CN116439815A - State detection method and device for frozen fat-dissolving instrument - Google Patents
State detection method and device for frozen fat-dissolving instrument Download PDFInfo
- Publication number
- CN116439815A CN116439815A CN202310714275.0A CN202310714275A CN116439815A CN 116439815 A CN116439815 A CN 116439815A CN 202310714275 A CN202310714275 A CN 202310714275A CN 116439815 A CN116439815 A CN 116439815A
- Authority
- CN
- China
- Prior art keywords
- parameter
- fat
- dissolving
- freezing
- frozen
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 82
- 238000007710 freezing Methods 0.000 claims abstract description 353
- 230000008014 freezing Effects 0.000 claims abstract description 352
- 238000000034 method Methods 0.000 claims abstract description 186
- 230000008569 process Effects 0.000 claims abstract description 157
- 239000011159 matrix material Substances 0.000 claims abstract description 134
- 238000011156 evaluation Methods 0.000 claims abstract description 90
- 238000004090 dissolution Methods 0.000 claims abstract description 80
- 238000013507 mapping Methods 0.000 claims abstract description 13
- 239000013078 crystal Substances 0.000 claims description 57
- 239000013598 vector Substances 0.000 claims description 39
- 238000006243 chemical reaction Methods 0.000 claims description 34
- 238000002844 melting Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 230000010354 integration Effects 0.000 claims description 12
- 230000004130 lipolysis Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000005057 refrigeration Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 37
- 230000001276 controlling effect Effects 0.000 description 16
- 150000002632 lipids Chemical class 0.000 description 13
- 230000001186 cumulative effect Effects 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 11
- 239000000284 extract Substances 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000002035 prolonged effect Effects 0.000 description 4
- 238000002604 ultrasonography Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 210000001789 adipocyte Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
- A61B18/02—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by cooling, e.g. cryogenic techniques
- A61B18/0206—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by cooling, e.g. cryogenic techniques ultrasonic, e.g. for destroying tissue or enhancing freezing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
- A61B2018/00636—Sensing and controlling the application of energy
- A61B2018/00696—Controlled or regulated parameters
- A61B2018/00702—Power or energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Surgery (AREA)
- Pure & Applied Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Computer Hardware Design (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Otolaryngology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a state detection method and device of a frozen fat-dissolving instrument, which are used for improving the state detection accuracy of the frozen fat-dissolving instrument and improving the accuracy of parameter adjustment. The method comprises the following steps: extracting characteristic parameters of the freezing parameter data and the fat-dissolving parameter data respectively to obtain a first characteristic parameter cluster and a second characteristic parameter cluster; mapping the matrix to obtain a freezing characteristic parameter matrix and a fat-dissolving characteristic parameter matrix; inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes; generating a first parameter adjustment set according to the freezing state evaluation index to control the state of the freezing process, generating a second parameter adjustment set according to the fat dissolution state evaluation index to control the state of the fat dissolution process, and generating a target state control result.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a state detection method and device of a frozen fat-dissolving instrument.
Background
Currently, a freeze fat-dissolving device is becoming more and more popular as a non-operative fat-reducing method. However, the quality and effectiveness of current frozen fat-liquors is difficult to monitor and control effectively, mainly due to the lack of accurate state detection and control means. Therefore, there is a strong need for an efficient, accurate and reliable method of detecting and controlling the state of a frozen lipolyzer to ensure its safety and effectiveness.
The defects of the existing scheme are that most of the frozen fat-dissolving meters in the current market still do not realize intelligent management and have no reliable state detection and control functions. In addition, many frozen lipolysis apparatuses have difficulty meeting the needs of users. Therefore, research and application of intelligent management of the frozen fat-dissolving instrument are further advanced, the safety and effectiveness of the frozen fat-dissolving instrument are improved, and more comprehensive, accurate and practical state detection and control are realized.
Disclosure of Invention
The invention provides a state detection method and device of a frozen fat-dissolving instrument, which are used for improving the state detection accuracy of the frozen fat-dissolving instrument and improving the accuracy of parameter adjustment.
The first aspect of the invention provides a method for detecting the state of a frozen fat-dissolving instrument, which comprises the following steps:
Acquiring state parameter data of a target frozen fat-dissolving instrument, and carrying out state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
and respectively extracting characteristic parameters of the freezing parameter data and the fat-dissolving parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters and ice crystal size parameters, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
performing matrix mapping on the first characteristic parameter cluster to obtain a frozen characteristic parameter matrix, and performing matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix;
inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model for state detection to obtain a frozen state evaluation index and a fat dissolving state evaluation index;
generating a first parameter adjustment set according to the frozen state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature, and the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients;
And controlling the state of the freezing process of the target frozen fat-dissolving instrument based on the first parameter adjustment set, controlling the state of the fat-dissolving process of the target frozen fat-dissolving instrument through the second parameter adjustment set, and generating a target state control result.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the obtaining state parameter data of the target frozen fat-dissolving device, and performing state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data includes:
acquiring state parameter data of a target frozen fat-dissolving instrument, and acquiring a plurality of frozen parameter attribute tags and a plurality of fat-dissolving parameter attribute tags;
acquiring a plurality of initial freezing parameters from the state parameter data according to the plurality of freezing parameter attribute tags, and acquiring a plurality of initial fat-dissolving parameters from the state parameter data according to the plurality of fat-dissolving parameter attribute tags;
and carrying out freezing time sequence distribution integration on the plurality of initial freezing parameters to obtain freezing parameter data, and carrying out fat dissolving time sequence distribution integration on the plurality of initial fat dissolving parameters to obtain fat dissolving parameter data.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the extracting feature parameters of the freezing parameter data and the fat-dissolving parameter data to obtain a first feature parameter cluster and a second feature parameter cluster includes:
constructing a plurality of first parameter distribution curves corresponding to the freezing parameter data according to the plurality of freezing parameter attribute tags, and constructing a plurality of second parameter distribution curves corresponding to the fat-dissolving parameter data according to the plurality of fat-dissolving parameter attribute tags;
calculating curve characteristic values of each first parameter distribution curve to obtain a plurality of first curve characteristic values of each first parameter distribution curve, and calculating curve characteristic values of each second parameter distribution curve to obtain a plurality of second curve characteristic values of each second parameter distribution curve;
generating a first characteristic parameter cluster according to a plurality of first curve characteristic values of each first parameter distribution curve, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters, and ice crystal size parameters;
generating a second characteristic parameter cluster according to a plurality of second curve characteristic values of each second parameter distribution curve, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters, and lipolysis time parameters.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the performing matrix mapping on the first feature parameter cluster to obtain a frozen feature parameter matrix, and performing matrix conversion on the second feature parameter cluster to obtain a fat-soluble feature parameter matrix includes:
performing sequence conversion on the first characteristic parameter cluster to obtain a freezing temperature sequence, a freezing time sequence and an ice crystal size sequence, and performing sequence conversion on the second characteristic parameter cluster to obtain an ultrasonic power sequence, a microneedle process sequence and a fat dissolving time sequence;
data alignment is carried out on the freezing temperature sequence, the freezing time sequence and the ice crystal size sequence, and a plurality of first target triples are extracted according to a preset first triplet rule;
data alignment is carried out on the ultrasonic power sequence, the microneedle process sequence and the fat-dissolving time sequence, and a plurality of second target triples are extracted according to a preset second triplet rule;
and performing matrix conversion on the plurality of first target triples to obtain a freezing characteristic parameter matrix, and performing matrix conversion on the plurality of second target triples to obtain a fat-dissolving characteristic parameter matrix.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, inputting the frozen characteristic parameter matrix and the fat-dissolving characteristic parameter matrix into a preset frozen fat-dissolving instrument state detection model to perform state detection, to obtain a frozen state evaluation index and a fat-dissolving state evaluation index, where the method includes:
inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model, wherein the frozen fat dissolving instrument state detection model comprises the following components: a first codec network, a second codec network, a first classifier, and a second classifier;
extracting the characteristics of the frozen characteristic parameter matrix through the first encoding and decoding network to obtain a first characteristic vector, and extracting the characteristics of the fat-soluble characteristic parameter matrix through the second encoding and decoding network to obtain a second characteristic vector;
and predicting the freezing state of the first feature vector through the first classifier to obtain a freezing state evaluation index, and predicting the fat dissolution state of the second feature vector through the second classifier to obtain a fat dissolution state evaluation index.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the generating a first parameter adjustment set according to the frozen state evaluation index, and generating a second parameter adjustment set according to the fat-soluble state evaluation index includes:
Matching a plurality of freezing parameter thresholds according to the freezing state evaluation index, and matching a plurality of fat-dissolving parameter thresholds according to the fat-dissolving state evaluation index;
calculating a first parameter adjustment value for each refrigeration parameter according to the plurality of refrigeration parameter thresholds, and calculating a second parameter adjustment value for each fat-melting parameter according to the plurality of fat-melting parameter thresholds;
generating a first parameter adjustment set according to the first parameter adjustment value of each freezing parameter, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature;
generating a second parameter adjustment set according to the second parameter adjustment value of each fat-dissolving parameter, wherein the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the performing, based on the first parameter adjustment set, a freezing process state control on the target frozen fat-dissolving device, and performing, by the second parameter adjustment set, a fat-dissolving process state control on the target frozen fat-dissolving device, to generate a target state control result, includes:
Performing freezing parameter adjustment on the target frozen fat-dissolving instrument based on the first parameter adjustment set, and performing fat-dissolving parameter adjustment on the target frozen fat-dissolving instrument based on the second parameter adjustment set;
performing freezing process state control on the target frozen fat-dissolving instrument to obtain a first state control result, and performing fat-dissolving process state control on the target frozen fat-dissolving instrument to obtain a second state control result;
and comprehensively analyzing the first state control result and the second state control result to obtain a target state control result.
The second aspect of the present invention provides a state detection device of a frozen fat-dissolving meter, the state detection device of the frozen fat-dissolving meter comprising:
the acquisition module is used for acquiring state parameter data of the target frozen fat-dissolving instrument, and carrying out state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
the extraction module is used for extracting characteristic parameters of the freezing parameter data and the fat-dissolving parameter data respectively to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters and ice crystal size parameters, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
The conversion module is used for performing matrix mapping on the first characteristic parameter cluster to obtain a frozen characteristic parameter matrix, and performing matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix;
the detection module is used for inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes;
the generation module is used for generating a first parameter adjustment set according to the freezing state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature, and the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients;
and the control module is used for controlling the state of the freezing process of the target frozen fat-dissolving instrument based on the first parameter adjustment set, controlling the state of the fat-dissolving process of the target frozen fat-dissolving instrument through the second parameter adjustment set, and generating a target state control result.
A third aspect of the present invention provides a state detection apparatus for a frozen fat-dissolving meter, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the state detection device of the frozen lipolysis instrument to perform the state detection method of the frozen lipolysis instrument described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of detecting a state of a frozen fat meter as described above.
In the technical scheme provided by the invention, characteristic parameter extraction is respectively carried out on freezing parameter data and fat-dissolving parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster; mapping the matrix to obtain a freezing characteristic parameter matrix and a fat-dissolving characteristic parameter matrix; inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes; according to the invention, the effective monitoring and control of the state of the frozen fat-dissolving instrument are realized by utilizing a deep learning technology, the intelligent management of the frozen fat-dissolving instrument is realized, the frozen parameters and the fat-dissolving parameters are precisely controlled, the function of the frozen fat-dissolving instrument can be exerted to the greatest extent, the possibility of misoperation is reduced, the service life of equipment is prolonged, the possible faults of the equipment in the operation process can be reduced to the greatest extent by precisely controlling the frozen parameters and the fat-dissolving parameters, and the state detection accuracy of the frozen fat-dissolving instrument and the accuracy of parameter adjustment are improved.
Drawings
FIG. 1 is a schematic diagram showing an embodiment of a method for detecting a state of a lipid-dissolving device in an embodiment of the present invention;
FIG. 2 is a flow chart of feature parameter extraction in an embodiment of the invention;
FIG. 3 is a flow chart of matrix conversion in an embodiment of the invention;
FIG. 4 is a flow chart of state detection in an embodiment of the invention;
FIG. 5 is a schematic view showing an embodiment of a state detection device of a lipid-dissolving device in an embodiment of the present invention;
fig. 6 is a schematic diagram showing an embodiment of a state detection apparatus for a lipid freezing and dissolving device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a state detection method and device of a frozen fat-dissolving instrument, which are used for improving the state detection accuracy of the frozen fat-dissolving instrument and improving the accuracy of parameter adjustment. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of a method for detecting a state of a lipid-dissolving device in an embodiment of the present invention includes:
s101, acquiring state parameter data of a target frozen fat-dissolving instrument, and carrying out state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
it is to be understood that the execution body of the present invention may be a state detection device of a frozen fat-dissolving device, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the server acquires state parameter data of the target frozen fat-dissolving instrument, wherein the parameter data can comprise information such as temperature, time, ice crystal size and the like in the freezing process, and information such as ultrasonic power, microneedle process, fat dissolving time and the like in the fat dissolving process. The state parameter data are acquired in real time by a sensor or instrument. At the same time, a plurality of freezing parameter attribute tags and fat-dissolving parameter attribute tags are defined. For example, the freezing parameter attribute tags may be "freezing temperature", "freezing time" and "ice crystal size", while the fat-dissolving parameter attribute tags may be "ultrasonic power", "microneedle process" and "fat-dissolving time". And extracting corresponding initial freezing parameters and initial fat dissolving parameters from the state parameter data according to the attribute labels. For example, the freezing temperature, freezing time and ice crystal size are extracted from the state parameter data as initial freezing parameters, and the ultrasonic power, microneedle progress and fat dissolution time are extracted from the state parameter data as initial fat dissolution parameters. The server integrates the initial freezing parameters in a freezing time sequence distribution mode to obtain freezing parameter data. This means that multiple freezing parameters are integrated and counted over a time series. For example, statistical features such as an average value, a maximum value, a minimum value, etc. of the freezing temperature during the whole freezing process, and an accumulated value and a distribution condition of the freezing time may be calculated, and these statistical features may be formed into the freezing parameter data. Further, the initial fat-dissolving parameters are subjected to fat-dissolving time sequence distribution integration so as to obtain fat-dissolving parameter data. The method comprises the steps of calculating an average value of ultrasonic power, an accumulated value of microneedle progress, a distribution condition of fat dissolution time and the like, and integrating the statistical characteristics to form fat dissolution parameter data. For example, assume that the state parameter data of the frozen lipolyzer includes freezing temperature, freezing time, ice crystal size, ultrasonic power, microneedle process, and lipolyzing time. The server selects the freezing temperature, freezing time and ice crystal size as freezing parameter attribute tags, and ultrasonic power, microneedle process and fat dissolution time as fat dissolution parameter attribute tags. Freezing temperature, freezing time and ice crystal size are extracted from the state parameter data as initial freezing parameters. Assume that the server gets the following data: freezing temperature: [ -10, -8, -9, -12, -11] (degrees celsius), freezing time: [20,25,30,22,28] (min), ice crystal size: [5,6,4,5.5,6.5] (mm). And the server performs freezing time sequence distribution integration on the initial freezing parameters to obtain freezing parameter data. The server calculates the average, maximum and minimum values of the freezing temperatures, and the cumulative value and distribution of the freezing times. For example: average value of freezing temperature: (-10-8-9-12-11)/5= -10, maximum value of freezing temperature: -8, minimum value of freezing temperature: -12, cumulative value of freezing time: distribution of frozen time at 20+25+30+22+28=125: [20,25,30,22,28]. These statistics were integrated to obtain the following data for the freezing parameters: freezing temperature: average value: -10 ℃, maximum: -8 ℃, minimum: -12 ℃; freezing time: cumulative value: 125 minutes, distribution: [20,25,30,22,28]. Further, ultrasonic power, microneedle progress and fat-dissolving time are extracted from the state parameter data as initial fat-dissolving parameters. Assume that the server gets the following data: ultrasonic power: [30,32,28,29,31] (Watts), microneedle Process: [10,12,11,10.5,12.5] (mm), fat-dissolving time: [40,45,50,42,48] (min). And the server performs fat dissolution time sequence distribution integration on the initial fat dissolution parameters to obtain fat dissolution parameter data. The server calculates the average value of the ultrasonic power, the cumulative value of the microneedle process and the distribution of the fat-dissolving time. For example: average value of ultrasonic power: (30+32+28+29+31)/5=30, cumulative value of microneedle process: distribution of 10+12+11+10.5+12.5=56, fat-dissolving time: [40,45,50,42,48]. These statistical features were integrated to obtain the following data for lipid dissolution parameters: ultrasonic power: average value: 30 watts, microneedle process: cumulative value: 56 mm, fat-dissolving time: distribution conditions: [40,45,50,42,48] min. In this embodiment, the server successfully acquires the state parameter data of the target frozen fat-dissolving instrument and divides the state parameter data into the frozen parameter data and the fat-dissolving parameter data.
S102, extracting characteristic parameters of freezing parameter data and fat dissolving parameter data respectively to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters and ice crystal size parameters, and the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
specifically, the server constructs a plurality of first parameter distribution curves corresponding to the freezing parameter data according to the plurality of freezing parameter attribute tags, and constructs a plurality of second parameter distribution curves corresponding to the fat-dissolving parameter data according to the plurality of fat-dissolving parameter attribute tags. These profiles can be used to describe the trend and distribution of the parameters throughout the process. For example, for freeze parameter data, assume that the server has the following attribute tags: freezing temperature, freezing time, and ice crystal size. Wherein the server constructs a freezing temperature profile, a freezing time profile, and an ice crystal size profile. The server calculates curve characteristic values for each of the first parameter distribution curve and the second parameter distribution curve to obtain a plurality of characteristic values of each curve. These characteristic values may reflect the shape, trend and distribution characteristics of the parameter curve. For example, for a freezing temperature distribution curve, the server calculates characteristic values such as an average value, standard deviation, peak value, valley value, and the like. For the freeze time profile, the server calculates the characteristic values of the cumulative value, the point in time when the peak occurs, the skewness of the profile, and the like. Further, corresponding characteristic values may also be calculated for the fat-dissolving parameter profile. And generating a first characteristic parameter cluster according to a plurality of first curve characteristic values of each first parameter distribution curve. For example, the average value of the freezing temperature is used as the freezing temperature parameter, the cumulative value of the freezing time is used as the freezing time parameter, and the peak value of the ice crystal size distribution is used as the ice crystal size parameter. And generating a second characteristic parameter cluster according to a plurality of second curve characteristic values of each second parameter distribution curve. For example, the peak value of the ultrasonic power distribution is used as an ultrasonic power parameter, the standard deviation of the microneedle process distribution is used as a microneedle process parameter, and the distribution bias of the fat dissolution time is used as a fat dissolution time parameter. For example, assume that the server has a freezing temperature profile, a freezing time profile, and a characteristic value calculation of ice crystal size profile as follows: characteristic values of the freezing temperature distribution curve: average value: -10 ℃, peak: -8 ℃, valley: -12 ℃; characteristic values of the freeze time profile: cumulative value: 125 minutes, peak time point: uncomputed, distributed skewness: not calculated; characteristic value of ice crystal size distribution curve: peak value: 6.5 mm, valley: 4 mm. From these feature values, the server generates a first cluster of feature parameters: freezing temperature parameters: average value-10 ℃, peak value-8 ℃ and valley value-12 ℃; freezing time parameters: cumulative 125 minutes, peak time point (not calculated), distribution bias (not calculated); ice crystal size parameters: peak 6.5 mm, valley 4 mm. Further, assuming that the server has an ultrasonic power distribution curve, a microneedle process distribution curve and a characteristic value calculation result of the fat-dissolving time distribution curve are as follows: characteristic value of ultrasonic power distribution curve: peak value: characteristic value of 31 watt, microneedle process profile: standard deviation: characteristic value of 0.75 mm, fat-dissolving time distribution curve: distribution bias degree: not calculated. From these feature values, the server generates a second cluster of feature parameters: ultrasonic power parameters: peak 31 watt, microneedle process parameters: standard deviation 0.75 mm, lipid dissolution time parameter: distribution bias (not calculated). In this embodiment, the server successfully performs feature parameter extraction on the freezing parameter data and the fat-dissolving parameter data, and obtains a first feature parameter cluster and a second feature parameter cluster.
S103, performing matrix mapping on the first characteristic parameter cluster to obtain a frozen characteristic parameter matrix, and performing matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix;
it should be noted that, for the first feature parameter cluster, the server performs sequence conversion. According to the previous example, the server obtains a sequence of freezing temperatures, a sequence of freezing times and a sequence of ice crystal sizes. These sequences represent key parameter changes during the freezing process. Further, for the second characteristic parameter cluster, the server performs sequence conversion to obtain an ultrasonic power sequence, a microneedle process sequence and a fat-dissolving time sequence, which represent key parameter changes in the fat-dissolving process. The server performs data alignment on the freezing temperature sequence, the freezing time sequence, and the ice crystal size sequence. The data alignment is to ensure consistent sequence length for subsequent processing and analysis. In the data alignment process, interpolation and other methods can be used to fill in the missing values, so that the time points corresponding to the data points in the sequence are consistent. Further, data alignment was also performed on the ultrasound power sequence, the microneedle process sequence, and the lipid-dissolving time sequence. After the data alignment is completed, the server extracts a plurality of first target triples according to a preset first triplet rule. These triplets generally consist of freezing temperature, freezing time and ice crystal size, representing important features in the freezing process. Further, according to a preset second triplet rule, the server extracts a plurality of second target triples, which are composed of ultrasonic power, microneedle process and fat dissolving time, and represent important characteristics in the fat dissolving process. Finally, aiming at a plurality of first target triples, the server performs matrix conversion to obtain a freezing characteristic parameter matrix. In general, matrix conversion may be by organizing the parameter values in triplets in columns to form a matrix. Further, matrix conversion is carried out on the plurality of second target triples, and a fat-dissolving characteristic parameter matrix is obtained. Assume that the server has the following first and second clusters of characteristic parameters: first characteristic parameter cluster: freezing temperature parameters: average value-10 ℃, peak value-8 ℃ and valley value-12 ℃; freezing time parameters: cumulative value is 125 minutes, peak time point is 60 minutes, and distribution deviation is 2.5; ice crystal size parameters: peak 6.5 mm, valley 4 mm. Second characteristic parameter cluster: ultrasonic power parameters: average 55 w, peak 60 w, valley 50 w; microneedle process parameters: minimum value of 8 mm, maximum value of 12 mm; time to fat dissolution parameters: mean 30 minutes, peak time point (not calculated), distribution bias (not calculated). And then performing sequence conversion to convert parameters in the first characteristic parameter cluster and the second characteristic parameter cluster into sequences. Freezing temperature sequence: -10, -8, -12,; freezing time sequence: [125 min, 60 min, 2.5]; ice crystal size sequence: [6.5 mm, 4 mm ]; ultrasonic power sequence: [ 55W, 60W, 50W ]; microneedle process sequence: [8 mm, 12 mm ]; time sequence of fat-dissolving: [30 minutes, peak time point, distribution bias ]. And then aligning data, and ensuring that the lengths of the freezing temperature sequence, the freezing time sequence and the ice crystal size sequence are equal according to a preset rule. Freezing temperature sequence: -10, -8, -12,; freezing time sequence: [125 min, 60 min, 2.5]; ice crystal size sequence: [6.5 mm, 4 mm ]. Ultrasonic power sequence: [ 55W, 60W, 50W ]; microneedle process sequence: [8 mm, 12 mm ]; time sequence of fat-dissolving: [30 minutes, peak time point, distribution bias ]. And extracting target triples, wherein a plurality of first target triples are extracted from the aligned freezing temperature sequence, the aligned freezing time sequence and the aligned ice crystal size sequence according to a preset first triplet rule. Assuming that the first triplet rule is to extract the maximum value, the minimum value and the average value of each sequence, the server obtains the following first target triplet: a first target triplet: triplet 1 (-10 ℃,125 minutes, 6.5 mm); triplet 2 (-8 ℃,60 minutes, 4 mm); triplet 3 (-12 ℃, 2.5) without data. Finally, matrix mapping and conversion are performed. And performing matrix conversion on the first target triplet to obtain a freezing characteristic parameter matrix. Freezing characteristic parameter matrix: [ -10 ℃,125 minutes, 6.5 mm ]; [ -8 ℃,60 minutes, 4 mm ]; [ -12 ℃,2.5, no data ]. And performing similar sequence conversion, data alignment, extraction of target triples and matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix. Fat-dissolving characteristic parameter matrix: [55 Watts, 8 mm, 30 min ]; [60 watts, 12 millimeters, peak time point ]; [50 watts, no data, distribution bias ]. Through the processing, the server converts the original first characteristic parameter cluster and the second characteristic parameter cluster into a matrix form, so that subsequent data analysis and processing are facilitated. Each of the characteristic parameters is mapped into a row or column of the matrix, respectively, to form a characteristic parameter matrix. In this way, the server more conveniently performs statistics, analysis and comparison on the characteristic parameters, thereby obtaining deeper information and insight.
S104, inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes;
specifically, the server detects the model through a preset frozen fat-dissolving instrument state. The model may be composed of a plurality of components including a first codec network, a second codec network, a first classifier, and a second classifier. The purpose of these components is to extract features and make state predictions. The server inputs the freezing characteristic parameter matrix into a first encoding and decoding network, and extracts a first characteristic vector of the freezing characteristic parameter through an encoding process. Further, inputting the characteristic parameter matrix of the fat-soluble into a second encoding and decoding network, and extracting a second characteristic vector of the characteristic parameter of the fat-soluble through the encoding process. And finally, inputting the first feature vector into a first classifier, predicting the freezing state through the prediction process of the classifier, and obtaining a freezing state evaluation index. And simultaneously, inputting the second feature vector into a second classifier, predicting the fat dissolution state through the prediction process of the classifier, and obtaining a fat dissolution state evaluation index. For example, assume that the server has a freeze characterization parameter matrix and a fat-dissolving characterization parameter matrix as follows: freezing characteristic parameter matrix: [ -10 ℃,125 minutes, 6.5 mm ]; [ -8 ℃,60 minutes, 4 mm ]; [ -12 ℃,2.5, no data ]. Fat-dissolving characteristic parameter matrix: [55 Watts, 8 mm, 30 min ]; [60 watts, 12 millimeters, peak time point ]; [50 watts, no data, distribution bias ]. The server inputs the freezing characteristic parameter matrix into a first encoding and decoding network, and extracts a first characteristic vector of the freezing characteristic parameter as [0.2,0.8]. And inputting the characteristic parameter matrix of the dissolved fat into a second encoding and decoding network, and extracting a second characteristic vector of the characteristic parameter of the dissolved fat to be [0.6,0.4]. The server inputs the first feature vectors [0.2,0.8] into the first classifier, and the prediction result of the freezing state is obtained through the prediction process of the classifier to be good. And simultaneously, inputting a second characteristic vector [0.6,0.4] into a second classifier, and obtaining a predicted result of the fat-dissolving state as normal through a prediction process of the classifier. Therefore, according to a preset frozen fat-dissolving instrument state detection model, the server obtains good frozen state evaluation index and normal fat-dissolving state evaluation index.
S105, generating a first parameter adjustment set according to the freezing state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature, and the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients;
specifically, the server sets a plurality of freezing parameter thresholds, such as upper and lower limits of freezing temperature, maximum value of freezing time, and the like, according to the freezing state evaluation index. The server determines an adjustment value for each parameter by comparing with the actual parameter value. These adjustment values may be calculated based on algorithms such as degree of variance, weighted average, etc. The server generates a first parameter adjustment set according to the adjustment value of each parameter. The first set of parameter adjustments may include factors such as fit strength, surface contact area, and temperature. Then, the server generates a second parameter adjustment set according to the fat dissolution state evaluation index, and further, the server sets a plurality of fat dissolution parameter thresholds, such as a range of ultrasonic power, a minimum value of fat dissolution time, and the like, according to the fat dissolution state evaluation index. The server determines an adjustment value for each parameter by comparing with the actual parameter value. Finally, a second parameter adjustment set is generated based on the adjustment value for each parameter. The second parameter adjustment set may include factors such as energy input and output, ultrasound, and mechanical vibration stability coefficients. For example, assume that the server sets a threshold for the freezing parameter in the freezing temperature range of-15 ℃ to-5 ℃ and the freezing time is not more than 60 minutes. If the current freezing temperature is-10 ℃, the freezing time is 45 minutes, and the server calculates corresponding adjustment values. Freezing parameter adjustment value: the adjustment value of the freezing temperature=target temperature-current temperature= -8 ℃ (-10 ℃) =2 ℃; adjustment value of freezing time = target time-current time = 50 min-45 min = 5 min based on the adjustment value, the server generates the following first parameter adjustment set: the bonding force is adjusted to be medium; the surface contact area is adjusted to be larger; the temperature is adjusted to a low temperature. Assume that the threshold value of the fat dissolving parameter set by the server is that the ultrasonic power range is 50-70, and the fat dissolving time is not less than 20 minutes. If the current ultrasonic power is 60 and the fat dissolving time is 25 minutes, the server calculates the corresponding adjustment value. Lipid dissolution parameter adjustment value: an adjustment value of ultrasonic power=target power-current power=55-60= -5; adjusted value of fat-dissolving time = target time-current time = 20 min-25 min = -5 min. Based on the adjustment values, the server generates the following second parameter adjustment set: the energy input and output are adjusted to be high energy output; adjusting the ultrasonic wave to medium frequency; the mechanical vibration stability factor is adjusted to be relatively stable. In this embodiment, the server generates a first parameter adjustment set based on the freeze state evaluation index and a second parameter adjustment set based on the fat-soluble state evaluation index. These adjustment sets can be used as references to help optimize the effectiveness and outcome of the freeze-fat-dissolving process.
S106, performing freezing process state control on the target frozen fat-dissolving instrument based on the first parameter adjustment set, and performing fat-dissolving process state control on the target frozen fat-dissolving instrument through the second parameter adjustment set, so as to generate a target state control result.
Specifically, parameters such as bonding strength, surface contact area, temperature and the like in the set are adjusted according to the first parameters, and the freezing parameters of the target frozen fat-dissolving meter are correspondingly adjusted. The optimization of the freezing parameters is realized by adjusting the vacuum tightness, the size of the freezing area and the set value of the freezing temperature. And then, according to the parameters such as energy input and output, ultrasonic wave and mechanical vibration stability coefficient and the like in the second parameter adjustment set, correspondingly adjusting the fat dissolving parameters of the target frozen fat dissolving instrument. The energy intensity, the frequency and power of the ultrasonic wave and the stability of vibration are adjusted to optimize the setting of the fat dissolving parameters. And controlling the state of the freezing process and the state of the fat dissolving process based on the adjusted freezing parameters and the adjusted fat dissolving parameters. By monitoring and feedback control, stability of the freezing process, control of the freezing time and control of the ice crystal size are ensured. Meanwhile, the accurate control of the fat dissolving process is realized by accurately controlling the action intensity and frequency of ultrasonic waves, the control of the microneedle process and the control of the fat dissolving time. And finally, comprehensively analyzing the first state control result and the second state control result to obtain a target state control result. And comprehensively considering indexes such as freezing effect, fat dissolving effect, comfort level of a patient and the like, and further optimizing parameter adjustment and state control strategies. For example, assume that the target cryolipid-solubilizing instrument is used for facial fat-freezing and lipid-solubilizing treatment. According to the first parameter adjustment set, parameters such as freezing temperature, bonding strength, surface contact area and the like are adjusted by the server. By analyzing the patient's fat type and treatment requirements, the server sets the freezing temperature to-10 ℃ to ensure the freezing effect. Meanwhile, the server adjusts the vacuum tightness to improve the fitting force, and selects a proper freezing mask according to the size and shape of the facial area of the patient to ensure complete coverage of the target area. According to the second parameter adjustment set, the server adjusts parameters such as energy input and output, ultrasonic wave and mechanical vibration stability coefficients and the like. The server adjusts the power and energy output intensity of the energy input-output device according to the density and depth of fat so as to ensure proper fat dissolving effect. Meanwhile, the server sets the frequency and power of the ultrasonic waves to effectively break the fat cells in the fat dissolving process. In addition, by controlling the stability factor of the mechanical vibration, the server ensures stable vibration in the fat dissolving process, thereby improving the therapeutic effect. Based on the adjusted freezing parameters and fat dissolution parameters, the server starts the freezing process state control and the fat dissolution process state control. Through sensor and monitoring system inside the instrument, the temperature variation and the ice crystal size of server real-time supervision freezing in-process to adjust according to preset freezing time and ice crystal size target. Meanwhile, the server monitors the output power of ultrasonic waves and the control of the microneedle process so as to ensure the stability and accuracy of the fat dissolving process. Finally, the server obtains a target state control result by comprehensively analyzing the effect of the freezing process, the effect of the fat dissolving process and the feedback of the patient. The server evaluates a plurality of indexes such as freezing effect, fat dissolving effect, comfort level of the patient and the like, and adjusts and optimizes according to the comprehensive analysis results. For example, if the patient feedback is uncomfortable during freezing, the server fine-tunes the freezing temperature or the fitting force to improve the comfort of the treatment. Through the state control process and comprehensive analysis, the server can realize the accurate control of the freezing process and the fat dissolving process of the target frozen fat dissolving instrument and generate a target state control result meeting the treatment requirement. This means that the server can achieve better results and patient satisfaction in the freeze-fat-dissolving treatment.
In the embodiment of the invention, characteristic parameter extraction is respectively carried out on freezing parameter data and fat dissolving parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster; mapping the matrix to obtain a freezing characteristic parameter matrix and a fat-dissolving characteristic parameter matrix; inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes; according to the invention, the effective monitoring and control of the state of the frozen fat-dissolving instrument are realized by utilizing a deep learning technology, the intelligent management of the frozen fat-dissolving instrument is realized, the frozen parameters and the fat-dissolving parameters are precisely controlled, the function of the frozen fat-dissolving instrument can be exerted to the greatest extent, the possibility of misoperation is reduced, the service life of equipment is prolonged, the possible faults of the equipment in the operation process can be reduced to the greatest extent by precisely controlling the frozen parameters and the fat-dissolving parameters, and the state detection accuracy of the frozen fat-dissolving instrument and the accuracy of parameter adjustment are improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Acquiring state parameter data of a target frozen fat-dissolving instrument, and acquiring a plurality of frozen parameter attribute tags and a plurality of fat-dissolving parameter attribute tags;
(2) Acquiring a plurality of initial freezing parameters from the state parameter data according to the plurality of freezing parameter attribute tags, and acquiring a plurality of initial fat-dissolving parameters from the state parameter data according to the plurality of fat-dissolving parameter attribute tags;
(3) And carrying out freezing time sequence distribution integration on the plurality of initial freezing parameters to obtain freezing parameter data, and carrying out fat dissolving time sequence distribution integration on the plurality of initial fat dissolving parameters to obtain fat dissolving parameter data.
Specifically, the server can acquire state parameter data of the target frozen fat-dissolving instrument in real time through a sensor and a monitoring system in the instrument, wherein the state parameter data comprise parameters such as temperature, vacuum tightness, energy input and output and the like. The server defines a freezing parameter attribute tag and a fat-melting parameter attribute tag for describing different attributes of the freezing parameter and the fat-melting parameter. For example, the freezing parameter attribute tags may include freezing temperature, fitting force, and freezing area, while the fat-dissolving parameter attribute tags may include ultrasonic frequency, energy output intensity, vibration stability, and the like. Based on the plurality of freezing parameter attribute labels, the server extracts corresponding freezing parameter values from the state parameter data to obtain a plurality of initial freezing parameters. For example, if the server sets the freezing parameter attribute tag to be a freezing temperature and a bonding strength, the server obtains an initial freezing temperature of-10 ℃ and an initial bonding strength of 85% from the state parameter data. Further, according to the plurality of fat-dissolving parameter attribute tags, the server extracts corresponding fat-dissolving parameter values from the state parameter data to obtain a plurality of initial fat-dissolving parameters. For example, if the server sets the fat-dissolving parameter attribute tag to an ultrasonic frequency and an energy output intensity, the server acquires an initial ultrasonic frequency of 40kHz and an initial energy output intensity of 5W/cm from the state parameter data. Then, by carrying out freezing time sequence distribution integration on a plurality of initial freezing parameters, the server generates freezing parameter data, and dynamic adjustment and change are realized. For example, the server sets the freezing temperature to-8 ℃ at the beginning of the treatment, gradually decreases to-10 ℃ in the middle phase, and rises back to-5 ℃ in the end phase to meet the treatment needs and patient feedback. Further, through carrying out the time sequence distribution integration of the fat dissolution to a plurality of initial fat dissolution parameters, the server generates fat dissolution parameter data, and personalized adjustment is realized. For example, the server gradually increases the ultrasound power during the treatment to enhance the fat dissolving effect. Through the time sequence distribution integration, the server can optimize the freezing and fat dissolving process according to the fat distribution and the treatment target of the patient, so that better treatment effect and patient satisfaction are realized.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, constructing a plurality of first parameter distribution curves corresponding to the freezing parameter data according to a plurality of freezing parameter attribute tags, and constructing a plurality of second parameter distribution curves corresponding to the fat-dissolving parameter data according to a plurality of fat-dissolving parameter attribute tags;
s202, calculating curve characteristic values of each first parameter distribution curve to obtain a plurality of first curve characteristic values of each first parameter distribution curve, and calculating curve characteristic values of each second parameter distribution curve to obtain a plurality of second curve characteristic values of each second parameter distribution curve;
s203, generating a first characteristic parameter cluster according to a plurality of first curve characteristic values of each first parameter distribution curve, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters, and ice crystal size parameters;
s204, generating a second characteristic parameter cluster according to a plurality of second curve characteristic values of each second parameter distribution curve, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters, and lipolysis time parameters.
Specifically, the server acquires state parameter data of the target frozen fat-dissolving instrument and a plurality of frozen parameter attribute tags and fat-dissolving parameter attribute tags. The server extracts a plurality of initial freezing parameters and initial fat-dissolving parameters from the state parameter data according to the attribute tags. The server builds a plurality of first parameter distribution curves corresponding to the freezing parameter data aiming at the freezing parameter attribute tags, and builds a plurality of second parameter distribution curves corresponding to the fat-dissolving parameter data according to the fat-dissolving parameter attribute tags. And then, calculating the curve characteristic value of each first parameter distribution curve to obtain a plurality of first curve characteristic values, such as peak values, valley values, average values and the like, of each first parameter distribution curve. And similarly, calculating the curve characteristic value of each second parameter distribution curve to obtain a plurality of second curve characteristic values of each second parameter distribution curve. A first characteristic parameter cluster is generated based on a plurality of first curve characteristic values for each first parameter distribution curve, including a freezing temperature parameter, a freezing time parameter, and an ice crystal size parameter. Further, a second characteristic parameter cluster is generated based on a plurality of second curve characteristic values of each second parameter distribution curve, wherein the second characteristic parameter cluster comprises an ultrasonic power parameter, a microneedle process parameter and a fat dissolution time parameter. Assuming the server has a frozen fat-dissolving meter, a batch of relevant state parameter data is collected. The freezing parameter attribute tag comprises bonding strength, surface contact area and temperature, and the fat dissolving parameter attribute tag comprises energy input and output, ultrasonic wave and mechanical vibration stability coefficients. Examples of freeze parameter data: bonding strength: [20,25,18,22,23] (unit: N), surface contact area: [30,35,32,28,33] (unit: cm), temperature: [ -10, -8, -12, -9, -11] (units: degrees celsius); examples of lipid dissolution parameter data: energy input/output: [40,45,50,38,42] (unit: J), ultrasonic waves: [30,35,28,32,33] (unit: kHz), mechanical vibration stability coefficient: [0.6,0.5,0.7,0.8,0.6]. Based on these data, the server constructs a profile of the freezing and fat-dissolving parameters and calculates its eigenvalues. Taking freezing parameters as an example, the server obtains the distribution characteristics of the bonding strength, the surface contact area and the temperature by drawing a distribution curve of the bonding strength, the surface contact area and the temperature. For example, by plotting the distribution of the applied force, the server observes that the peak occurs near 20N, the trough near 18N, and the average value is about 21.6N. These characteristic values can be used for adjustment and control of the freezing parameters. Further, for the fat-dissolving parameters, the server obtains their characteristic values by plotting the distribution curves of the energy input and output, ultrasonic wave and mechanical vibration stability coefficients. For example, the energy input/output profile shows a peak value of about 45J, the ultrasonic profile shows a peak value of about 33kHz, and the mechanical vibration stability factor profile shows an average value of about 0.64. These characteristic values can be used for the adjustment and control of the fat-dissolving parameters. In summary, by using the actually collected data to construct a distribution curve of the freezing parameters and the fat-dissolving parameters and calculating the characteristic values thereof, the server can generate a specific first characteristic parameter cluster and a specific second characteristic parameter cluster, thereby providing actual control and optimization of the state of the target frozen fat-dissolving instrument
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, performing sequence conversion on a first characteristic parameter cluster to obtain a freezing temperature sequence, a freezing time sequence and an ice crystal size sequence, and performing sequence conversion on a second characteristic parameter cluster to obtain an ultrasonic power sequence, a microneedle process sequence and a fat dissolving time sequence;
s302, carrying out data alignment on a freezing temperature sequence, a freezing time sequence and an ice crystal size sequence, and extracting a plurality of first target triples according to a preset first triplet rule;
s303, carrying out data alignment on the ultrasonic power sequence, the microneedle process sequence and the fat-dissolving time sequence, and extracting a plurality of second target triples according to a preset second triplet rule;
s304, performing matrix conversion on the first target triplets to obtain a freezing characteristic parameter matrix, and performing matrix conversion on the second target triplets to obtain a fat-dissolving characteristic parameter matrix.
Specifically, the server obtains corresponding parameter data according to the freezing parameter attribute tags, such as bonding strength, surface contact area and temperature, and the fat dissolving parameter attribute tags, such as energy input and output, ultrasonic wave and mechanical vibration stability coefficients. Assume that the server has collected the following freeze parameter data and fat-dissolving parameter data: examples of freeze parameter data: bonding strength: [20,25,18,22,23] (unit: N), surface contact area: [30,35,32,28,33] (unit: cm), temperature: [ -10, -8, -12, -9, -11] (units: degrees celsius); examples of lipid dissolution parameter data: energy input/output: [40,45,50,38,42] (unit: J), ultrasonic waves: [30,35,28,32,33] (unit: kHz), mechanical vibration stability coefficient: [0.6,0.5,0.7,0.8,0.6]. The server uses the data to construct a first parameter profile corresponding to the freeze parameter data and a second parameter profile corresponding to the fat-dissolving parameter data. Taking the freezing parameters as an example, the server draws a distribution curve of corresponding parameter values for each freezing parameter attribute tag. For example, according to the data of the bonding strength, a distribution curve of the bonding strength and the frequency is drawn; drawing a distribution curve of the surface contact area and the frequency according to the data of the surface contact area; and drawing a temperature and frequency distribution curve according to the temperature data. Further, for the fat-dissolving parameters, the server draws a distribution curve of corresponding parameter values according to the fat-dissolving parameter attribute tags. Then, for each of the first parameter distribution curve and the second parameter distribution curve, the server performs curve characteristic value calculation to acquire more information. For example, for a first parameter profile (freeze parameter), the server calculates the characteristic values of the profile, such as peak, trough, mean, standard deviation, etc. These eigenvalues reflect the shape, center position, and degree of dispersion of the parameter distribution. For the second parameter profile (fat-dissolving parameter), the server may also calculate corresponding characteristic values, such as peak values, valley values, average values, standard deviations, etc. Based on the calculated characteristic values of the first parameter distribution curve and the second parameter distribution curve, the server generates a first characteristic parameter cluster and a second characteristic parameter cluster, and the freezing and fat-dissolving process is further optimized. For example, by curve eigenvalue calculation, the server gets the following first and second clusters of eigenvalues: first characteristic parameter cluster: freezing temperature parameters: -10 ℃ and freeze time parameter: 120 seconds, ice crystal size parameters: 50 microns; second characteristic parameter cluster: ultrasonic power parameters: 40W, microneedle process parameters: 2mm, fat-dissolving time parameter: 180 seconds. These feature parameter clusters represent important indicators of the freezing and fat-dissolving parameters in the optimization process. By adjusting these characteristic parameters, the server achieves more accurate freezing and fat-dissolving effects. For example, according to the first characteristic parameter cluster, the server controls the freezing temperature parameter to be-10 ℃ so as to ensure that the freezing process achieves the required low-temperature effect; setting the freezing time parameter to 120 seconds, and ensuring enough freezing time; and controlling the ice crystal size parameter to be 50 microns, so that the proper ice crystal size is formed in the freezing process. Further, according to the second characteristic parameter cluster, the server adjusts the ultrasonic power parameter to 40W, so that sufficient energy is provided in the fat dissolving process; setting the process parameters of the microneedles to be 2mm, and controlling the process depth of the microneedles; and controlling the fat-dissolving time parameter to be 180 seconds, so as to ensure sufficient fat-dissolving time. In summary, by constructing the parameter distribution curve and calculating the characteristic value, the server generates the first characteristic parameter cluster and the second characteristic parameter cluster, thereby optimizing the control and adjustment of the freezing and fat-dissolving process and realizing more accurate freezing and fat-dissolving effect.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, inputting a frozen characteristic parameter matrix and a fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model, wherein the frozen fat dissolving instrument state detection model comprises: a first codec network, a second codec network, a first classifier, and a second classifier;
s402, performing feature extraction on the frozen feature parameter matrix through a first encoding and decoding network to obtain a first feature vector, and performing feature extraction on the fat-soluble feature parameter matrix through a second encoding and decoding network to obtain a second feature vector;
s403, performing freezing state prediction on the first characteristic vector through a first classifier to obtain a freezing state evaluation index, and performing fat dissolution state prediction on the second characteristic vector through a second classifier to obtain a fat dissolution state evaluation index.
Specifically, the server frozen fat meter state detection model comprises a first encoding and decoding network, a second encoding and decoding network, a first classifier and a second classifier. The server takes the freezing characteristic parameter matrix and the fat-dissolving characteristic parameter matrix as input. The server extracts the characteristics of the frozen characteristic parameter matrix by using a first encoding and decoding network, and obtains a first characteristic vector from the frozen characteristic parameter matrix. This step maps the feature parameter matrix to a low-dimensional feature space through an encoding process and reconstructs the original feature parameter matrix through a decoding process. And simultaneously, performing feature extraction on the fat-soluble feature parameter matrix by using a second encoding and decoding network to obtain a second feature vector. The server then inputs the first feature vector into a first classifier that predicts the freeze state. Through model training, the classifier can learn the relations between different feature vectors and different freezing states and generate a freezing state evaluation index. Further, the server inputs the second feature vector into a second classifier, and the classifier predicts the fat dissolution state to obtain a fat dissolution state evaluation index. Through the process, the server can convert the freezing characteristic parameter matrix and the fat dissolving characteristic parameter matrix into the freezing state evaluation index and the fat dissolving state evaluation index by using a preset freezing fat dissolving instrument state detection model. The indicators can provide the operators with important information about the current state of the frozen fat-dissolving meter, and help them to make decisions and adjust operation parameters so as to achieve better frozen fat-dissolving effect. For example, assume that the server has a frozen fat-dissolving meter, whose freezing parameter attribute tags include freezing temperature, freezing time, and ice crystal size, and fat-dissolving parameter attribute tags include ultrasonic power, microneedle progress, and fat-dissolving time. The server collects a set of freeze characterization parameter data, such as: freezing temperature: -10, -12, -15, -18 ℃; freezing time: 20 minutes, 25 minutes, 30 minutes, 35 minutes; ice crystal size: small size, medium size and large size. At the same time, the server also collects a set of data of characteristic parameters of fat dissolution, for example: ultrasonic power: 30W,35W,40W,45W; microneedle process: 0.5mm,1.0mm,1.5mm,2.0mm; fat-dissolving time: 40 minutes, 45 minutes, 50 minutes, 55 minutes. And the server constructs a first parameter distribution curve corresponding to the freezing parameter data according to the freezing parameter attribute tag. For example, the server uses a histogram or kernel density estimation method to map the freezing temperature, freezing time, and ice crystal size distribution curve. Further, according to the lipid dissolution parameter attribute tag, the server constructs a second parameter distribution curve corresponding to the lipid dissolution parameter data, such as a distribution curve of ultrasonic power, microneedle process and lipid dissolution time. For each first parameter distribution curve, the server calculates curve characteristic values, such as calculating statistical indexes of average value, standard deviation, kurtosis, skewness and the like. The server thus obtains a plurality of first curve characteristic values for each first parameter distribution curve. Further, for each second parameter distribution curve, the server also performs curve characteristic value calculation to obtain a plurality of second curve characteristic values. Based on these characteristic values, the server generates a first cluster of characteristic parameters including a freezing temperature parameter, a freezing time parameter, and an ice crystal size parameter. Meanwhile, according to the characteristic values of the second parameter distribution curve, the server generates a second characteristic parameter cluster, wherein the second characteristic parameter cluster comprises an ultrasonic power parameter, a microneedle process parameter and a fat dissolving time parameter. And finally, inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model by the server. And through a first encoding and decoding network, the frozen feature parameter matrix is subjected to feature extraction to obtain a first feature vector. This vector contains important characteristic information about the freezing process. And obtaining a second feature vector through feature extraction of the fat-soluble feature parameter matrix through a second encoding and decoding network. This vector reflects the characteristics and changes of the lipid-dissolving parameters. The server then inputs the first feature vector into a first classifier that is used to predict the freeze state. Through training and learning, the classifier can judge the state of the freezing process according to the first feature vector and generate a corresponding freezing state evaluation index. Further, the server inputs the second feature vector into a second classifier, which is used to predict the fat-dissolving state. The classifier judges the state of the fat dissolving parameter according to different characteristic values of the second characteristic vector and generates a corresponding fat dissolving state evaluation index. Through the process, the server converts the freezing characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a freezing state evaluation index and a fat dissolving state evaluation index by using a preset freezing fat dissolving instrument state detection model. The indicators can provide the operators with important information about the current state of the frozen fat-dissolving meter, and help them make decisions and adjust operation parameters so as to achieve better frozen fat-dissolving effect. For example, when the frozen feature parameter matrix is input, the first codec network may extract features, resulting in a first feature vector. This vector may contain information such as a freezing temperature of-15 ℃, a freezing time of 30 minutes, and a medium ice crystal size. The first classifier of the server can predict whether the freezing state is good or excellent according to the feature vector and generate a corresponding freezing state evaluation index. Further, for the input of the fat-soluble feature parameter matrix, the second codec network may extract features to obtain a second feature vector. This vector may contain information such as 40W of ultrasonic power, 1.0mm of microneedle progression, 50 minutes of lipolysis time. The second classifier can predict whether the fat dissolution state is moderate or good according to the feature vector, and generate a corresponding fat dissolution state evaluation index. Through such a state detection process, the server obtains the frozen state evaluation index and the fat-dissolving state evaluation index, thereby evaluating and monitoring the state of the frozen fat-dissolving instrument.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Matching a plurality of freezing parameter thresholds according to the freezing state evaluation index, and matching a plurality of fat dissolving parameter thresholds according to the fat dissolving state evaluation index;
(2) Calculating a first parameter adjustment value for each of the plurality of freeze parameters according to the plurality of freeze parameter thresholds, and calculating a second parameter adjustment value for each of the plurality of fat-dissolving parameters according to the plurality of fat-dissolving parameter thresholds;
(3) Generating a first parameter adjustment set according to the first parameter adjustment value of each freezing parameter, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature;
(4) Generating a second parameter adjustment set according to the second parameter adjustment value of each fat-dissolving parameter, wherein the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients.
Specifically, the server matches a plurality of freeze parameter thresholds according to the freeze state evaluation index. These thresholds may be determined based on previous experience and experimental results. For example, if the freeze status evaluation index indicates that the freezing effect is poor, the server matches a lower freezing temperature and a longer freezing time as the freezing parameter thresholds. Further, the server matches a plurality of lipid dissolution parameter thresholds according to the lipid dissolution state evaluation index. These thresholds may also be determined based on experimental and clinical data. For example, if the fat dissolution status evaluation index shows that the fat dissolution effect is too strong or too weak, the server matches the appropriate ultrasonic power and microneedle process as the fat dissolution parameter threshold. The server calculates a first parameter adjustment value for each refrigeration parameter according to the plurality of refrigeration parameter thresholds. These values may be determined from the gap between the threshold and the target state. For example, if the freezing temperature is below a threshold, the server calculates a value that requires an increase in temperature to achieve the adjustment of the target state. Further, the server calculates a second parameter adjustment value for each of the fat-dissolving parameters based on the plurality of fat-dissolving parameter thresholds. These values may be determined from the difference between the threshold and the target state. For example, if the ultrasonic power is too high, the server calculates the value that the power needs to be reduced to bring the fat-dissolving parameters to the desired adjustment. Based on the calculated first parameter adjustment value, the server generates a first parameter adjustment set, wherein the first parameter adjustment set comprises freezing parameters such as bonding strength, surface contact area, temperature and the like. These adjustment sets can help the operator accurately adjust parameters of the freezer to achieve the desired freezing effect. Further, according to the calculated second parameter adjustment value, the server generates a second parameter adjustment set, wherein the second parameter adjustment set comprises energy input and output, ultrasonic waves, mechanical vibration stability coefficients and other fat-dissolving parameters. The adjustment sets can guide operators to accurately adjust parameters of the fat dissolving instrument so as to realize ideal fat dissolving effect. For example, assume that the server is processing data for a frozen lipolyzer and that the server has obtained the following data and evaluation metrics: frozen state evaluation index: freezing effect score (range: 0-10), fat dissolution status evaluation index: fat dissolution scores (range: 0-10). The server also has predetermined thresholds for freezing and fat dissolution parameters, as follows: freezing parameter threshold: freezing temperature threshold: -10 ℃ and freezing time threshold: 30 minutes, ice crystal size threshold: 2mm; threshold of lipid dissolution parameter: ultrasonic power threshold: 50%, microneedle process threshold: 5mm, lipid dissolution time threshold: 45 minutes. Based on these data and the threshold values, the server calculates an adjustment value for each of the freezing parameters and the fat-dissolving parameters and generates a corresponding parameter adjustment set. For example, the server obtains a freezing effect score of 7 based on the freezing state evaluation index and the freezing effect score. Based on the difference between the threshold and the score, the server calculates a first parameter adjustment value for the freezing temperature and the freezing time. Assuming that the difference between the score and the threshold is-2, the server sets the temperature adjustment value to +2℃, indicating that the freezing temperature needs to be increased by 2 ℃. Further, the server sets the time adjustment value to +10 minutes, indicating that the freezing time needs to be increased by 10 minutes. For the fat dissolution parameters, the server obtains a fat dissolution score of 8, assuming that the fat dissolution score is based on the fat dissolution state evaluation index and the fat dissolution score. Based on the difference between the threshold and the score, the server calculates an ultrasound power and a second parameter adjustment value for the microneedle process. Assuming that the difference between the score and the threshold is +2, the server sets the power adjustment value to-5%, indicating that the ultrasonic power needs to be reduced by 5%. Further, the server sets the progress adjustment value to-2 mm, indicating that the microneedle progress needs to be reduced by 2mm. Based on the adjustment values calculated above, the server generates a corresponding parameter adjustment set: a first set of parameter adjustments: freezing temperature adjustment: +2℃, freezing time adjustment: +10 minutes, ice crystal size parameters remained unchanged; a second set of parameter adjustments: and (3) ultrasonic power adjustment: -5%, microneedle process adjustment: -2mm, the fat-dissolving time parameter remains unchanged. Thus, the server calculates specific parameter adjustment values and corresponding parameter adjustment sets according to the freezing state evaluation index, the fat dissolution state evaluation index and preset freezing and fat dissolution parameter thresholds. Through the adjustment sets, the server carries out parameter adjustment on the freezing and fat-dissolving instrument according to actual conditions. For example, according to the freezing temperature adjustment value and the freezing time adjustment value in the first parameter adjustment set, the server adjusts the temperature and the time of the freezing instrument appropriately to improve the freezing effect. Further, according to the ultrasonic power adjustment value and the microneedle process adjustment value in the second parameter adjustment set, the server adjusts the power and the process of the fat dissolving instrument so as to achieve an ideal fat dissolving effect. For example, assume that the server obtains a freezing effect score of 7 based on the freezing state evaluation index and the freezing effect score, and calculates a freezing temperature adjustment value of +2 ℃, and a freezing time adjustment value of +10 minutes. The server adjusts the freezing temperature from a preset-10 ℃ to-8 ℃ according to the adjustment values, and increases the freezing time from 30 minutes to 40 minutes to improve the freezing effect. Further, assuming that the fat dissolution degree score is 8 according to the fat dissolution state evaluation index and the fat dissolution degree score, the server calculates an ultrasonic power adjustment value of-5% and a microneedle process adjustment value of-2 mm. According to the adjustment values, the server reduces the ultrasonic power from 50% to 45% and reduces the microneedle process from 5mm to 3mm, so as to achieve a more ideal fat dissolving effect.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Performing freezing parameter adjustment on the target frozen fat-dissolving instrument based on the first parameter adjustment set, and performing fat-dissolving parameter adjustment on the target frozen fat-dissolving instrument based on the second parameter adjustment set;
(2) Performing freezing process state control on the target frozen fat-dissolving instrument to obtain a first state control result, and performing fat-dissolving process state control on the target frozen fat-dissolving instrument to obtain a second state control result;
(3) And comprehensively analyzing the first state control result and the second state control result to obtain a target state control result.
Specifically, according to the first parameter adjustment set, the freezing parameters of the freezing instrument are adjusted. For example, according to the freezing temperature adjustment value, the freezing time adjustment value and the ice crystal size adjustment value in the first parameter adjustment set, the temperature, the time and the freezing mode of the target frozen fat-liquoring instrument are correspondingly adjusted. Further, according to the second parameter adjustment set, the fat dissolving parameters of the fat dissolving instrument are adjusted. For example, according to the ultrasonic power adjustment value, the microneedle process adjustment value and the fat dissolution time adjustment value in the second parameter adjustment set, the ultrasonic power, the microneedle process and the fat dissolution time of the target frozen fat dissolution instrument are correspondingly adjusted. And the server controls the state of the freezing process of the target frozen fat-dissolving instrument. By monitoring and controlling various parameters of the freezing instrument, such as temperature, time, ice crystal size, etc., real-time control of the freezing process can be achieved. According to the set freezing parameters and the adjusted parameter values, the system can accurately control the freezing process, and stability and controllability of the freezing effect are ensured. Thus, a first state control result is obtained. Further, the state control of the fat dissolving process is carried out on the target frozen fat dissolving instrument. By monitoring and controlling various parameters of the fat dissolving instrument, such as ultrasonic power, microneedle process, fat dissolving time and the like, the real-time control of the fat dissolving process can be realized. According to the set fat dissolving parameters and the adjusted parameter values, the system can accurately control the fat dissolving process, and stability and controllability of the fat dissolving effect are ensured. Thus, the second state control result is obtained. And finally, comprehensively analyzing the first state control result and the second state control result to obtain a target state control result. The comprehensive analysis can be based on actual values of various parameters, feedback information in the control process and set target standards. Through comprehensive evaluation and judgment of the state control result, whether the target frozen fat-dissolving instrument achieves the expected state control effect can be determined. For example, assume that the server obtains the following adjustment values based on the first parameter adjustment set: the freezing temperature was adjusted to-5 ℃, the freezing time was adjusted to +10 minutes, and the ice crystal size was adjusted to +20%. According to the second parameter adjustment set, the server obtains the following adjustment values: the ultrasonic power adjustment value is +15%, the microneedle process adjustment value is-2 mm, and the fat dissolving time adjustment value is +5 minutes. Based on these adjustment values, the server performs parameter adjustment on the target frozen fat-dissolving device. The temperature of the freezer will be adjusted to the original set temperature minus 5 ℃, the freezing time will be extended by 10 minutes and the ice crystal size will be increased by 20%. Meanwhile, the ultrasonic power of the fat dissolving instrument is increased by 15%, the microneedle process is reduced by 2mm, and the fat dissolving time is prolonged by 5 minutes. The server performs state control of the freezing process. The output signals of the controller are adjusted in real time by monitoring parameters such as the temperature, the freezing time, the ice crystal size and the like of the instrument so as to ensure the stability and the accuracy of the parameters in the freezing process. The server controls the freezing process by continuous adjustment and feedback control to achieve the intended freezing effect. Meanwhile, the server also performs state control on the fat dissolving process. The output signals of the controller are regulated in real time by monitoring parameters such as ultrasonic power, microneedle process, fat dissolving time and the like of the instrument, so that the stability and the accuracy of the parameters in the fat dissolving process are ensured. Through continuous adjustment and feedback control, the server controls the fat dissolving process to achieve the expected fat dissolving effect. And comprehensively analyzing a first state control result of the freezing process and a second state control result of the fat dissolving process, and obtaining a target state control result by the server. This result will take into account the effect of various parameter adjustments and controls during freezing and fat-liquoring, as well as preset target criteria. Through comprehensive evaluation, the server judges whether the target frozen fat-dissolving instrument achieves the expected state control effect, and further adjusts and optimizes according to the needs. For example, through comprehensive analysis, the server obtains that the target state control result is that the temperature and time control in the freezing process are good, the ice crystal size accords with the expected target, the ultrasonic power and the microneedle process adjustment in the fat dissolving process are effective, and the fat dissolving time accords with the preset target. The method shows that the target frozen fat-dissolving instrument has good effects on parameter adjustment and state control of freezing and fat-dissolving processes, and achieves the expected target state control result. In summary, based on the first parameter adjustment set and the second parameter adjustment set, the server performs parameter adjustment on the target frozen fat-dissolving device, and achieves the expected effect through the state control of the freezing and fat-dissolving process. And comprehensively analyzing control results of the freezing and fat dissolving processes, and obtaining a target state control result by the server so as to evaluate the performance and effect of the frozen fat dissolving instrument.
The method for detecting the state of the freeze-thaw apparatus in the embodiment of the present invention is described above, and the following describes a state detection device of the freeze-thaw apparatus in the embodiment of the present invention, referring to fig. 5, one embodiment of the state detection device of the freeze-thaw apparatus in the embodiment of the present invention includes:
the obtaining module 501 is configured to obtain state parameter data of a target frozen fat-dissolving instrument, and perform state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
the extracting module 502 is configured to extract the characteristic parameters of the freezing parameter data and the fat-dissolving parameter data respectively, to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, where the first characteristic parameter cluster includes: freezing temperature parameters, freezing time parameters and ice crystal size parameters, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
a conversion module 503, configured to perform matrix mapping on the first feature parameter cluster to obtain a frozen feature parameter matrix, and perform matrix conversion on the second feature parameter cluster to obtain a fat-soluble feature parameter matrix;
The detection module 504 is configured to input the frozen characteristic parameter matrix and the fat-dissolving characteristic parameter matrix into a preset frozen fat-dissolving instrument state detection model for state detection, so as to obtain a frozen state evaluation index and a fat-dissolving state evaluation index;
the generating module 505 is configured to generate a first parameter adjustment set according to the freezing state evaluation index, and generate a second parameter adjustment set according to the fat-dissolving state evaluation index, where the first parameter adjustment set includes bonding strength, surface contact area, and temperature, and the second parameter adjustment set includes energy input and output, ultrasonic wave, and mechanical vibration stability coefficient;
the control module 506 is configured to perform a refrigeration process state control on the target frozen fat-dissolving instrument based on the first parameter adjustment set, and perform a fat-dissolving process state control on the target frozen fat-dissolving instrument through the second parameter adjustment set, so as to generate a target state control result.
Through the cooperation of the components, characteristic parameter extraction is respectively carried out on the freezing parameter data and the fat dissolving parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster; mapping the matrix to obtain a freezing characteristic parameter matrix and a fat-dissolving characteristic parameter matrix; inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes; according to the invention, the effective monitoring and control of the state of the frozen fat-dissolving instrument are realized by utilizing a deep learning technology, the intelligent management of the frozen fat-dissolving instrument is realized, the frozen parameters and the fat-dissolving parameters are precisely controlled, the function of the frozen fat-dissolving instrument can be exerted to the greatest extent, the possibility of misoperation is reduced, the service life of equipment is prolonged, the possible faults of the equipment in the operation process can be reduced to the greatest extent by precisely controlling the frozen parameters and the fat-dissolving parameters, and the state detection accuracy of the frozen fat-dissolving instrument and the accuracy of parameter adjustment are improved.
Fig. 5 above describes the state detection device of the freeze-fat liquoring device in the embodiment of the present invention in detail from the viewpoint of a modularized functional entity, and the state detection device of the freeze-fat liquoring device in the embodiment of the present invention is described in detail from the viewpoint of hardware processing.
Fig. 6 is a schematic structural diagram of a state detection device of a frozen fat-dissolving device according to an embodiment of the present invention, where the state detection device 600 of the frozen fat-dissolving device may have relatively large differences according to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the state detection apparatus 600 of the frozen fat meter. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the state detection device 600 of the frozen lipolyzer.
The state detection device 600 of the frozen lipolyzer may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the configuration of the state detection device of the frozen lipolyzer shown in fig. 6 is not limiting of the state detection device of the frozen lipolyzer and may include more or fewer components than shown, or may be combined with certain components or a different arrangement of components.
The invention also provides a state detection device of the frozen fat-dissolving instrument, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the state detection method of the frozen fat-dissolving instrument in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or may be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the method for detecting a state of the frozen fat-dissolving meter.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The method for detecting the state of the frozen fat-dissolving instrument is characterized by comprising the following steps of:
acquiring state parameter data of a target frozen fat-dissolving instrument, and carrying out state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
and respectively extracting characteristic parameters of the freezing parameter data and the fat-dissolving parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters and ice crystal size parameters, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
Performing matrix mapping on the first characteristic parameter cluster to obtain a frozen characteristic parameter matrix, and performing matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix;
inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model for state detection to obtain a frozen state evaluation index and a fat dissolving state evaluation index;
generating a first parameter adjustment set according to the frozen state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature, and the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients;
and controlling the state of the freezing process of the target frozen fat-dissolving instrument based on the first parameter adjustment set, controlling the state of the fat-dissolving process of the target frozen fat-dissolving instrument through the second parameter adjustment set, and generating a target state control result.
2. The method for detecting the state of a frozen fat-melting instrument according to claim 1, wherein the steps of obtaining the state parameter data of the target frozen fat-melting instrument, and performing state attribute parameter segmentation on the state parameter data to obtain the frozen parameter data and the fat-melting parameter data, comprise:
Acquiring state parameter data of a target frozen fat-dissolving instrument, and acquiring a plurality of frozen parameter attribute tags and a plurality of fat-dissolving parameter attribute tags;
acquiring a plurality of initial freezing parameters from the state parameter data according to the plurality of freezing parameter attribute tags, and acquiring a plurality of initial fat-dissolving parameters from the state parameter data according to the plurality of fat-dissolving parameter attribute tags;
and carrying out freezing time sequence distribution integration on the plurality of initial freezing parameters to obtain freezing parameter data, and carrying out fat dissolving time sequence distribution integration on the plurality of initial fat dissolving parameters to obtain fat dissolving parameter data.
3. The method for detecting a state of a frozen fat-melting instrument according to claim 2, wherein the extracting the characteristic parameters of the frozen parameter data and the fat-melting parameter data to obtain a first characteristic parameter cluster and a second characteristic parameter cluster includes:
constructing a plurality of first parameter distribution curves corresponding to the freezing parameter data according to the plurality of freezing parameter attribute tags, and constructing a plurality of second parameter distribution curves corresponding to the fat-dissolving parameter data according to the plurality of fat-dissolving parameter attribute tags;
Calculating curve characteristic values of each first parameter distribution curve to obtain a plurality of first curve characteristic values of each first parameter distribution curve, and calculating curve characteristic values of each second parameter distribution curve to obtain a plurality of second curve characteristic values of each second parameter distribution curve;
generating a first characteristic parameter cluster according to a plurality of first curve characteristic values of each first parameter distribution curve, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters, and ice crystal size parameters;
generating a second characteristic parameter cluster according to a plurality of second curve characteristic values of each second parameter distribution curve, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters, and lipolysis time parameters.
4. The method for detecting the state of a frozen fat-dissolving instrument according to claim 1, wherein the performing matrix mapping on the first feature parameter cluster to obtain a frozen feature parameter matrix, and performing matrix conversion on the second feature parameter cluster to obtain a fat-dissolving feature parameter matrix comprises:
performing sequence conversion on the first characteristic parameter cluster to obtain a freezing temperature sequence, a freezing time sequence and an ice crystal size sequence, and performing sequence conversion on the second characteristic parameter cluster to obtain an ultrasonic power sequence, a microneedle process sequence and a fat dissolving time sequence;
Data alignment is carried out on the freezing temperature sequence, the freezing time sequence and the ice crystal size sequence, and a plurality of first target triples are extracted according to a preset first triplet rule;
data alignment is carried out on the ultrasonic power sequence, the microneedle process sequence and the fat-dissolving time sequence, and a plurality of second target triples are extracted according to a preset second triplet rule;
and performing matrix conversion on the plurality of first target triples to obtain a freezing characteristic parameter matrix, and performing matrix conversion on the plurality of second target triples to obtain a fat-dissolving characteristic parameter matrix.
5. The method for detecting the state of a frozen fat-dissolving instrument according to claim 1, wherein the step of inputting the frozen characteristic parameter matrix and the fat-dissolving characteristic parameter matrix into a preset frozen fat-dissolving instrument state detection model to perform state detection to obtain a frozen state evaluation index and a fat-dissolving state evaluation index comprises the steps of:
inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model, wherein the frozen fat dissolving instrument state detection model comprises the following components: a first codec network, a second codec network, a first classifier, and a second classifier;
Extracting the characteristics of the frozen characteristic parameter matrix through the first encoding and decoding network to obtain a first characteristic vector, and extracting the characteristics of the fat-soluble characteristic parameter matrix through the second encoding and decoding network to obtain a second characteristic vector;
and predicting the freezing state of the first feature vector through the first classifier to obtain a freezing state evaluation index, and predicting the fat dissolution state of the second feature vector through the second classifier to obtain a fat dissolution state evaluation index.
6. The method according to claim 1, wherein generating a first parameter adjustment set according to the frozen state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index comprises:
matching a plurality of freezing parameter thresholds according to the freezing state evaluation index, and matching a plurality of fat-dissolving parameter thresholds according to the fat-dissolving state evaluation index;
calculating a first parameter adjustment value for each refrigeration parameter according to the plurality of refrigeration parameter thresholds, and calculating a second parameter adjustment value for each fat-melting parameter according to the plurality of fat-melting parameter thresholds;
Generating a first parameter adjustment set according to the first parameter adjustment value of each freezing parameter, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature;
generating a second parameter adjustment set according to the second parameter adjustment value of each fat-dissolving parameter, wherein the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients.
7. The method according to claim 1, wherein the performing the freezing process state control on the target frozen fat-dissolving meter based on the first parameter adjustment set and performing the fat-dissolving process state control on the target frozen fat-dissolving meter through the second parameter adjustment set, generating a target state control result includes:
performing freezing parameter adjustment on the target frozen fat-dissolving instrument based on the first parameter adjustment set, and performing fat-dissolving parameter adjustment on the target frozen fat-dissolving instrument based on the second parameter adjustment set;
performing freezing process state control on the target frozen fat-dissolving instrument to obtain a first state control result, and performing fat-dissolving process state control on the target frozen fat-dissolving instrument to obtain a second state control result;
And comprehensively analyzing the first state control result and the second state control result to obtain a target state control result.
8. A state detection device of a frozen fat-melting instrument, characterized in that the state detection device of the frozen fat-melting instrument comprises:
the acquisition module is used for acquiring state parameter data of the target frozen fat-dissolving instrument, and carrying out state attribute parameter segmentation on the state parameter data to obtain frozen parameter data and fat-dissolving parameter data;
the extraction module is used for extracting characteristic parameters of the freezing parameter data and the fat-dissolving parameter data respectively to obtain a first characteristic parameter cluster and a second characteristic parameter cluster, wherein the first characteristic parameter cluster comprises: freezing temperature parameters, freezing time parameters and ice crystal size parameters, wherein the second characteristic parameter cluster comprises: ultrasonic power parameters, microneedle process parameters and fat dissolution time parameters;
the conversion module is used for performing matrix mapping on the first characteristic parameter cluster to obtain a frozen characteristic parameter matrix, and performing matrix conversion on the second characteristic parameter cluster to obtain a fat-soluble characteristic parameter matrix;
the detection module is used for inputting the frozen characteristic parameter matrix and the fat dissolving characteristic parameter matrix into a preset frozen fat dissolving instrument state detection model for state detection to obtain frozen state evaluation indexes and fat dissolving state evaluation indexes;
The generation module is used for generating a first parameter adjustment set according to the freezing state evaluation index and generating a second parameter adjustment set according to the fat dissolution state evaluation index, wherein the first parameter adjustment set comprises bonding strength, surface contact area and temperature, and the second parameter adjustment set comprises energy input and output, ultrasonic waves and mechanical vibration stability coefficients;
and the control module is used for controlling the state of the freezing process of the target frozen fat-dissolving instrument based on the first parameter adjustment set, controlling the state of the fat-dissolving process of the target frozen fat-dissolving instrument through the second parameter adjustment set, and generating a target state control result.
9. A state detection apparatus of a frozen fat-melting instrument, characterized in that the state detection apparatus of a frozen fat-melting instrument comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the state detection device of the frozen lipolysis instrument to perform the state detection method of the frozen lipolysis instrument of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the method of detecting the state of a frozen fat-lyzer according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310714275.0A CN116439815B (en) | 2023-06-16 | 2023-06-16 | State detection method and device for frozen fat-dissolving instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310714275.0A CN116439815B (en) | 2023-06-16 | 2023-06-16 | State detection method and device for frozen fat-dissolving instrument |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116439815A true CN116439815A (en) | 2023-07-18 |
| CN116439815B CN116439815B (en) | 2023-08-18 |
Family
ID=87125960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310714275.0A Active CN116439815B (en) | 2023-06-16 | 2023-06-16 | State detection method and device for frozen fat-dissolving instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116439815B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013180554A2 (en) * | 2012-06-01 | 2013-12-05 | 노슨(Nohsn) | Lipid removal system accounting for real-time patient body state information |
| CN113295925A (en) * | 2021-05-08 | 2021-08-24 | 上海微创医疗器械（集团）有限公司 | State detection and control device |
| CN113486586A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment health state evaluation method and device, computer equipment and storage medium |
| CN114271923A (en) * | 2020-09-28 | 2022-04-05 | 上海微创惟美医疗科技(集团)有限公司 | State detection and control method, device and medium |
| WO2022089111A1 (en) * | 2020-10-30 | 2022-05-05 | 上海微创惟美医疗科技(集团)有限公司 | Fat freezing and reducing device, and readable storage medium |
| CN115826645A (en) * | 2023-02-16 | 2023-03-21 | 北京新科以仁科技发展有限公司 | Temperature control method, device, equipment and storage medium of laser |
| WO2023082862A1 (en) * | 2021-11-10 | 2023-05-19 | 上海微创惟美医疗科技(集团)有限公司 | Temperature control method and apparatus for medical instrument, and therapeutic apparatus |
| CN116236275A (en) * | 2022-12-30 | 2023-06-09 | 武汉锐科光纤激光技术股份有限公司 | Control method and device of fat dissolving instrument, storage medium and electronic device |
| WO2023102644A1 (en) * | 2021-12-09 | 2023-06-15 | Medtronic Cryocath Lp | Method for optimization of cooling power for cryoablation |
-
2023
- 2023-06-16 CN CN202310714275.0A patent/CN116439815B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013180554A2 (en) * | 2012-06-01 | 2013-12-05 | 노슨(Nohsn) | Lipid removal system accounting for real-time patient body state information |
| CN114271923A (en) * | 2020-09-28 | 2022-04-05 | 上海微创惟美医疗科技(集团)有限公司 | State detection and control method, device and medium |
| WO2022089111A1 (en) * | 2020-10-30 | 2022-05-05 | 上海微创惟美医疗科技(集团)有限公司 | Fat freezing and reducing device, and readable storage medium |
| CN113295925A (en) * | 2021-05-08 | 2021-08-24 | 上海微创医疗器械（集团）有限公司 | State detection and control device |
| CN113486586A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment health state evaluation method and device, computer equipment and storage medium |
| WO2023082862A1 (en) * | 2021-11-10 | 2023-05-19 | 上海微创惟美医疗科技(集团)有限公司 | Temperature control method and apparatus for medical instrument, and therapeutic apparatus |
| WO2023102644A1 (en) * | 2021-12-09 | 2023-06-15 | Medtronic Cryocath Lp | Method for optimization of cooling power for cryoablation |
| CN116236275A (en) * | 2022-12-30 | 2023-06-09 | 武汉锐科光纤激光技术股份有限公司 | Control method and device of fat dissolving instrument, storage medium and electronic device |
| CN115826645A (en) * | 2023-02-16 | 2023-03-21 | 北京新科以仁科技发展有限公司 | Temperature control method, device, equipment and storage medium of laser |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116439815B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110377447B (en) | Abnormal data detection method and device and server | |
| CN111837194A (en) | System and method for predicting a health state of a patient | |
| CN116439815B (en) | State detection method and device for frozen fat-dissolving instrument | |
| KR102336199B1 (en) | Ablation system | |
| CN112734014A (en) | Experience playback sampling reinforcement learning method and system based on confidence upper bound thought | |
| CN114587565B (en) | Temperature control method and system in radio frequency ablation | |
| WO2021164537A1 (en) | Method, apparatus, device and system for controlling grinding of bone, and storage medium | |
| CN116440425A (en) | Intelligent adjusting method and system of LED photodynamic therapeutic instrument | |
| CN115565697A (en) | Perioperative period process monitoring and control system based on data analysis | |
| EP3932632B1 (en) | Sensor-based shaving systems and methods of analyzing a user's shave event for determining a unique threshold value of the user | |
| EP4260828A1 (en) | Radio-frequency parameter configuration method, apparatus and system, and computer-readable storage medium | |
| US11115923B2 (en) | Method and control arrangement for controlling a response time of a wireless sensor device | |
| CN110022246A (en) | Distributed type assemblies equipment power dissipation monitoring method, device, system and associated component | |
| CN116269738B (en) | Intelligent control method, device, equipment and storage medium of radio frequency therapeutic apparatus | |
| WO2023221462A1 (en) | Sleep aid control method and device of air conditioner, and air conditioner | |
| CN109545365A (en) | Data collection system of the microwave therapy apparatus in the clinical application of hals,Nasen und Ohrenheilkunde | |
| CN114052513B (en) | Cooking processing method and device, household appliance and storage medium | |
| CN115191983A (en) | Beauty instrument control method, storage medium and electronic device | |
| CN115218399A (en) | Control method and device of indoor unit and air conditioner | |
| CN105125172B (en) | Analgesia control method and its device based on face-image identification | |
| CN117375177B (en) | Power supply management method, device, equipment and storage medium of millimeter wave therapeutic instrument | |
| CN118155805B (en) | Control method and device of ultrasonic embolism recanalization operation system | |
| CN117442895B (en) | Ultrasonic automatic control method and system based on machine learning | |
| CN117482389B (en) | Output power adjusting method, beauty instrument, storage medium and electronic equipment | |
| CN117482391B (en) | Output power adjusting method, beauty instrument, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |