks, Inc. | Providing menu and other services for an information processing system using a telephone or other audio interface |
CN104717674A (en) * | 2014-12-02 | 2015-06-17 | 北京奇虎科技有限公司 | Number attribute recognition method and device, terminal and server |
CN104618554A (en) * | 2014-12-18 | 2015-05-13 | 惠州Tcl移动通信有限公司 | Method and terminal for automatically saving unknown caller number by recognizing voice content |
Also Published As
Publication number | Publication date |
---|---|
CN105721660A (en) | 2016-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105721660B (en) | Harassing call recognition methods and system | |
CN106550155B (en) | Swindle sample is carried out to suspicious number and screens the method and system sorted out and intercepted | |
CN105261362B (en) | A kind of call voice monitoring method and system | |
CN106791229A (en) | The identification method and device of number | |
CN106024015A (en) | Call center agent monitoring method and system | |
CN108833722A (en) | Audio recognition method, device, computer equipment and storage medium | |
CN107093431A (en) | A kind of method and device that quality inspection is carried out to service quality | |
WO2015007107A1 (en) | Device and method for performing quality inspection on service quality of customer service staff | |
CN102622696B (en) | A kind of method and apparatus of customer service return visit | |
CN106302933B (en) | Voice information processing method and terminal | |
CN101621393A (en) | Determining a preferable mode of communicating with a called party | |
CN104717674A (en) | Number attribute recognition method and device, terminal and server | |
CN110337059A (en) | A kind of parser, server and the network system of subscriber household relationship | |
CN111128241A (en) | Intelligent quality inspection method and system for voice call | |
CN107332765A (en) | Method and apparatus for repairing router failure | |
CN112995422A (en) | Call control method and device, electronic equipment and storage medium | |
JP2008257539A (en) | Communication analyzing device and method | |
CN106791237A (en) | For consumers' opinions processing unit, the system and method for Utilities Electric Co. | |
CN108965613A (en) | Method, storage medium and application server based on the monitoring of collection system quality | |
CN109120613B (en) | Communication data monitoring method and system | |
CN104715045A (en) | Information transmitting method and terminal | |
CN105657146B (en) | A kind of communication information prompt method and device | |
CN108347531A (en) | Recourse method, recourse device, electronic equipment and computer readable storage medium | |
CN106817710A (en) | The localization method and device of a kind of network problem | |
CN108335213A (en) | Declaration form tip-offs about environmental issues processing method and processing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |