CN106686191A - Processing method for adaptively identifying harassing call and processing system thereof - Google Patents

Processing method for adaptively identifying harassing call and processing system thereof Download PDF

Info

Publication number
CN106686191A
CN106686191A CN201510752441.1A CN201510752441A CN106686191A CN 106686191 A CN106686191 A CN 106686191A CN 201510752441 A CN201510752441 A CN 201510752441A CN 106686191 A CN106686191 A CN 106686191A
Authority
CN
China
Prior art keywords
number
harassing
suspicion
harassing call
terminal
Prior art date
Application number
CN201510752441.1A
Other languages
Chinese (zh)
Inventor
王务志
王军
Original Assignee
北京奇虎科技有限公司
奇智软件(北京)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京奇虎科技有限公司, 奇智软件(北京)有限公司 filed Critical 北京奇虎科技有限公司
Priority to CN201510752441.1A priority Critical patent/CN106686191A/en
Publication of CN106686191A publication Critical patent/CN106686191A/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L29/00Arrangements, apparatus, circuits or systems, not covered by a single one of groups H04L1/00 - H04L27/00
    • H04L29/02Communication control; Communication processing
    • H04L29/06Communication control; Communication processing characterised by a protocol
    • H04L29/08Transmission control procedure, e.g. data link level control procedure
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers; Analogous equipment at exchanges
    • H04M1/66Substation equipment, e.g. for use by subscribers; Analogous equipment at exchanges with means for preventing unauthorised or fraudulent calling
    • H04M1/663Preventing unauthorised calls to a telephone set

Abstract

The invention discloses a processing method for adaptively identifying a harassing call and a processing system thereof. The processing method comprises the steps that trigging of an answer key is detected, and a terminal built-in recorder is automatically started to recording voice in the conversation process; the suspicion of the harassing call of the current answer number read from the screen of the terminal is judged, and the characters corresponding to the audios recorded by the recorder are analyzed and multiple keywords are extracted from the characters if the suspicion exists; and the keywords are matched with experience words collected in a database in advance in turn; and when the matching hit rate of the keywords exceeds the preset threshold, matching is stopped and the current answer number is determined to be the harassing number. The conversation process is recorded and the keywords in the record are extracted for matching so as to judge and set whether the unknown number is the harassing call.

Description

A kind of processing method and system of self-adapting estimation harassing call

Technical field

The application belongs to moving communicating field, specifically, is related to the processing method and system of a kind of self-adapting estimation harassing call.

Background technology

With the development of the communication technology, increasing businessman, lawless person are in order to reach the purpose of profit, ad promotions, illegal publicity and financial swindling are carried out by means of communication technologys such as mobile phone, landline telephone, networks, the Jing for causing many telephone subscribers is often harassed, in some instances it may even be possible to bring economic loss to individual.And the telephone number that prior art is mainly intercepted by record is realized intercepting, the keeping records table on service control point (SCP), the record sheet includes that one or more treat call interceptor number, receive Service Switching Point send including calling number and called number Initial Detection Point message when, service control point judges that whether the calling number is that call interceptor number is treated in configuration according to record sheet, obtain judged result, the calling is processed further according to judged result, the calling intercepted required for intercept called number correspondence user, but above-mentioned hold-up interception method can only intercept the blacklist number of called subscriber's setting, can not differentiate and arrange whether the unknown phone number not set is harassing call automatically.

Therefore, how to solve to differentiate and arrange whether the unknown phone number not set is harassing call automatically, become as technical problem urgently to be resolved hurrily.

The content of the invention

In view of this, technical problems to be solved in this application there is provided a kind of processing method and system of self-adapting estimation harassing call, to solve the problems, such as prior art in cannot differentiate and whether the unknown phone number not set is set automatically as harassing call.

In order to solve above-mentioned technical problem, this application discloses a kind of processing method of self-adapting estimation harassing call, is applied to mobile terminal, including:Detect and answer button and be triggered, automatically turn on terminal built-in phonographic recorder and voice in communication process is recorded;Judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple keywords are extracted from the word, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;By the harassing and wrecking number plus harassing and wrecking label, and the webserver is uploaded to by number is harassed described in the crucial word association.

This application discloses a kind of processing system of self-adapting estimation harassing call, is applied to mobile terminal, including:Triggering recording module, answers button and is triggered for detecting, and automatically turns on terminal built-in phonographic recorder and voice in communication process is recorded;Voice match module, for judging currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple keywords are extracted from the word, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;Associated storage module, for the harassing and wrecking number to be added into harassing and wrecking label, and uploads to the webserver by number is harassed described in the crucial word association.

Compared with prior art, the application can be obtained including following technique effect:

1) by recording to communication process, and extract multiple keywords from recording, if keyword shoots straight in setting threshold values with the advance experience terminology match collected, determine that the number is harassing call, realize whether the unknown phone number for differentiating and not setting automatically is harassing call.

2) multiple keywords are extracted from recording, if keyword shoots straight in setting threshold values with the advance experience terminology match collected, determines that the number is harassing call, the matching of multiple keywords reduces the probability of erroneous judgement harassing call.

3) by the harassing and wrecking number plus harassing and wrecking label, and upload to the webserver by number is harassed described in the crucial word association, point out when alloing other terminals again by the number call, the harassing and wrecking number of each terminal is collected by real-time performance is shared and is pointed out.

