CN109801632A - A kind of artificial intelligent voice robot system and method based on big data - Google Patents
A kind of artificial intelligent voice robot system and method based on big data Download PDFInfo
- Publication number
- CN109801632A CN109801632A CN201910178016.4A CN201910178016A CN109801632A CN 109801632 A CN109801632 A CN 109801632A CN 201910178016 A CN201910178016 A CN 201910178016A CN 109801632 A CN109801632 A CN 109801632A
- Authority
- CN
- China
- Prior art keywords
- information
- face
- module
- text information
- face recognition
- 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
- Manipulator (AREA)
- Toys (AREA)
Abstract
A kind of artificial intelligent voice robot system based on big data of the present invention includes voice acquisition module (100), is used to acquire the first acoustic information that registration user issues;First voice conversion module is used to convert the first text information for the first acoustic information;Face recognition module (200) is used to acquire the face information of registration user;Large database concept is equipped with and first text information and common corresponding second text information of face information;Control module is used to export the second text information according to first text information and face information by large database concept;Second voice conversion module (300) is used to convert second sound information for second text information.Face recognition module is added on traditional speech robot people's platform by the present invention by above-mentioned, so as to more accurately be replied according to the double-point information of the face information of user and the first acoustic information to make in large database concept.
Description
Technical field
The present invention relates to a kind of artificial intelligence systems based on big data, more particularly to a kind of based on the artificial of big data
Intelligent sound robot system.
Background technique
Artificial intelligence (AI) language is that one kind is adapted to artificial intelligence and knowledge engineering field, has Symbol processing and patrol
Collect the computer programming language of inferential capability.Program solution non-numerical computations can be write with it, knowledge processing, pushed away
Reason, planning, decision etc. have the various challenges of intelligence.
The siri of the higher apple of popularity, the day cat spirit of Alibaba, the small love classmate of millet are equal in existing market
For preferable speech robot people, however people thirst for obtaining preferably, the artificial intelligent voice robot system that more personalizes,
To increase user satisfaction, increase user's viscosity.
Therefore, a kind of artificial intelligent voice machine can satisfy user's greater demand, more personalizing is needed at present
People's system.
Summary of the invention
It can satisfy user's greater demand, the more people that personalizes the technical problem to be solved in the present invention is to provide a kind of
Work intelligent sound robot system.
A kind of artificial intelligent voice robot system based on big data of the present invention, including
Voice acquisition module is used to acquire the first acoustic information that registration user issues;
First voice conversion module is used to convert the first text information for the first acoustic information;
Face recognition module is used to acquire the face information of registration user;
Large database concept is equipped with and first text information and common corresponding second text information of face information;
Control module is used for through large database concept according to the second text of first text information and the output of face information
This information;
Second voice conversion module is used to convert second sound information for second text information.
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein the face recognition module acquires
In the first preset time after to the face information of user, control module is by large database concept according to first text information
The second text information is exported with face information.
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein at least eight voice collectings
Module is arranged on the base, and at least eight voice acquisition modules are arranged circumferentially along the pedestal, at least eight language
Sound acquisition module acquires the first acoustic information that registration user issues respectively, and be compared to each other the first acoustic information of its acquisition
Loudness, and the center by the voice acquisition module of maximum first acoustic information of collected loudness far from the pedestal
Direction and be determined as the first registration user direction;
The pedestal is configured with the face recognition module along its rotation, is configured at least one in the face recognition module
Gyroscope, the gyroscope is used to acquire the direction of the face recognition module, when the collected recognition of face of gyroscope
When angle between the direction of module and first registration user direction is less than the first predetermined angle, then control module passes through big
Database and the second text information is exported according to first text information and face information.
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein the control module is according to
Number a, the base width b of voice acquisition module export the first predetermined angle C according to the following formula:
Wherein, the unit of the first predetermined angle C is degree;
The unit of the number a is a;
The unit of the width b is decimetre;
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein the face recognition module passes through
Adjustment section configures on the pedestal, and the adjustment section includes substrate, shaft, sliding block, guide tube, output shaft, first motor, first
The outer surface of spring, the first electromagnet, the first permanent magnet, the face recognition module and substrate is fixed, the lower end of substrate and institute
The upper surface overlap joint of pedestal is stated, the upper end of the substrate is connect with the upper end hinge of the shaft, the lower end of the shaft and institute
The upper surface for stating sliding block is fixed, and the sliding block is moved up and down along the surface of the guide tube, the outer circumference surface of the sliding block with it is described
The inner peripheral surface shape of guide tube matches, and the sliding block and shaft jointly, coaxially offer the first screw hole, the output
The top of axis is equipped with the screw thread that matches with first screw hole, the upper end of the output shaft of the first motor and the sliding block,
First screw hole of shaft is threadedly coupled, and the lower end of the first motor and the upper surface of the pedestal are fixed, under the guide tube
It holds and is fixed with the upper surface of the pedestal, the lower surface of the sliding block and the upper end of the first spring are fixed, first spring
Lower end and the first permanent magnetism ferropexy, first permanent magnet are arranged right below the first electromagnet, first electromagnet and institute
The inner surface for stating guide tube is fixed;
First electromagnet, first motor, face recognition module are connect with the control module.
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein the first electromagnet described in two groups,
First permanent magnet, the first spring are arranged along the axisymmetrical of the shaft.
A kind of artificial intelligent voice robot system based on big data of the present invention, wherein first electromagnet and first
Shielding ring is equipped between motor, the outer circumference surface of the shielding ring and the inner peripheral surface of the guide tube are fixed, the shielding ring
Inner peripheral surface is surrounded with output shaft.
A kind of method of the artificial intelligent voice robot system based on big data of the present invention, including following steps:
S100, at least eight voice acquisition modules collect the first acoustic information of registration user;
S200, compare at least eight voice acquisition modules receive the first acoustic information loudness and most by collected loudness
The voice acquisition module of the first big acoustic information far from the pedestal center direction and be determined as the first registration
User direction;
First electromagnet of adjustment section is powered off and starts first motor by S300, control module, causes the recognition of face
The horizontally toward rotation of module to first registration user direction;
First electromagnet of adjustment section is powered and starts first motor by S400, control module, causes the recognition of face
The face of user is registered in the pitching of module towards rotation to face;
S500, the first text information is converted by the first acoustic information;
The face information of S600, acquisition registration user
S700, the second text information is exported according to first text information and face information by large database concept;
S800, second sound information is converted by second text information.
A kind of artificial intelligent voice robot system difference from prior art based on big data of the present invention is this
A kind of artificial intelligent voice robot system present invention based on big data is invented to be added to face recognition module by above-mentioned
On traditional speech robot people's platform, so as to according to the double-point information of the face information of user and the first acoustic information come big
Database, which is made, more accurately to be replied, and is on the one hand said, only can just start speech robot when user is directed at face recognition module
On the other hand the answer of people is said, face information can represent user so that speech robot people be avoided disorderly to reply registration user's word
Identity, thus preferably to find out matching and more matched second text information of the first acoustic information in large database concept,
To more meet the needs of users.
A kind of artificial intelligent voice robot system based on big data of the invention is made with reference to the accompanying drawing further
Explanation.
Detailed description of the invention
Fig. 1 is a kind of circuit connection diagram of artificial intelligent voice robot system based on big data;
Fig. 2 is a kind of top view of artificial intelligent voice robot system based on big data;
Fig. 3 is the main view of Fig. 2;
Fig. 4 is the right view of the first state of Fig. 3;
Fig. 5 is the right view of the second state of Fig. 3;
Fig. 6 is the partial enlarged view of Fig. 4;
Fig. 7 is the partial enlarged view of Fig. 5.
Specific embodiment
As shown in Fig. 1~7, referring to Fig. 1, a kind of artificial intelligent voice robot system based on big data of the present invention includes
Voice acquisition module 100 is used to acquire the first acoustic information that registration user issues;
First voice conversion module is used to convert the first text information for the first acoustic information;
Face recognition module 200 is used to acquire the face information of registration user;
Large database concept is equipped with and first text information and common corresponding second text information of face information;
Control module is used for through large database concept according to the second text of first text information and the output of face information
This information;
Second voice conversion module 300 is used to convert second sound information for second text information.
Face recognition module is added on traditional speech robot people's platform by the present invention by above-mentioned, so as to according to
The face information at family and the double-point information of the first acoustic information more accurately reply to make in large database concept, on the one hand say,
The answer that only can just start speech robot people when user is directed at face recognition module 200, so that speech robot people be avoided disorderly to return
User's word is registered again, is on the other hand said, face information can represent the identity of user, thus preferably in large database concept
Matching and more matched second text information of the first acoustic information are found out, to more meet the needs of users.
For example, register the first acoustic information that user says as " you are problematic? ", when face information monitoring arrives user's
When age is 12 years old, the second text information stored in large database concept can be enabled for " you are just problematic " to increase aughty sense
User's body and mind is pleasant;And when the age of face information monitoring to user is 42 years old, the second text envelope of storage in large database concept
Breath can be " particular problem is please input to the method that search engine inquiry solves the problems, such as " and/or jump directly to user terminal
Search engine, so as to help user to solve the problems, such as, such answer seems serious and practical.Wherein, the registration user
Age can be stored to large database concept together with the face information in user's registration.
It is emphasized that SIRI takes " hey siri at present!", small love classmate takes " small love classmate!" cry out
Starting scheme is talked about, and in this scheme, being likely to occur speech robot people, disorderly starting causes to influence user's use, or even therefore quilt
Permanent the phenomenon that closing, therefore, the present invention just makes reply when default collects the face information of registration user, then can avoid beating
Disturb user.
Therefore, when user is not towards face recognition module 200, the face recognition module 200 can not detect use
The face information at family, so that control module, large database concept can not also obtain face information, therefore, it is impossible to export the second text envelope
Breath.That is, in order to avoid bothering registration, user is daily speaks, and the present invention is in the face information for not acquiring registration user
When, the second text information and second sound information are not exported, to avoid bothering user.
Wherein, the face information includes following any one or more combination:
Nationality, gender, the age, height, weight, occupation, educational background, marital status, birthplace, resident address, bearing status,
Cell-phone number, monthly income, medical history, previous conviction.
Wherein, the face information one or more can be stored to large database concept when registering user's registration by above-mentioned.
Wherein, the first voice conversion module, the second voice conversion module can be same module, with the control module
Connection.
Wherein, the first voice conversion module can be control module, and the second voice conversion module can be sound equipment, and the first voice turns
Change module, the second voice conversion module can be connect with control module.
Preferably, the face recognition module 200 collects in the first preset time after the face information of user, control
Module exports the second text information according to first text information and face information by large database concept.
The present invention through the above way can be for being judged to acquiring in the first preset time after acquisition face information
To the face information of registration user, so as to continuously interact with speech robot people convenient for user, while chat robots are avoided again
It disorderly replies and only replies in the first preset time, consequently facilitating user uses.
Wherein, first preset time can be (0.1s, 120s), preferably 15s.
Preferably, referring to fig. 2, at least eight voice acquisition modules 100 are arranged on pedestal 400, at least eight languages
Sound acquisition module 100 is arranged circumferentially along the pedestal 400, and at least eight voice acquisition module 100 acquires respectively
The first acoustic information that user issues is registered, and is compared to each other the loudness of the first acoustic information of its acquisition, and will be collected
The voice acquisition module 100 of maximum first acoustic information of loudness far from the pedestal 400 center direction and sentence
It is set to the first registration user direction;
The pedestal 400 is configured with the face recognition module 200 along its rotation, configures in the face recognition module 200
There is at least one gyroscope, the gyroscope is used to acquire the direction of the face recognition module 200, when gyroscope is collected
The face recognition module direction it is described first registration user direction between angle less than the first predetermined angle when, then control
Molding block exports the second text information according to first text information and face information by large database concept.
The present invention first passes through 100 loudness of voice acquisition module for comparing different location, and determines the first registration user direction,
Determine whether first registration user direction is substantially consistent with the face recognition module 200 again, when consistent, then by first
Text information is converted into the second text information, to further increase a decision condition for the starting of speech robot people, to keep away
Exempt from speech robot people disorderly to reply and the normal life of sound equipment user.That is, collecting use and if only if face recognition module
The face information at family, also, voice acquisition module 100 collects the first registration user direction and the face recognition module of user
200 towards it is almost the same when, the first text information and face information are just exported into the second text information, so as to further keep away
Exempt from the phenomenon that speech robot people disorderly replies.
Wherein, the voice acquisition module 100 can be equipped with 3,4,5,6,7,8,9,10,11,12,13,14,15,16, preferably
It is 8.
Wherein, the pedestal 400 is preferably cylindrical body, and circular upper surface may be configured with 8 voice acquisition modules
100。
Wherein, gyroscope can be equipped with 1,2,3,4,5,6,7,8,9,10, preferably two, precisely to determine the face
The direction of identification module 200.
Wherein, the first predetermined angle can be (1 °, 119 °), preferably 15 °.
Wherein, the gyroscope can be embedded in the face recognition module 200, also, the gyroscope, recognition of face
Module 200 with the wired or wireless connection of the control module.
Preferably, the control module is according to number a, the 400 width b of pedestal of the voice acquisition module 100 according to such as
Lower formula exports the first predetermined angle C:
Wherein, the unit of the first predetermined angle C is degree;
The unit of the number a is a;
The unit of the width b is decimetre;
The present invention through the above way can be with number a for a basic parameter, and number is more, certainly will be by number a bring
Entire circumferential swingable angle is bigger, to keep the first predetermined angle C bigger, and the width b of pedestal 400 is wider can be as far as possible
Ground reduces the error of swing angle, so as to reduce standard value the first predetermined angle C, most connects to accurately and quickly find
The voice acquisition module 100 of nearly user, so that quick definition first registers user direction.
Wherein, the face recognition module 200 can be directly anchored on pedestal 400, the face recognition module 200 and institute
State the wired or wireless connection of control module.
Preferably, referring to fig. 2,3,4,5,6,7, the face recognition module 200 by adjusting portion 500 configure in the base
On seat 400, the adjustment section 500 includes substrate 501, shaft 502, sliding block 503, guide tube 504, output shaft 505, first motor
506, the first spring 507, the first electromagnet 508, the first permanent magnet 509, the face recognition module 200 are outer with substrate 501
Surface is fixed, and the upper surface of the lower end of substrate 501 and the pedestal 400 overlaps, the upper end of the substrate 501 and the shaft
502 upper end hinge connection, the lower end of the shaft 502 and the upper surface of the sliding block 503 are fixed, and the sliding block 503 is along institute
The surface for stating guide tube 504 moves up and down, and the inner peripheral surface shape of the outer circumference surface of the sliding block 503 and the guide tube 504 matches
Conjunction, the sliding block 503 and shaft 502 jointly, coaxially offer the first screw hole 511, and the top of the output shaft 505 is set
There are the screw thread matched with first screw hole 511, the upper end of the output shaft 505 of the first motor 506 and the sliding block
503, the first screw hole 511 of shaft 502 is threadedly coupled, and the upper surface of the lower end of the first motor 506 and the pedestal 400 is solid
Fixed, the lower end of the guide tube 504 and the upper surface of the pedestal 400 are fixed, the lower surface of the sliding block 503 and the first spring
507 upper end is fixed, and the lower end of first spring 507 and the first permanent magnet 509 are fixed, and first permanent magnet 509 is just
Lower section is equipped with the first electromagnet 508, and the inner surface of first electromagnet 508 and the guide tube 504 is fixed;
First electromagnet 508, first motor 506, face recognition module 200 are connect with the control module.
The present invention can enable the face recognition module 200 on substrate 501 in the first electromagnet by above-mentioned adjustment section 500
508, the first permanent magnet 509 be attracted and first motor 506 rotate when realize towards pitch regulation, face recognition module 200 exists
It realizes when first electromagnet 508, the first permanent magnet 509 are not attracted and first motor 506 rotates and is adjusted towards horizontal rotation,
Can be enough towards angle to be provided for face recognition module 200, to preferably capture face, and defeated into large database concept
Enter the face information of its acquisition.
Wherein, first electromagnet 508, first motor 506, face recognition module and the control module is wired or nothing
Line connection.
Wherein, in order to increase the first screw hole 511 and output shaft 505 screw thread self-lock ability, the screw thread and the first spiral shell
The screw pitch in hole 511 is smaller, lead angle is smaller, can be the screw thread of triangle thread form;Preferably triangle thread form, screw pitch are less than
1mm, lead angle are less than 3 °.The strong screw thread of self-lock ability can allow shaft 502 to rotate with the rotation of output shaft 505, and
It will not the born rotation by the gravity of substrate 501.It, can be in the screw thread of output shaft 505 also, in order to increase the self-lock ability of screw thread
And first increase adhesive tape or Filamentous filler between screw hole 511, to increase the force-bearing situation between screw thread, to allow shaft 502
It can be rotated with the rotation of output shaft 505, and stop as it stops.
Wherein, the sliding block 503 is disc-shaped, the outer circumference surface of the inner peripheral surface of the guide tube 504 and the sliding block 503
Shape matches.
Preferably, the first electromagnet 508, the first permanent magnet 509 described in two groups, the first spring 507 are along the shaft 502
Axisymmetrical setting.
The present invention can preferably fix sliding block by two group of first electromagnet 508, the first permanent magnet 509, the first spring 507
503, make the rotation of sliding block 503 and does not rotate and can preferably be controlled.
Preferably, shielding ring 510, the shielding ring 510 are equipped between first electromagnet 508 and first motor 506
The inner peripheral surface of outer circumference surface and the guide tube 504 fix, the inner peripheral surface of the shielding ring 510 is surrounded with output shaft 505.
Wherein, the material of the shielding ring 510 can be magnetic shield material, preferably with a thickness of 0.002 to 0.010 inch
Foil.
The present invention can avoid the first electromagnet 508 by above-mentioned shielding ring 510, the magnetic field of the first permanent magnet 509 influences the
The rotation of one motor 506.
A kind of method of the artificial intelligent voice robot system based on big data of the present invention, it is characterised in that including as follows
Step:
S100, at least eight voice acquisition modules 100 collect the first acoustic information of registration user;
S200, compare at least eight voice acquisition modules 100 and receive the loudness of the first acoustic information and by collected sound
It spends the direction of the center far from the pedestal 400 of the voice acquisition module 100 of maximum first acoustic information and determines
For the first registration user direction;
First electromagnet 508 of adjustment section 500 is powered off and starts first motor 506 by S300, control module, is caused described
The horizontally toward rotation of face recognition module 200 to first registration user direction;
First electromagnet 508 of adjustment section 500 is powered and starts first motor 506 by S400, control module, causes described
The face of user is registered in the pitching of face recognition module 200 towards rotation to face;
S500, the first text information is converted by the first acoustic information;
The face information of S600, acquisition registration user
S700, the second text information is exported according to first text information and face information by large database concept;
S800, second sound information is converted by second text information.
Embodiment described above only describe the preferred embodiments of the invention, not to model of the invention
It encloses and is defined, without departing from the spirit of the design of the present invention, those of ordinary skill in the art are to technical side of the invention
The various changes and improvements that case is made should all be fallen into the protection scope that claims of the present invention determines.
Claims (8)
1. a kind of artificial intelligent voice robot system based on big data, it is characterised in that: including
Voice acquisition module (100) is used to acquire the first acoustic information that registration user issues;
First voice conversion module is used to convert the first text information for the first acoustic information;
Face recognition module (200) is used to acquire the face information of registration user;
Large database concept is equipped with and first text information and common corresponding second text information of face information;
Control module is used to export the second text envelope according to first text information and face information by large database concept
Breath;
Second voice conversion module (300) is used to convert second sound information for second text information.
2. a kind of artificial intelligent voice robot system based on big data according to claim 1, it is characterised in that: institute
It states in the first preset time after face recognition module (200) collects the face information of user, control module passes through big data
Library and the second text information is exported according to first text information and face information.
3. a kind of artificial intelligent voice robot system based on big data according to claim 2, it is characterised in that: extremely
Few eight voice acquisition modules (100) are arranged on pedestal (400), and at least eight voice acquisition modules (100) are along described
Pedestal (400) are arranged circumferentially, and at least eight voice acquisition module (100) acquires that registration user issues respectively
One acoustic information, and it is compared to each other the loudness of the first acoustic information of its acquisition, and by maximum first sound of collected loudness
Message breath voice acquisition module (100) far from the pedestal (400) center direction and be determined as the first registration
User direction;
The pedestal (400) is configured with the face recognition module (200) along its rotation, matches on the face recognition module (200)
It is equipped at least one gyroscope, the gyroscope is used to acquire the direction of the face recognition module (200), when gyroscope acquires
The face recognition module arrived direction it is described first registration user direction between angle less than the first predetermined angle when,
Then control module exports the second text information according to first text information and face information by large database concept.
4. a kind of artificial intelligent voice robot system based on big data according to claim 3, it is characterised in that: institute
It states control module and exports first according to the following formula according to number a, pedestal (400) width b of the voice acquisition module (100)
Predetermined angle C:
Wherein, the unit of the first predetermined angle C is degree;
The unit of the number a is a;
The unit of the width b is decimetre.
5. a kind of artificial intelligent voice robot system based on big data according to claim 4, it is characterised in that: institute
Face recognition module (200) is stated by adjusting portion (500) configuration on the pedestal (400), the adjustment section (500) includes base
Plate (501), shaft (502), sliding block (503), guide tube (504), output shaft (505), first motor (506), the first spring
(507), the first electromagnet (508), the first permanent magnet (509), the appearance of the face recognition module (200) and substrate (501)
Face is fixed, and the upper surface of the lower end of substrate (501) and the pedestal (400) overlaps, the upper end of the substrate (501) with described turn
The upper end hinge of axis (502) connects, and the lower end of the shaft (502) and the upper surface of the sliding block (503) are fixed, the sliding block
(503) surface along the guide tube (504) moves up and down, and the outer circumference surface of the sliding block (503) is interior with the guide tube (504)
Periphery shape matches, and the sliding block (503) and shaft (502) jointly, coaxially offer the first screw hole (511),
The top of the output shaft (505) is equipped with the screw thread matched with first screw hole (511), the first motor (506)
The upper end of output shaft (505) is threadedly coupled with the first screw hole (511) of the sliding block (503), shaft (502), first electricity
The lower end of machine (506) and the upper surface of the pedestal (400) are fixed, lower end and the pedestal (400) of the guide tube (504)
Upper surface is fixed, and the lower surface of the sliding block (503) and the upper end of the first spring (507) are fixed, first spring (507)
Lower end and the first permanent magnet (509) are fixed, and being arranged right below the first electromagnet (508) for first permanent magnet (509) is described
First electromagnet (508) and the inner surface of the guide tube (504) are fixed;
First electromagnet (508), first motor (506), face recognition module (200) are connect with the control module.
6. a kind of artificial intelligent voice robot system based on big data according to claim 5, it is characterised in that: two
Group first electromagnet (508), the first permanent magnet (509), the first spring (507) along the shaft (502) axisymmetrical
Setting.
7. a kind of artificial intelligent voice robot system based on big data according to claim 6, it is characterised in that: institute
It states and is equipped with shielding ring (510) between the first electromagnet (508) and first motor (506), the outer circumference surface of the shielding ring (510)
It is fixed with the inner peripheral surface of the guide tube (504), the inner peripheral surface of the shielding ring (510) is surrounded with output shaft (505).
8. using a kind of method of artificial intelligent voice robot system based on big data as claimed in claim 7, feature
It is to include the following steps:
S100, at least eight voice acquisition modules (100) collect the first acoustic information of registration user;
S200, compare at least eight voice acquisition modules (100) and receive the loudness of the first acoustic information and by collected loudness
The voice acquisition module (100) of maximum first acoustic information far from the pedestal (400) center direction and sentence
It is set to the first registration user direction;
The first electromagnet (508) of adjustment section (500) is powered off and starts first motor (506) by S300, control module, causes institute
The horizontally toward rotation of face recognition module (200) is stated to the first registration user direction;
The first electromagnet (508) of adjustment section (500) is powered and starts first motor (506) by S400, control module, causes institute
State face of the pitching of face recognition module (200) towards rotation to face registration user;
S500, the first text information is converted by the first acoustic information;
The face information of S600, acquisition registration user
S700, the second text information is exported according to first text information and face information by large database concept;
S800, second sound information is converted by second text information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910178016.4A CN109801632A (en) | 2019-03-08 | 2019-03-08 | A kind of artificial intelligent voice robot system and method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910178016.4A CN109801632A (en) | 2019-03-08 | 2019-03-08 | A kind of artificial intelligent voice robot system and method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109801632A true CN109801632A (en) | 2019-05-24 |
Family
ID=66561740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910178016.4A Pending CN109801632A (en) | 2019-03-08 | 2019-03-08 | A kind of artificial intelligent voice robot system and method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109801632A (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1383110A (en) * | 2001-04-09 | 2002-12-04 | 申光燮 | Language learning system |
CN103552617A (en) * | 2013-11-04 | 2014-02-05 | 沈阳工业大学 | Bouncing omnidirectional rolling spherical robot provided with stable platform |
US9086757B1 (en) * | 2011-08-19 | 2015-07-21 | Google Inc. | Methods and systems for providing functionality of an interface to control directional orientations of a device |
CN205033208U (en) * | 2015-10-15 | 2016-02-17 | 南京工业职业技术学院 | Float guide arm with decide sliding sleeve combined type echelon transmission gear hand |
CN106128453A (en) * | 2016-08-30 | 2016-11-16 | 深圳市容大数字技术有限公司 | The Intelligent Recognition voice auto-answer method of a kind of robot and robot |
CN106231168A (en) * | 2016-09-03 | 2016-12-14 | 湖北鑫美电子科技股份有限公司 | A kind of camera |
US20170263251A1 (en) * | 2014-01-20 | 2017-09-14 | Huawei Technologies Co.,Ltd. | Speech interaction method and apparatus |
CN206519942U (en) * | 2017-01-18 | 2017-09-26 | 王怀亮 | A kind of limb action electronic switching equipment |
CN107247750A (en) * | 2017-05-26 | 2017-10-13 | 深圳千尘计算机技术有限公司 | Artificial intelligence exchange method and system |
CN107297745A (en) * | 2017-06-28 | 2017-10-27 | 上海木爷机器人技术有限公司 | voice interactive method, voice interaction device and robot |
CN108209262A (en) * | 2018-03-22 | 2018-06-29 | 宁波史瑞迪信息科技有限公司 | A kind of correcting sitting posture robot |
CN108363706A (en) * | 2017-01-25 | 2018-08-03 | 北京搜狗科技发展有限公司 | The method and apparatus of human-computer dialogue interaction, the device interacted for human-computer dialogue |
CN207824896U (en) * | 2017-12-18 | 2018-09-07 | 西安丁子电子信息科技有限公司 | A kind of mechanical arm for rescuing robot for fire control |
CN208138810U (en) * | 2018-04-21 | 2018-11-23 | 长泰广鑫贸易有限公司 | A kind of safety monitoring fixing device |
CN109376282A (en) * | 2018-09-26 | 2019-02-22 | 北京子歌人工智能科技有限公司 | A kind of method and apparatus of human-machine intelligence's chat based on artificial intelligence |
-
2019
- 2019-03-08 CN CN201910178016.4A patent/CN109801632A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1383110A (en) * | 2001-04-09 | 2002-12-04 | 申光燮 | Language learning system |
US9086757B1 (en) * | 2011-08-19 | 2015-07-21 | Google Inc. | Methods and systems for providing functionality of an interface to control directional orientations of a device |
CN103552617A (en) * | 2013-11-04 | 2014-02-05 | 沈阳工业大学 | Bouncing omnidirectional rolling spherical robot provided with stable platform |
US20170263251A1 (en) * | 2014-01-20 | 2017-09-14 | Huawei Technologies Co.,Ltd. | Speech interaction method and apparatus |
CN205033208U (en) * | 2015-10-15 | 2016-02-17 | 南京工业职业技术学院 | Float guide arm with decide sliding sleeve combined type echelon transmission gear hand |
CN106128453A (en) * | 2016-08-30 | 2016-11-16 | 深圳市容大数字技术有限公司 | The Intelligent Recognition voice auto-answer method of a kind of robot and robot |
CN106231168A (en) * | 2016-09-03 | 2016-12-14 | 湖北鑫美电子科技股份有限公司 | A kind of camera |
CN206519942U (en) * | 2017-01-18 | 2017-09-26 | 王怀亮 | A kind of limb action electronic switching equipment |
CN108363706A (en) * | 2017-01-25 | 2018-08-03 | 北京搜狗科技发展有限公司 | The method and apparatus of human-computer dialogue interaction, the device interacted for human-computer dialogue |
CN107247750A (en) * | 2017-05-26 | 2017-10-13 | 深圳千尘计算机技术有限公司 | Artificial intelligence exchange method and system |
CN107297745A (en) * | 2017-06-28 | 2017-10-27 | 上海木爷机器人技术有限公司 | voice interactive method, voice interaction device and robot |
CN207824896U (en) * | 2017-12-18 | 2018-09-07 | 西安丁子电子信息科技有限公司 | A kind of mechanical arm for rescuing robot for fire control |
CN108209262A (en) * | 2018-03-22 | 2018-06-29 | 宁波史瑞迪信息科技有限公司 | A kind of correcting sitting posture robot |
CN208138810U (en) * | 2018-04-21 | 2018-11-23 | 长泰广鑫贸易有限公司 | A kind of safety monitoring fixing device |
CN109376282A (en) * | 2018-09-26 | 2019-02-22 | 北京子歌人工智能科技有限公司 | A kind of method and apparatus of human-machine intelligence's chat based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220157320A1 (en) | System and method for customizing smart home speech interfaces using personalized speech profiles | |
US10777206B2 (en) | Voiceprint update method, client, and electronic device | |
EP3020040B1 (en) | Method and apparatus for assigning keyword model to voice operated function | |
CN106663430B (en) | Keyword detection for speaker-independent keyword models using user-specified keywords | |
EP3047622B1 (en) | Method and apparatus for controlling access to applications | |
EP3608906B1 (en) | System for processing user voice utterance and method for operating same | |
EP2881939A1 (en) | System for speech keyword detection and associated method | |
US20180293236A1 (en) | Fast identification method and household intelligent robot | |
US10388280B2 (en) | Method and apparatus for managing multiple voice operation trigger phrases | |
US20150269938A1 (en) | Adjusting language models | |
US20090122198A1 (en) | Automatic identifying | |
CN104952138A (en) | Voice interactive access control system and achievement method thereof | |
EP4006899A1 (en) | Speech interaction method, server and speech interaction system | |
US11437042B2 (en) | Communication robot and method for operating the same | |
KR20190096308A (en) | electronic device | |
US20210398539A1 (en) | Systems and methods for processing audio and video | |
CN112567718A (en) | Electronic device for performing tasks including calls in response to user speech and method of operation | |
US20230005471A1 (en) | Responding to a user query based on captured images and audio | |
CN109801632A (en) | A kind of artificial intelligent voice robot system and method based on big data | |
WO2012121856A1 (en) | Sound recognition method and system | |
KR20200016774A (en) | System for processing user utterance and operating method thereof | |
CN111744170B (en) | Game control method based on wearable device and wearable device | |
US20230042310A1 (en) | Wearable apparatus and methods for approving transcription and/or summary | |
US12020709B2 (en) | Wearable systems and methods for processing audio and video based on information from multiple individuals | |
WO2020147011A1 (en) | Wireless control method, apparatus and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
RJ01 | Rejection of invention patent application after publication |