CN107578102A - One species neurode information processing method and smart machine - Google Patents
One species neurode information processing method and smart machine Download PDFInfo
- Publication number
- CN107578102A CN107578102A CN201710662763.6A CN201710662763A CN107578102A CN 107578102 A CN107578102 A CN 107578102A CN 201710662763 A CN201710662763 A CN 201710662763A CN 107578102 A CN107578102 A CN 107578102A
- Authority
- CN
- China
- Prior art keywords
- attribute
- perceptual system
- sensory perceptual
- identification
- identifying center
- 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
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The species neurode information processing method of disclosure one, including:Object identifying center receives the more attribute for the object that sensory perceptual system is identified;The memory block of object, and more attribute of conservation object are established in Object identifying center;In identification object, the one or more Attribute Recognition objects for the object that Object identifying center obtains according to sensory perceptual system.A kind of smart machine is also disclosed in the application.The application establishes sensory perceptual system in a manner of neuron, the information storage mode of human brain is applied to artificial intelligence field, allow computer silicon imitate human neuronal mode ponder a problem, input to external information can trigger neuron as people by an information, and recall other attributes of things, each sensory information is handled with the polymerization of multiple information systems, solve existing artificial intelligence be necessarily dependent upon big data calculate the drawbacks of, can overcome when the sensory perceptual system of smart machine can cooperate existing artificial intelligence can not autonomous learning scarce limit.
Description
Technical field
The application is related to field of artificial intelligence, more particularly to a species neurode information processing method and intelligence are set
It is standby.
Background technology
Realize that AI (Artificial Intelligence, artificial intelligence) mode mainly there are two kinds at present:1st, using volume
Journey technology, make system that the effect of intelligence be presented, without considering whether method therefor is identical with the method used in human or animal's body,
It has made achievement in some fields, and such as Text region, computer is played chess.In order to reach intelligent effect, it is necessary to artificial
Specified in more detail programmed logic, if it is simple in rule, or easily.If regular complicated, role's quantity and activity space increase,
Corresponding logic will very complicated (press Exponential growth), artificial programming is just very cumbersome, easily malfunctions, does not possess study energy
Power.2nd, based on the machine learning of big data come the intelligence realized, but this method is mainly used in identifying things at present.Recognize
Regulated procedure is performed using method one again after things.Such as present intelligent sound, using the machine learning of big data, allow machine
Device can intelligently recognize voice content, then perform certain content again and such as call.
Human brain includes to the storing mode of information (so that human brain is to the storage for this information of setting off fireworks as an example illustrate):
The eyes of people see the color of fireworks blast, and ear hears the sound of fireworks blast, but the Visual Neuron of eyes and ear
Auditory neuron both information storages can all be belonged among this cerebral cortex of " fireworks " in same.So work as people
Even next time has closed eyes, as long as but he has heard the explosive sound of fireworks, will be same big because of being stored in before
The information of cortex come associate fireworks blast color.And artificial intelligence storage information of the prior art can not be according to things
The incoming of information recall the other information of this things.
The content of the invention
The application provides a species neurode information processing method and smart machine.
According to the application's in a first aspect, the application provides a species neurode information processing method, including:
Object identifying center receives the more attribute for the object that sensory perceptual system is identified;
The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;
In identification object, the one kind or more for the object that the Object identifying center obtains according to the sensory perceptual system
Attribute identification object.
According to the second aspect of the application, the application provides a species neurode information processing method, including:
More attribute of the object of identification are sent to Object identifying center and preserved by sensory perceptual system;
In identification object, one or more attributes of the object of acquisition are sent to the object by the sensory perceptual system to be known
Other center is identified;
The sensory perceptual system receives the result of the Object identifying center identification.
According to the third aspect of the application, the application provides a species neurode information processing method, including:
More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;
The Object identifying center receives the more attribute for the object that sensory perceptual system is identified;
The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;
In identification object, one or more attributes of the object of acquisition are sent to the object by the sensory perceptual system to be known
Other center;
The Object identifying center is according to the Attribute Recognition object of reception.
According to the fourth aspect of the application, the application provides a kind of smart machine, including:
Sensory perceptual system, for more attribute of the object of identification to be sent into Object identifying center;
The Object identifying center, more attribute of the object identified for receiving sensory perceptual system, establishes the object
Memory block, and preserve more attribute of the object;
The sensory perceptual system, it is additionally operable to be sent to one or more attributes of the object of acquisition in identification object described
Object identifying center;
The Object identifying center, it is additionally operable to the Attribute Recognition object according to reception.
According to the 5th of the application the aspect, the application provides a kind of smart machine, including memory and processor, described to deposit
Reservoir instructs for storage program, and the processor, which is used to be instructed according to described program, performs following steps:
More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;
The Object identifying center receives the more attribute for the object that sensory perceptual system is identified;
The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;
In identification object, one or more attributes of the object of acquisition are sent to the object by the sensory perceptual system to be known
Other center;
The Object identifying center is according to the Attribute Recognition object of reception.
As a result of above technical scheme, it is the beneficial effect that the application possesses:
In the embodiment of the application, because the memory block of the object is established at Object identifying center, and preserve
More attribute of the object, in identification object, it is described right that the Object identifying center obtains according to the sensory perceptual system
One or more Attribute Recognition objects of elephant.The application the application establishes sensory perceptual system in a manner of neuron, human brain
Information storage mode is applied to artificial intelligence field, allow computer silicon imitate human neuronal mode ponder a problem,
Input to external information can trigger neuron as people by an information, and recall other attributes of things, with more
Individual information system polymerization handles each sensory information, solves existing artificial intelligence and is necessarily dependent upon the drawbacks of big data calculates,
Can overcome when the sensory perceptual system of smart machine can cooperate existing artificial intelligence can not autonomous learning scarce limit.
Brief description of the drawings
Fig. 1 is the flow chart of the present processes in one embodiment;
Fig. 2 is the flow chart of the present processes in another embodiment;
Fig. 3 is flow chart of the present processes in another embodiment;
Fig. 4 is the schematic flow sheet that the present processes store things in one embodiment;
Fig. 5 is the schematic flow sheet that the present processes identify things in one embodiment;
Fig. 6 is the identification process schematic diagram of the AI systems of the application;
Fig. 7 is the structural representation of the smart machine of the application in one embodiment.
Embodiment
The application is described in further detail below by embodiment combination accompanying drawing.
The application uses the information transmission of nerve synapse and the principle of storage from the neurology angle of the mankind.Allow machine with
Human nervous system stores up stored mode to store and ponder a problem, will by way of the various receive informations of artificial intelligence
It is stored among " neurode " (memory cell) of computer information unification, while connects and integrate all touch
Information, and when artificial intelligence runs into a similar plot inside similar scene afterwards, can be with call out simultaneously before
The scene occurred.
Embodiment one:
As shown in figure 1, the class neurode information processing method of the application, a kind of its embodiment, can include following
Step:
Step 102:Object identifying center receives the more attribute for the object that sensory perceptual system is identified.
Step 104:The memory block of object, and more attribute of conservation object are established in Object identifying center.Memory block can be with
There is a memory cell, it is possibility to have multiple memory cell.More attribute of object can be respectively stored in different storage lists
In member, it can also be stored in a memory cell.
Step 106:In identification object, the one or more category for the object that Object identifying center obtains according to sensory perceptual system
Property identification object.
In one embodiment, step 106 can also include:
Remaining attribute of the object of preservation is sent to sensory perceptual system by Object identifying center.
As shown in figure 4, in the application, such as storage apple this things, the visual processes of artificial intelligence can be passed through
System obtains the image parameter of apple.
Each attribute of one apple is gone to obtain by computer by different modes, and then these different attributes are stored
In same object, because each attribute of object belongs to same object, so associating other when we want AI
When the information of attribute, just only with telling its attribute can to associate other attributes.
, then can be with call function when artificial intelligence obtains other attributes of apple.Such as after knowing the image parameters of apple
Obtain the use information of apple.
Above-mentioned flow is to embody the thought to artificial intelligence information storage, is not specific implementation.Similarly can be
Some attributes being associated by word can also be stored in same graph structure.And each node in chart as
One neurode of biological neuron is the same, can pass through the nearly each related node to dissipate of a neurode.
The present processes in one embodiment, identify the flow of things as shown in figure 5, when any one perception system
System is when recognizing object, informs Object identifying center, Object identifying center the news for recognizing this object it is all this
The sensory perceptual system that individual object possesses, so as to reach the target of collaborative work, i.e., built between sensory perceptual system by Object identifying center
Vertical communication contact.
As a people, " this is the apple that I buys " is said to AI systems, while lifts " iPhone " in hand, AI systems
Identification process is as shown in Figure 6.
Embodiment two:
As shown in Fig. 2 the class neurode information processing method of the application, a kind of its embodiment, can include following
Step:
Step 202:More attribute of the object of identification are sent to Object identifying center and preserved by sensory perceptual system;
Step 204:In identification object, one or more attributes of the object of acquisition are sent to object by sensory perceptual system to be known
Other center is identified;
Step 206:Sensory perceptual system receives the result of Object identifying center identification.
In one embodiment, step 206 can also include:
Sensory perceptual system receives remaining attribute for the object that Object identifying center preserves, and assigns remaining attribute to object.
Embodiment three:
As shown in figure 3, the class neurode information processing method of the application, a kind of its embodiment, can include following
Step:
Step 302:More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;
Step 304:Object identifying center receives the more attribute for the object that sensory perceptual system is identified;
Step 306:The memory block of object, and more attribute of conservation object are established in Object identifying center;
Step 308:In identification object, one or more attributes of the object of acquisition are sent to object by sensory perceptual system to be known
Other center;
Step 310:Object identifying center is according to the Attribute Recognition object of reception.
In one embodiment, the present processes can also comprise the following steps:
Step 312:Remaining attribute of the object of preservation is sent to sensory perceptual system by Object identifying center;
Step 314:Sensory perceptual system receives remaining attribute for the object that Object identifying center preserves, and remaining attribute is assigned
Object.
Example IV:
As shown in fig. 7, the smart machine of the application, a kind of its embodiment, including sensory perceptual system and Object identifying center.
Sensory perceptual system can include one or more.
Sensory perceptual system, for more attribute of the object of identification to be sent into Object identifying center.Object identifying center, use
In the more attribute of object for receiving sensory perceptual system and being identified, the memory block of object, and more attribute of conservation object are established;Sense
Know system, be additionally operable to that one or more attributes of the object of acquisition are sent into Object identifying center in identification object;Object
Identification center, it is additionally operable to the Attribute Recognition object according to reception.
In one embodiment, in the smart machine of the application, Object identifying center, it is additionally operable to the object of preservation
Remaining attribute is sent to sensory perceptual system;Sensory perceptual system, be additionally operable to receive object remaining attribute, and by remaining attribute assign pair
As.
Embodiment five:
The smart machine of the application, a kind of its embodiment can include memory and processor, and memory is used to store
Programmed instruction, processor are used to perform following steps according to programmed instruction:
More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;
Object identifying center receives the more attribute for the object that sensory perceptual system is identified;
The memory block of object, and more attribute of conservation object are established in Object identifying center;
In identification object, one or more attributes of the object of acquisition are sent to Object identifying center by sensory perceptual system;
Object identifying center is according to the Attribute Recognition object of reception.
Above content is to combine the further description that specific embodiment is made to the application, it is impossible to assert this Shen
Specific implementation please is confined to these explanations.For the application person of an ordinary skill in the technical field, do not taking off
On the premise of conceiving from the application, some simple deduction or replace can also be made.
Claims (9)
- A 1. species neurode information processing method, it is characterised in that including:Object identifying center receives the more attribute for the object that sensory perceptual system is identified;The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;In identification object, the one or more category for the object that the Object identifying center obtains according to the sensory perceptual system Property identification object.
- 2. class neurode information processing method as claimed in claim 1, it is characterised in that step is in identification object, institute The one or more Attribute Recognition objects for the object that Object identifying center obtains according to the sensory perceptual system are stated, in addition to:Remaining attribute of the object of preservation is sent to the sensory perceptual system by the Object identifying center.
- A 3. species neurode information processing method, it is characterised in that including:More attribute of the object of identification are sent to Object identifying center and preserved by sensory perceptual system;In identification object, one or more attributes of the object of acquisition are sent in the Object identifying by the sensory perceptual system The heart is identified;The sensory perceptual system receives the result of the Object identifying center identification.
- 4. class neurode information processing method as claimed in claim 3, it is characterised in that sensory perceptual system described in step receives The result of the Object identifying center identification, in addition to:The sensory perceptual system receives remaining attribute for the object that the Object identifying center preserves, and will remaining described attribute Assign the object.
- A 5. species neurode information processing method, it is characterised in that including:More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;The Object identifying center receives the more attribute for the object that sensory perceptual system is identified;The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;In identification object, one or more attributes of the object of acquisition are sent in the Object identifying by the sensory perceptual system The heart;The Object identifying center is according to the Attribute Recognition object of reception.
- 6. class neurode information processing method as claimed in claim 5, it is characterised in that also include:Remaining attribute of the object of preservation is sent to the sensory perceptual system by the Object identifying center;The sensory perceptual system receives remaining attribute for the object that the Object identifying center preserves, and will remaining described attribute Assign the object.
- A kind of 7. smart machine, it is characterised in that including:Sensory perceptual system, for more attribute of the object of identification to be sent into Object identifying center;The Object identifying center, more attribute of the object identified for receiving sensory perceptual system, establishes depositing for the object Storage area, and preserve more attribute of the object;The sensory perceptual system, it is additionally operable to that one or more attributes of the object of acquisition are sent into the object in identification object Identification center;The Object identifying center, it is additionally operable to the Attribute Recognition object according to reception.
- 8. smart machine as claimed in claim 7, it is characterised in that:The Object identifying center, it is additionally operable to remaining attribute of the object of preservation being sent to the sensory perceptual system;The sensory perceptual system, it is additionally operable to receive remaining described attribute of the object, and remaining attribute imparting is described right As.
- A kind of 9. smart machine, it is characterised in that including memory and processor, the memory instructs for storage program, The processor, which is used to be instructed according to described program, performs following steps:More attribute of the object of identification are sent to Object identifying center by sensory perceptual system;The Object identifying center receives the more attribute for the object that sensory perceptual system is identified;The memory block of the object is established at the Object identifying center, and preserves more attribute of the object;In identification object, one or more attributes of the object of acquisition are sent in the Object identifying by the sensory perceptual system The heart;The Object identifying center is according to the Attribute Recognition object of reception.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710602381 | 2017-07-21 | ||
CN2017106023814 | 2017-07-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107578102A true CN107578102A (en) | 2018-01-12 |
Family
ID=61035701
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710662763.6A Pending CN107578102A (en) | 2017-07-21 | 2017-08-04 | One species neurode information processing method and smart machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107578102A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112434800A (en) * | 2020-11-20 | 2021-03-02 | 清华大学 | Control device and brain-like computing system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103262103A (en) * | 2010-07-13 | 2013-08-21 | M8公司 | Processor for situational analysis |
CN104809426A (en) * | 2014-01-27 | 2015-07-29 | 日本电气株式会社 | Convolutional neural network training method and target identification method and device |
US20150268989A1 (en) * | 2014-03-24 | 2015-09-24 | Sandisk Enterprise Ip Llc | Methods and Systems for Extending the Object Store of an Application Virtual Machine |
CN106575380A (en) * | 2014-07-23 | 2017-04-19 | 赫尔实验室有限公司 | A general formal concept analysis (fca) framework for classification |
-
2017
- 2017-08-04 CN CN201710662763.6A patent/CN107578102A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103262103A (en) * | 2010-07-13 | 2013-08-21 | M8公司 | Processor for situational analysis |
CN104809426A (en) * | 2014-01-27 | 2015-07-29 | 日本电气株式会社 | Convolutional neural network training method and target identification method and device |
US20150268989A1 (en) * | 2014-03-24 | 2015-09-24 | Sandisk Enterprise Ip Llc | Methods and Systems for Extending the Object Store of an Application Virtual Machine |
CN106575380A (en) * | 2014-07-23 | 2017-04-19 | 赫尔实验室有限公司 | A general formal concept analysis (fca) framework for classification |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112434800A (en) * | 2020-11-20 | 2021-03-02 | 清华大学 | Control device and brain-like computing system |
CN112434800B (en) * | 2020-11-20 | 2024-02-20 | 清华大学 | Control device and brain-like computing system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109472206B (en) | Risk assessment method, device, equipment and medium based on micro-expressions | |
CN106982359B (en) | A kind of binocular video monitoring method, system and computer readable storage medium | |
KR102444165B1 (en) | Apparatus and method for providing a meeting adaptively | |
CN106295275B (en) | The method, apparatus and terminal of management are freezed in a kind of application | |
Berko et al. | The path to paradise: The inner world of suicide bombers and their dispatchers. | |
Bowers et al. | Is that what Bayesians believe? reply to Griffiths, Chater, Norris, and Pouget (2012). | |
DE112017001573T5 (en) | Autonomous robot performing a welcome action | |
Mead | The Self, the I, and the Me | |
CN108050674A (en) | Control method and device, the terminal of air-conditioning equipment | |
CN107598934A (en) | A kind of intelligent robot foreground application system and method | |
CN108388343B (en) | Teaching management system for VR immersion based on concentration degree electroencephalogram feature feedback | |
CN112651334B (en) | Robot video interaction method and system | |
CN109278051A (en) | Exchange method and system based on intelligent robot | |
CN108681390A (en) | Information interacting method and device, storage medium and electronic device | |
EP3435293A1 (en) | Storage control system, system, and program | |
CN107578102A (en) | One species neurode information processing method and smart machine | |
Gordon | Talking (for, with) dogs: Science fiction breaks a species barrier | |
EP4064289A1 (en) | Method and device for determining psychological counseling training scheme | |
CN109101928A (en) | WatchChild method and robot | |
Johnson | Keeping the pragmatism in neuropragmatism | |
DE112018007850B4 (en) | VOICE RECOGNITION SYSTEM AND OPERATING METHOD OF A VOICE RECOGNITION SYSTEM | |
CN106682386A (en) | Space-time structured emotional soothing tree and its generation method and emotional soothing interaction system | |
Botzheim et al. | Spiking neural network based emotional model for robot partner | |
EP4102398A1 (en) | Context-based social agent interaction | |
Heath et al. | Lingodroids: Cross-situational learning for episodic elements |
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: 20180112 |
|
RJ01 | Rejection of invention patent application after publication |