CN107168111B - Intelligence adapts to the Multi-variables optimum design driving control system and method on surface - Google Patents
Intelligence adapts to the Multi-variables optimum design driving control system and method on surface Download PDFInfo
- Publication number
- CN107168111B CN107168111B CN201710166523.7A CN201710166523A CN107168111B CN 107168111 B CN107168111 B CN 107168111B CN 201710166523 A CN201710166523 A CN 201710166523A CN 107168111 B CN107168111 B CN 107168111B
- Authority
- CN
- China
- Prior art keywords
- module
- driving
- user
- adapts
- target value
- 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.)
- Active
Links
- 238000013461 design Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 238000003909 pattern recognition Methods 0.000 claims abstract description 24
- 230000006978 adaptation Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 9
- 210000000746 body region Anatomy 0.000 claims description 3
- 238000012938 design process Methods 0.000 claims description 3
- 238000009790 rate-determining step (RDS) Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 2
- 230000003472 neutralizing effect Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 29
- 230000008667 sleep stage Effects 0.000 description 11
- 230000002045 lasting effect Effects 0.000 description 8
- 230000007958 sleep Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 4
- 206010062519 Poor quality sleep Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000004617 sleep duration Effects 0.000 description 2
- 230000003860 sleep quality Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides Multi-variables optimum design driving control systems and method that a kind of intelligence adapts to surface, comprising: data call module, data access module, user behavior and stateful pattern recognition module, user environment adapt to decision-making module, Multi-variables optimum design resolves module, distributed drives subsystem control module and distributed multiple drives subsystem modules.System and method in the present invention is particularly suitable for the optimal control of multiple drive system multiple target tasks, and the change of complex surface movement can be performed in unison under the control of global optimization strategy, has good user experience.And it can satisfy the preference strategy and calculation method of user personality customization.Become considering user individual customization, multiple environment adapt to and driving the Multi-variables optimum design driving of the optimisation strategies such as resource from the driving of simple target value, the user experience is improved in a manner of data-driven and artificial intelligence, and complex surface change movement can be performed in unison under the control system of global optimization strategy.
Description
Technical field
The present invention relates to computer and intelligent System Control Technology fields, and in particular, to intelligence adapts to the changeable of surface
Amount optimization driving control system and method.
Background technique
With the arrival in artificial intelligence epoch, multidimensional data acquisition and user mode are identified as intellectual product and better adapt to
User experience provides more possibility.In man-machine interactive system, it is related to the complicated driving with contact object relationship surface and changes
Often there is multiple target, the feature of multitask simultaneously.In order to optimize user experience, this complicated driving, which changes, to be needed especially to carry out
The optimisation strategy of a variety of Variable Factors calculates.Meanwhile the drive system itself is also required to integrate software and hardware system, for multivariable
The implementation of optimisation strategy and be specially optimized design.
Drive system can be being generally required simultaneously to surface multiple spot multizone from the surface support system that main regulation adapts to
Carry out identical or different change and adjustment.In order to optimize user experience, the drivings of these multivariables execution generally require simultaneously,
Synchronous synergetic progress or completion.Meanwhile the ambient condition of the individual demand and real-time change for user, drive system also need
There is relatively flexible optimisation strategy to execute resource allocation proposal, to meet the implementation requirement of different task.It is in previous
In system, due to using centralized driving system, the task module of unitary variant cannot achieve above-mentioned mission requirements.The present invention passes through
A kind of the distributed modular optimization drive system and method for software and hardware combining, realize above-mentioned multivariable collaboration, are optimal
Drive the requirement of implementation effect.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide the Multi-variables optimum design drives that a kind of intelligence adapts to surface
Autocontrol system and method.
The intelligence provided according to the present invention adapts to the Multi-variables optimum design driving control system on surface, comprising: data call mould
Block, data access module, user behavior and stateful pattern recognition module, user environment adapt to decision-making module, Multi-variables optimum design solution
Calculate module, distributed drives subsystem control module and distributed multiple drives subsystem modules, in which:
The data call module, for lasting and real-time behavior the contact object transferred from data access module
User behavior and stateful pattern recognition module are transmitted to status indication data and user environment adapts to decision-making module；
Data access module, for accessing lasting and real-time behavior and status indication data for contact object；
User behavior and stateful pattern recognition module for will acquire real-time and last contact object behavior and state mark
Numeration is compared according to the pattern class feature with lane database, and carries out pattern-recognition and classification to active user's pattern class
Active user's pattern class numerical value is written in data access module label；
User environment adapts to decision-making module, for obtaining active user's pattern class from data access module, and from number
Target value group is adapted to according to the corresponding user environment of active user's pattern class is recalled in access module, the target value group is exported and arrives
Multi-variables optimum design resolves module, obtains the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design resolves module, right according to driving strategy for generating driving strategy to active user's pattern class
User environment adapts to target value group and is parsed, optimized and corrected, and output driving target value group to user environment adapts to decision model
Block；
Distributed drives subsystem control module adapts to the driving target of decision-making module output for receiving user environment
Value group generates respective drive value group and/or task order, is output to corresponding drives subsystem module progress coordinated drive and holds
Row completes goal task, and returns to operating value, and the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem modules, for executing the driving task to support surface adjustment.
Preferably, the data access module includes: data temporary storage module and database, in which: in data temporary storage module
It is stored with active user's pattern class numerical value, the lasting of contact object, real-time behavior and state mark are stored in database
Count evidence.
Preferably, the contact object include: user lie down, sit, by when contact partially or completely with support surface
Body region.
Preferably, the Multi-variables optimum design resolve module include: user customize optimisation strategy module, user environment adapt to it is excellent
Change policy module, driving resource optimization policy module, goal task resolving decision-making module, specifically:
The user customizes optimisation strategy module and is used to set under different user individual requirement conditions, active user's mould
The corresponding user environment of formula classification adapts to optimisation strategy and driving resource optimization strategy protocol；
Specifically, different user individual strategies includes:
1), sleep quality preference strategy:
The sleep stage is using comfort level preference strategy and/or adapts to preference strategy immediately；
Shallow sleep stage uses with comfort level preference strategy and/or non-discovers adaptation preference strategy；
The deep sleep stage is using posture preference strategy and/or non-discovers adaptation preference strategy；
When meeting sleep duration requirement, preference strategy is adapted to using uncomfortable strategy and/or immediately in the sleep wakefulness phase；
2), special posture keeps preference strategy:
Whole sleep stages use posture preference strategy；
User is in targeted attitude simultaneously, using global pressure balance policy；
User is in non-targeted posture, using uncomfortable strategy；
4), physical signs monitors preference strategy:
Whole sleep stages keep monitoring contact preference strategy；
The user environment adapts to optimisation strategy module and drives variable under different adjustable strategies and the strategy for setting
Between target value adjust priority relationship.
Specifically, in the application scenarios of intelligent bed, there is the adjustment height variable based on user's posture, also have based on user
The adjustment pressure variations of comfort level, therefore under different user environment adaptive strategies, the priority and power of these adjustment variables
Series of fortified passes system is also different.Such as:
1, posture preference strategy, adjustment posture (high deformation) the variable strategy preferential to target value；
2, comfort level preference strategy, the adjustment pressure variations strategy preferential to target value；
3, global pressure balance policy, the strategy of equilibrium adjustment parts of body pressure variations to target value；
4, emphasis local pressure balance policy, keypoint part pressure variations are adjusted to the preferential strategy of target value；
5, monitoring contact preference strategy keeps monitoring sensor module region to be in reasonable contact always
State；
6, uncomfortable strategy.
The driving resource optimization policy module is for setting under the driving resource optimization strategy of different requirements, different driving
The invocation scheme of resource；Specifically, such as:
1, preference strategy is adapted to immediately；
2, non-to discover adaptation preference strategy.
It is suitable that the goal task resolves user environment of the decision-making module for receiving user environment adaptation decision-making module output
Target value group is answered, customizes optimisation strategy module, user environment adaptation optimisation strategy module, driving resource optimization strategy mould in user
The driving target value group for adapting to driving operation is generated under the constraint of block, is output to drives subsystem control module.
Preferably, the distributed drives subsystem control module includes: that instruction receives to execute with communication module, driving
Module,
Described instruction receives and communication module is used to receive to drive the driving value group of execution module output and driving task life
It enables, and output driving value group and/or task order are to corresponding drives subsystem module；
Driving execution module is used to receive the driving target value group that Multi-variables optimum design resolves module output, generates driving value group
With driving task order to instruction receiving and communication module, and returns to operating value and be stored in data access module.
The intelligence provided according to the present invention adapts to the Multi-variables optimum design drive control method on surface, includes the following steps:
Data call step: the contact object transferred from data access module is lasted and real-time behavior and state mark
Numeration evidence is transmitted to user behavior and stateful pattern recognition module and user environment adapts to decision-making module；
Data access step: lasting and real-time behavior and status indication data for contact object is accessed；
User behavior and stateful pattern recognition step: will acquire real-time and contact object behavior and status indication number are lasted
It is compared according to the pattern class feature with lane database, and pattern-recognition and contingency table is carried out to active user's pattern class
Active user's pattern class numerical value is written in data access module note；
User environment adapts to steps in decision-making: obtaining active user's pattern class from data access module, and deposits from data
The corresponding user environment of active user's pattern class is recalled in modulus block and adapts to target value group, exports the target value group to changeable
Amount optimization resolves module, obtains the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design process of solution: driving strategy is generated to active user's pattern class, according to driving strategy to user
Environment adapts to target value group and is parsed, optimized and corrected, and output driving target value group to user environment adapts to decision-making module；
Distributed drives subsystem rate-determining steps: the driving target value that user environment adapts to decision-making module output is received
Group generates respective drive value group and/or task order, is output to corresponding drives subsystem module and carries out coordinated drive execution,
Goal task is completed, and returns to operating value, the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem steps: the driving task adjusted to support surface is executed.
Compared with prior art, the present invention have it is following the utility model has the advantages that
1, intelligence provided in the present invention adapts to the Multi-variables optimum design driving control system on surface and method is particularly suitable for
It is dynamic can be performed in unison with complex surface under the control of global optimization strategy for the optimal control of multiple drive system multiple target tasks
The change of work has good user experience.And it can satisfy the preference strategy and calculation method of user personality customization.
2, the present invention becomes considering user individual customization, multiple environment adapt to and driving money from the driving of simple target value
The Multi-variables optimum design of the optimisation strategies such as source drives, and the user experience is improved in a manner of data-driven and artificial intelligence.
3, multiple drives subsystems of the distributed modular in the present invention, can be in the control system of global optimization strategy
Under be performed in unison with complex surface change movement.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the schematic diagram for the Multi-variables optimum design driving control system that intelligence provided in the present invention adapts to surface.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
The intelligence provided according to the present invention adapts to the Multi-variables optimum design driving control system on surface, comprising: data call mould
Block, data access module, user behavior and stateful pattern recognition module, user environment adapt to decision-making module, Multi-variables optimum design solution
Calculate module, distributed drives subsystem control module and distributed multiple drives subsystem modules, in which:
The data call module, for lasting and real-time behavior the contact object transferred from data access module
User behavior and stateful pattern recognition module are transmitted to status indication data and user environment adapts to decision-making module；
Data access module, for accessing lasting and real-time behavior and status indication data for contact object；
User behavior and stateful pattern recognition module for will acquire real-time and last contact object behavior and state mark
Numeration is compared according to the pattern class feature with lane database, and carries out pattern-recognition and classification to active user's pattern class
Active user's pattern class numerical value is written in data access module label；
User environment adapts to decision-making module, for obtaining active user's pattern class from data access module, and from number
Target value group is adapted to according to the corresponding user environment of active user's pattern class is recalled in access module, the target value group is exported and arrives
Multi-variables optimum design resolves module, obtains the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design resolves module, right according to driving strategy for generating driving strategy to active user's pattern class
User environment adapts to target value group and is parsed, optimized and corrected, and output driving target value group to user environment adapts to decision model
Block；
Distributed drives subsystem control module adapts to the driving target of decision-making module output for receiving user environment
Value group generates respective drive value group and/or task order, is output to corresponding drives subsystem module progress coordinated drive and holds
Row completes goal task, and returns to operating value, and the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem modules, for executing the driving task to support surface adjustment.
The data access module includes: data temporary storage module and database, in which: is stored with and works as in data temporary storage module
Preceding user mode categorization values are stored with the lasting of contact object, real-time behavior and status indication data in database.
The contact object include: user lie down, sit, by when the partially or completely body region that is contacted with support surface
Domain.
It includes: that user customizes optimisation strategy module, user environment adapts to optimisation strategy that the Multi-variables optimum design, which resolves module,
Module, driving resource optimization policy module, goal task resolve decision-making module, specifically:
The user customizes optimisation strategy module and is used to set under different user individual requirement conditions, active user's mould
The corresponding user environment of formula classification adapts to optimisation strategy and driving resource optimization strategy protocol；
Specifically, different user individual strategies includes:
1), sleep quality preference strategy:
The sleep stage is using comfort level preference strategy and/or adapts to preference strategy immediately；
Shallow sleep stage uses with comfort level preference strategy and/or non-discovers adaptation preference strategy；
The deep sleep stage is using posture preference strategy and/or non-discovers adaptation preference strategy；
When meeting sleep duration requirement, preference strategy is adapted to using uncomfortable strategy and/or immediately in the sleep wakefulness phase；
2), special posture keeps preference strategy:
Whole sleep stages use posture preference strategy；
User is in targeted attitude simultaneously, using global pressure balance policy；
User is in non-targeted posture, using uncomfortable strategy；
4), physical signs monitors preference strategy:
Whole sleep stages keep monitoring contact preference strategy；
The user environment adapts to optimisation strategy module and drives variable under different adjustable strategies and the strategy for setting
Between target value adjust priority relationship；
Specifically, in the application scenarios of intelligent bed, there is the adjustment height variable based on user's posture, also have based on user
The adjustment pressure variations of comfort level, therefore under different user environment adaptive strategies, the priority and power of these adjustment variables
Series of fortified passes system is also different.Such as:
Posture preference strategy, adjustment posture (high deformation) the variable strategy preferential to target value；
Comfort level preference strategy, the adjustment pressure variations strategy preferential to target value；
Global pressure balance policy, the strategy of equilibrium adjustment parts of body pressure variations to target value；
Emphasis local pressure balance policy, keypoint part pressure variations are adjusted to the preferential strategy of target value；
Monitoring contact preference strategy, keeps monitoring sensor module region to be in reasonable contact condition always；
Uncomfortable strategy.
The driving resource optimization policy module is for setting under the driving resource optimization strategy of different requirements, different driving
The invocation scheme of resource；Specifically, such as:
Immediately preference strategy is adapted to；
It is non-to discover adaptation preference strategy.
It is suitable that the goal task resolves user environment of the decision-making module for receiving user environment adaptation decision-making module output
Target value group is answered, customizes optimisation strategy module, user environment adaptation optimisation strategy module, driving resource optimization strategy mould in user
The driving target value group for adapting to driving operation is generated under the constraint of block, is output to drives subsystem control module.
The distributed drives subsystem control module includes: instruction receiving and communication module, drives execution module,
Described instruction receives and communication module is used to receive to drive the driving value group of execution module output and driving task life
It enables, and output driving value group and/or task order are to corresponding drives subsystem module；
Driving execution module is used to receive the driving target value group that Multi-variables optimum design resolves module output, generates driving value group
With driving task order to instruction receiving and communication module, and returns to operating value and be stored in data access module.
The intelligence provided according to the present invention adapts to the Multi-variables optimum design drive control method on surface, includes the following steps:
Data call step: the contact object transferred from data access module is lasted and real-time behavior and state mark
Numeration evidence is transmitted to user behavior and stateful pattern recognition module and user environment adapts to decision-making module；
Data access step: lasting and real-time behavior and status indication data for contact object is accessed；
User behavior and stateful pattern recognition step: will acquire real-time and contact object behavior and status indication number are lasted
It is compared according to the pattern class feature with lane database, and pattern-recognition and contingency table is carried out to active user's pattern class
Active user's pattern class numerical value is written in data access module note；
User environment adapts to steps in decision-making: obtaining active user's pattern class from data access module, and deposits from data
The corresponding user environment of active user's pattern class is recalled in modulus block and adapts to target value group, exports the target value group to changeable
Amount optimization resolves module, obtains the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design process of solution: driving strategy is generated to active user's pattern class, according to driving strategy to user
Environment adapts to target value group and is parsed, optimized and corrected, and output driving target value group to user environment adapts to decision-making module；
Distributed drives subsystem rate-determining steps: the driving target value that user environment adapts to decision-making module output is received
Group generates respective drive value group and/or task order, is output to corresponding drives subsystem module and carries out coordinated drive execution,
Goal task is completed, and returns to operating value, the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem steps: the driving task adjusted to support surface is executed.
It should be noted that the intelligence provided by the invention adapts in the Multi-variables optimum design drive control method on surface
Step can use the intelligence and adapt to corresponding module, device, unit etc. in the Multi-variables optimum design driving control system on surface
It is achieved, the technical solution that those skilled in the art are referred to the system realizes the step process of the method, that is, institute
Stating the embodiment in system can be regarded as realizing the preference of the method, and it will not be described here.
More detailed explanation is done to the technical solution in the present invention combined with specific embodiments below.
Embodiment 1
Method in the present invention is applied drives the support surface for adapting to user's sleep behavior and state to control distributed
On.For adaptive human body lie down can deformation support surface, in addition to accurately calculate adapt to user's current state surface mesh
Outside scale value, the process of the deformation driving of support surface is completed, is also extremely important for user experience.In particular, being directed to
The surface for the physical feeling that different user preference requires, sleep state demands locating for user, user are different adapts to want
It asks, needs one group of optimisation strategy to control, manage driving process.For example, for the physical feeling of different weight, how
Adaptation movement is naturally completed simultaneously, is very important for user experience.
Human body lies down in support surface, and by calling database module, obtaining contact object lasts and instant behavior
With status indication data, user behavior and state model evaluation module and user environment adaptive pattern evaluation module are inputted.
User behavior and stateful pattern recognition module according to the instant of acquisition and last contact object behavior and status indication
Data compare the pattern class feature pre-entered and are identified, to active user's pattern class according to sleep cycle and stage
Feature, body move behavioural characteristic, posture state feature etc. and carry out pattern-recognition and classification marker, by the sleep cycle of active user/
Data access module --- data temporary storage module is written in stage, posture state pattern class numerical value.
User environment adapts to decision-making module from data access module --- the sleep of data temporary storage module acquisition active user
Period/stage, posture state pattern class numerical value, and recall the corresponding user environment of the pattern class from database module and adapt to
Target value group.Then, calling Multi-variables optimum design to resolve, the user in module customizes optimisation strategy module, user environment adapts to optimization
Active user's mode and ambient condition are assessed in policy module and driving resource optimization policy module, for example, falling asleep
Stage uses users'comfort preference strategy, and in the deep sleep stage using user's posture preference strategy etc.；According to driving resource
Optimisation strategy optimizes global drive, is suitble to user experience, driving realization process for coordinating etc. naturally to obtain.So
Afterwards, invocation target task resolves decision-making module and target value group is optimized and corrected.According to the revised driving target of resolving
Value, output driving target value to drives subsystem control module.
Drives subsystem control module generates driving value group and driving task order according to the driving target value group received
Coordinated drive execution is carried out to distributed multiple drives subsystem modules, completes goal task, and returns to operating value to driving
Subsystem control module records write-in data memory module --- database module as device drives by the module.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (6)
1. the Multi-variables optimum design driving control system that a kind of intelligence adapts to surface characterized by comprising user environment adaptation is determined
Plan module, Multi-variables optimum design resolve module；
User environment adapts to decision-making module and exports target value group to Multi-variables optimum design resolving module, obtains the driving target value of return
Group is output to distributed drives subsystem control module；
Multi-variables optimum design resolves module and target value group adjusted is output to user environment adaptation decision-making module；
Further include: data call module, data access module, user behavior and stateful pattern recognition module, distributed driving
Subsystem control module and distributed multiple drives subsystem modules, in which:
The data call module, contact object history and real-time behavior and shape for will be transferred from data access module
State flag data is transmitted to user behavior and stateful pattern recognition module and user environment adapts to decision-making module；
Data access module, for accessing the history and real-time behavior and status indication data of contact object；
User behavior and stateful pattern recognition module, for the real-time and history contact object behavior that will acquire and status indication number
It is compared according to the pattern class feature with lane database, and pattern-recognition and contingency table is carried out to active user's pattern class
Active user's pattern class numerical value is written in data access module note；
User environment adapts to decision-making module, for obtaining active user's pattern class from data access module, and deposits from data
The corresponding user environment of active user's pattern class is recalled in modulus block and adapts to target value group, exports the target value group to changeable
Amount optimization resolves module, obtains the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design resolves module, for generating driving strategy to active user's pattern class, according to driving strategy to user
Environment adapts to target value group and is parsed, optimized and corrected, and output driving target value group to user environment adapts to decision-making module；
Distributed drives subsystem control module adapts to the driving target value of decision-making module output for receiving user environment
Group generates respective drive value group and/or task order, is output to corresponding drives subsystem module and carries out coordinated drive execution,
Goal task is completed, and returns to operating value, the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem modules, for executing the driving task to support surface adjustment.
2. the Multi-variables optimum design driving control system that intelligence according to claim 1 adapts to surface, which is characterized in that described
Data access module includes: data temporary storage module and database, in which: active user's mode class is stored in data temporary storage module
Other numerical value is stored with history, real-time behavior and the status indication data of contact object in database.
3. the Multi-variables optimum design driving control system that intelligence according to claim 1 adapts to surface, which is characterized in that described
Contact object include: user lie down, sit, by when the partially or completely body region that is contacted with support surface.
4. the Multi-variables optimum design driving control system that intelligence according to claim 1 adapts to surface, which is characterized in that described
It includes: that user customizes optimisation strategy module, user environment adapts to optimisation strategy module, driving resource that Multi-variables optimum design, which resolves module,
Optimisation strategy module, goal task resolve decision-making module, specifically:
The user customizes optimisation strategy module and is used to set under different user individual requirement conditions, active user's mode class
Not corresponding user environment adapts to optimisation strategy and driving resource optimization strategy protocol；
The user environment adapts to optimisation strategy module and is used to set under different adjustable strategies and the strategy mesh between driving variable
The priority relationship of scale value adjustment；
The driving resource optimization policy module is for setting under the driving resource optimization strategy of different requirements, different driving resource
Invocation scheme；
The goal task resolves decision-making module and is used to receive the user environment adaptation mesh that user environment adapts to decision-making module output
Scale value group in user's customization optimisation strategy module, user environment adaptation optimisation strategy module, drives resource optimization policy module
The driving target value group for adapting to driving operation is generated under constraint, is output to drives subsystem control module.
