CN111862970A - False propaganda treatment application method and device based on intelligent voice robot - Google Patents
False propaganda treatment application method and device based on intelligent voice robot Download PDFInfo
- Publication number
- CN111862970A CN111862970A CN202010505265.2A CN202010505265A CN111862970A CN 111862970 A CN111862970 A CN 111862970A CN 202010505265 A CN202010505265 A CN 202010505265A CN 111862970 A CN111862970 A CN 111862970A
- Authority
- CN
- China
- Prior art keywords
- intelligent voice
- false
- voice robot
- data
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000011664 signaling Effects 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- 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
- H04M3/436—Arrangements for screening incoming calls, i.e. evaluating the characteristics of a call before deciding whether to answer it
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The invention relates to a false propaganda treatment application method and a device based on an intelligent voice robot, comprising the following steps: carrying out voice analysis on the accessed signaling and the media data to obtain real-time media stream and/or text data; the intelligent voice robot carries out semantic understanding and intention judgment according to the real-time media stream and the character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding call media data, and sends the call media data to a calling party; recording each false call profile information for using the false call profile information as a corresponding application scenario during subsequent call identification. The invention has the beneficial effects that: the intelligent voice robot is introduced to carry out voice interaction, so that the communication time of a false propaganda source can be effectively occupied, and the connection times of a victim and the like are indirectly reduced; the false propaganda source is interfered, and the fraud success rate is reduced.
Description
Technical Field
The invention relates to the field of communication and voice recognition, in particular to a false propaganda treatment application method and device based on an intelligent voice robot.
Background
At present, with the development of artificial intelligence, intelligent voice robots have entered into enterprise marketing applications on a large scale. The intelligent voice robot multi-industry scene application covers the fields of service industry, e-commerce industry, financial industry, real estate industry, automobile industry, education and training and the like, and is mainly applied to the telephone marketing scene, the customer service after-sale scene and the telephone notification scene of an enterprise, such as a financial credit industry application scene; the intelligent voice robot is a marketing strategy capable of enhancing the current business efficiency of an enterprise, and is also a boosting agent for continuously and highly increasing the performance of an AI-era power-assisted enterprise. Of course, with the progress and development, the intelligent voice robot is also continuously promoted and improved.
At present, a series of intelligent voice robots such as an answering robot and an outbound robot are put forward by manufacturers, and certain effects are also started in commercial application. However, in the false propaganda treatment, the application is less, and particularly, an effective means for treating the source of the false propaganda activity is not available, and the false propaganda activity cannot be effectively treated and is more unfavorable for business development.
Disclosure of Invention
The invention aims to solve at least one technical problem in the prior art, and provides a false propaganda treatment application method and device based on an intelligent voice robot, which are used for identifying access false voice and interacting with false propaganda through the intelligent voice robot, so that the defects in the prior art are overcome.
The technical scheme of the invention comprises a false propaganda treatment application method based on an intelligent voice robot, which is characterized by comprising the following steps: s100, carrying out voice analysis on the accessed signaling and media data to obtain real-time media stream and/or text data; s200, establishing communication connection with the intelligent voice robot, and sending the real-time media stream and/or text data; s300, the intelligent voice robot carries out semantic understanding and intention judgment according to the real-time media stream and the character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding conversation media data, and sends the conversation media data to a calling party; s400, recording each false call file information, and using the false call file information as a corresponding application scene during the subsequent call identification.
According to the false propaganda treatment application method based on the intelligent voice robot, signaling accords with a telecommunication network signaling data access and accords with a telecommunication network unified standard interface.
According to the false propaganda treatment application method based on the intelligent voice robot, signaling accords with a telecommunication network signaling data access and accords with a telecommunication network unified standard interface. S100 further includes directly releasing the called party if the signaling message is identified as a signaling message that conforms to the spurious promotional characteristics.
According to the false propaganda treatment application method based on the intelligent voice robot, the access and transmission of media data conform to a telecommunication network media interface specification protocol.
According to the false propaganda treatment application method based on the intelligent voice robot, S200 sends real-time media streams and/or characters by calling an interface of the intelligent voice robot.
According to the false propaganda treatment application method based on the intelligent voice robot, S300 specifically comprises the following steps: s310, carrying out semantic understanding and recognition on the single sentence intention, the whole intention and the real intention of the real-time media stream and/or the character data based on the jieba word segmentation, the LSTM model and rule matching; s320, automatically generating corresponding reply content according to at least one of the single sentence intention, the whole intention and the real intention; s330, matching the corresponding scene model according to the reply content, simulating the corresponding media stream and/or character data and returning the media stream and/or character data to the calling party.
According to the false propaganda treatment application method based on the intelligent voice robot, the S310 specifically comprises the following steps: s311, presetting a corpus and preprocessing, processing the real-time media stream and/or the text data through a word segmentation tool, and storing the obtained sentences, word segmentation results, keywords and preprocessed contents; s312, completing construction of a word vector model by training the corpus, and storing the word vector model, a corresponding word vector dictionary and an index dictionary; s313, training an LSTM model, storing data, and performing HMM and search mode word segmentation on character data by using a word segmentation tool to extract keywords; and S314, carrying out rapid global search on the keywords in the sentences of the text data to obtain the category where the words with the maximum matching score are located to finish intention understanding.
According to the false propaganda treatment application method based on the intelligent voice robot, the method further comprises the following steps: s315, if the recorded characters are not found in the model base, carrying out LSTM model prediction or word2vec similar word category weighted average prediction; s316, understanding the context by adopting an LSTM algorithm, and searching a word set similar to the existing keywords in a word bank by adopting word2vec similar word category weighting, and performing intention understanding in a similarity weighted average mode.
The technical scheme of the invention also comprises a false propaganda treatment application device based on the intelligent voice robot, the device comprises an access end and the intelligent voice robot, and the false propaganda treatment application device is characterized in that: the access end is used for carrying out voice analysis on the accessed signaling and the media data to obtain real-time media stream and/or text data, establishing communication connection with the intelligent voice robot and sending the real-time media stream and/or text data; and, also used for recording the file information of false call each time, is used in while calling out the identification subsequently, call the file information as the correspondent application scene falsely; the intelligent voice robot carries out semantic understanding and intention judgment according to real-time media stream and/or character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding call media data, and sends the call media data back.
The invention has the beneficial effects that: the intelligent voice robot is introduced to carry out voice interaction, so that the communication time of a false propaganda source can be effectively occupied, and the connection times of a victim and the like are indirectly reduced; the false propaganda source is interfered, and the fraud success rate is reduced.
Drawings
The invention is further described below with reference to the accompanying drawings and examples;
FIG. 1 illustrates an overall flow diagram according to an embodiment of the invention;
FIG. 2 is an interaction diagram according to an embodiment of the invention;
FIG. 3 illustrates a semantic understanding flow diagram according to an embodiment of the present invention;
FIG. 4 is a diagram of a media device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number.
In the description of the present invention, the consecutive reference numbers of the method steps are for convenience of examination and understanding, and the implementation order between the steps is adjusted without affecting the technical effect achieved by the technical solution of the present invention by combining the whole technical solution of the present invention and the logical relationship between the steps.
Interpretation of terms:
LSTM is a neural network algorithm for long and short term memory;
word2 vec: a group of correlation models for generating word vectors, which are shallow and double-layer neural networks for training to reconstruct linguistic word texts;
jieba word segmentation: a word segmentation tool can perform functions of word segmentation, part of speech tagging, keyword extraction and the like on a Chinese text and supports a user-defined dictionary.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
FIG. 1 shows a general flow diagram according to an embodiment of the invention. The process comprises the following steps: s100, carrying out voice analysis on the accessed signaling and media data to obtain real-time media stream and/or text data; s200, establishing communication connection with the intelligent voice robot, and sending real-time media stream and/or text data; s300, the intelligent voice robot carries out semantic understanding and intention judgment according to the real-time media stream and the character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding conversation media data, and sends the conversation media data to a calling party; s400, recording each false call file information, and using the false call file information as a corresponding application scene during the subsequent call identification.
Fig. 2 is an interaction diagram according to an embodiment of the present invention, and the following flow description is specifically made in conjunction with fig. 2:
(1) according to a certain strategy, the signaling message which accords with the characteristics of the false publicity is subjected to signaling control in real time, and the called party can be directly released for the incoming call which belongs to the false publicity source.
(2) Through accessing every day, after voice analysis, real-time media streams or characters are called through an interface and output to the intelligent voice robot.
(3) And after understanding the word senses according to the media stream information, the intelligent voice robot generates media information content which is in conversation with the false propaganda source and sends the media information content to the media injection module.
(4) The intelligent voice robot can adopt special effect processing such as sound changing and magic sound according to different numbers to generate corresponding call media data.
(5) The injection of the medium feeds the media data into the transmission line in a standardized format.
(6) The call profile information is established, the application scenario is maintained, and a basis is provided for subsequent tracking.
The intelligent voice robot comprises a signaling access device, a media data access device and an intelligent voice robot. The signaling access module is used for accessing signaling data of the telecommunication network and unifying standard interfaces of the telecommunication network;
the media data access module is compatible with the current telecommunication network media interface standard protocol;
The intelligent voice robot functions include semantic understanding, intent understanding, dialog maintenance, voice synthesis, and the like.
The semantic understanding realizes functions of single sentence intention recognition, whole intention recognition, real intention recognition and the like based on self-correlation models such as jieba participles and LSTM models, rule matching and the like.
The single sentence intention identification judges the intention of each sentence spoken by the user, carries out positive response and interaction according to the tone and the pause time, and generates reply content according to the comprehension of the meaning of the media content;
the whole-turn intention identification is used for judging the whole intention of the user after the call is ended;
the real intention recognition is used for judging how the machine should reply next after the user replies;
synthesizing voice according to word meaning and synthesizing voice according to a voice synthesis algorithm, and presetting a plurality of models, such as tone changes, such as sound change and magic sound, and identity changes, such as the aged, the adult, the child, the male and the female speaking and the like; and flexible service interaction is completed according to the false propaganda scene model, so that the false propaganda source is considered to be in communication with a real user, and the communication seat is occupied for a long time.
Wherein, the examples of the intelligent voice robot in the intelligent voice robot are as follows:
Content replies of different scenes are preset manually to form some conversation models, and the scenes frequently appearing on the network are as follows:
1. sending a short message to inform a family member that an accident occurs, and carrying out false propaganda in the modes of communication and the like at present;
2. submitting various fees by taking the winning as the basis;
3. borrowing money by using the information of friends;
4. some harassment information may promote certain shopping products;
5. the information sent by the bank is falsely issued, the account password is leaked, and the information needs to be reset to be falsely publicized and the like.
The intelligent voice robot performs voice analysis and flexible dialogue interaction in real time according to a preset scene flow, and the purpose of deceiving a false propaganda source is achieved.
The access terminal is an intelligent device used for completing signaling receiving and sending, such as a mobile phone and a tablet computer.
Fig. 3 is a flow chart of semantic understanding according to an embodiment of the present invention, which specifically includes the following steps: s311, presetting a corpus and preprocessing, processing the real-time media stream and/or text data through a word segmentation tool, and storing the obtained sentences, word segmentation results, keywords and preprocessed contents; s312, completing construction of a word vector model by training the corpus, and storing the word vector model, a corresponding word vector dictionary and an index dictionary; s313, training an LSTM model, storing data, and performing HMM and search mode word segmentation on character data by using a word segmentation tool to extract keywords; s314, carrying out rapid global search on keywords in sentences of the text data to obtain the category of the words with the maximum matching score to finish intention understanding; s315, if the recorded characters are not found in the model base, carrying out LSTM model prediction or word2vec similar word category weighted average prediction; s316, understanding the context by adopting an LSTM algorithm, and searching a word set similar to the existing keywords in a word bank by adopting word2vec similar word category weighting, and performing intention understanding in a similarity weighted average mode.
FIG. 4 is a diagram of a media device according to an embodiment of the present invention. Referring to fig. 2, both the access terminal and the intelligent voice robot are provided with a memory 100 and a processor 200 as shown in fig. 4, the memory 100 is used for storing text data and media stream data of voice recognition, and the processor is used for executing the process shown in fig. 1.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (9)
1. A false propaganda treatment application method based on an intelligent voice robot is characterized by comprising the following steps:
s100, carrying out voice analysis on the accessed signaling and media data to obtain real-time media stream and/or text data;
s200, establishing communication connection with the intelligent voice robot, and sending the real-time media stream and/or text data;
s300, the intelligent voice robot carries out semantic understanding and intention judgment according to the real-time media stream and the character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding conversation media data, and sends the conversation media data to a calling party;
S400, recording each false call file information, and using the false call file information as a corresponding application scene during the subsequent call identification.
2. The intelligent voice robot-based false publicity improvement application method according to claim 1, characterized in that the signaling conforms to telecommunication network signaling data access and conforms to telecommunication network unified standard interface.
3. The method of claim 1, wherein S100 further comprises releasing the called party directly if the signaling message is identified as a signaling message that matches the characteristics of the false publicity.
4. The intelligent voice robot-based false promotion abatement application method of claim 1, wherein the access and transmission of the media data conform to a telecommunication network media interface specification protocol.
5. The application method of false promotion abatement based on intelligent voice robot as claimed in claim 1, wherein S200 sends real-time media stream and/or text by calling the interface of the intelligent voice robot.
6. The application method of false publicity improvement based on intelligent voice robot of claim 1, wherein the S300 specifically includes:
S310, carrying out semantic understanding and recognition on the single sentence intention, the whole intention and the real intention of the real-time media stream and/or the character data based on the jieba word segmentation, the LSTM model and rule matching;
s320, automatically generating corresponding reply content according to at least one of the single sentence intention, the whole intention and the real intention;
s330, matching the corresponding scene model according to the reply content, simulating the corresponding media stream and/or character data and returning the media stream and/or character data to the calling party.
7. The application method of false publicity improvement based on intelligent voice robot of claim 1, wherein S310 specifically includes:
s311, presetting a corpus and preprocessing, processing the real-time media stream and/or the text data through a word segmentation tool, and storing the obtained sentences, word segmentation results, keywords and preprocessed contents;
s312, completing construction of a word vector model by training the corpus, and storing the word vector model, a corresponding word vector dictionary and an index dictionary;
s313, training an LSTM model, storing data, and performing HMM and search mode word segmentation on character data by using a word segmentation tool to extract keywords;
And S314, carrying out rapid global search on the keywords in the sentences of the text data to obtain the category where the words with the maximum matching score are located to finish intention understanding.
8. The application method of false publicity improvement based on intelligent voice robot as claimed in claim 7, characterized in that the method further comprises:
s315, if the recorded characters are not found in the model base, carrying out LSTM model prediction or word2vec similar word category weighted average prediction;
s316, understanding the context by adopting an LSTM algorithm, and searching a word set similar to the existing keywords in a word bank by adopting word2vec similar word category weighting, and performing intention understanding in a similarity weighted average mode.
9. The utility model provides a false propaganda improvement application device based on intelligent voice robot, the device includes conversation end and intelligent voice robot, its characterized in that:
the access end is used for carrying out voice analysis on the accessed signaling and the media data to obtain real-time media stream and/or text data, establishing communication connection with the intelligent voice robot and sending the real-time media stream and/or text data; and, also used for recording the file information of false call each time, is used in while calling out the identification subsequently, call the file information as the correspondent application scene falsely;
The intelligent voice robot carries out semantic understanding and intention judgment according to real-time media stream and/or character data, generates a corresponding reply sentence according to the semantic understanding and the intention judgment, further generates corresponding call media data, and sends the call media data back.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505265.2A CN111862970A (en) | 2020-06-05 | 2020-06-05 | False propaganda treatment application method and device based on intelligent voice robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505265.2A CN111862970A (en) | 2020-06-05 | 2020-06-05 | False propaganda treatment application method and device based on intelligent voice robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111862970A true CN111862970A (en) | 2020-10-30 |
Family
ID=72985030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505265.2A Pending CN111862970A (en) | 2020-06-05 | 2020-06-05 | False propaganda treatment application method and device based on intelligent voice robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111862970A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113297365A (en) * | 2021-06-22 | 2021-08-24 | 中国平安财产保险股份有限公司 | User intention determination method, device, equipment and storage medium |
| CN115101067A (en) * | 2022-06-16 | 2022-09-23 | 陈明华 | Smart power grids voice system based on block chain technique |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345795A (en) * | 2008-08-08 | 2009-01-14 | 中国移动通信集团山东有限公司 | Method and system automatic monitoring and real-time blocking false calling of communication network |
| CN106847271A (en) * | 2016-12-12 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of data processing method and device for talking with interactive system |
| CN107644642A (en) * | 2017-09-20 | 2018-01-30 | 广东欧珀移动通信有限公司 | Method for recognizing semantics, device, storage medium and electronic equipment |
| US20190020759A1 (en) * | 2017-07-16 | 2019-01-17 | Shaobo Kuang | System and method for detecting phone frauds or scams |
| CN109377983A (en) * | 2018-10-18 | 2019-02-22 | 深圳壹账通智能科技有限公司 | A kind of harassing call hold-up interception method and relevant device based on interactive voice |
| US20190149575A1 (en) * | 2017-11-13 | 2019-05-16 | International Business Machines Corporation | System to prevent scams |
| CN110349568A (en) * | 2019-06-06 | 2019-10-18 | 平安科技（深圳）有限公司 | Speech retrieval method, apparatus, computer equipment and storage medium |
| US20190373105A1 (en) * | 2018-05-30 | 2019-12-05 | International Business Machines Corporation | Cognitive telephone fraud detection |
| CN110933219A (en) * | 2018-09-19 | 2020-03-27 | 上海航空电器有限公司 | Terminal incoming call assistant method based on intelligent voice interaction and terminal |
| CN111091826A (en) * | 2019-12-13 | 2020-05-01 | 中博信息技术研究院有限公司 | Intelligent voice robot system based on deep learning and finite-state machine |
-
2020
- 2020-06-05 CN CN202010505265.2A patent/CN111862970A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345795A (en) * | 2008-08-08 | 2009-01-14 | 中国移动通信集团山东有限公司 | Method and system automatic monitoring and real-time blocking false calling of communication network |
| CN106847271A (en) * | 2016-12-12 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of data processing method and device for talking with interactive system |
| US20190020759A1 (en) * | 2017-07-16 | 2019-01-17 | Shaobo Kuang | System and method for detecting phone frauds or scams |
| CN107644642A (en) * | 2017-09-20 | 2018-01-30 | 广东欧珀移动通信有限公司 | Method for recognizing semantics, device, storage medium and electronic equipment |
| US20190149575A1 (en) * | 2017-11-13 | 2019-05-16 | International Business Machines Corporation | System to prevent scams |
| US20190373105A1 (en) * | 2018-05-30 | 2019-12-05 | International Business Machines Corporation | Cognitive telephone fraud detection |
| CN110933219A (en) * | 2018-09-19 | 2020-03-27 | 上海航空电器有限公司 | Terminal incoming call assistant method based on intelligent voice interaction and terminal |
| CN109377983A (en) * | 2018-10-18 | 2019-02-22 | 深圳壹账通智能科技有限公司 | A kind of harassing call hold-up interception method and relevant device based on interactive voice |
| CN110349568A (en) * | 2019-06-06 | 2019-10-18 | 平安科技（深圳）有限公司 | Speech retrieval method, apparatus, computer equipment and storage medium |
| CN111091826A (en) * | 2019-12-13 | 2020-05-01 | 中博信息技术研究院有限公司 | Intelligent voice robot system based on deep learning and finite-state machine |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113297365A (en) * | 2021-06-22 | 2021-08-24 | 中国平安财产保险股份有限公司 | User intention determination method, device, equipment and storage medium |
| CN113297365B (en) * | 2021-06-22 | 2023-09-26 | 中国平安财产保险股份有限公司 | User intention judging method, device, equipment and storage medium |
| CN115101067A (en) * | 2022-06-16 | 2022-09-23 | 陈明华 | Smart power grids voice system based on block chain technique |
| CN115101067B (en) * | 2022-06-16 | 2024-04-16 | 陈明华 | Smart power grids voice system based on blockchain technique |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488433B (en) | Artificial intelligence interactive system suitable for bank and capable of improving field experience | |
| KR101872863B1 (en) | Business support method using a chatting bot | |
| CN107481720B (en) | Explicit voiceprint recognition method and device | |
| CN109064315A (en) | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium | |
| EP2109097B1 (en) | A method for personalization of a service | |
| CN108831439A (en) | Audio recognition method, device, equipment and system | |
| CN111739516A (en) | Speech recognition system for intelligent customer service call | |
| CN110597952A (en) | Information processing method, server, and computer storage medium | |
| CN111653262A (en) | Intelligent voice interaction system and method | |
| CN106230689B (en) | A kind of method, apparatus and server of voice messaging interaction | |
| CN111696558A (en) | Intelligent outbound method, device, computer equipment and storage medium | |
| CN108010513B (en) | Voice processing method and device | |
| CN111862970A (en) | False propaganda treatment application method and device based on intelligent voice robot | |
| CN112632244A (en) | Man-machine conversation optimization method and device, computer equipment and storage medium | |
| CN116049360A (en) | Intelligent voice dialogue scene conversation intervention method and system based on client image | |
| CN110335135A (en) | A kind of intelligence collection robot and intelligent collection method | |
| CN112071300B (en) | Voice conversation method, device, computer equipment and storage medium | |
| CN112487381A (en) | Identity authentication method and device, electronic equipment and readable storage medium | |
| CN115563290A (en) | Intelligent emotion recognition method based on context modeling | |
| CN111881273A (en) | Question and answer processing method and device | |
| CN111246008A (en) | Method, system and device for realizing telephone assistant | |
| CN115022471B (en) | Intelligent robot voice interaction system and method | |
| CN113744742A (en) | Role identification method, device and system in conversation scene | |
| CN111464687A (en) | Strange call request processing method and device | |
| CN112866491B (en) | Multi-meaning intelligent question-answering method based on specific field |
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 |