CN112732887A - Processing device and system for multi-turn conversation - Google Patents
Processing device and system for multi-turn conversation Download PDFInfo
- Publication number
- CN112732887A CN112732887A CN202110093184.0A CN202110093184A CN112732887A CN 112732887 A CN112732887 A CN 112732887A CN 202110093184 A CN202110093184 A CN 202110093184A CN 112732887 A CN112732887 A CN 112732887A
- Authority
- CN
- China
- Prior art keywords
- module
- shell
- information
- end surface
- conversation
- 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
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 230000009471 action Effects 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 238000003786 synthesis reaction Methods 0.000 claims description 8
- 230000001815 facial effect Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 230000006698 induction Effects 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
Images
Classifications
-
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a processing device and a system for multi-round conversation, and the processing device comprises a fixed seat and a system, wherein the upper end surface of the fixed seat is fixedly welded with a connecting column a, the upper end of the connecting column a is sleeved with a rotating shaft, the upper end of the rotating shaft is sleeved with a connecting column b, the upper end surface of the connecting column b is fixedly welded with a shell, the front end surface of the shell is fixedly embedded with a touch screen, a camera is arranged above the touch screen and is embedded inside the upper part of the shell, a switch is fixedly embedded in the middle of the upper end surface of the shell, a charging port is fixedly embedded below the rear end surface of the shell, a filter layer is fixedly arranged above the inner part of the shell through screws, a driving mainboard is arranged below the filter layer, the left end; the invention has the advantages of high association performance and intelligence of equipment, targeted language change of user information and maintenance of conversation state by multiple rounds of conversations.
Description
Technical Field
The invention relates to the technical field of multi-turn conversations, in particular to a processing device and a processing system for the multi-turn conversations.
Background
The DM determines the reaction to the user at the moment according to the historical information of the conversation, the most common application is the task-driven multi-turn conversation, the user has definite purposes such as meal ordering, ticket ordering and the like, the user requirement is complex, a plurality of limiting conditions exist, and the statement can be given in multiple turns, on one hand, the user can continuously modify or perfect the requirement in the conversation process, and on the other hand, when the statement requirement of the user is not specific or definite, the machine can help the user to find a satisfactory result through inquiry, clarification or confirmation;
the existing multi-turn conversation technology controls the process of man-machine conversation, when user conversation information is incomplete, the intellectualization of the association performance of the equipment is poor, the equipment cannot change the language of the user information in a pertinence manner, and the multi-turn conversation cannot maintain the conversation state: there is a further need for a multi-session processing device and system.
Disclosure of Invention
The invention aims to provide a processing device and a system thereof for multi-turn conversations, which have the advantages of high equipment association performance and intelligence, pertinence language change of user information, and capability of maintaining conversation states through multi-turn conversations, and solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a processing apparatus and system that many rounds of dialogue, includes fixing base and system, the fixing base upper end surface is equipped with spliced pole an through welded fastening, spliced pole a upper end is equipped with the pivot through the suit, the pivot upper end is equipped with spliced pole b through the suit, spliced pole b upper end surface is equipped with the shell through welded fastening, the shell front end surface is equipped with the touch-sensitive screen through inlaying the fixed, the touch-sensitive screen top is equipped with the camera and through inlaying inside the shell top, be equipped with the switch through inlaying the fixed in the middle of the shell upper end surface, shell rear end surface below is equipped with the mouth that charges through inlaying the fixed, the inside top of shell is equipped with the filter layer through the screw fixation, the filter layer below is equipped with the drive mainboard and controls both ends through the screw fixation inside the shell, drive mainboard upper end surface loops through, The multi-round conversation processing module, the storage module and the cloud database module are arranged, loudspeakers are arranged at the left end and the right end below the driving main board and are fixed on the inner wall of the shell through screws, a protection box is fixedly arranged at the bottom in the shell through screws, and a storage battery is fixedly arranged in the protection box through screws;
preferably, the system comprises a storage battery, a camera, a touch screen and a driving main board, wherein the driving main board comprises a multi-round conversation processing module, a single chip microcomputer, a storage module and a cloud database module;
the cloud database module searches and stores the information on the network in a database by adopting a 5G network;
the single chip is an integrated circuit chip, and adopts the super-large scale integrated circuit technology to realize the functions of a central processing unit CPU with data processing capacity, a random access memory RAM, a read only memory ROM, various I/O ports, an interrupt system, a timer/counter and the like;
the storage module stores user information;
the multi-turn dialogue processing module controls the process of man-machine dialogue, and the DM determines the reaction to the user at the moment according to the dialogue historical information;
the camera is a video input device which is convenient for collecting the facial information of the user;
the touch screen can receive an induction type liquid crystal display device of input signals such as a contact and the like, and realizes manual touch operation and instructions;
the storage battery is powered by a device for converting chemical energy into electric energy;
and the loudspeaker is a transducer device for converting the electric signal converted by the system into an acoustic signal.
Preferably, the shell is in a trapezoidal shape, four corners of the shell are rounded, sound pickup holes are formed in the left side and the right side of the upper end surface of the shell, sound scattering holes are formed in the surfaces of the left end and the right end of the upper end surface of the shell, and the sound scattering holes are in contact with the loudspeaker.
Preferably, the fixing seat is disc-shaped, and four corners of the upper end of the fixing seat are provided with fixing holes.
Preferably, the charging port is connected to the switch, the storage battery, the camera, the touch screen, the driving main board, the storage module, the multi-round dialogue processing module, the single chip microcomputer, the storage module, the loudspeaker and the cloud database module through cables.
Compared with the prior art, the invention has the following beneficial effects:
1. this processing apparatus of many rounds of dialogues and system thereof gathers user's terminal surface portion information through the camera and passes through singlechip and storage module conveying and search for the required language kind of facial feature in high in the clouds database module to save and convey the NLU pronunciation understanding module in many rounds of dialogue processing module in storage module and make things convenient for equipment to understand and associate.
2. The processing device and the system thereof of the multi-round conversation identify the user voice through an ASR voice identification module in a multi-round conversation processing module, an NLU voice understanding module identifies the language type and compares the language type with the retrieval and storage information of a camera and a cloud database module in a storage module, when the information is not accordant, the information is retrieved on line in the cloud database module through the storage module until the information is accordant, when the information is accordant, the information is transmitted in a DST conversation state maintenance module and is transmitted in the storage module to enable the user to switch topics and state to be stored, so that the user can conveniently inquire related problems twice, meanwhile, the retrieved information and the maintenance information are arranged in sequence through a Policy action candidate sorting module, and an NLG language generation module generates the language of the retrieval information for the information provided by the user side; the TTS voice synthesis module makes corresponding answer analysis through the loudspeaker through the information of 5G network search for the cloud database module and combining the state of the system, and the sound scattering holes are formed in the surfaces of the left end and the right end of the shell and are in contact with the loudspeaker, so that the sound can be conveniently played through the shell.
Drawings
FIG. 1 is a schematic diagram of a multi-session processing apparatus and a system thereof according to the present invention;
FIG. 2 is a schematic diagram of a rear end structure of a housing of a multi-session processing device and a system thereof according to the present invention;
FIG. 3 is a schematic diagram of an internal structure of a housing of a multi-session processing device and a system thereof according to the present invention;
fig. 4 is a schematic view of a multi-turn dialog processing device and a dialog processing system of the multi-turn dialog processing device system according to the present invention.
The figure is marked with: 1. a fixed seat; 2. connecting column a; 3. a rotating shaft; 4. connecting a column b; 5. a housing; 6. A touch screen; 7. a camera; 8. a switch; 9. a charging port; 11. a filter layer; 12. driving the main board; 13. a single chip microcomputer; 14. a multi-turn dialogue processing module; 15. a storage module; 16. a cloud database module; 17. A speaker; 18. a protection box; 19. and (4) a storage battery.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Referring to fig. 1, 2 and 3, a multi-turn dialogue processing device and system thereof includes a fixing base 1 and a system, wherein the upper end surface of the fixing base 1 is fixedly welded with a connection column a2, the upper end of the connection column a2 is provided with a rotation shaft 3 through a sleeving manner, the upper end of the rotation shaft 3 is provided with a connection column b4 through a sleeving manner, the upper end surface of the connection column b4 is fixedly welded with a housing 5, the front end surface of the housing 5 is fixedly embedded with a touch screen 6, a camera 7 is arranged above the touch screen 6 and is embedded in the housing 5, a switch 8 is fixedly embedded in the middle of the upper end surface of the housing 5, a charging port 9 is fixedly embedded below the rear end surface of the housing 5, a filter layer 11 is fixedly arranged above the housing 5 through screws, a driving main board 12 is arranged below the filter layer 11 and is fixed in the housing 5 through screws at left and right ends, and a single chip, The multi-round conversation processing module 14, the storage module 15 and the cloud database module 16 are respectively provided with a loudspeaker 17 at the left end and the right end below the driving mainboard 12 and fixed on the inner wall of the shell 5 through screws, a protection box 18 is fixedly arranged at the bottom in the shell 5 through screws, and a storage battery 19 is fixedly arranged in the protection box 18 through screws; the shell 5 is processed by chamfering the four corners of the shell into a trapezoidal shape, sound pickup holes are formed in the left side and the right side of the upper end surface of the shell, sound scattering holes are formed in the left end surface and the right end surface of the shell and are in contact with the loudspeaker 17, the fixing seat 1 is disc-shaped, fixing holes are formed in the four corners of the upper end of the fixing seat, and the charging port 9 is connected to the switch 8, the storage battery 19, the camera 7, the touch screen 6, the driving main board 12, the storage module 15, the multi-wheel conversation processing module 14, the single chip microcomputer 13, the storage module 15;
it is specific, conveniently fix spliced pole a2 through fixing base 1, pivot 3 makes things convenient for spliced pole b4 to drive shell 5 and carries out rotation regulation simultaneously, 6 convenience of customers manual operation orders of touch-sensitive screen, camera 7 conveniently gathers user's facial information, switch 8 opens as opening of equipment and stops the button, the external power source is conveniently connected to mouth 9 that charges, filter layer 11 conveniently filters the dust, drive mainboard 12 conveniently drives the equipment program drive, singlechip 13 conveniently carries out operation control, many rounds of dialogue processing module 14 conveniently carry out the dialogue processing, storage module 15 conveniently saves information, high in the clouds database module 16 conveniently retrieves information, speaker 17 conveniently transmits sound, the effectual protection battery 19's of protection box 18 security.
Example 2:
referring to fig. 4, a processing device and a system for multi-round conversations includes a storage battery 19, a camera 7, a touch screen 6 and a driving main board 12, where the driving main board 12 includes a multi-round conversation processing module 14, a single chip 13, a storage module 15 and a cloud database module 16;
the cloud database module 16 searches and stores the information on the network in a database by adopting a 5G network;
the single chip microcomputer 13 is an integrated circuit chip, and adopts the super large scale integrated circuit technology to perform the functions of a central processing unit CPU with data processing capacity, a random access memory RAM, a read only memory ROM, various I/O ports, an interrupt system, a timer/counter and the like;
the storage module 15 stores the user information;
the multi-turn dialogue processing module 14 controls the process of man-machine dialogue, and the DM determines the reaction to the user at the moment according to the dialogue historical information;
the camera 7 is a video input device which is convenient for collecting the facial information of the user;
the touch screen 6 can receive the induction type liquid crystal display device of input signals such as a contact, etc., and realize manual touch operation and instructions;
the storage battery 19 is powered by a device for converting chemical energy into electric energy;
a transducer device for converting the electric signal converted by the system into an acoustic signal by the loudspeaker 17;
the multi-round dialogue processing module 14 comprises an ASR voice recognition module, an NLU voice understanding module, a DST dialogue state maintenance module, a Policy action candidate sorting module, an NLG language generation module and a TTS voice synthesis module; the ASR speech recognition module adopts a sound pick-up to pick up and recognize sound; the NLU speech understanding module is used for understanding, analyzing and processing the recognized sound; the DST conversation state maintenance module maintains the information state of the conversation provided by the user side by adopting state switching and topic switching; the Policy action candidate sorting module is used for sorting the information provided by the user side; the NLG language generation module generates a language of retrieval information for the information provided by the user side; the TTS speech synthesis module adopts information searched by a 5G network and makes corresponding answer analysis by combining the state of the system;
specifically, the storage battery 19 is used for conveniently supplying power to the interior of the equipment, the touch screen 6 is used for conveniently performing manual operation on a user side, the camera 7 is used for collecting information of the user side and transmitting the information to be searched for the language type required by the facial features in the cloud database module through the single chip microcomputer 13 and the storage module, the information is stored in the storage module 15, and the multi-round conversation processing module 14 comprises an ASR (auto-regressive) speech recognition module, an NLU (non-linear speech) speech understanding module, a DST (traffic state maintenance) module, a Policy action candidate sorting module, an NLG (non-linear speech) generation module and a TTS; the ASR speech recognition module adopts a sound pick-up to pick up and recognize sound; the NLU speech understanding module is used for understanding, analyzing and processing the recognized sound; the DST conversation state maintenance module maintains the information state of the conversation provided by the user side by adopting state switching and topic switching; the Policy action candidate sorting module is used for sorting the information provided by the user side; the NLG language generation module generates a language of retrieval information for the information provided by the user side; the TTS speech synthesis module adopts the information searched by the 5G network and makes corresponding answer analysis by combining the state of the system.
The working principle is as follows: the invention relates to a multi-wheel dialogue processing device and a system thereof, wherein a charging port 9 is connected with a switch 8, a storage battery 19, a camera 7, a touch screen 6, a driving main board 12, a storage module 15, a multi-wheel dialogue processing module 14, a single chip microcomputer 13, the storage module 15, a loudspeaker 17 and a cloud database module 16 through cables and an external 5G network, the normal electrification property of equipment is ensured, meanwhile, a protection box 18 ensures the safety of the storage battery 19, a fixing seat 1 is disc-shaped, four corners at the upper end of the fixing seat are provided with fixing holes, a worker can conveniently fix the equipment at a working place through the fixing seat 1, a connecting column a2 and a connecting column b4 are connected through a rotating shaft 3, the shell 5 can conveniently drive a connecting column b4 to rotate and adjust on the rotating shaft 3, the switch 8 is opened, the storage battery 19 drives the equipment to work, and meanwhile, four corners of the, sound pickup holes are formed in the left side and the right side of the upper end surface of the multi-round conversation processing module, so that the multi-round conversation processing module 14 on the driving main board 12 can recognize sound conveniently, meanwhile, the filter layer 11 ensures the cleanness of the driving main board 12, the camera 7 collects information of the end face of a user and transmits the information to the cloud end database module 16 through the singlechip 13 and the storage module 15 to search for the type of language needed by facial features, the information is stored in the storage module 15 and transmitted to the NLU speech understanding module in the multi-round conversation processing module 14 to facilitate understanding and association of equipment, the ASR speech recognition module in the multi-round conversation processing module 14 recognizes the type of language through recognizing the voice of the user and the NLU speech understanding module, and compares the type of language with the information stored in the storage module 15, when the information does not accord with each other, the information is searched online in the cloud end database module 16, the information is transmitted in the DST dialogue state maintenance module and is transmitted in the storage module 15 to enable the user to switch topics and state for storage, so that the user can conveniently inquire related problems twice, meanwhile, the searched information and maintenance information are ranked through the Policy action candidate ranking module, and the NLG language generation module generates the language of the searched information for the information provided by the user side; the TTS voice synthesis module uses information searched by a 5G network through the cloud database module 16 and performs corresponding answer analysis through the loudspeaker 17 in combination with the state of the system, sound scattering holes are formed in the surfaces of the left end and the right end of the shell 5 and are in contact with the loudspeaker 17, so that the sound is conveniently played through the shell 5, and the TTS voice synthesis module has the advantages of being high in equipment association performance and intelligence, and maintaining conversation states through change languages of user information pertinence and multi-turn conversation.
While there have been shown and described the fundamental principles and essential features of the invention and advantages thereof, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof; the present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (6)
1. A processing device and system for multi-turn conversations is characterized in that: including fixing base (1) and system, fixing base (1) upper end surface is equipped with spliced pole a (2) through welded fastening, spliced pole a (2) upper end is equipped with pivot (3) through the suit, pivot (3) upper end is equipped with spliced pole b (4) through the suit, spliced pole b (4) upper end surface is equipped with shell (5) through welded fastening, shell (5) front end surface is equipped with touch-sensitive screen (6) through inlaying the fixation, touch-sensitive screen (6) top is equipped with camera (7) and inside through inlaying in shell (5) top, be equipped with switch (8) through inlaying the fixation in the middle of shell (5) upper end surface, shell (5) rear end surface below is equipped with charge mouth (9) through inlaying the fixation, shell (5) inside top is equipped with filter layer (11) through the screw fixation, filter layer (11) below is equipped with drive mainboard (12) and controls both ends and passes through the screw fixation at shell (5) through the ) Inside, drive mainboard (12) upper end surface loops through from a left side to the right side and inlays fixed singlechip (13), many rounds of dialogue processing module (14), storage module (15) and high in the clouds database module (16) of being equipped with, both ends are equipped with speaker (17) and pass through the screw fixation on shell (5) inner wall about drive mainboard (12) below, the bottom is equipped with protection box (18) through the screw fixation in shell (5), protection box (18) are inside to be equipped with battery (19) through the screw fixation.
2. The processing device and the system thereof for multi-turn dialog according to claim 1, wherein: the system comprises a storage battery (19), a camera (7), a touch screen (6) and a driving main board (12), wherein the driving main board (12) comprises a multi-wheel dialogue processing module (14), a single chip microcomputer (13), a storage module (15) and a cloud database module (16);
the cloud database module (16) adopts a 5G network to retrieve and store the information on the network in a database;
the single chip microcomputer (13) is an integrated circuit chip and adopts the super-large scale integrated circuit technology to realize the functions of a central processing unit CPU with data processing capacity, a random access memory RAM, a read only memory ROM, various I/O ports, an interrupt system, a timer/a counter and the like;
the storage module (15) stores user information;
the multi-round conversation processing module (14) controls the process of man-machine conversation, and the DM determines the reaction to the user at the moment according to the history information of the conversation;
the camera (7) is a video input device which is convenient for collecting the facial information of the user;
the touch screen (6) can receive an induction type liquid crystal display device of input signals such as a contact and the like, and realizes manual touch operation and instructions;
the storage battery (19) is powered by a device for converting chemical energy into electric energy;
the loudspeaker (17) is a transducer device for converting the electrical signal converted by the system into an acoustic signal.
3. A multi-turn dialog processing device and system thereof according to claim 2, wherein: the multi-round dialogue processing module (14) comprises an ASR voice recognition module, an NLU voice understanding module, a DST dialogue state maintenance module, a Policy action candidate sorting module, an NLG language generation module and a TTS voice synthesis module; the ASR speech recognition module adopts a sound pick-up to pick up and recognize sound; the NLU speech understanding module is used for understanding, analyzing and processing the recognized sound; the DST conversation state maintenance module maintains the information state of the conversation provided by the user side by adopting state switching and topic switching; the Policy action candidate sorting module is used for sorting the information provided by the user side; the NLG language generation module generates a language of retrieval information for the information provided by the user side; the TTS speech synthesis module adopts the information searched by the 5G network and makes corresponding answer analysis by combining the state of the system.
4. The processing device and the system thereof for multi-turn dialog according to claim 1, wherein: the shell (5) is in a trapezoidal shape, four corners of the shell are all rounded, sound pickup holes are formed in the left side and the right side of the upper end surface of the shell, sound scattering holes are formed in the surfaces of the left end and the right end of the shell, and the surfaces of the left end and the right end of the shell are in contact with the loudspeaker (17).
5. The processing device and the system thereof for multi-turn dialog according to claim 1, wherein: the fixing seat (1) is disc-shaped, and four corners of the upper end of the fixing seat are provided with fixing holes.
6. The processing device and the system thereof for multi-turn dialog according to claim 1, wherein: charging port (9) are connected on switch (8), battery (19), camera (7), touch-sensitive screen (6), drive mainboard (12), storage module (15), many rounds of dialogue processing module (14), singlechip (13), storage module (15), speaker (17) and high in the clouds database module (16) through the cable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110093184.0A CN112732887A (en) | 2021-01-22 | 2021-01-22 | Processing device and system for multi-turn conversation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110093184.0A CN112732887A (en) | 2021-01-22 | 2021-01-22 | Processing device and system for multi-turn conversation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732887A true CN112732887A (en) | 2021-04-30 |
Family
ID=75593490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110093184.0A Pending CN112732887A (en) | 2021-01-22 | 2021-01-22 | Processing device and system for multi-turn conversation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732887A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114464179A (en) * | 2022-01-28 | 2022-05-10 | 达闼机器人股份有限公司 | Voice interaction method, system, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328166A (en) * | 2016-08-31 | 2017-01-11 | 上海交通大学 | Man-machine dialogue anomaly detection system and method |
| CN107369443A (en) * | 2017-06-29 | 2017-11-21 | 北京百度网讯科技有限公司 | Dialogue management method and device based on artificial intelligence |
| CN207744095U (en) * | 2018-01-27 | 2018-08-17 | 东莞市乐放实业有限公司 | A kind of intelligent things speaker |
| CN208273169U (en) * | 2018-03-25 | 2018-12-21 | 泉州市伟升网络科技有限公司 | A kind of dust-proof intelligent sound box shell |
| CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
| CN110457447A (en) * | 2019-05-15 | 2019-11-15 | 国网浙江省电力有限公司电力科学研究院 | A kind of power grid Task conversational system |
| CN210958669U (en) * | 2019-11-25 | 2020-07-07 | 深圳市拓步电子科技有限公司 | Screen display and sound box integrated equipment with communication function |
-
2021
- 2021-01-22 CN CN202110093184.0A patent/CN112732887A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328166A (en) * | 2016-08-31 | 2017-01-11 | 上海交通大学 | Man-machine dialogue anomaly detection system and method |
| CN107369443A (en) * | 2017-06-29 | 2017-11-21 | 北京百度网讯科技有限公司 | Dialogue management method and device based on artificial intelligence |
| CN207744095U (en) * | 2018-01-27 | 2018-08-17 | 东莞市乐放实业有限公司 | A kind of intelligent things speaker |
| CN208273169U (en) * | 2018-03-25 | 2018-12-21 | 泉州市伟升网络科技有限公司 | A kind of dust-proof intelligent sound box shell |
| CN110457447A (en) * | 2019-05-15 | 2019-11-15 | 国网浙江省电力有限公司电力科学研究院 | A kind of power grid Task conversational system |
| CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
| CN210958669U (en) * | 2019-11-25 | 2020-07-07 | 深圳市拓步电子科技有限公司 | Screen display and sound box integrated equipment with communication function |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114464179A (en) * | 2022-01-28 | 2022-05-10 | 达闼机器人股份有限公司 | Voice interaction method, system, device, equipment and storage medium |
| WO2023143439A1 (en) * | 2022-01-28 | 2023-08-03 | 达闼机器人股份有限公司 | Speech interaction method, system and apparatus, and device and storage medium |
| CN114464179B (en) * | 2022-01-28 | 2024-03-19 | 达闼机器人股份有限公司 | Voice interaction method, system, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5475798A (en) | Speech-to-text translator | |
| CN111008532B (en) | Voice interaction method, vehicle and computer readable storage medium | |
| CN203861914U (en) | Pet robot | |
| CN108010531A (en) | A kind of visible intelligent inquiry method and system | |
| CN108877805A (en) | Speech processes mould group and terminal with phonetic function | |
| CN108009490A (en) | A kind of determination methods of chat robots system based on identification mood and the system | |
| CN206029912U (en) | Interactive VR's intelligent robot | |
| CN112732887A (en) | Processing device and system for multi-turn conversation | |
| CN112735418A (en) | Voice interaction processing method and device, terminal and storage medium | |
| CN209625783U (en) | Intelligent sound box and smart home system | |
| CN106019977A (en) | Gesture and emotion recognition home control system | |
| CN213400154U (en) | STC single chip microcomputer-based glove for translating language for language-handicapped person | |
| CN210349312U (en) | Voice internet equipment | |
| CN114020143A (en) | Intelligent reading auxiliary device | |
| CN218547485U (en) | Order management platform based on mobile terminal | |
| CN106708775A (en) | Mathematical formula searching method and device | |
| CN208094702U (en) | A kind of electronic peephole viewer system for antitheft door | |
| CN207731643U (en) | A kind of intelligent sound identification interaction controller | |
| CN112589619A (en) | Master-apprentice type intelligent grinding and polishing machine based on expert system | |
| CN208861494U (en) | A kind of children education intelligent robot | |
| CN215181936U (en) | Intelligent equipment classification device | |
| CN219016818U (en) | Multifunctional application equipment based on inverter power supply | |
| CN108010528A (en) | A kind of intelligent sound identifies interaction controller | |
| CN108389448A (en) | A kind of guidance of Students' Innovation entrepreneurship process and counseling services recording device | |
| CN212782046U (en) | Electric power service information retrieval electronic equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210430 |
|
| WD01 | Invention patent application deemed withdrawn after publication |