CN110472400A - A kind of trusted computer system and implementation method based on recognition of face - Google Patents
A kind of trusted computer system and implementation method based on recognition of face Download PDFInfo
- Publication number
- CN110472400A CN110472400A CN201910776696.XA CN201910776696A CN110472400A CN 110472400 A CN110472400 A CN 110472400A CN 201910776696 A CN201910776696 A CN 201910776696A CN 110472400 A CN110472400 A CN 110472400A
- Authority
- CN
- China
- Prior art keywords
- face
- layers
- convolutional neural
- neural networks
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/71—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information
- G06F21/72—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information in cryptographic circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/81—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer by operating on the power supply, e.g. enabling or disabling power-on, sleep or resume operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of trusted computer system and implementation method based on recognition of face, belong to information security field, the technical problem to be solved in the present invention is that the intelligent protection of trusted computer system how is realized based on recognition of face, reduce Ukey verification process, reduce management cost, the technical solution of use are as follows: the system includes general-purpose computing system, face recognition device and credible chip, general-purpose computing system identifies user by integrated face recognition device, face recognition device sends control signal control credible chip and powers and issue protection key components, trusted root, which is decrypted, after credible chip synthesis component and measures BIOS opens normal boot-strap process.The trusted computer implementation method based on recognition of face that the invention discloses a kind of.
Description
Technical field
The present invention relates to information security field, specifically a kind of trusted computer system and reality based on recognition of face
Existing method.
Background technique
Trust computing, credible use calculating (Trusted Computing, TC) are one by Trusted Computing Group (Trusted
It is Computing Group, preceding to be known as TCPA) it pushes and the technology of exploitation.This term derives from trusted system (Trusted
Systems), and there is its specific meanings.Technically, " believable " (Trusted) do not necessarily imply that user and
Speech is " trustworthy " (Trustworthy).Specifically, it means sufficiently believe that its behavior can be abided by more fully
Design is followed, and the probability for executing the behavior that designer and software programming person are forbidden is very low.
The English name of recognition of face is that Human Face Recognition. face recognition products utilize AVS03A image
Processor；Face light and shade can be detected, the compensation of adjust automatically dynamic exposure, face tracking detecting, adjust automatically image zoom.
The practical recognition of face of broad sense includes a series of the relevant technologies for constructing face identification system, including man face image acquiring, face
Positioning, recognition of face pretreatment, identity validation and identity finder etc.；And the recognition of face of narrow sense refers in particular to carry out body by face
The technology or system of part confirmation or identity finder.
The algorithm that convolutional neural networks algorithm is most widely used in artificial intelligence field, be widely used in security protection, from
The fields such as dynamic driving, computer vision, recognition of face.CNN is substantially a multi-layer perception (MLP), and successful reason key exists
The mode that weight is locally connected and shared used by it, the quantity of the weight on the one hand reduced make network be easy to excellent
Change, on the other hand reduces the risk of over-fitting.CNN is one of neural network, its weight is shared network structure and is allowed to
It is more closely similar to biological neural network, reduces the complexity of network model, reduces the quantity of weight.The advantage is in the defeated of network
Enter becoming apparent of showing when being multidimensional image, image is allow to avoid tional identification algorithm directly as the input of network
The feature extraction and data reconstruction processes of middle complexity.
In conclusion how to realize the intelligent protection of trusted computer system based on recognition of face, reduces Ukey and recognize
Card process, reducing management cost is technical problem urgently to be solved in currently available technology.
Summary of the invention
Technical assignment of the invention is to provide a kind of trusted computer system and implementation method based on recognition of face, to solve
The intelligent protection that trusted computer system certainly how is realized based on recognition of face, is reduced Ukey verification process, reduces pipe
The problem of managing cost.
Technical assignment of the invention realizes in the following manner, a kind of trusted computer system based on recognition of face,
The system includes general-purpose computing system, face recognition device and credible chip, and general-purpose computing system is known by integrated face
Other equipment identifies user, and face recognition device sends control signal control credible chip and powers and issue protection key components, can
It decrypts trusted root after letter chip synthesis component and measures BIOS and open normal boot-strap process.
Preferably, the face recognition device is individually powered by Standby power supply, power independently of trusted computer
Except system, it can not be modified by operating system and credible chip COS, guarantee user information safety.
Preferably, the algorithm that the face recognition device uses is 12 layers of convolutional neural networks model.
More preferably, 12 layers of convolutional neural networks model specifically includes:
Convolutional neural networks model building module, for the convolutional layer substitution pond layer for adjusting convolution kernel step-length to be established 12
Layer convolutional neural networks model, simplifies face recognition device complexity；
Convolutional neural networks model training module, for carrying out model training to 12 layers of convolutional neural networks model；
Network quantization modules, for carrying out network quantization to 12 layers of convolutional neural networks model；
Overweight training module, for carrying out retraining to 12 layers of convolutional neural networks model and exporting final mask；
Face recognition device insmods, for being disassembled final mask by compiler as multiplication, step-length, being added up, defeated
The operational order enter, exported is loaded into face recognition device.
More preferably, described to specifically include to 12 layers of convolutional neural networks models progress network quantization: weight is output and input
8bit shaping quantization is carried out by 32bit floating-point, increment part carries out 32bit floating-point to 9bit shaping quantization, and multiplication part carries out
32bit floating-point guarantees that model parameter calculation amount simplifies and keeps precision to 12bit shaping quantization.
More preferably, described that 12 layers of convolutional neural networks model were carried out retraining and exported final mask to specifically include:
Binaryzation carried out to 4 layer networks in 12 layer networks, further compression network parameter, and after carrying out retraining again, output
Final mask.
A kind of trusted computer implementation method based on recognition of face, the method steps are as follows:
S1,12 layers of convolutional neural networks model are established and 12 layers of convolutional neural networks model are loaded into face recognition device；
S2, face recognition device identify face；
After S3, face recognition device identification face pass through, credible chip power supply circuit is opened, by interconnecting with credible chip
Interface negotiation communication key；
S4, credible chip will be sent to after the encryption of system protection key components；
The system protection key components and chip that receive are deposited component certainly and synthesize system by displacement by S5, credible chip
Protect key；
S6, it decrypts trusted root and measures trusted computer BIOS, into normal trusted computer Booting sequence.
Preferably, establishing 12 layers of convolutional neural networks model in the step S1 and by 12 layers of convolutional neural networks model
Being loaded into face recognition device, specific step is as follows:
S101,12 layers of convolutional neural networks model are established, pond layer, essence is substituted using the convolutional layer of adjustment convolution kernel step-length
Simple face recognition device complexity；
S102, model training is carried out to 12 layers of convolutional neural networks model；
S103, network quantization is carried out to 12 layers of convolutional neural networks model；
S104, retraining was carried out to 12 layers of convolutional neural networks model and exports final mask；
S105, final mask is disassembled by compiler as multiplication, step-length, cumulative, input, output operational order, load
Enter face recognition device.
More preferably, network quantization is carried out to 12 layers of convolutional neural networks model in the step S103 to specifically include: weight,
It outputs and inputs and 8bit shaping quantization is carried out by 32bit floating-point, increment part carries out 32bit floating-point to 9bit shaping quantization, multiplies
Method part carries out 32bit floating-point to 12bit shaping quantization, guarantees that model parameter calculation amount simplifies and keeps precision.
More preferably, retraining was carried out to 12 layers of convolutional neural networks model in the step S104 and exported final mask
It specifically includes and binaryzation, further compression network parameter is carried out to 4 layer networks in 12 layer networks, and carried out retraining again
Afterwards, final mask is exported.
Of the invention trusted computer system and implementation method based on recognition of face has the advantage that
(1), the present invention realizes the intelligent protection of trusted computer system, and subtract by increasing recognition of face process
Lack Ukey verification process, reduces management cost；
(2), face recognition device is that Standby power supply is individually powered, except trusted computer power supply system,
It can not be modified by operating system and credible chip COS, guarantee user information safety；
(3), the algorithm of face recognition device is using 12 layers of convolutional neural networks of customization, using adjustment convolution kernel step-length
Convolutional layer substitutes pond layer, so that simplifying recognition of face hardware complexity；
(4), the present invention to convolutional neural networks model carry out network quantization, wherein weight, output and input by 32bit
Floating-point carries out 8bit shaping quantization, and increment part carries out 32bit floating-point to 9bit shaping quantization, and it is floating that multiplication part carries out 32bit
Point guarantees that model parameter calculation amount simplifies and keeps precision to 12bit shaping quantization.
Detailed description of the invention
The following further describes the present invention with reference to the drawings.
Attached drawing 1 is the trusted computer system structural block diagram based on recognition of face；
Attached drawing 2 is the flow diagram of the trusted computer based on recognition of face.
Specific embodiment
Referring to Figure of description and specific embodiment to a kind of trusted computer system based on recognition of face of the invention
And implementation method is described in detail below.