5. the Multi-variables optimum design driving control system that intelligence according to claim 1 adapts to surface, which is characterized in that described
Distributed drives subsystem control module includes: instruction receiving and communication module, drives execution module,
The driving value group and driving task order that described instruction receives and communication module is used to receive to drive execution module output, and
Output driving value group and/or task order are to corresponding drives subsystem module；
Driving execution module is used to receive the driving target value group that Multi-variables optimum design resolves module output, generates driving value group and drive
Dynamic task order receives to instruction and communication module, and returns to operating value and be stored in data access module.
6. a kind of Multi-variables optimum design drive control method that intelligence adapts to surface, which comprises the steps of:
Data call step: by the contact object history transferred from data access module and real-time behavior and status indication number
Decision-making module is adapted to according to user behavior and stateful pattern recognition module and user environment is transmitted to；
Data access step: the history and real-time behavior and status indication data of contact object are accessed；
User behavior and stateful pattern recognition step: the real-time and history contact object behavior that will acquire and status indication data with
The pattern class feature of lane database compares, and carries out pattern-recognition and classification marker to active user's pattern class, will
Active user's pattern class numerical value is written in data access module；
User environment adapts to steps in decision-making: active user's pattern class is obtained from data access module, and from data access mould
The corresponding user environment of active user's pattern class is recalled in block and adapts to target value group, and it is excellent to multivariable to export the target value group
Module is calculated in neutralizing, is obtained the driving target value group of return, is output to distributed drives subsystem control module；
Multi-variables optimum design process of solution: driving strategy is generated to active user's pattern class, according to driving strategy to user environment
It adapts to target value group to be parsed, optimized and corrected, output driving target value group to user environment adapts to decision-making module；
Distributed drives subsystem rate-determining steps: receiving the driving target value group that user environment adapts to decision-making module output, produces
Raw respective drive value group and/or task order are output to corresponding drives subsystem module and carry out coordinated drive execution, complete mesh
Mark task, and operating value is returned, the operating value is stored in data access module as device drives record；
Distributed multiple drives subsystem steps: the driving task adjusted to support surface is executed.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710166523.7A CN107168111B (en) | 2017-03-20 | 2017-03-20 | Intelligence adapts to the Multi-variables optimum design driving control system and method on surface |
| PCT/CN2017/084095 WO2018171019A1 (en) | 2017-03-20 | 2017-05-12 | Multivariable optimization driving and control system and method capable of intelligently adapting surface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710166523.7A CN107168111B (en) | 2017-03-20 | 2017-03-20 | Intelligence adapts to the Multi-variables optimum design driving control system and method on surface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107168111A CN107168111A (en) | 2017-09-15 |
| CN107168111B true CN107168111B (en) | 2019-03-08 |
Family
ID=59849306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710166523.7A Active CN107168111B (en) | 2017-03-20 | 2017-03-20 | Intelligence adapts to the Multi-variables optimum design driving control system and method on surface |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107168111B (en) |
| WO (1) | WO2018171019A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201097174Y (en) * | 2007-10-29 | 2008-08-06 | 吴远宁 | Electronic controller for medial health care mattress |
| CN102436246A (en) * | 2011-12-19 | 2012-05-02 | 厦门万安智能股份有限公司 | Intelligent house furnishing centralized control device with environmental adaptive contextual models |
| CN103780691A (en) * | 2014-01-20 | 2014-05-07 | 辛志宇 | Intelligent sleep system, user side system of intelligent sleep system, and cloud system of intelligent sleep system |
| CN203838535U (en) * | 2014-01-20 | 2014-09-17 | 辛志宇 | Matrix modularization sleep data acquisition and environment motion system achieving flexible arrangement and replacement |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8429778B2 (en) * | 2011-04-11 | 2013-04-30 | Hill-Rom Services, Inc. | Low noise linear diaphragm compressor by variable amplitude driver |
| CN102298346A (en) * | 2011-05-26 | 2011-12-28 | 江苏科技大学 | Intelligent wheel chair voice drive controller and identification and control method thereof |
| WO2015188156A1 (en) * | 2014-06-05 | 2015-12-10 | Morphy Inc. | Methods and systems for gathering human biological signals and controlling a bed device |
| CN106959636B (en) * | 2017-03-20 | 2018-12-11 | 魔玛智能科技（上海）有限公司 | Intelligence adapts to the modularized distribution type driving control system and method for support surface |
-
2017
- 2017-03-20 CN CN201710166523.7A patent/CN107168111B/en active Active
- 2017-05-12 WO PCT/CN2017/084095 patent/WO2018171019A1/en not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201097174Y (en) * | 2007-10-29 | 2008-08-06 | 吴远宁 | Electronic controller for medial health care mattress |
| CN102436246A (en) * | 2011-12-19 | 2012-05-02 | 厦门万安智能股份有限公司 | Intelligent house furnishing centralized control device with environmental adaptive contextual models |
| CN103780691A (en) * | 2014-01-20 | 2014-05-07 | 辛志宇 | Intelligent sleep system, user side system of intelligent sleep system, and cloud system of intelligent sleep system |
| CN203838535U (en) * | 2014-01-20 | 2014-09-17 | 辛志宇 | Matrix modularization sleep data acquisition and environment motion system achieving flexible arrangement and replacement |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018171019A1 (en) | 2018-09-27 |
| CN107168111A (en) | 2017-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230384771A1 (en) | Method for automatic production line planning based on industrial internet of things, system and storage medium thereof | |
| EP3871166A1 (en) | Deep reinforcement learning for production scheduling | |
| CN106959636B (en) | Intelligence adapts to the modularized distribution type driving control system and method for support surface | |
| CN112598313B (en) | Electricity scheduling method, device and computer equipment based on beetle whisker search algorithm | |
| CN111461525A (en) | Parallel computing production scheduling system and method based on dynamic load | |
| CN105936047A (en) | Brain imitation robot controlling and studying system | |
| CN107168111B (en) | Intelligence adapts to the Multi-variables optimum design driving control system and method on surface | |
| CN115545329A (en) | Integrated dynamic scheduling method suitable for clothing manufacturing production line | |
| CN113925311A (en) | A fully automatic interaction method and system for an intelligent seat that fits the back of the human body | |
| Arie et al. | Creating novel goal-directed actions at criticality: A neuro-robotic experiment | |
| CN109301820A (en) | A kind of enterprise's electrical control method and system | |
| US20200289030A1 (en) | Assist device control system | |
| Alexander | Cognitive control strategies derive from dimension reliability | |
| Benjaafar | Intelligent simulation for flexible manufacturing systems: An integrated approach | |
| Houghton et al. | A planning model for just‐in‐time batch manufacturing | |
| JP6795240B1 (en) | Controls, methods and programs | |
| CN119761407B (en) | An adaptive hybrid expert model training framework for multi-agent systems | |
| CN115001048A (en) | Power grid frequency control method, device, equipment and storage medium of AGC system | |
| US20220207285A1 (en) | Classifier system and method for generating classification models in a distributed manner | |
| CN116719873B (en) | Distributed power supply edge autonomous software control system | |
| CN119273124B (en) | Island type assembly scheduling method and device | |
| CN119346679B (en) | An intelligent shape correction method and system for thin-walled components based on digital elevation technology | |
| Nasuto et al. | Anticipation in neurocybernetics | |
| Protasov et al. | Development of an Automated Scheduling System Using Neural Network Technologies and Sorting Algorithms | |
| Schuh et al. | Real-time capable Production Planning and Control in the Order Management of builtto-order Companies |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |