CN109949723A - A kind of device and method carrying out Products Show by Intelligent voice dialog - Google Patents
A kind of device and method carrying out Products Show by Intelligent voice dialog Download PDFInfo
- Publication number
- CN109949723A CN109949723A CN201910236514.XA CN201910236514A CN109949723A CN 109949723 A CN109949723 A CN 109949723A CN 201910236514 A CN201910236514 A CN 201910236514A CN 109949723 A CN109949723 A CN 109949723A
- Authority
- CN
- China
- Prior art keywords
- screen
- answer
- client
- semantic parsing
- voice
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a kind of device and methods that Products Show is carried out by Intelligent voice dialog, Intelligent voice dialog screen apparatus guides client to engage in the dialogue by sound and text, the audio of client is converted into text information by speech recognition system, the text information of conversion passes to semantic parsing system, semantic parsing system is analyzed client and is intended to, the action command for obtaining corresponding answer or needing to be implemented；The multimedia and text information of answer are shown by screen when answering answer, while the text of answer is synthesized by speech synthesis system by voice and is played back by loudspeaker；When needing to be implemented corresponding actions instruction, action command is sent to master control system by semantic parsing system, and master control system realizes that screen acts according to action command.By the above-mentioned means, the ability that the present invention can make advertisement screen have voice dialogue interaction, can carry out product broadcasting according to the specific requirements of advertiser are seen, keep advertising information more precisely more effective.
Description
Technical field
The present invention relates to advertising equipment fields, more particularly to a kind of dress for carrying out Products Show by Intelligent voice dialog
It sets and method.
Background technique
There is advertisement screen to be substantially the transmission of unidirectional information, the rule of screen carousel in sequence is shown broadcasting for content
It puts.Screen exhibition method is that unidirectional information is propagated, and client can only passively be received.Advertisement screen cannot receive thinking for client
Method cannot play out the switching of content according to the demand of client.
Summary of the invention
The invention mainly solves the technical problem of providing a kind of devices that Products Show is carried out by Intelligent voice dialog
And method, solve the problems, such as the two-way communication interaction between advertisement screen and the people for seeing advertisement, by introducing voice conversation technology,
Realize screen and the two-way communication interaction of people.
In order to solve the above technical problems, one technical scheme adopted by the invention is that: it provides a kind of by intelligent sound pair
Words carry out the device and method of Products Show, including pass through Intelligent voice dialog screen apparatus combination face identification system, semanteme
Analysis system and Content Management System carry out Products Show；The Intelligent voice dialog screen apparatus include screen, master control system,
Recognition of face camera, human body proximity sensor, noise reduction microphone and loudspeaker, master control system are taken the photograph with screen, recognition of face respectively
As head, human body proximity sensor, noise reduction microphone are connected with loudspeaker；The face identification system integrates face recognition algorithms, into
The identification of row customer information；The semantic parsing system includes the intention dictionary set of entity mark, many-to-one question and answer library and dynamic
Make instruction database, semantic parsing system analyzes the dialogue intention and the corresponding answer of customer issue of client；The Content Management system
System classifies the multimedia messages of importing and marked, and multimedia messages are first first divided into several major class by Content Management System,
Major class is divided into (A, B, C ...), does corresponding with the intention dictionary set that entity in semantic parsing system marks by major class, then distinguishes
Each major class is divided into several groups, group is divided into [A=(A-1, A-2 ...), B=(B-1, B-2 ...), C=(C-1, C-
2 ...) ...], group is done with the intention dictionary set that entity in semantic parsing system marks corresponding；
Human body proximity sensor first obtains peripheral information, and the human testing data that human body proximity sensor obtains are distance D,
When the numerical value of human body proximity sensor is less than numerical value D < 1000mm of setting, master control system, which is judged as, has client before equipment
And client's welcome message is issued, noise reduction microphone pickup state since being converted to closed state；Intelligent voice dialog screen dress
It sets and guides client to engage in the dialogue by sound and text, Intelligent voice dialog screen apparatus is integrated with speech recognition system and voice
Synthesis system, the audio that client speaks are converted into text information by speech recognition system, and the text information of conversion passes to language
Adopted analysis system, semantic parsing system are analyzed client and are intended to, obtain corresponding answer by many-to-one question and answer library or pass through movement
The action command that instruction database is needed to be implemented；The multimedia and text information of answer are shown by screen when answering answer
Out, while by speech synthesis system, the text synthesis voice of answer is played back by loudspeaker, realizes voice dialogue
With the multimedia voice interlocking of display；When needing to be implemented corresponding actions instruction, action command is sent to by semantic parsing system
Master control system, master control system realize that screen acts according to action command.
Further, client's welcome message is played out in a voice form by the loudspeaker, is shown by the screen
Intelligent dialogue interface.
The beneficial effects of the present invention are: the present invention realizes the two-way communication of screen and people by introducing voice conversation technology
Interaction.To solve client passive reception advertising information status, realize the function of advertisement screen to a greater extent, allow advertisement
It is more valuable.
Detailed description of the invention
Fig. 1, which is that the present invention is a kind of, carries out Intelligent voice dialog in the device and method of Products Show by Intelligent voice dialog
The framework map of screen apparatus；
Fig. 2 is a kind of shown device and method session operational scenarios demonstration graph that Products Show is carried out by Intelligent voice dialog.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
Fig. 1 and Fig. 2 are please referred to, the embodiment of the present invention includes:
A kind of device and method carrying out Products Show by Intelligent voice dialog, including pass through Intelligent voice dialog screen
Device combination face identification system, semantic parsing system and Content Management System carry out Products Show；The Intelligent voice dialog
Screen apparatus includes screen, master control system, recognition of face camera, human body proximity sensor, noise reduction microphone and loudspeaker, master control
System is connect with screen, recognition of face camera, human body proximity sensor, noise reduction microphone and loudspeaker respectively；
The face identification system integrates face recognition algorithms, carries out customer information identification；
The semantic parsing system includes intention dictionary set, many-to-one question and answer library and the action command library of entity mark
(next, previous, turn to ...), semantic parsing system analyzes the dialogue intention of client and customer issue is corresponding answers
Case；
The Content Management System classifies the multimedia messages of importing and marked, and Content Management System is first by more matchmakers
Body information is first divided into several major class, and major class is divided into (A, B, C ...), by the intention word of entity mark in major class and semantic parsing system
Allusion quotation set does correspondence, and each major class is then divided into several groups respectively, group be divided into [A=(A-1, A-2 ...), B=(B-1,
B-2 ...), C=(C-1, C-2 ...) ...], the intention dictionary set of entity mark in group and semantic parsing system is done pair
It answers；Such as the relevant multimedia of bank card is labeled as A, the multimedia that bank card classification includes is divided into A-1, A-2, A-3 ...；
Human body proximity sensor first obtains peripheral information, and the human testing data that human body proximity sensor obtains are distance D,
When the numerical value of human body proximity sensor is less than numerical value D < 1000mm of setting, master control system, which is judged as, has client before equipment
And client's welcome message is issued, client's welcome message is played out in a voice form by loudspeaker, such as welcome XXXX,
May I ask the help of what needs, while Intelligent dialogue interface is shown by screen, noise reduction microphone is converted from closed state
To start pickup state；Intelligent voice dialog screen apparatus guides client to engage in the dialogue by sound and text, intelligent sound pair
Words screen apparatus is integrated with speech recognition system and speech synthesis system, and the audio that client speaks is converted by speech recognition system
At text information, the text information of conversion passes to semantic parsing system, and semantic parsing system is analyzed client and is intended to, by multipair
The action command that one question and answer library obtains corresponding answer or needed to be implemented by action command library；When answering answer, handle is returned
The multimedia and text information answered are shown by screen, while by speech synthesis system, the text of answer is synthesized language
Sound is played back by loudspeaker, is realized voice dialogue and is shown multimedia voice interlocking；Refer to when needing to be implemented corresponding actions
When enabling, action command is sent to master control system by semantic parsing system, and master control system realizes that screen acts according to action command.
Session operational scenarios one, elemental motion instruction dialogue: after activation voice system, client can be triggered one page under voice control
Next movement, page up trigger previous movement, and xth page jumps triggering turn to x movement.
Session operational scenarios two, random session: after activation voice system, after semantic parsing system analyzes the stochastic problem of client,
Corresponding media resource is matched to show on the screen.As shown in Figure 2, if matching resource has multiple and≤6, one page is carried out
It shows, the number of resource is shown on resource page, if matching resource quantity > 6,6 are one page, and carry out rolling exhibition
Show, the resource accordingly numbered can be played by saying resource number by voice.
The ability that the present invention can make advertisement screen have voice dialogue interaction, can be according to the specific requirements for seeing advertiser
Product broadcasting is carried out, keeps advertising information more precisely more effective.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (2)
1. a kind of device and method for carrying out Products Show by Intelligent voice dialog, which is characterized in that including passing through intelligent language
Sound dialog screen device combination face identification system, semantic parsing system and Content Management System carry out Products Show；The intelligence
Energy voice dialogue screen apparatus includes screen, master control system, recognition of face camera, human body proximity sensor, noise reduction microphone
And loudspeaker, master control system are connect with screen, recognition of face camera, human body proximity sensor, noise reduction microphone and loudspeaker respectively；
The face identification system integrates face recognition algorithms, carries out customer information identification；The semantic parsing system includes entity mark
The intention dictionary set of note, many-to-one question and answer library and action command library, the dialogue that semantic parsing system analyzes client are intended to
Answer corresponding with customer issue；The Content Management System classifies the multimedia messages of importing and marked, content pipe
Multimedia messages are first first divided into several major class by reason system, and major class is divided into (A, B, C ...), will be real in major class and semantic parsing system
The intention dictionary set of body mark does correspondence, each major class is then divided into several groups respectively, group is divided into [A=(A-1, A-
2 ...), B=(B-1, B-2 ...), C=(C-1, C-2 ...) ...], by the intention of entity mark in group and semantic parsing system
Dictionary set does correspondence；
Human body proximity sensor first obtains peripheral information, and the human testing data that human body proximity sensor obtains are distance D, works as people
When the numerical value of body proximity sensor is less than numerical value D < 1000mm of setting, master control system, which is judged as, has client concurrent before equipment
Client's welcome message out, noise reduction microphone pickup state since being converted to closed state；Intelligent voice dialog screen apparatus is logical
It crosses sound and text guidance client engages in the dialogue, Intelligent voice dialog screen apparatus is integrated with speech recognition system and speech synthesis
System, the audio that client speaks are converted into text information by speech recognition system, and the text information of conversion passes to semantic point
Analysis system, semantic parsing system are analyzed client and are intended to, obtain corresponding answer by many-to-one question and answer library or pass through action command
The action command that library is needed to be implemented；The multimedia and text information of answer are shown by screen when answering answer
Come, while by speech synthesis system, the text synthesis voice of answer played back by loudspeaker, realize voice dialogue and
Show multimedia voice interlocking；When needing to be implemented corresponding actions instruction, action command is sent to master by semantic parsing system
Control system, master control system realize that screen acts according to action command.
2. a kind of device and method for carrying out Products Show by Intelligent voice dialog according to claim 1, feature
Be: client's welcome message is played out in a voice form by the loudspeaker, shows Intelligent dialogue circle by the screen
Face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236514.XA CN109949723A (en) | 2019-03-27 | 2019-03-27 | A kind of device and method carrying out Products Show by Intelligent voice dialog |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236514.XA CN109949723A (en) | 2019-03-27 | 2019-03-27 | A kind of device and method carrying out Products Show by Intelligent voice dialog |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109949723A true CN109949723A (en) | 2019-06-28 |
Family
ID=67011594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910236514.XA Pending CN109949723A (en) | 2019-03-27 | 2019-03-27 | A kind of device and method carrying out Products Show by Intelligent voice dialog |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949723A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334352A (en) * | 2019-07-08 | 2019-10-15 | 腾讯科技（深圳）有限公司 | Guidance information display methods, device, terminal and storage medium |
| CN112115282A (en) * | 2020-09-17 | 2020-12-22 | 北京达佳互联信息技术有限公司 | Question answering method, device, equipment and storage medium based on search |
| CN115187345A (en) * | 2022-09-13 | 2022-10-14 | 深圳装速配科技有限公司 | Intelligent household building material recommendation method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040093309A (en) * | 2003-04-29 | 2004-11-05 | 주식회사 팬택앤큐리텔 | Wireless Telecommunication Terminal using External Antenna which can be attatching and Built-in Antenna |
| KR20130122839A (en) * | 2012-05-01 | 2013-11-11 | 엘지전자 주식회사 | Mobile device for having at least one microphone sensor and method for controlling the same |
| CN104951077A (en) * | 2015-06-24 | 2015-09-30 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and device based on artificial intelligence and terminal equipment |
| CN105335498A (en) * | 2015-10-23 | 2016-02-17 | 广东小天才科技有限公司 | Method and system for information recommendation based on voice information |
| CN107515944A (en) * | 2017-08-31 | 2017-12-26 | 广东美的制冷设备有限公司 | Exchange method, user terminal and storage medium based on artificial intelligence |
| CN108292502A (en) * | 2015-11-25 | 2018-07-17 | 三菱电机株式会社 | Voice dialogue device and speech dialog method |
| CN108965584A (en) * | 2018-06-21 | 2018-12-07 | 北京百度网讯科技有限公司 | A kind of processing method of voice messaging, device, terminal and storage medium |
| CN109102320A (en) * | 2018-07-02 | 2018-12-28 | 大连大商天狗电子商务有限公司 | A kind of intelligent guidance system |
-
2019
- 2019-03-27 CN CN201910236514.XA patent/CN109949723A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040093309A (en) * | 2003-04-29 | 2004-11-05 | 주식회사 팬택앤큐리텔 | Wireless Telecommunication Terminal using External Antenna which can be attatching and Built-in Antenna |
| KR20130122839A (en) * | 2012-05-01 | 2013-11-11 | 엘지전자 주식회사 | Mobile device for having at least one microphone sensor and method for controlling the same |
| CN104951077A (en) * | 2015-06-24 | 2015-09-30 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and device based on artificial intelligence and terminal equipment |
| CN105335498A (en) * | 2015-10-23 | 2016-02-17 | 广东小天才科技有限公司 | Method and system for information recommendation based on voice information |
| CN108292502A (en) * | 2015-11-25 | 2018-07-17 | 三菱电机株式会社 | Voice dialogue device and speech dialog method |
| CN107515944A (en) * | 2017-08-31 | 2017-12-26 | 广东美的制冷设备有限公司 | Exchange method, user terminal and storage medium based on artificial intelligence |
| CN108965584A (en) * | 2018-06-21 | 2018-12-07 | 北京百度网讯科技有限公司 | A kind of processing method of voice messaging, device, terminal and storage medium |
| CN109102320A (en) * | 2018-07-02 | 2018-12-28 | 大连大商天狗电子商务有限公司 | A kind of intelligent guidance system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334352A (en) * | 2019-07-08 | 2019-10-15 | 腾讯科技（深圳）有限公司 | Guidance information display methods, device, terminal and storage medium |
| CN112115282A (en) * | 2020-09-17 | 2020-12-22 | 北京达佳互联信息技术有限公司 | Question answering method, device, equipment and storage medium based on search |
| CN115187345A (en) * | 2022-09-13 | 2022-10-14 | 深圳装速配科技有限公司 | Intelligent household building material recommendation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9621851B2 (en) | Augmenting web conferences via text extracted from audio content | |
| Cen et al. | A real-time speech emotion recognition system and its application in online learning | |
| CN109949723A (en) | A kind of device and method carrying out Products Show by Intelligent voice dialog | |
| CN107210045A (en) | The playback of search session and search result | |
| CN107211061A (en) | The optimization virtual scene layout played back for space meeting | |
| CN107211027A (en) | Perceived quality original higher rear meeting playback system heard than in meeting | |
| CN107728780A (en) | A kind of man-machine interaction method and device based on virtual robot | |
| CN107211058A (en) | Dialogue-based dynamic meeting segmentation | |
| CN111833861B (en) | Event evaluation report generation based on artificial intelligence | |
| CN107210034A (en) | selective conference summary | |
| CN107210036A (en) | Meeting word cloud | |
| CN111556279A (en) | Monitoring method and communication method of instant session | |
| Antunes et al. | A framework to support development of sign language human-computer interaction: Building tools for effective information access and inclusion of the deaf | |
| CN117615182B (en) | Live broadcast interaction dynamic switching method, system and terminal | |
| CN115222857A (en) | Method, apparatus, electronic device and computer readable medium for generating avatar | |
| Blumentals et al. | Emotion recognition in real-world support call center data for latvian language | |
| Vinciarelli | 17 Social Signal Processing for Automatic Role Recognition | |
| CN114201596A (en) | Virtual digital human use method, electronic device and storage medium | |
| Siegert et al. | A new Dataset of Telephone-Based Human-Human Call-Center Interaction with Emotional Evaluation. | |
| CN115831125A (en) | Speech recognition method, device, equipment, storage medium and product | |
| CN113782010B (en) | Robot response method, device, electronic equipment and storage medium | |
| Kothalkar et al. | Child-adult speech diarization in naturalistic conditions of preschool classrooms using room-independent ResNet model and automatic speech recognition-based re-segmentation | |
| CN111897434A (en) | System, method, and medium for signal control of virtual portrait | |
| CN111177343A (en) | Method and system for automatically constructing medical and American inquiry guide logic | |
| Walker | Teacher-pupil question-answer sequences: Some problems of analysis |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190628 |