Certainly, implementing arbitrary product of the application must be not necessarily required to while reaching all the above technique effect.

Description of the drawings

Accompanying drawing described herein is used for providing further understanding of the present application, constitutes the part of the application, and the schematic description and description of the application is used to explain the application, does not constitute the improper restriction to the application.In the accompanying drawings:

Fig. 1 is the processing method of the identification harassing call of the embodiment of the present application;

Fig. 2 is the processing method of the another identification harassing call of the embodiment of the present application;

Fig. 3 is the processing method of the another identification harassing call of the embodiment of the present application;

Fig. 4 is the Organization Chart of the processing system of the identification harassing call of the embodiment of the present application.

Specific embodiment

Describe presently filed embodiment in detail below in conjunction with drawings and Examples, thereby to the application how application technology means come solve technical problem and reach technology effect realize that process can fully understand and implement according to this.

The current interception to harassing call, mainly by intercepting the blacklist number that called subscriber sets, can not differentiate and arrange whether the unknown phone number not set is harassing call automatically, and the application to communication process by recording, and extract multiple keywords from recording, if keyword shoots straight in setting threshold values with the advance experience terminology match collected, determine that the number is harassing call, and harassing and wrecking number is uploaded into the webserver plus harassing and wrecking label association keyword, not only can differentiate and arrange whether the unknown phone number not set is harassing call automatically, the harassing and wrecking number of each terminal can also be collected by real-time performance and share and point out.

It is the processing method of the identification harassing call described in the application one embodiment shown in Fig. 1, including:

Step S100, detects and answers button and be triggered, and automatically turns on terminal built-in phonographic recorder and voice in communication process is recorded;

During incoming call, detect user's triggering to answer after button, automatically turn on terminal built-in phonographic recorder or recording software to record voice in communication process, user is voluntarily arranged to be recorded by terminal built-in phonographic recorder or recording software, and the preferable equipment of recorded audio quality can be selected to be recorded;

Step S102, judges currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then execution step S104;

During call, phonographic recorder can record to voice in communication process, no matter incoming call is normal telephone or harassing call, it is required for just to be learnt by the conversation audio analysis to recording, and when it is clearly not harassing call to receive calls, still needs the conversation audio to recording to be analyzed operation, equivalent to repeating, increased system operation burden and store burden, so suspicion judgement can be carried out before operation is analyzed to the conversation audio recorded, following several ways can be applied:

(1) user sees strangeness numbers when calling, especially atypical number, and the first reaction is exactly to think the possibly harassing call such as distribution or swindle, therefore, the application takes mode 1:The number of currently answering is matched one by one with storage number in terminal, it is described if matching is unsuccessful to answer number for strangeness numbers, and determine and described currently answer the suspicion that number has harassing call, wherein, all numbers that number includes being stored in address list, message registration and note case are stored in terminal.All numbers in traversal matching address list, message registration and note case, can determine the suspicion of harassing call by the condition of strangeness numbers in time, and can prevent from for user being considered strangeness numbers to the newest number not stored that communicates.

User receive calls in Recording Process or after End of Tape (such as:Very short time is hung up the telephone to record and is also just terminated therewith), will currently answer number and first matched successively with all telephone numbers in address list, then there is no harassing and wrecking suspicion when the match is successful and stop matching;If, all without the match is successful, continuation is matched with all numbers in message registration currently to answer all numbers in number and address list, then there is no harassing and wrecking suspicion when the match is successful and stop matching;If all the match is successful currently to answer all numbers in number and message registration, then continue to be matched with all numbers in note case, then there is no harassing and wrecking suspicion when the match is successful and stop matching, if all the match is successful currently to answer all numbers in number and note case, it is determined that described currently to answer the suspicion that number has harassing call;If telephone number is not strangeness numbers, with number in address list the match is successful degree highest, according to the matching order successively of address list, message registration and note case, can reduce match working strength.

(2) when user is connected to harassing call, due to content being told about it and being lost interest in or is had psychology is taken precautions against, usual user can select to hang up the telephone quickly to show refusal, therefore, the application takes mode 2:Whether judgement answers the air time less than Preset Time threshold values, if it is determines the suspicion that there is harassing call, and wherein Preset Time threshold values is to count the mean value that harassing call hangs up the time.

Phonographic recorder is carried out recording simultaneously timing to voice in communication process after user receives calls, when timing time exceedes Preset Time threshold values, it is determined that there is no the suspicion of harassing call;When End of Tape (user records and voluntarily terminate after hanging up the telephone, or user is manually operated stop recording) and timing time is less than Preset Time threshold values, if it is determines the suspicion that there is harassing call.The suspicion of harassing call is judged whether by timing air time length, be on the one hand it is simple to operate be easily obtained time value, be on the other hand that to there is no the result that any analysis phase error obtains more direct.

For example:After user receives calls; timer can carry out timing to the air time and show automatically on mobile phone screen; if other side is the people that user is familiar with or knows; user tells about it content will not be interested in and hang up the telephone quickly naturally; if other side is the potential personnel for promoting or swindling; user would generally tell about it content and lose interest in so as to think to terminate call as early as possible; continue to do the thing that user is doing; so; the suspicion of harassing call is determined using the mode for judging air time length, is not only operated directly but also the degree of accuracy is higher.

(3) when user is connected to harassing call; due to content being told about it and being lost interest in or is had take precautions against psychology; out of politeness user would generally hang up the telephone after mild and roundabout refusal; but it is sometimes based upon other side and constantly tells about different new contents, user carries out again mild and roundabout refusal after may understanding telling about content, in a word; no matter user is to telling about whether content understands; mild and roundabout refusal vocabulary necessarily occurs during the speech of user, therefore, the application takes mode 3:The user voice fragment that microphone is gathered is matched with the audio fragment that prestores in database, if Audio Matching similarity is more than default similar threshold values, then determine the suspicion that there is harassing call, wherein, the audio fragment that prestores is the audio frequency containing refusal mark vocabulary.The user voice that microphone is recognized directly does semantic analysis, because the user voice that microphone Direct Recognition is arrived is more three-dimensional and direct, so the corresponding word degree of accuracy is higher after semantic analysis, and causes the process of semantic analysis and Audio Matching more convenient.

The audio fragment that prestores is the audio frequency containing refusal mark vocabulary, for example:User says mild and roundabout refusal vocabulary such as " thanks, not need, being out of use, need not ".

It is timing Multitake recording or one section of whole recording that user can pre-set the user voice to microphone collection, what if user set be timing Multitake recording (user talk every time the dead time it is longer when as one recording fragment), then per section of recording is matched successively with the audio fragment that prestores in database, when there is recording matching similarity more than similar threshold values is preset, it is determined that the suspicion that there is harassing call and the matching for stopping remaining audio fragment;If what user set is one section of whole recording, whole process recording is matched with the audio fragment that prestores in database, such as Audio Matching similarity is more than default similar threshold values, it is determined that there is the suspicion of harassing call.The audio fragment of recording matches the matching for refusing vocabulary in actually audio fragment with the audio fragment that prestores, user is timing Multitake recording or one section of whole recording according to the actual demand of oneself setting, timing Multitake recording matching process is very fast but matching accuracy is relatively low, and one section whole recording matching process is relatively slow but matching accuracy is higher.

For example:After user receives calls, if it find that other side wants to push the sale of one's products, user mild and roundabout may say refusal vocabulary, other side can as far as possible talk about the content for attracting user during user refuses, so as to user may tell about the language understood its product, and while user talks, the user voice of microphone Real-time Collection, the sound clip semantic analysis for collecting is correspondence word on backstage by system, and the sound clip for collecting this and the Audio Matching containing the significant vocabulary of refusal, the suspicion that there is harassing call is determined when similarity is higher, to carry out subsequent treatment.

Certainly, all there is certain probability of error in above-mentioned three kinds of modes, and error is reduced it can be considered to be judged by way of with upper type synergistic combination, and concrete combination is as follows:

1) mode 1+ mode 2

The number of currently answering is matched one by one with storage number in terminal, it is described if matching is unsuccessful to answer number for strangeness numbers;Judge to answer that the air time, whether less than Preset Time threshold values, if it is determines the suspicion that there is harassing call again.

First determine whether whether current Number is strangeness numbers, if it is not necessarily so harassing call that current Number is not strangeness numbers, so determining whether the number is harassing call without any subsequent operation is carried out again;If current Number is strangeness numbers, whether it is further continued for judging its air time less than Preset Time threshold values, if current Number is strangeness numbers and air time to be less than Preset Time threshold values, it is determined that there is the suspicion of harassing call.

For example:When current Number is not strangeness numbers but stores number in mobile phone, it is likely to because time is pressing, telling about that content is simple etc. the time of hanging up the telephone short phenomenon occurs, will determine that strangeness numbers and judging the air time by way of combining determining whether there is the suspicion of harassing call, can avoid missing in this case and current Number is determined the suspicion that there is harassing call, improve accuracy of judgement degree.

2) mode 1+ mode 3

The number of currently answering is matched one by one with storage number in terminal, it is described if matching is unsuccessful to answer number for strangeness numbers;The user voice fragment that microphone is gathered is matched with the audio fragment that prestores in database again, if Audio Matching similarity is more than default similar threshold values, it is determined that there is the suspicion of harassing call.

First determine whether whether current Number is strangeness numbers, if it is not necessarily so harassing call that current Number is not strangeness numbers, so determining whether the number is harassing call without any subsequent operation is carried out again;If current Number is strangeness numbers, it is further continued for being matched the user voice fragment that microphone is recognized with the audio fragment that prestores, if current Number is strangeness numbers and Audio Matching similarity more than presetting similar threshold values, it is determined that there is the suspicion of harassing call.

For example:When current Number is not strangeness numbers but stores number in mobile phone, it is likely to the phenomenon for wanting occur the mild and roundabout refusal of user with a little presents etc. to user because other side goes on a tour, will determine that strangeness numbers and judging Audio Matching by way of combining determining whether there is the suspicion of harassing call, can avoid missing in this case and current Number is determined the suspicion that there is harassing call, improve accuracy of judgement degree.

Step S104, analyzes the corresponding word of audio frequency of phonographic recorder recording and multiple keywords is extracted from the word;

The suspicion of harassing call is either judged by above-mentioned which kind of mode, in order to avoid the operation for repeating to judge, only in the case of it is determined that current Number has harassing call suspicion, just continues to analyze the audio frequency that the communication process both sides of phonographic recorder recording speak.If the air time extremely short (recording terminates with end of conversation), then the process of analysis recording audio occurs after user hangs up the telephone, if in the case that the user's communication time is not extremely short;The process for so analyzing recording audio occurs in Recording Process, to be in real time analyzed recording, but either occurs to go back after hanging up the telephone in Recording Process, and the process of analysis recording audio is as follows:

The audio frequency of recording is converted into corresponding text using audio converter, then analyze in text word and carries out participle to the word, the part of speech table of comparisons in database judges the part of speech of each participle, choose a number of part of speech for verb and noun participle as keyword, the quantity and part of speech of keyword are limited respectively, keyword quality is improve, and then causes matching accuracy higher.

For example:Text after audio frequency conversion is " you are good, and we are so-and-so finance companies, and our companies newly release the various financing schemes for different wage-earners ", and we can carry out participle and be divided into one one to the text:You, it is good, we, be, so-and-so finance companies, we, company, it is new, release, for, different wage-earners, various, financing scheme;Then the participle to obtaining after division carries out duplicate removal process, the part of speech of each participle is recognized further according to the part of speech table of comparisons in database, due to verb and noun it is larger as the possibility of the keyword of a text, so a number of participle is chosen from verb and noun as keyword.

Step S106, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;

When the air time is excessively brief, the word that then recording audio is converted into will certainly be less, and then occur that extraction keyword is less in the word from after conversion, and utilize the inadequate objectivity of result of the less Keywords matching such as one or two, the degree of accuracy certainly will not be high, so, also comprise the steps when keyword is matched with experience vocabulary:

The keyword number of extraction is compared with predetermined minimum first, if keyword number is less than or equal to predetermined minimum, then the degree of accuracy of judged result is relatively low, abandon judging whether current Number is harassing call, if keyword number is more than predetermined minimum, then the multiple keywords for extracting are matched successively with the experience vocabulary collected in advance in database, each keyword respectively with had experience terminology match, stop matching if the match is successful, otherwise continue to match and think that matching is unsuccessful after had experience terminology match is finished;So proceed matching for next keyword and had experience vocabulary, when the match hit rate of keyword exceedes presets threshold values, stop matching and determine described currently to answer number for harassing and wrecking number;Extract multiple keywords to shoot straight in setting threshold values with the advance experience terminology match collected, determine that the number is harassing call, the matching of multiple keywords reduces the probability of erroneous judgement harassing call.

Wherein, the experience vocabulary collected in advance in database can be the significant vocabulary that insurance, house, financing, financial product, prize-winning etc. are promoted or swindled.

Step S108, by the harassing and wrecking number plus harassing and wrecking label, and uploads to the webserver by number is harassed described in the crucial word association.

The harassing and wrecking number is added into harassing and wrecking label for pointing out the number to be harassing call, and upload to the webserver by number is harassed described in all crucial word associations that the match is successful, the webserver can count the number of times for receiving the harassing and wrecking number information, also need to recognize whether the terminal for sending the harassing and wrecking number information is same terminal simultaneously, if the information of all number of times is all sent by same terminal, then there may exist malicious sabotage, in this case the webserver will not carry out any operation to the harassing and wrecking number information, if the number of times that the webserver receives the harassing and wrecking number information is more and respectively from different transmission terminals, it is unified after then the webserver collects to the harassing and wrecking number and its corresponding keyword to generate blacklist, so that the newest blacklist for generating is issued in time other terminals by the webserver, other terminals number is pointed out for harassing and wrecking number, and the harassing and wrecking number of each terminal is collected by real-time performance share and point out.

Label is harassed for adding the harassing and wrecking number in step S108 in Fig. 1, and is uploaded to number is harassed described in the crucial word association after the webserver, as shown in Fig. 2 also comprising the steps:

Step S200, receives the harassing call blacklist that the webserver side is sent, wherein, the harassing call blacklist is unified after the webserver collects according to harassing and wrecking label to harassing and wrecking number and correspondence keyword generation.

Terminal is received after the newest blacklist that the webserver is issued, and stores into terminal and delete original blacklist by newest blacklist in time, and the newest blacklist is set to apply interception prompting;The transmission times of the identical harassing and wrecking number that the webserver sends to each terminal is counted, if the information of all number of times is all sent by same terminal, malicious sabotage is then there may exist, in this case the webserver will not carry out any operation to the harassing and wrecking number information;If the transmission times of the number is more and respectively from different transmission terminals, then the webserver is unified after being collected to harassing and wrecking number and correspondence keyword according to the harassing and wrecking label that terminal sends generates harassing call blacklist, the webserver is constantly updated process to harassing call blacklist, newest harassing call blacklist is issued into each mobile terminal, to point out other terminals number for harassing and wrecking number.

Step S202, when phone incoming call is detected, the telephone number of identification incoming call, and carry out traversal comparison in the harassing call blacklist, as hit, then preset for telephone number prompting harassing and wrecking label or according to user and directly hang up Inbound Calls and point out the telephone number to be harassing call.

When detecting terminal and having phone incoming call, the telephone number of identification incoming call, and carry out traversal comparison in the newest harassing call blacklist that terminal is received, if the incoming call is consistent with harassing and wrecking number in blacklist, then it can be pointed out using the corresponding harassing and wrecking label of the incoming call, directly hang up Inbound Calls can preset according to user and point out the telephone number as harassing call, the harassing and wrecking number of each terminal be collected by real-time performance is shared and is pointed out.

It is the processing method of the identification harassing call described in the application another embodiment shown in Fig. 3, including:

Step S300, detects and answers button and be triggered, and automatically turns on terminal built-in phonographic recorder and voice in communication process is recorded;

During incoming call, detect user's triggering and answer after button, automatically turn on terminal built-in phonographic recorder or recording software and voice in communication process is recorded;

Step S302, judges currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is no suspicion, otherwise execution step S304, execution step S306;

Step S304, if there is no suspicion, then deletes the respective audio that phonographic recorder is recorded;

The respective audio recorded is deleted when there is no suspicion, can both mitigate the storage pressure of mobile terminal, can prevent terminal audio frequency storage chaotic again.

Step S306, analyzes the corresponding word of audio frequency of phonographic recorder recording and multiple keywords is extracted from the word;

Step S308, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;

Step S3010, by the harassing and wrecking number plus harassing and wrecking label, and uploads to the webserver by number is harassed described in the crucial word association.

The webserver can count the number of times for receiving the harassing and wrecking number information, also need to recognize whether the terminal for sending the harassing and wrecking number information is same terminal simultaneously, if the information of all number of times is all sent by same terminal, then there may exist malicious sabotage, in this case the webserver will not carry out any operation to the harassing and wrecking number information, if the number of times that the webserver receives the harassing and wrecking number information is more and respectively from different transmission terminals, it is unified after then the webserver collects to the harassing and wrecking number and its corresponding keyword to generate blacklist, then the newest blacklist for generating is issued in time other terminals by the webserver;

Terminal is received after the newest blacklist that the webserver is issued, and stores into terminal and delete original blacklist by newest blacklist in time, and the newest blacklist is set to apply interception prompting, such as:When the strange telephone number of incoming call is recognized, and carry out traversal comparison in the newest harassing call blacklist that terminal is received, if the incoming call is consistent with harassing and wrecking number in blacklist, then it can be pointed out using the corresponding harassing and wrecking label of the incoming call, directly hang up Inbound Calls can preset according to user and point out the telephone number as harassing call, the harassing and wrecking number of each terminal be collected by real-time performance is shared and is pointed out.

A new embodiment can also be formed after embodiment shown in Fig. 3 with reference to embodiment illustrated in fig. 2 content.

As shown in figure 4, the processing system of the identification harassing call described in the application one embodiment, including:

Triggering recording module 400, answers button and is triggered for detecting, and automatically turns on terminal built-in phonographic recorder and voice in communication process is recorded;

Voice match module 402, for judging currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple keywords are extracted from the word, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;

Associated storage module 404, for the harassing and wrecking number to be added into harassing and wrecking label, and uploads to the webserver by number is harassed described in the crucial word association.

Voice match module 402, it is further used for one by one being matched the number of currently answering with storage number in terminal, it is described if matching is unsuccessful to answer number for strangeness numbers, and determine it is described currently answer the suspicion that number has harassing call, wherein in the terminal store number include address list, message registration and note case in store all numbers.

Voice match module 402, is further used for judgement and whether answers the air time less than Preset Time threshold values, if it is determines the suspicion that there is harassing call.

Voice match module 402, it is further used for being matched the user voice fragment that microphone is gathered with the audio fragment that prestores in database, if Audio Matching similarity is more than default similar threshold values, then determine the suspicion that there is harassing call, wherein, the audio fragment that prestores is the audio frequency containing refusal mark vocabulary.

Voice match module 402, is further used for carrying out participle to the word, and the part of speech table of comparisons in database judges the part of speech of each participle, and the participle for choosing a number of part of speech for verb and noun is used as keyword.

Voice match module 402, is further used for if there is no suspicion, then deleting the respective audio that phonographic recorder is recorded.

Associated storage module 404, is additionally operable to receive the harassing call blacklist that the webserver side is sent, wherein, the harassing call blacklist is unified after the webserver collects according to harassing and wrecking label to harassing and wrecking number and correspondence keyword generation.

Associated storage module 404, it is further used for when phone incoming call is detected, the telephone number of identification incoming call, and carry out traversal comparison in the harassing call blacklist, as hit, then preset for telephone number prompting harassing and wrecking label or according to user and directly hang up Inbound Calls and point out the telephone number to be harassing call.

The processing system of the identification harassing call shown in Fig. 4, above-mentioned weak point for prompt operation system described in mutually corresponding with embodiment of the method feature and scheme shown in Fig. 1-3 refer to the description of the embodiment of the method shown in Fig. 1-3.

The application by receiving calls after communication process is recorded, and extract multiple keywords from recording, if keyword shoots straight in setting threshold values with the advance experience terminology match collected, determine that the number is harassing call, realize whether the unknown phone number for differentiating and not setting automatically is harassing call, you can so that the strangeness numbers beyond number are stored in voluntarily judging blacklist and terminal whether as harassing call.

In a typical configuration, computing device includes one or more processors (CPU), input/output interface, network interface and internal memory.

Internal memory potentially includes the volatile memory in computer-readable medium, the such as form such as random access memory (RAM) and/or Nonvolatile memory, read-only storage (ROM) or flash memory (flash RAM).Internal memory is the example of computer-readable medium.

Computer-readable medium includes that permanent and non-permanent, removable and non-removable media can realize information Store by any method or technique.Information can be computer-readable instruction, data structure, the module of program or other data.The example of the storage medium of computer includes, but it is not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk is stored or other magnetic storage apparatus or any other non-transmission medium, can be used to store the information that can be accessed by a computing device.Define according to herein, computer-readable medium does not include non-temporary computer readable media (transitory media), the such as data-signal and carrier wave of modulation.

As in specification and claim some vocabulary used in censuring specific components.Those skilled in the art are, it is to be appreciated that hardware manufacturer may call same component with different nouns.This specification and claims are not in the way of the difference of title is used as distinguishing component, but the difference with component functionally is used as the criterion distinguished.If the "comprising" in specification in the whole text and claim mentioned in is an open language, therefore should be construed to " include but be not limited to "." substantially " refer in receivable error range, those skilled in the art can solve the technical problem in the range of certain error, basically reach the technique effect.Additionally, " coupling " word here includes any directly and indirectly electric property coupling means.Therefore, if a first device is coupled to a second device described in text, representing the first device can directly be electrically coupled to the second device, or be electrically coupled to the second device indirectly by other devices or coupling means.Specification subsequent descriptions are to implement the better embodiment of the application, and so the description is for the purpose of the rule for illustrating the application, to be not limited to scope of the present application.The protection domain of the application ought be defined depending on the claims person of defining.

It can further be stated that, term " including ", "comprising" or its any other variant are intended to including for nonexcludability, so that not only including those key elements including the commodity or system of a series of key elements, but also including other key elements being not expressly set out, or also include the key element intrinsic for this commodity or system.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that also there is other identical element in the commodity or system including the key element.

Described above illustrates and describes some preferred embodiments of the application, but as previously mentioned, it should be understood that the present invention is not limited to form disclosed herein, it is not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and environment, and can be modified by the technology or knowledge of above-mentioned teaching or association area in invention contemplated scope described herein.And change that those skilled in the art are carried out and change be without departing from spirit and scope, then all should be in the protection domain of the application claims.

A1, a kind of processing method of self-adapting estimation harassing call, are applied to mobile terminal, including:

Detect and answer button and be triggered, automatically turn on terminal built-in phonographic recorder and voice in communication process is recorded;

Judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple keywords are extracted from the word, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;

By the harassing and wrecking number plus harassing and wrecking label, and the webserver is uploaded to by number is harassed described in the crucial word association.

A2, the method as described in claim a1, extract multiple keywords from the word, further include:Participle is carried out to the word, the part of speech table of comparisons in database judges the part of speech of each participle, the participle for choosing a number of part of speech for verb and noun is used as keyword.

A3, the method as described in claim a1, judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, further include:Currently answer described number and number is stored in terminal matched one by one, if match it is unsuccessful if the number of answering for strangeness numbers, and determine and described currently answer the suspicion that number has harassing call.

A4, the method as described in claim a3, store all numbers that number includes being stored in address list, message registration and note case in the terminal.

A5, the method as described in claim a1, judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, further include:Whether judgement answers the air time less than Preset Time threshold values, if it is determines the suspicion that there is harassing call.

Suspicion of the number with the presence or absence of harassing call is currently answered in a6, the method as described in claim a1, judgement, is further included:The user voice fragment that microphone is gathered is matched with the audio fragment that prestores in database, if Audio Matching similarity is more than default similar threshold values, then determine the suspicion that there is harassing call, wherein, the audio fragment that prestores is the audio frequency containing refusal mark vocabulary.

A7, the method as described in claim a1, receive the harassing call blacklist that the webserver side is sent, wherein, the harassing call blacklist is unified after the webserver collects according to harassing and wrecking label to harassing and wrecking number and correspondence keyword generation.

A8, the method as described in claim a7, when phone incoming call is detected, the telephone number of identification incoming call, and carry out traversal comparison in the harassing call blacklist, as hit, then preset for telephone number prompting harassing and wrecking label or according to user and directly hang up Inbound Calls and point out the telephone number to be harassing call.

A9, the method as described in claim a1, judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, further include:If there is no suspicion, then the respective audio that phonographic recorder is recorded is deleted.

B10, a kind of processing system of self-adapting estimation harassing call, are applied to mobile terminal, including:

Triggering recording module, answers button and is triggered for detecting, and automatically turns on terminal built-in phonographic recorder and voice in communication process is recorded;

Voice match module, for judging currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if there is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple keywords are extracted from the word, the keyword is matched with the experience vocabulary collected in advance in database successively, when the match hit rate of the keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;

Associated storage module, for the harassing and wrecking number to be added into harassing and wrecking label, and uploads to the webserver by number is harassed described in the crucial word association.

B11, the system as described in claim b10, the voice match module, it is further used for carrying out participle to the word, the part of speech table of comparisons in database judges the part of speech of each participle, the participle for choosing a number of part of speech for verb and noun is used as keyword.

B12, the system as described in claim b10, the voice match module, it is further used for one by one being matched the number of currently answering with storage number in terminal, if match it is unsuccessful if the number of answering for strangeness numbers, and determine and described currently answer the suspicion that number has harassing call.

B13, the system as described in claim b12, the voice match module is further used in the terminal storing all numbers that number includes being stored in address list, message registration and note case.

B14, the system as described in claim b10, the voice match module is further used for judgement and whether answers the air time less than Preset Time threshold values, if it is determines the suspicion that there is harassing call.

B15, the system as described in claim b10, the voice match module, it is further used for being matched the user voice fragment that microphone is gathered with the audio fragment that prestores in database, if Audio Matching similarity is more than default similar threshold values, then determine the suspicion that there is harassing call, wherein, the audio fragment that prestores is the audio frequency containing refusal mark vocabulary.

B16, the system as described in claim b10, the associated storage module, it is additionally operable to receive the harassing call blacklist that the webserver side is sent, wherein, the harassing call blacklist is unified after the webserver collects according to harassing and wrecking label to harassing and wrecking number and correspondence keyword generation.

B17, the system as described in claim b16, the associated storage module, it is further used for when phone incoming call is detected, the telephone number of identification incoming call, and carry out traversal comparison in the harassing call blacklist, as hit, then preset for telephone number prompting harassing and wrecking label or according to user and directly hang up Inbound Calls and point out the telephone number to be harassing call.

B18, the system as described in claim b10, the voice match module is further used for if there is no suspicion, then deleting the respective audio that phonographic recorder is recorded.

Claims (10)

1. a kind of processing method of self-adapting estimation harassing call, is applied to mobile terminal, and its feature exists In, including:
Detect and answer button and be triggered, automatically turn on terminal built-in phonographic recorder and voice in communication process is entered Row recording;
Judge currently to answer suspicion of the number with the presence or absence of harassing call by what is read on terminal screen, if There is suspicion, then analyze the corresponding word of audio frequency of phonographic recorder recording and multiple passes are extracted from the word Keyword, is successively matched the keyword with the experience vocabulary collected in advance in database, when described When the match hit rate of keyword exceedes setting threshold values, stop matching and determine that the number of currently answering is Harassing and wrecking number, wherein the experience vocabulary is the significant vocabulary in the dialog context of harassing call;
By the harassing and wrecking number plus harassing and wrecking label, and upload number is harassed described in the crucial word association To the webserver.
2. the method for claim 1, it is characterised in that multiple passes are extracted from the word Keyword, further includes:Participle is carried out to the word, the part of speech table of comparisons in database judges The part of speech of each participle, the participle for choosing a number of part of speech for verb and noun is used as key Word.
3. the method for claim 1, it is characterised in that judge by reading on terminal screen Suspicion of the number with the presence or absence of harassing call is currently answered, is further included:Number is currently answered by described Matched one by one with number is stored in terminal, it is described if matching is unsuccessful to answer number for strange number Code, and determine and described currently answer the suspicion that number has harassing call.
4. method as claimed in claim 3, it is characterised in that number is stored in the terminal to be included The all numbers stored in address list, message registration and note case.
5. the method for claim 1, it is characterised in that judge by reading on terminal screen Suspicion of the number with the presence or absence of harassing call is currently answered, is further included:Judge that answering the air time is It is no less than Preset Time threshold values, if it is determine the suspicion that there is harassing call.
6. a kind of processing system of self-adapting estimation harassing call, is applied to mobile terminal, and its feature exists In, including:
Triggering recording module, answers button and is triggered for detecting, and automatically turns on terminal built-in phonographic recorder Voice in communication process is recorded;
Voice match module, for judging currently to answer number with the presence or absence of disturbing by what is read on terminal screen The suspicion of phone is disturbed, if there is suspicion, then the corresponding word of audio frequency of phonographic recorder recording is analyzed and from institute State and extract in word multiple keywords, the experience word that will in advance collect in the keyword and database successively Remittance is matched, and when the match hit rate of the keyword exceedes setting threshold values, is stopped matching and is determined It is described currently to answer number to harass number, wherein the experience vocabulary is in the dialog context of harassing call Significant vocabulary;
Associated storage module, for the harassing and wrecking number to be added into harassing and wrecking label, and the keyword is closed The connection harassing and wrecking number uploads to the webserver.
7. system as claimed in claim 6, it is characterised in that the voice match module, enters one Walk for carrying out participle to the word, the part of speech table of comparisons in database judges described each participle Part of speech, choose participle that a number of part of speech is verb and noun as keyword.
8. system as claimed in claim 6, it is characterised in that the voice match module, enters one Walk for the number of currently answering to be matched one by one with storage number in terminal, if matching is unsuccessful Then the number of answering is for strangeness numbers, and determines and described currently answer the suspicion that number has harassing call Doubt.
9. system as claimed in claim 8, it is characterised in that the voice match module, enters one Walk for storing all numbers that number includes being stored in address list, message registration and note case in the terminal Code.
10. system as claimed in claim 6, it is characterised in that the voice match module, enters one Walk and whether answer the air time less than Preset Time threshold values for judgement, if it is determine there is harassing and wrecking electricity The suspicion of words.
CN201510752441.1A 2015-11-06 2015-11-06 Processing method for adaptively identifying harassing call and processing system thereof CN106686191A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510752441.1A CN106686191A (en) 2015-11-06 2015-11-06 Processing method for adaptively identifying harassing call and processing system thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510752441.1A CN106686191A (en) 2015-11-06 2015-11-06 Processing method for adaptively identifying harassing call and processing system thereof
PCT/CN2016/104504 WO2017076314A1 (en) 2015-11-06 2016-11-04 Processing method and system for adaptive unwanted call identification

Publications (1)

Publication Number Publication Date
CN106686191A true CN106686191A (en) 2017-05-17

Family

ID=58661779

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510752441.1A CN106686191A (en) 2015-11-06 2015-11-06 Processing method for adaptively identifying harassing call and processing system thereof

Country Status (2)

Country Link
CN (1) CN106686191A (en)
WO (1) WO2017076314A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107205091A (en) * 2017-05-31 2017-09-26 广东欧珀移动通信有限公司 Call control method and related product
CN107734128A (en) * 2017-09-28 2018-02-23 努比亚技术有限公司 One kind swindle number identification method and equipment
CN107770354A (en) * 2017-10-25 2018-03-06 维沃移动通信有限公司 A kind of incoming call processing method and mobile terminal
CN109348037A (en) * 2018-11-28 2019-02-15 东南大学 A kind of anti-harassing and wrecking fixed telephone of anti-swindle based on intelligent answer
CN109348036A (en) * 2018-11-28 2019-02-15 张力予 Based on intelligent answer _ human-computer interaction mechanism harassing call countermeasure and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101112078A (en) * 2005-02-08 2008-01-23 日本电信电话株式会社 Information communication terminal, information communication system, information communication method, information communication program, and recording medium on which program is recorded
CN104113466A (en) * 2013-04-17 2014-10-22 腾讯科技(深圳)有限公司 Harassing phone call identification method, client, server and system
CN104253869A (en) * 2014-09-25 2014-12-31 北京搜狗科技发展有限公司 Blacklist sharing method, blacklist updating method, blacklist sharing device and blacklist updating device
CN104580650A (en) * 2014-12-25 2015-04-29 广东欧珀移动通信有限公司 Method for pointing out defrauding call and communication terminal

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101827367B (en) * 2009-03-06 2012-07-18 中兴通讯股份有限公司 Recognition method and device of harassing calls
CN105338157A (en) * 2014-07-29 2016-02-17 小米科技有限责任公司 Nuisance call processing method, and device and telephone

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101112078A (en) * 2005-02-08 2008-01-23 日本电信电话株式会社 Information communication terminal, information communication system, information communication method, information communication program, and recording medium on which program is recorded
CN104113466A (en) * 2013-04-17 2014-10-22 腾讯科技(深圳)有限公司 Harassing phone call identification method, client, server and system
CN104253869A (en) * 2014-09-25 2014-12-31 北京搜狗科技发展有限公司 Blacklist sharing method, blacklist updating method, blacklist sharing device and blacklist updating device
CN104580650A (en) * 2014-12-25 2015-04-29 广东欧珀移动通信有限公司 Method for pointing out defrauding call and communication terminal

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107205091A (en) * 2017-05-31 2017-09-26 广东欧珀移动通信有限公司 Call control method and related product
CN107734128A (en) * 2017-09-28 2018-02-23 努比亚技术有限公司 One kind swindle number identification method and equipment
CN107770354A (en) * 2017-10-25 2018-03-06 维沃移动通信有限公司 A kind of incoming call processing method and mobile terminal
CN109348037A (en) * 2018-11-28 2019-02-15 东南大学 A kind of anti-harassing and wrecking fixed telephone of anti-swindle based on intelligent answer
CN109348036A (en) * 2018-11-28 2019-02-15 张力予 Based on intelligent answer _ human-computer interaction mechanism harassing call countermeasure and system

Also Published As

Publication number Publication date
WO2017076314A1 (en) 2017-05-11

Similar Documents

Publication Publication Date Title
US10135976B2 (en) Identifying and filtering incoming telephone calls to enhance privacy
US10446134B2 (en) Computer-implemented system and method for identifying special information within a voice recording
US9374463B2 (en) System and method for tracking persons of interest via voiceprint
US10210870B2 (en) Method for verification and blacklist detection using a biometrics platform
US9038178B1 (en) Detection of malware beaconing activities
US10362172B2 (en) Fraud detection in interactive voice response systems
EP2550795B1 (en) Transaction security method and system
US8942767B2 (en) Communications convergence and user interface systems, apparatuses, and methods
US7813482B2 (en) Internet telephone voice mail management
US6363346B1 (en) Call distribution system inferring mental or physiological state
US6775360B2 (en) Method and system for providing textual content along with voice messages
RU2383938C2 (en) Improved calling subscriber identification based on speech recognition
US6233556B1 (en) Voice processing and verification system
CA2279870C (en) Calling party identification authentication and routing in response thereto
DE102005029287B4 (en) A method for preventing the switching of unwanted telephone calls
US8526580B2 (en) System and method for voicemail organization
EP0833489B1 (en) Signal monitoring apparatus
US9531873B2 (en) System, method and apparatus for classifying communications in a communications system
CN103152740B (en) A kind of anti-monitor method and system for mobile terminal
US9906642B2 (en) Identity identification method and apparatus and communication terminal
US8219404B2 (en) Method and apparatus for recognizing a speaker in lawful interception systems
US8750464B2 (en) System and method for indexing voice mail messages by speaker
EP2018747B1 (en) Method for identifying undesired telephone calls
McMillan et al. Investigating the increase in mobile phone evidence in criminal activities
US10645214B1 (en) Identical conversation detection method and apparatus

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