CN112422749A - Method for preventing harassment outbound based on intelligent dialogue analysis - Google Patents
Method for preventing harassment outbound based on intelligent dialogue analysis Download PDFInfo
- Publication number
- CN112422749A CN112422749A CN202011419937.4A CN202011419937A CN112422749A CN 112422749 A CN112422749 A CN 112422749A CN 202011419937 A CN202011419937 A CN 202011419937A CN 112422749 A CN112422749 A CN 112422749A
- Authority
- CN
- China
- Prior art keywords
- processed
- robot
- text
- user
- intelligent dialogue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a method for preventing harassment outbound based on intelligent dialogue analysis, which comprises the following steps: the AI robot monitors a user to-be-processed voice stream sent by a freeswitch through an SIP client; processing the voice stream to be processed through ASR to obtain a first text to be processed; processing a first text to be processed by an NLP (non line segment) to a second text to be processed, wherein the second text to be processed is an understandable text of the first text to be processed; analyzing the second text to be processed through a preconfigured Decision Tree to obtain the user intention; and responding to the user intention by the AI robot, and executing a corresponding control instruction according to a preset rule.
Description
Technical Field
The invention relates to the field of voice recognition, in particular to a method for preventing harassment outbound based on intelligent dialogue analysis.
Background
With the gradual maturity of artificial intelligence technology, the traditional call center is gradually replaced by an AI intelligent call center, marketing outbound is also more and more replaced by AI robot outbound, and people are also more and more disturbed by marketing calls dialed by AI robots. At present, the main means for dealing with telephone harassment is to set up an anti-harassment strategy at a called end through various mobile phone housekeeping software and provide harassment number marking function for each large security manufacturer.
However, most of the above anti-harassment schemes prevent harassment to the customer by means of the customer complaint marketing number after the fact, the marketing number prevents harassment to the customer by means of blacklisting, the intention of the user cannot be judged in real time when the AI robot and the customer make a first call, harassment is easily caused to the user and the marketing number is marked, and at this time, the AI robot is complained to the department of industry and telecommunication by the customer, so that the AI robot is penalized and the number is sealed.
Disclosure of Invention
The invention aims to solve the technical problem that disturbance caused by the fact that the user intention cannot be recognized in real time by the aid of an existing AI robot outbound call.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a method for preventing harassment outbound based on intelligent dialogue analysis, which comprises the following steps:
the AI robot monitors a user to-be-processed voice stream sent by a freeswitch through an SIP client;
processing the voice stream to be processed through ASR to obtain a first text to be processed;
processing the first text to be processed by NLP to be a second text to be processed, wherein the second text to be processed
The text is an understandable text of the first text to be processed;
analyzing the second text to be processed through a preconfigured Decision Tree to obtain the user intention;
and the AI robot responds to the user intention and executes a corresponding control instruction according to a preset rule.
In the above scheme, the executing, by the AI robot in response to the user intention, the corresponding control instruction according to a preset rule includes:
the AI robot executes hang-up control instructions when the user intent includes at least any one or more of refusal, anger, and abuse.
In the above scheme, before the AI robot executes the hang-up control instruction, the AI robot sends an apology expression to the user.
In the above scheme, the AI robot adds the user who sent the user intention to a blacklist list after executing a hang-up control instruction.
In the above aspect, the method further includes:
before the AI robot initiates voice interaction to a user, the AI robot checks whether the user is listed in a blacklist, and if so, the AI robot stops initiating voice interaction to the user.
In the above scheme, the SIP client performs voice interaction with freeswitch through an RTP protocol.
The invention has the beneficial effects that: the invention provides an intelligent dialogue analysis-based harassment outbound call prevention method, which is characterized in that user voice information is recognized in real time through an ASR (auto-regress rule) and an NLP (non-linear programming) and user intention is analyzed, and an AI robot executes a corresponding control instruction based on the user intention, such as apology and hang-up, so as to prevent harassment to a user.
Drawings
Fig. 1 is a schematic flow chart of a method for preventing harassment outbound based on intelligent dialogue analysis according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to specific embodiments, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
With the gradual maturity of artificial intelligence technology, the traditional call center is gradually replaced by an AI intelligent call center, marketing outbound is also more and more replaced by AI robot outbound, and people are also more and more disturbed by marketing calls dialed by AI robots. At present, the main means for dealing with telephone harassment is to set up an anti-harassment strategy at a called end through various mobile phone housekeeping software and provide harassment number marking function for each large security manufacturer.
However, most of the above anti-harassment schemes prevent harassment to the customer by means of the customer complaint marketing number after the fact, the marketing number prevents harassment to the customer by means of blacklisting, the intention of the user cannot be judged in real time when the AI robot and the customer make a first call, harassment is easily caused to the user and the marketing number is marked, and at this time, the AI robot is complained to the department of industry and telecommunication by the customer, so that the AI robot is penalized and the number is sealed.
In order to solve the technical problem that disturbance is caused to a user due to the fact that the existing AI robot outbound cannot recognize the intention of the user in real time, the embodiment of the invention provides a disturbance outbound prevention method based on intelligent dialogue analysis.
The technical solutions provided by the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of a method for preventing harassing outbound based on intelligent dialogue analysis according to an embodiment of the present invention is shown, where the method includes:
s101, an AI robot monitors a user to-be-processed voice stream sent by a freeswitch through an SIP client;
aiming at the step S101, the SIP client performs voice interaction with the freeswitch through an RTP protocol, and the AI robot acquires the voice stream to be processed of the user, which is sent by the freeswitch, through the SIP client.
S102, processing the voice stream to be processed through an ASR to obtain a first text to be processed;
s103, processing a second text to be processed by the first text to be processed through NLP, wherein the second text to be processed is a comprehensible text of the first text to be processed;
s104, analyzing the second text to be processed through a preconfigured Decision Tree of Decision Tree to obtain the user intention;
and S105, responding to the user intention, and executing a corresponding control instruction according to a preset rule by the AI robot.
With respect to step S105, the AI robot, in response to the user intention, executing a corresponding control instruction according to a preset rule includes:
the AI robot executes hang-up control instructions when the user intent includes at least any one or more of refusal, anger, and abuse.
In one example, the AI robot issues an apology indication to the user before the AI robot executes the hang control instruction.
In one example, the AI robot adds the user who issued the user's intent to a blacklist after executing a hang-up control instruction.
In one example, the method further comprises:
before the AI robot initiates voice interaction to a user, the AI robot checks whether the user is listed in a blacklist, and if so, the AI robot stops initiating voice interaction to the user.
It will be appreciated that when the user of the AI robot initiating the voice interaction has been added to the blacklist, the AI robot no longer initiates a voice call to the user in the blacklist.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, which are within the protection scope of the present invention.
Claims (6)
1. A method for preventing harassment outbound based on intelligent dialogue analysis is characterized by comprising the following steps:
the AI robot monitors a user to-be-processed voice stream sent by a freeswitch through an SIP client;
processing the voice stream to be processed through ASR to obtain a first text to be processed;
processing the first text to be processed by NLP to a second text to be processed, wherein the second text to be processed is
The text to be processed is an understandable text of the first text to be processed;
analyzing the second text to be processed through a preconfigured Decision Tree
A user intent;
and the AI robot responds to the user intention and executes a corresponding control instruction according to a preset rule.
2. A method for preventing harassing outbound call based on intelligent dialogue analysis according to claim 1, characterised in that
If the AI robot responds to the user intention, executing a corresponding control instruction according to a preset rule includes:
the AI robot executes hang-up control instructions when the user intent includes at least any one or more of refusal, anger, and abuse.
3. A method for preventing harassing outbound call based on intelligent dialogue analysis according to claim 2, characterized in that
If so, before the AI robot executes the hang-up control instruction, the AI robot sends an apology to the user.
4. A method for preventing harassing outbound call based on intelligent dialogue analysis according to claim 2, characterized in that
If so, the AI robot adds the user sending the user intention into a blacklist after executing a hang-up control instruction.
5. A method for preventing harassing outbound call based on intelligent dialogue analysis according to claim 1, characterised in that
The method further comprises the following steps:
before the AI robot initiates voice interaction to a user, the AI robot checks whether the user is listed in a blacklist, and if so, the AI robot stops initiating voice interaction to the user.
6. A method for preventing harassing outbound call based on intelligent dialogue analysis according to claim 1 which is
Is characterized in that the SIP client-side carries out voice interaction with freeswitch through RTP protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419937.4A CN112422749A (en) | 2020-12-08 | 2020-12-08 | Method for preventing harassment outbound based on intelligent dialogue analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419937.4A CN112422749A (en) | 2020-12-08 | 2020-12-08 | Method for preventing harassment outbound based on intelligent dialogue analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112422749A true CN112422749A (en) | 2021-02-26 |
Family
ID=74775398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011419937.4A Pending CN112422749A (en) | 2020-12-08 | 2020-12-08 | Method for preventing harassment outbound based on intelligent dialogue analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112422749A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954104A (en) * | 2021-04-15 | 2021-06-11 | 北京蓦然认知科技有限公司 | Method and device for line quality inspection |
| CN113726963A (en) * | 2021-08-31 | 2021-11-30 | 中国平安财产保险股份有限公司 | Intelligent outbound harassment prevention method, device, equipment and medium |
| CN114025050A (en) * | 2021-11-08 | 2022-02-08 | 浙江百应科技有限公司 | Speech recognition method and device based on intelligent outbound and text analysis |
| CN116055614A (en) * | 2023-02-03 | 2023-05-02 | 浙江东上数字科技有限公司 | Intelligent voice outbound system and method for realizing SIP relay through mobile phone |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107331383A (en) * | 2017-06-27 | 2017-11-07 | 苏州咖啦魔哆信息技术有限公司 | One kind is based on artificial intelligence telephone outbound system and its implementation |
| CN108846127A (en) * | 2018-06-29 | 2018-11-20 | 北京百度网讯科技有限公司 | A kind of voice interactive method, device, electronic equipment and storage medium |
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| CN111353026A (en) * | 2018-12-21 | 2020-06-30 | 沈阳新松机器人自动化股份有限公司 | Intelligent law attorney assistant customer service system |
| CN111597818A (en) * | 2020-04-09 | 2020-08-28 | 深圳追一科技有限公司 | Call quality inspection method, call quality inspection device, computer equipment and computer readable storage medium |
-
2020
- 2020-12-08 CN CN202011419937.4A patent/CN112422749A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107331383A (en) * | 2017-06-27 | 2017-11-07 | 苏州咖啦魔哆信息技术有限公司 | One kind is based on artificial intelligence telephone outbound system and its implementation |
| CN108846127A (en) * | 2018-06-29 | 2018-11-20 | 北京百度网讯科技有限公司 | A kind of voice interactive method, device, electronic equipment and storage medium |
| CN111353026A (en) * | 2018-12-21 | 2020-06-30 | 沈阳新松机器人自动化股份有限公司 | Intelligent law attorney assistant customer service system |
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| CN111597818A (en) * | 2020-04-09 | 2020-08-28 | 深圳追一科技有限公司 | Call quality inspection method, call quality inspection device, computer equipment and computer readable storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954104A (en) * | 2021-04-15 | 2021-06-11 | 北京蓦然认知科技有限公司 | Method and device for line quality inspection |
| CN113726963A (en) * | 2021-08-31 | 2021-11-30 | 中国平安财产保险股份有限公司 | Intelligent outbound harassment prevention method, device, equipment and medium |
| CN113726963B (en) * | 2021-08-31 | 2022-11-18 | 中国平安财产保险股份有限公司 | Intelligent outbound harassment prevention method, device, equipment and medium |
| CN114025050A (en) * | 2021-11-08 | 2022-02-08 | 浙江百应科技有限公司 | Speech recognition method and device based on intelligent outbound and text analysis |
| CN116055614A (en) * | 2023-02-03 | 2023-05-02 | 浙江东上数字科技有限公司 | Intelligent voice outbound system and method for realizing SIP relay through mobile phone |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112422749A (en) | Method for preventing harassment outbound based on intelligent dialogue analysis | |
| CN105187606A (en) | Method for preventing crank calls based on identity authentication | |
| WO2008008242A3 (en) | Call priority management system for communication network | |
| CN101911666A (en) | Intelligent do not disturb rule | |
| EP1657937A3 (en) | Method and system for selective call completion | |
| US11671532B2 (en) | Call traffic data monitoring and management | |
| CN108347537A (en) | Call center management system | |
| CN101764870A (en) | Method for realizing firewall of mobile phone calls | |
| WO2021138520A1 (en) | Call traffic data monitoring and management | |
| CN110445944B (en) | Method and system for preventing telephone disturbance of call center | |
| CN107368326A (en) | Course control method and device | |
| US20020087741A1 (en) | Plugable call control application program interface | |
| CN104618593B (en) | A kind of operating method when mobile terminal and its third party's incoming call | |
| CN101494677A (en) | Method for actively controlling incoming call by called part | |
| CN101127777A (en) | Method, device and system for processing security threat information of voice communication | |
| CN107968731A (en) | The aobvious number method for detecting abnormality of one kind and server | |
| CN105100364B (en) | A kind of method and apparatus carrying out call blocking on communication apparatus | |
| CN113489850B (en) | Telephone number protection method, device, system and storage medium | |
| CN103108084A (en) | Anti-monitor method and system used for mobile terminal | |
| CN110661922B (en) | Call control method, network device and system | |
| CN105306753A (en) | System and method for disclosing mobile phone number and intercepting harassing calls and short messages | |
| CN114979992B (en) | Call state determining method and device | |
| CN111756694B (en) | Dynamic processing method of session media, storage medium and server | |
| CN101847300B (en) | Parameter consultation method and equipment for accessing POS terminal access interface of server | |
| WO2008024608A3 (en) | Method and apparatus for a processing of calls in a telecommunications system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |
|
| RJ01 | Rejection of invention patent application after publication |