Embodiment 1:
As shown in Fig. 1, the trusted computer system of the invention based on recognition of face, the system include general purpose computer
System, face recognition device and credible chip, general-purpose computing system identify user by integrated face recognition device, and face is known
Other equipment sends control signal control credible chip and powers and issue protection key components, and decryption can after credible chip synthesizes component
Letter root simultaneously measures BIOS unlatching normal boot-strap process.Wherein, face recognition device is individually powered by Standby power supply, independent
Except trusted computer power supply system, it can not be modified by operating system and credible chip COS, guarantee user information safety.
The algorithm that face recognition device uses is 12 layers of convolutional neural networks model.12 layers of convolutional neural networks model are specific
Include:
Convolutional neural networks model building module, for the convolutional layer substitution pond layer for adjusting convolution kernel step-length to be established 12
Layer convolutional neural networks model, simplifies face recognition device complexity；
Convolutional neural networks model training module, for carrying out model training to 12 layers of convolutional neural networks model；
Network quantization modules, for carrying out network quantizations to 12 layers of convolutional neural networks model, wherein weight, input and defeated
8bit shaping quantization is carried out by 32bit floating-point out, increment part carries out 32bit floating-point to 9bit shaping quantization, multiplication part into
Row 32bit floating-point guarantees that model parameter calculation amount simplifies and keeps precision to 12bit shaping quantization；
Overweight training module, it is right for carrying out retraining to 12 layers of convolutional neural networks model and exporting final mask
4 layer networks in 12 layer networks carry out binaryzation, further compression network parameter, and after carrying out retraining again, output is most
Final cast；
Face recognition device insmods, for being disassembled final mask by compiler as multiplication, step-length, being added up, defeated
The operational order enter, exported is loaded into face recognition device.
Embodiment 2:
As shown in Fig. 2, the trusted computer implementation method of the invention based on recognition of face, the method steps are as follows:
S1,12 layers of convolutional neural networks model are established and 12 layers of convolutional neural networks model are loaded into face recognition device；
S2, face recognition device identify face；
After S3, face recognition device identification face pass through, credible chip power supply circuit is opened, by interconnecting with credible chip
Interface negotiation communication key；
S4, credible chip will be sent to after the encryption of system protection key components；
The system protection key components and chip that receive are deposited component certainly and synthesize system by displacement by S5, credible chip
Protect key；
S6, it decrypts trusted root and measures trusted computer BIOS, into normal trusted computer Booting sequence.
12 layers of convolutional neural networks model are established in step S1 and 12 layers of convolutional neural networks model are loaded into recognition of face
Specific step is as follows for equipment:
S101,12 layers of convolutional neural networks model are established, pond layer, essence is substituted using the convolutional layer of adjustment convolution kernel step-length
Simple face recognition device complexity；
S102, model training is carried out to 12 layers of convolutional neural networks model；
S103, network quantizations are carried out to 12 layers of convolutional neural networks model, wherein weight, output and input and floated by 32bit
Point carries out 8bit shaping quantization, and increment part carries out 32bit floating-point to 9bit shaping quantization, and multiplication part carries out 32bit floating-point
To 12bit shaping quantization, guarantee that model parameter calculation amount simplifies and keeps precision；
S104, retraining was carried out to 12 layers of convolutional neural networks model and exports final mask, to 4 in 12 layer networks
Layer network carries out binaryzation, further compression network parameter, and after carrying out retraining again, exports final mask；
S105, final mask is disassembled by compiler as multiplication, step-length, cumulative, input, output operational order, load
Enter face recognition device.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of trusted computer system based on recognition of face, which is characterized in that the system includes general-purpose computing system, people
Face identifies that equipment and credible chip, general-purpose computing system identify user, face recognition device by integrated face recognition device
It sends control signal control credible chip to power and issue protection key components, credible chip decrypts trusted root simultaneously after synthesizing component
It measures BIOS and opens normal boot-strap process.
2. the trusted computer system according to claim 1 based on recognition of face, which is characterized in that the recognition of face
Equipment is individually powered by Standby power supply.
3. the trusted computer system according to claim 1 or 2 based on recognition of face, which is characterized in that the face
The algorithm for identifying that equipment uses is 12 layers of convolutional neural networks model.
4. the trusted computer system according to claim 3 based on recognition of face, which is characterized in that 12 layers of convolution
Neural network model specifically includes:
Convolutional neural networks model building module, for the convolutional layer substitution pond layer for adjusting convolution kernel step-length to be established 12 layers of volume
Product neural network model, simplifies face recognition device complexity；
Convolutional neural networks model training module, for carrying out model training to 12 layers of convolutional neural networks model；
Network quantization modules, for carrying out network quantization to 12 layers of convolutional neural networks model；
Overweight training module, for carrying out retraining to 12 layers of convolutional neural networks model and exporting final mask；
Face recognition device insmods, for by final mask by compiler disassemble for multiplication, step-length, add up, input, it is defeated
Operational order out is loaded into face recognition device.
5. the trusted computer system according to claim 4 based on recognition of face, which is characterized in that described to be rolled up to 12 layers
Product neural network model carries out network quantization and specifically includes: weight is output and input by 32bit floating-point progress 8bit shaping amount
Change, increment part carries out 32bit floating-point to 9bit shaping quantization, and multiplication part carries out 32bit floating-point to 12bit shaping quantization.
6. the trusted computer system according to claim 5 based on recognition of face, which is characterized in that described to be rolled up to 12 layers
Product neural network model carried out retraining and exported final mask specifically including: carrying out two to 4 layer networks in 12 layer networks
Value, further compression network parameter, and after carrying out retraining again, export final mask.
7. a kind of trusted computer implementation method based on recognition of face, which is characterized in that the method steps are as follows:
S1,12 layers of convolutional neural networks model are established and 12 layers of convolutional neural networks model are loaded into face recognition device；
S2, face recognition device identify face；
S3, face recognition device identification face pass through after, open credible chip power supply circuit, by with credible chip interconnecting interface
Negotiation communication key；
S4, credible chip will be sent to after the encryption of system protection key components；
The system protection key components and chip that receive are deposited component certainly and synthesize system protection by displacement by S5, credible chip
Key；
S6, it decrypts trusted root and measures trusted computer BIOS, into normal trusted computer Booting sequence.
8. the trusted computer implementation method according to claim 7 based on recognition of face, which is characterized in that the step
12 layers of convolutional neural networks model are established in S1 and 12 layers of convolutional neural networks model are loaded into the specific step of face recognition device
It is rapid as follows:
S101,12 layers of convolutional neural networks model are established, pond layer is substituted using the convolutional layer of adjustment convolution kernel step-length, simplifies people
Face identifies that the device is complicated and spends；
S102, model training is carried out to 12 layers of convolutional neural networks model；
S103, network quantization is carried out to 12 layers of convolutional neural networks model；
S104, retraining was carried out to 12 layers of convolutional neural networks model and exports final mask；
S105, final mask is disassembled by compiler as multiplication, step-length, cumulative, input, output operational order, loading people
Face identifies equipment.
9. the trusted computer implementation method according to claim 8 based on recognition of face, which is characterized in that the step
Networks quantization is carried out to 12 layers of convolutional neural networks model in S103 to specifically include: weight, output and input by 32bit floating-point into
Row 8bit shaping quantization, increment part carry out 32bit floating-point to 9bit shaping quantization, and multiplication part carries out 32bit floating-point extremely
12bit shaping quantization.
10. the trusted computer implementation method based on recognition of face according to claim 8 or claim 9, which is characterized in that described
Retraining was carried out to 12 layers of convolutional neural networks model in step S104 and exports final mask specifically including to 12 layer networks
In 4 layer networks carry out binaryzation, further compression network parameter, and after carrying out retraining again exports final mask.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776696.XA CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776696.XA CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110472400A true CN110472400A (en) | 2019-11-19 |
| CN110472400B CN110472400B (en) | 2021-06-01 |
Family
ID=68512736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910776696.XA Active CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472400B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6763400B2 (en) * | 2000-09-12 | 2004-07-13 | Kabushiki Kaisha Toshiba | Computer having control means for determining an operation state of an audio sources selecting switch when the computer is powered on/off, in a standby and a pause states |
| CN205377891U (en) * | 2016-01-05 | 2016-07-06 | 北京神州新桥科技有限公司 | Identity authentication device and system |
| CN107247991A (en) * | 2017-06-15 | 2017-10-13 | 北京图森未来科技有限公司 | A kind of method and device for building neutral net |
| CN107341463A (en) * | 2017-06-28 | 2017-11-10 | 北京飞搜科技有限公司 | A kind of face characteristic recognition methods of combination image quality analysis and metric learning |
| CN108345856A (en) * | 2018-02-09 | 2018-07-31 | 电子科技大学 | The SAR automatic target recognition methods integrated based on isomery convolutional neural networks |
| CN108572861A (en) * | 2018-04-26 | 2018-09-25 | 浪潮(北京)电子信息产业有限公司 | A kind of guard method, system, equipment and the storage medium of virtual credible root |
| CN109992973A (en) * | 2019-04-10 | 2019-07-09 | 北京可信华泰信息技术有限公司 | A kind of starting measure and device using OPROM mechanism |
| CN110008841A (en) * | 2019-03-08 | 2019-07-12 | 中国华戎科技集团有限公司 | A kind of Expression Recognition model building method and system |
-
2019
- 2019-08-22 CN CN201910776696.XA patent/CN110472400B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6763400B2 (en) * | 2000-09-12 | 2004-07-13 | Kabushiki Kaisha Toshiba | Computer having control means for determining an operation state of an audio sources selecting switch when the computer is powered on/off, in a standby and a pause states |
| CN205377891U (en) * | 2016-01-05 | 2016-07-06 | 北京神州新桥科技有限公司 | Identity authentication device and system |
| CN107247991A (en) * | 2017-06-15 | 2017-10-13 | 北京图森未来科技有限公司 | A kind of method and device for building neutral net |
| CN107341463A (en) * | 2017-06-28 | 2017-11-10 | 北京飞搜科技有限公司 | A kind of face characteristic recognition methods of combination image quality analysis and metric learning |
| CN108345856A (en) * | 2018-02-09 | 2018-07-31 | 电子科技大学 | The SAR automatic target recognition methods integrated based on isomery convolutional neural networks |
| CN108572861A (en) * | 2018-04-26 | 2018-09-25 | 浪潮(北京)电子信息产业有限公司 | A kind of guard method, system, equipment and the storage medium of virtual credible root |
| CN110008841A (en) * | 2019-03-08 | 2019-07-12 | 中国华戎科技集团有限公司 | A kind of Expression Recognition model building method and system |
| CN109992973A (en) * | 2019-04-10 | 2019-07-09 | 北京可信华泰信息技术有限公司 | A kind of starting measure and device using OPROM mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472400B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104584024B (en) | The various equipment of the unlocking mechanism based on different stage is allowed to access | |
| IL268145B2 (en) | Universal bchain e3a connections (ubec) | |
| CN107408251A (en) | The electronic equipment and its operating method of electronic payment function are provided | |
| Cai et al. | A many-objective optimization based federal deep generation model for enhancing data processing capability in IoT | |
| CN110378470B (en) | Optimization method and device for neural network model and computer storage medium | |
| US11163983B2 (en) | Methods and apparatus for aligning sampling points of facial profiles of users | |
| Ray et al. | Wearables, implants, and internet of things: the technology needs in the evolving landscape | |
| CN109710680A (en) | A kind of block chain data processing engine and operating method | |
| CN113705929B (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
| WO2021204086A1 (en) | Identity authentication method, and method and device for training identity authentication model | |
| AU2019322625A1 (en) | Methods and apparatus for facial recognition | |
| CN109473177A (en) | The method and Related product of medical development trend are determined based on prediction model | |
| DE102023111576A1 (en) | CONTROL THE PRIMARY COOLING CIRCUIT TO MANAGE Fluctuating DEMAND ON SECONDARY COOLING CIRCUIT FOR DATA CENTER COOLING SYSTEMS | |
| Kim et al. | Advanced internet of things and big data Technology for Smart Human-Care Services | |
| CN113973018B (en) | Endogenous safety-based Internet of things terminal data processing method and system | |
| CN113674856B (en) | Medical data processing method, device, equipment and medium based on artificial intelligence | |
| US20200193145A1 (en) | Methods and apparatus for facial recognition | |
| CN110472400A (en) | A kind of trusted computer system and implementation method based on recognition of face | |
| CN112116979B (en) | Electronic prescription circulation security working method based on blockchain account distribution protocol | |
| CN111738182B (en) | Identity verification method, device, terminal and storage medium based on image recognition | |
| CN116681045A (en) | Report generation method, report generation device, computer equipment and storage medium | |
| CN111275059A (en) | Image processing method and device and computer readable storage medium | |
| Morozkin et al. | Neural network based eye tracking | |
| Tang et al. | Edge Intelligence with Distributed Processing of DNNs: A Survey. | |
| Lin et al. | Study of Iterative Learning Control Algorithm in Tourism Management IoT Platform Application |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210512 Address after: No. 1036, Shandong high tech Zone wave road, Ji'nan, Shandong Applicant after: INSPUR GROUP Co.,Ltd. Address before: North 6th floor, S05 building, Langchao Science Park, 1036 Langchao Road, hi tech Zone, Jinan City, Shandong Province, 250100 Applicant before: SHANDONG INSPUR ARTIFICIAL INTELLIGENCE RESEARCH INSTITUTE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |