CN109886500A - Method and apparatus for determining processing technology information - Google Patents
Method and apparatus for determining processing technology information Download PDFInfo
- Publication number
- CN109886500A CN109886500A CN201910165217.0A CN201910165217A CN109886500A CN 109886500 A CN109886500 A CN 109886500A CN 201910165217 A CN201910165217 A CN 201910165217A CN 109886500 A CN109886500 A CN 109886500A
- Authority
- CN
- China
- Prior art keywords
- information
- individual
- population
- processing technology
- fitness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for determining processing technology information.One specific embodiment of this method includes: to obtain target raw material information and target processing environment information;Random to generate population, the individual in population includes the processing technology information of target raw material information, target processing environment information and generation;Execute following cross and variation operation;Processing technology information in the maximum individual of fitness in population is determined as optimal processing technology information.The embodiment, which realizes, automatically determines optimal processing technology information corresponding with target raw material information and target processing environment information.
Description
Technical field
The invention relates to field of computer technology, and in particular to for determining the method and dress of processing technology information
It sets.
Background technique
In the prior art, the production technology of many industry is mostly summarized passing knowhow by expert and is obtained.However this
The production technology that kind mode obtains depends critically upon expert personal experience, often has biggish tuning space.This phenomenon exists
It is particularly evident in flue-cured tobacco industry.After tobacco leaf is mature, tobacco grower toasts after picking tobacco leaf, and once baking can continue to count
It.The baking process of tobacco leaf has an important influence final quality of tobacco, for each batch tobacco leaf, needs according to original cigarette
Leaf maturity, tobacco leaf position, tobacco variety, dry-bulb temperature, wet-bulb temperature, oven type etc. set different baking process,
The most important factor of middle baking process is baking time and baking temperature.General tobacco grower can engage the baker of profession to dry
Roasting operation, but because of baker's level difference, it bakes the quality of tobacco come and has bigger difference.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for determining processing technology information.
In a first aspect, the embodiment of the present application provides a kind of method for determining processing technology information, this method comprises:
Obtain target raw material information and target processing environment information;Random to generate population, the individual in population includes target raw material
The processing technology information of information, target processing environment information and generation;Execute following cross and variation operation: in population
Individual input product quality score computation model trained in advance is obtained product quality score corresponding with the individual by body,
And product quality score corresponding with the individual is determined as to the fitness of the individual;According to the adaptation of individual each in population
Degree chooses at least one candidate individual;Selected candidate individual is intersected and/or makes a variation to obtain at least one next generation
Individual;With the individual at least one obtained next-generation individual Population Regeneration;Cross and variation operation is continued to execute until full
Sufficient preset stopping condition;Processing technology information in the maximum individual of fitness in population is determined as optimal processing technology letter
Breath.
In some embodiments, this method further include: according to processing technology indicated by optimal processing technology information to mesh
Raw material indicated by mark raw material information are processed in the processing environment indicated by target processing environment information.
In some embodiments, product quality score computation model is that training obtains in advance by following training step:
It determines the model structure of initial product mass fraction computation model and initializes the mould of initial product mass fraction computation model
Shape parameter;Obtain training sample set, wherein training sample includes that sample raw material information, sample processing environment information, sample add
Work technique information and corresponding mark product quality score;Sample raw material letter in the training sample that training sample is concentrated
Breath, the input of sample processing environment information and sample processing technology information as initial product mass fraction computation model, and
Using the mark product quality score in corresponding training sample as the desired output of initial product mass fraction computation model, utilize
Machine learning method trains initial product mass fraction computation model;The initial product mass fraction computation model that training is obtained
It is determined as the product quality score computation model trained in advance.
In some embodiments, product quality score computation model is neural network.
In some embodiments, preset stopping condition includes at least one of the following: that the number for executing cross and variation operation is big
In being equal to preset times threshold value, this cross and variation operates corresponding fitness changing value and is less than default fitness change threshold,
Wherein, this cross and variation operate corresponding fitness changing value be the population that is calculated of this cross and variation operation it is each each and every one
Maximum in the fitness for each individual of population that maximum value and the operation of last time cross and variation in the fitness of body are calculated
The difference of value, this cross and variation operate the maximum value in the fitness for each individual of population being calculated and are greater than default adapt to
Spend threshold value.
In some embodiments, target raw material information includes target tobacco leaf information, target processing environment information include with
At least one of lower: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level, oven type, processing technology information include baking
Curve is toasted composed by time and baking temperature.
In some embodiments, this method further include: export optimal processing technology information.
Second aspect, the embodiment of the present application provide a kind of for determining the device of processing technology information, which includes:
Information acquisition unit is configured to obtain target raw material information and target processing environment information;Population generation unit, is configured
Population is generated at random, the individual in population includes the processing work of target raw material information, target processing environment information and generation
Skill information;Cross and variation unit is configured to execute following cross and variation operation: for the individual in population, the individual is defeated
Enter product quality score computation model trained in advance, obtains product quality score corresponding with the individual, and will be with this
The corresponding product quality score of body is determined as the fitness of the individual;At least one is chosen according to the fitness of individual each in population
A candidate individual;Selected candidate individual is intersected and/or makes a variation to obtain at least one next-generation individual;With acquired
At least one next-generation individual Population Regeneration in individual;Cross and variation operation is continued to execute until meeting preset stopping item
Part;Technique determination unit is configured to the processing technology information in the maximum individual of fitness in population being determined as optimal add
Work technique information.
In some embodiments, device further include: processing unit is configured to signified according to optimal processing technology information
The processing technology shown is to the processing environment indicated by target processing environment information of raw material indicated by target raw material information
In processed.
In some embodiments, product quality score computation model is that training obtains in advance by following training step:
It determines the model structure of initial product mass fraction computation model and initializes the mould of initial product mass fraction computation model
Shape parameter;Obtain training sample set, wherein training sample includes that sample raw material information, sample processing environment information, sample add
Work technique information and corresponding mark product quality score;Sample raw material letter in the training sample that training sample is concentrated
Breath, the input of sample processing environment information and sample processing technology information as initial product mass fraction computation model, and
Using the mark product quality score in corresponding training sample as the desired output of initial product mass fraction computation model, utilize
Machine learning method trains initial product mass fraction computation model;The initial product mass fraction computation model that training is obtained
It is determined as the product quality score computation model trained in advance.
In some embodiments, product quality score computation model is neural network.
In some embodiments, preset stopping condition includes at least one of the following: that the number for executing cross and variation operation is big
In being equal to preset times threshold value, this cross and variation operates corresponding fitness changing value and is less than default fitness change threshold,
Wherein, this cross and variation operate corresponding fitness changing value be the population that is calculated of this cross and variation operation it is each each and every one
Maximum in the fitness for each individual of population that maximum value and the operation of last time cross and variation in the fitness of body are calculated
The difference of value, this cross and variation operate the maximum value in the fitness for each individual of population being calculated and are greater than default adapt to
Spend threshold value.
In some embodiments, target raw material information includes target tobacco leaf information, target processing environment information include with
At least one of lower: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level, oven type, processing technology information include baking
Curve is toasted composed by time and baking temperature.
In some embodiments, device further include: output unit is configured to export optimal processing technology information.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, comprising: one or more processors;Storage dress
It sets, is stored thereon with one or more programs, when said one or multiple programs are executed by said one or multiple processors,
So that said one or multiple processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, wherein realized when the computer program is executed by one or more processors such as implementation description any in first aspect
Method.
Method and apparatus provided by the embodiments of the present application for determining processing technology information, by being selected using genetic algorithm
Optimal processing technology information corresponding with target raw material information and target processing environment information is taken, the individual in genetic algorithm is
Be made of the processing technology information of target raw material information, target processing environment information and generation, and fitness function be then by
The product that target raw material information, target processing environment information in individual and the processing technology information input of generation are trained in advance
Mass fraction computation model obtains product quality score corresponding with the individual.It realizes to automatically determine and believe with target raw material
Optimal processing technology information corresponding with target processing environment information is ceased, is mentioned how to process raw material under certain processing environment
Foundation, the final product quality for improving the product that processing obtains are provided for optimal processing technology.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein;
Fig. 2A is the flow chart according to one embodiment of the method for determining processing technology information of the application;
Fig. 2 B is the decomposition process figure according to one embodiment of the cross and variation of the application operation;
Fig. 3 is the flow chart according to one embodiment of the training step of the application;
Fig. 4 is the schematic diagram according to an application scenarios of the method for determining processing technology information of the application;
Fig. 5 is the flow chart according to another embodiment of the method for determining processing technology information of the application;
Fig. 6 is the structural schematic diagram according to one embodiment of the device for determining processing technology information of the application;
Fig. 7 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for detecting table of the application or the implementation of the device for detecting table
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as web browser is answered on terminal device 101,102,103
With, shopping class application, searching class application, instant messaging tools, mailbox client, social platform software etc..Certainly, user can also
With the local function of realizing determining processing technology of direct using terminal equipment 101,102,103, the branch of server 105 is not needed
It holds.In this case, exemplary system architecture 100 can also be without the server 105 in Fig. 1.
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with display screen, including but not limited to smart phone, tablet computer, e-book reading
(Moving Picture Experts Group Audio Layer III, dynamic image expert compress mark for device, MP3 player
Quasi- audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression
Standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is
When software, it may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as with
To provide Distributed Services), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as to receiving from terminal device 101,102,103
Target raw material information and target processing environment information, which provide, determines that the technique information of optimal processing technology information service determines clothes
Business device.Technique information determines that server can analyze the target raw material information and target processing environment information received
Deng processing, and processing result (such as optimal processing technology information) is fed back into terminal device.
It should be noted that the method provided by the embodiment of the present application for detecting table is generally held by server 105
Row, correspondingly, the device for detecting table is generally positioned in server 105.
It should be noted that server 105 can be hardware, it is also possible to software.When server is hardware, Ke Yishi
The distributed server cluster of ready-made multiple server compositions, also may be implemented into individual server.When server is software,
Multiple softwares or software module (such as providing Distributed Services) may be implemented into, single software or soft also may be implemented into
Part module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates an implementations according to the method for determining processing technology information of the application
The process 200 of example.The method for being used to determine processing technology information, comprising the following steps:
Step 201, target raw material information and target processing environment information are obtained.
In the present embodiment, for determining executing subject (such as the service shown in FIG. 1 of the method for processing technology information
Device) target raw material information and target processing environment information can be obtained first.Here, target raw material information and target processing
Environmental information can be stored in that above-mentioned executing subject is local, be also possible to other by being connected to the network with above-mentioned executing subject
Electronic equipment (for example, terminal device shown in FIG. 1) uploads to above-mentioned executing subject local.
In the present embodiment, target source material information only illustrates raw material by taking some specific raw material information as an example
Information is not the restriction to raw material information.Raw material information is used to describe the various relevant informations of raw material.
Target processing environment information only illustrates processing environment information by taking certain specific processing environment information as an example, not
It is the restriction to processing environment information.Processing environment information is used to describe the various relevant informations of processing environment.
In some optional implementations of the present embodiment, when the method for being used to determine processing technology information is applied to
When in tobacco workmanship, target source material information can be target tobacco leaf information, for example, target tobacco leaf information may include tobacco leaf
Maturity, tobacco leaf position and tobacco variety etc..And in tobacco workmanship, target processing environment information may include it is following at least
One: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level, oven type, similarly in tobacco workmanship, processing technology letter
Breath includes can be to toast curve composed by baking time and baking temperature.
Step 202, population is generated at random.
In the present embodiment, above-mentioned executing subject (such as server shown in FIG. 1) can using various implementations with
Machine generates population, and here, population is the concept of the population in genetic algorithm, and the individual in population generated includes target former material
Expect information, the processing technology information of target processing environment information and generation.Here, in individual different in population generated
Raw material information is all identical, i.e., is all adding in individual different in target raw material information and population generated
Work environmental information is also all identical, i.e., is all target processing environment information.And in individual different in population generated
Processing technology information is different, in order to ensure the difference of individual.
The application is not specifically limited the individual amount in the population generated in step 201.
It should be noted that the above-mentioned random method for generating population is the well-known technique studied and applied extensively at present,
This is repeated no more.It is understood that processing technology information is mainly randomly generated here, since this is for determining processing technology
The difference of processing industry applied by the method for information, the required processing technology information generated at random are also different.
Step 203, cross and variation operation is executed.
In the present embodiment, it after above-mentioned executing subject can generate population in step 202, is held based on population generated
The operation of row cross and variation.Here, cross and variation operation may include that sub-step 2031 as shown in Figure 2 B arrives sub-step 2035.Please
With reference to Fig. 2 B, it illustrates the decomposition process figures of the one embodiment operated according to the cross and variation of the application.
Individual input product quality score trained in advance is calculated mould for the individual in population by sub-step 2031
Type obtains product quality score corresponding with the individual, and product quality score corresponding with the individual is determined as this
The fitness of body.
It here, is exactly that the target in the individual is former by individual input product quality score computation model trained in advance
Material information, target processing environment information and processing technology information input product quality score computation model.
It should be noted that product quality score computation model is for characterizing raw material information, target processing environment information
Corresponding relationship between processing technology information three and product quality score.As an example, product quality score computation model
Can be technical staff be based on to a large amount of raw material information, target processing environment information and processing technology information three with it is corresponding
Product quality score statistics and pre-establish, be stored with multiple raw material informations, target processing environment information and processing
The mapping table of the corresponding relationship of technique information three and product quality score;It is also possible to technical staff to be based on to a large amount of numbers
According to statistics and preset and store it is into above-mentioned electronic equipment, to raw material information, target processing environment information and add
Work technique information three carries out one or more numerical value in the obtained feature vector of feature extraction and carries out numerical value calculating to obtain
To the calculation formula of the calculated result for characterizing product quality score.It is understood that this is used to determine that processing technology to be believed
Processing technology applied by the method for breath is different, and above-mentioned mapping table and calculation formula are also different.
In some optional implementations of the present embodiment, the said goods mass fraction computation model be can be by such as
Training step shown in Fig. 3 training in advance obtains.Referring to FIG. 3, it illustrates according to one of the training step of the application
The flow chart of embodiment.
Step 301, the model structure and initialization initial product quality of initial product mass fraction computation model are determined
The model parameter of score computation model.
Here, the executing subject of training product quality score computation model can be with the execution of the method for detecting table
Main body is same or different.If identical, train the executing subject of product quality score computation model that can obtain in training
By the model structure information and model parameter of trained product quality score computation model after product quality score computation model
Parameter value be stored in local.If it is different, then the executing subject of training product quality score computation model can be trained
The model structure information of trained product quality score computation model and model are joined after to product quality score computation model
Several parameter values is sent to the executing subject of the method for detecting table.
Here, since initial product mass fraction computation model may include various types of computation models, for difference
The model structure information of the computation model of type, required determination is not also identical.
Optionally, initial product mass fraction computation model may include neural network.As such, it is desirable to determine neural network
Which layer the initial product mass fraction computation model of type all includes, such as may include input layer, hidden layer and output layer,
And which parameter is every layer all include.For example, it may be determined which layer hidden layer all includes, the order of connection between layers is closed
System and each layer include which parameter (for example, weight weight, biasing bias) etc..For example, if hidden layer is usual
It further include excitation function layer, excitation function layer is used to carry out NONLINEAR CALCULATION to the information of input.For each excitation function layer
It can determine specific excitation function.For example, activation primitive can be the various mutation activation primitives of ReLU and ReLU,
Sigmoid function, Tanh (tanh) function, Maxout function etc..In another example leading to here in order to realize that numerical value calculates
Normal output layer includes the recurrence device for evaluation, then needs exist for the specific implementation algorithm and ginseng that determine and return device
Number.
It is then possible to initialize the model parameter of initial product mass fraction computation model.In practice, will can initially it produce
Each model parameter of quality score computation model is initialized with some different small random numbers." small random number " is used to
Guarantee that model will not enter saturation state because weight is excessive, so as to cause failure to train, " difference " is for guaranteeing that model can be with
Normally learn.
Step 302, training sample set is obtained.
Here, the training sample that training sample is concentrated may include sample raw material information, sample processing environment information, sample
This processing technology information and corresponding mark product quality score.For example, can be answered by the product quality score computation model
The expert in specific processing technology field provides above-mentioned training sample, and a training sample is for characterizing according to the training sample
In sample processing technology information indicated by processing technology, it is right under the processing environment indicated by sample processing environment information
The product quality score that raw material indicated by sample raw material information carry out processing obtained product is sample product quality
Score.
It should be noted that the executing subject of training step can both first carry out step 301 executes step 302 again, it can also
Step 301 is executed again to first carry out step 302, and the application is not specifically limited in this embodiment.
Step 303, by training sample concentrate training sample in sample raw material information, sample processing environment information and
Input of the sample processing technology information as initial product mass fraction computation model, and by the mark in corresponding training sample
Desired output of the product quality score as initial product mass fraction computation model is produced using machine learning method training is initial
Quality score computation model.
Specifically, the sample raw material information in training sample, the sample that can first concentrate training sample process ring
Border information and sample processing technology information input initial product mass fraction computation model, obtain reality corresponding with the training sample
Border product quality score.It is then possible to calculate the mark product in obtained actual product mass fraction and the training sample
Difference between mass fraction.Finally, initial product mass fraction computation model can be adjusted based on resulting difference is calculated
Model parameter, and in the case where meeting preset trained termination condition, terminate training.For example, the training here preset at terminates
Condition may include at least one of following: the training time is more than preset duration, and frequency of training is more than preset times, is calculated resulting
Difference is less than default discrepancy threshold.
Here it is possible to using various implementations based in obtained actual product mass fraction and the training sample
Mark the model parameter of the discrepancy adjustment initial product mass fraction computation model between product quality score.For example, can adopt
With stochastic gradient descent (SGD, Stochastic Gradient Descent), Newton method (Newton's Method), quasi- ox
Method (Quasi-Newton Methods), conjugate gradient method (Conjugate Gradient), Heuristic Method and
The various optimization algorithms of other currently known or following exploitations.
Step 304, the initial product mass fraction computation model that training obtains is determined as the product quality trained in advance
Score computation model.
By sub-step 2031, the individual in population is calculated the fitness of each individual.
Sub-step 2032 chooses at least one candidate individual according to the fitness of individual each in population.
Here it is possible to choose at least one candidate according to the fitness of individual each in population using various implementations
Body.Since the fitness of individual each in population is the obtained product quality of individual input product mass fraction computation model
Score, in order to realize " survival of the fittest " in genetic algorithm, the individual that fitness can be selected as far as possible big here, i.e. product quality point
The high individual of number.For example, the highest preceding preset number individual of fitness can be chosen from population as candidate individual.Example again
Such as, fitness in population can also be chosen and be more than or equal to all individuals of default fitness threshold value as candidate individual.
Sub-step 2033 intersect to selected candidate individual and variation obtains at least one next-generation individual.
Here it is possible to intersect using candidate individual selected in various implementation sub-paragraphs 2032 and/or
Variation obtains at least one next-generation individual, and the application does not do specific limit to the number of obtained next-generation individual yet
It is fixed.
Here, each individual includes three categories gene: raw material information, environmental information and processing technology information, Mei Yi great
Genoid has different gene parameters again.Here, for raw material information, environmental information in intersection and/or mutation process
This two major classes gene is fixed and invariable.What is changed is the gene parameter in processing technology information.Wherein, intersection can refer to
To two individuals, their portion gene is exchanged, the portion in the processing technology information in two individuals is exchanged for here
Divide gene parameter.And it makes a variation and refers to and so that some gene numerical value in an individual is changed at random.Here, referring to can make to process
Portion gene parameter values in technique information change.
Sub-step 2034, with the individual at least one obtained next-generation individual Population Regeneration.
Here, according to the principle of " survival of the fittest " in genetic algorithm, each individual in initial population can be deleted, then
By at least one next-generation individual obtained in sub-step 2033 as the individual in population.
Sub-step 2035, it is determined whether meet preset stopping condition.
Here, if it is determined that meet preset stopping condition, then terminate cross and variation operation.If it is determined that being unsatisfactory for default stop
Only condition then goes to sub-step 2031 and continues to execute cross and variation operation.
In some implementations, preset stopping condition may include at least one of following:
(1) number for executing cross and variation operation is more than or equal to preset times threshold value.
That is, the number for executing transaction mutation operation is enough.
(2) this cross and variation operates corresponding fitness changing value less than default fitness change threshold.
Wherein, it is that this cross and variation operates the kind being calculated that this cross and variation, which operates corresponding fitness changing value,
The fitness for each individual of population that maximum value and the operation of last time cross and variation in the fitness of each individual of group are calculated
In maximum value difference.
That is, executing the evolution degree very little of individual brought by cross and variation operation again, do not need to carry out intersection change again
It is different.
(3) maximum value in the fitness for each individual of population that the operation of this cross and variation is calculated is greater than default suitable
Response threshold value.
That is, having existed more excellent individual in the obtained population of this cross and variation, do not need to evolve again new
Individual.
Step 204, the processing technology information in the maximum individual of fitness in population is determined as optimal processing technology to believe
Breath.
In the present embodiment, above-mentioned executing subject can will fit after step 203 has executed cross and variation operation in population
Processing technology information in the maximum individual of response is determined as optimal processing technology information.
In some optional implementations of the present embodiment, above-mentioned executing subject can execute step after step 204
Rapid 205:
Step 205, optimal processing technology information is exported.
Here, above-mentioned executing subject can adopt exports optimal processing technology information in various manners.
For example, above-mentioned executing subject can firstly generate text information corresponding with optimal processing technology information, then again
Voice corresponding with text information generated is generated using speech synthesis technique, and plays upper predicate using audio playing device
Sound.Then, the staff for the processing technology that the method for the determination processing technology information is applied to can be according to institute's uppick
Voice, execute process operation during various working process parameters setting.
For example, above-mentioned executing subject can firstly generate text information corresponding with optimal processing technology information, then exist
Above-mentioned text information is presented with text or graphic form on display.Then, the method for the determination processing technology information is applied
In processing technology staff can according to the text or picture watched, execute process operation during various processing
The setting of technological parameter.
Connect in another example optimal processing technology information can also be sent to by above-mentioned executing subject with above-mentioned executing subject network
Other electronic equipments connect.
By step 205, optimal processing technology information can be exported in above-mentioned executing subject.
With continued reference to the application scenarios that Fig. 4, Fig. 4 are according to the method for determining processing technology information of the present embodiment
One schematic diagram.In the application scenarios of Fig. 4, server 401 can obtain target raw material information 402 and target processing first
Environmental information 403;Then, server 401 can generate population 404 at random, wherein the individual in population includes target raw material
Information 402, target processing environment information 403 and the processing technology information generated;Then, server 401 can execute intersection and become
Processing technology information in the maximum individual of fitness in population can be determined as optimal add by ETTHER-OR operation, last server 401
Work technique information 405.
The method provided by the above embodiment of the application using genetic algorithm by being chosen and target raw material information and mesh
The corresponding optimal processing technology information of processing environment information is marked, the individual in genetic algorithm is by target raw material information, target
Processing environment information and the processing technology information of generation composition, and fitness function is then by the target raw material letter in individual
The product quality score computation model that breath, target processing environment information and the processing technology information input of generation are trained in advance, obtains
To product quality score corresponding with the individual.It realizes and automatically determines and target raw material information and target processing environment information
Corresponding optimal processing technology information provides optimal processing technology and provides how to process raw material under certain processing environment
Foundation, the final product quality for improving the product that processing obtains.
With further reference to Fig. 5, it illustrates the processes for another embodiment for determining the method for processing technology information
500.This is used to determine the process 500 of the method for processing technology information, comprising the following steps:
Step 501, target raw material information and target processing environment information are obtained.
Step 502, population is generated at random.
Step 503, cross and variation operation is executed.
Step 504, the processing technology information in the maximum individual of fitness in population is determined as optimal processing technology to believe
Breath.
In the present embodiment, the concrete operations of step 501, step 502, step 503 and step 504 and reality shown in Fig. 2
The operation for applying step 201 in example, step 202, step 203 and step 204 is essentially identical, and details are not described herein.
Step 505, according to processing technology indicated by optimal processing technology information to indicated by target raw material information
Raw material are processed in the processing environment indicated by target processing environment information.
In some optional implementations of the present embodiment, above-mentioned executing subject, which can be, controls the determination processing technology
The control equipment for the processing technology that the method for information is applied to, in this way, above-mentioned executing subject can be directly according in step 504
Processing technology indicated by identified optimal processing technology information is to raw material indicated by target raw material information in target
It is processed in processing environment indicated by processing environment information.
In some optional implementations of the present embodiment, above-mentioned executing subject can also be by above-mentioned optimal processing technology
Information is sent to the control equipment for the processing technology that the method for controlling the determination processing technology information is applied to, in this way, above-mentioned
Controlling equipment can be signified to target raw material information according to processing technology indicated by the optimal processing technology information received
The raw material shown are processed in the processing environment indicated by target processing environment information.
From figure 5 it can be seen that being used to determine that processing technology to be believed in the present embodiment compared with the corresponding embodiment of Fig. 2
The process 500 of the method for breath, which is highlighted, is processed according to processing technology indicated by identified optimal processing technology information
Step.The scheme of the present embodiment description can be directly realized by according to target raw material information and target processing environment information as a result,
It determines optimal processing technology information, and is directly processed according to identified optimal processing technology information, determined without artificial access
Working process parameter, technical effect can include but is not limited to the following:
First, accelerate process velocity.The artificial process for determining processing technology can be longer.
Second, reduce cost of labor.It is not required to manpower intervention.
Third, independent of the personal experience of technology personnel, the quality of product generated is more unified.
With further reference to Fig. 6, as the realization to method shown in above-mentioned each figure, this application provides one kind to add for determining
One embodiment of the device of work technique information, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, device tool
Body can be applied in various electronic equipments.
As shown in fig. 6, the present embodiment is used to determine that the device 600 of processing technology information includes: information acquisition unit
601, population generation unit 602, cross and variation unit 603 and technique determination unit 604.Wherein, information acquisition unit 601, quilt
It is configured to obtain target raw material information and target processing environment information;Population generation unit 602 is configured to generate kind at random
Group, the individual in above-mentioned population includes the processing work of above-mentioned target raw material information, above-mentioned target processing environment information and generation
Skill information;Cross and variation unit 603 is configured to execute following cross and variation operation: for the individual in above-mentioned population, by this
Individual input product quality score computation model trained in advance obtains product quality score corresponding with the individual, and will
Product quality score corresponding with the individual is determined as the fitness of the individual;According to the fitness of individual each in above-mentioned population
Choose at least one candidate individual;Selected candidate individual is intersected and/or makes a variation to obtain at least one next-generation
Body;The individual in above-mentioned population is updated at least one obtained next-generation individual;Continue to execute above-mentioned cross and variation operation
Until meeting preset stopping condition;Technique determination unit 604, being configured to will be in the maximum individual of fitness in above-mentioned population
Processing technology information is determined as optimal processing technology information.
In the present embodiment, for determining that the information acquisition unit 601 of the device 600 of processing technology information, population generate
Unit 602, the specific processing of cross and variation unit 603 and technique determination unit 604 and its brought technical effect can be distinguished
With reference to the related description of step 201, step 202, step 203 and step 204 in Fig. 2A corresponding embodiment, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned apparatus 600 can also include: processing unit 605, quilt
It is configured to according to processing technology indicated by above-mentioned optimal processing technology information to original indicated by above-mentioned target raw material information
Material is processed in the processing environment indicated by above-mentioned target processing environment information.
In some optional implementations of the present embodiment, the said goods mass fraction computation model can be by with
The training in advance of lower training step obtains: determining that the model structure of initial product mass fraction computation model and initialization are above-mentioned
The model parameter of initial product mass fraction computation model;Obtain training sample set, wherein training sample includes sample raw material
Information, sample processing environment information, sample processing technology information and corresponding mark product quality score;By above-mentioned training sample
Sample raw material information, sample processing environment information and sample processing technology information in the training sample of concentration is as above-mentioned first
The input of beginning product quality score computation model, and using the mark product quality score in corresponding training sample as above-mentioned first
The desired output of beginning product quality score computation model is calculated using the above-mentioned initial product mass fraction of machine learning method training
Model;The above-mentioned initial product mass fraction computation model that training obtains is determined as above-mentioned product quality score trained in advance
Computation model.
In some optional implementations of the present embodiment, the said goods mass fraction computation model can be nerve net
Network.
In some optional implementations of the present embodiment, above-mentioned preset stopping condition may include following at least one
: the number for executing above-mentioned cross and variation operation is more than or equal to preset times threshold value, this cross and variation operates corresponding adaptation
It spends changing value and is less than default fitness change threshold, wherein it is this that this cross and variation, which operates corresponding fitness changing value,
Maximum value and the operation of last time cross and variation in the fitness for each individual of above-mentioned population that cross and variation operation is calculated are counted
The difference of maximum value in the fitness of each individual of obtained above-mentioned population, the operation of this cross and variation are calculated upper
It states the maximum value in the fitness of each individual of population and is greater than default fitness threshold value.
In some optional implementations of the present embodiment, above-mentioned target raw material information may include target tobacco leaf letter
Breath, above-mentioned target processing environment information include at least one of the following: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level,
Oven type, above-mentioned processing technology information include that curve is toasted composed by baking time and baking temperature.
In some optional implementations of the present embodiment, above-mentioned apparatus can also include: output unit 606, be matched
It is set to the above-mentioned optimal processing technology information of output.
It should be noted that provided by the embodiments of the present application for determining the reality of each unit in the device of processing technology information
Existing details and technical effect can be with reference to the explanations of other embodiments in the application, and details are not described herein.
Below with reference to Fig. 7, it illustrates the computer systems 700 for the electronic equipment for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Electronic equipment shown in Fig. 7 is only an example, function to the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (CPU, Central Processing Unit)
701, it can be according to the program being stored in read-only memory (ROM, Read Only Memory) 702 or from storage section
708 programs being loaded into random access storage device (RAM, Random Access Memory) 703 and execute various appropriate
Movement and processing.In RAM 703, also it is stored with system 700 and operates required various programs and data.CPU 701,ROM
702 and RAM 703 is connected with each other by bus 704.Input/output (I/O, Input/Output) interface 705 is also connected to
Bus 704.
I/O interface 705 is connected to lower component: the importation 706 including keyboard, mouse etc.;It is penetrated including such as cathode
Spool (CRT, Cathode Ray Tube), liquid crystal display (LCD, Liquid Crystal Display) etc. and loudspeaker
Deng output par, c 707;Storage section 708 including hard disk etc.;And including such as LAN (local area network, Local Area
Network) the communications portion 709 of the network interface card of card, modem etc..Communications portion 709 is via such as internet
Network executes communication process.Driver 710 is also connected to I/O interface 705 as needed.Detachable media 711, such as disk,
CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 710, in order to from the calculating read thereon
Machine program is mounted into storage section 708 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 709, and/or from detachable media
711 are mounted.When the computer program is executed by central processing unit (CPU) 701, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include information acquisition unit, population generation unit, cross and variation unit and technique determination unit.Wherein, the title of these units exists
The restriction to the unit itself is not constituted in the case of certain, for example, information acquisition unit is also described as " obtaining target
The unit of raw material information and target processing environment information ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment;It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: target raw material information and target processing environment information are obtained;Random to generate population, the individual in population includes target original
The processing technology information of material information, target processing environment information and generation;Execute following cross and variation operation: in population
Individual individual input product quality score computation model trained in advance is obtained into product quality corresponding with the individual
Score, and product quality score corresponding with the individual is determined as to the fitness of the individual;According to individual each in population
Fitness choose at least one candidate individual;Selected candidate individual is intersected and/or makes a variation to obtain at least one
Next-generation individual;With the individual at least one obtained next-generation individual Population Regeneration;Continue to execute cross and variation operation
Until meeting preset stopping condition;Processing technology information in the maximum individual of fitness in population is determined as optimal processing work
Skill information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (16)
1. a kind of method for determining processing technology information, comprising:
Obtain target raw material information and target processing environment information;
Random to generate population, the individual in the population includes the target raw material information, the target processing environment information
With the processing technology information of generation;
Execute following cross and variation operation: for the individual in the population, by individual input product quality trained in advance
Score computation model obtains product quality score corresponding with the individual, and will product quality score corresponding with the individual
It is determined as the fitness of the individual;At least one candidate individual is chosen according to the fitness of individual each in the population;To institute
The candidate individual of selection is intersected and/or makes a variation to obtain at least one next-generation individual;At least one is next with obtained
Generation individual updates the individual in the population;The cross and variation operation is continued to execute until meeting preset stopping condition;
Processing technology information in the maximum individual of fitness in the population is determined as optimal processing technology information.
2. according to the method described in claim 1, wherein, the method also includes:
According to processing technology indicated by the optimal processing technology information to former material indicated by the target raw material information
Material is processed in the processing environment indicated by the target processing environment information.
3. according to the method described in claim 1, wherein, the product quality score computation model is by following training step
Training obtains in advance:
The model structure and the initialization initial product mass fraction for determining initial product mass fraction computation model calculate
The model parameter of model;
Obtain training sample set, wherein training sample includes sample raw material information, sample processing environment information, sample processing
Technique information and corresponding mark product quality score;
Sample raw material information, sample processing environment information and sample processing in the training sample that the training sample is concentrated
Input of the technique information as the initial product mass fraction computation model, and by the mark product in corresponding training sample
Desired output of the mass fraction as the initial product mass fraction computation model, it is described just using machine learning method training
Beginning product quality score computation model;
The initial product mass fraction computation model that training obtains is determined as the product quality score trained in advance
Computation model.
4. according to the method described in claim 3, wherein, the product quality score computation model is neural network.
5. according to the method described in claim 4, wherein, the preset stopping condition includes at least one of the following: described in execution
The number of cross and variation operation is more than or equal to preset times threshold value, this cross and variation operates corresponding fitness changing value and is less than
Default fitness change threshold, wherein this cross and variation operates corresponding fitness changing value as the operation of this cross and variation
Maximum value in the fitness of each individual of the population being calculated is calculated described with the operation of last time cross and variation
The difference of maximum value in the fitness of each individual of population, the population that is calculated of this cross and variation operation it is each each and every one
Maximum value in the fitness of body is greater than default fitness threshold value.
6. according to the method described in claim 5, wherein, the target raw material information includes target tobacco leaf information, the mesh
Mark processing environment information includes at least one of the following: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level, oven type,
The processing technology information includes that curve is toasted composed by baking time and baking temperature.
7. according to the method described in claim 1, wherein, the method also includes:
Export the optimal processing technology information.
8. a kind of for determining the device of processing technology information, comprising:
Information acquisition unit is configured to obtain target raw material information and target processing environment information;
Population generation unit, is configured to generate population at random, the individual in the population include the target raw material information,
The processing technology information of the target processing environment information and generation;
Cross and variation unit is configured to execute following cross and variation operation: for the individual in the population, the individual is defeated
Enter product quality score computation model trained in advance, obtains product quality score corresponding with the individual, and will be with this
The corresponding product quality score of body is determined as the fitness of the individual;According to the fitness of individual each in the population choose to
A few candidate individual;Selected candidate individual is intersected and/or makes a variation to obtain at least one next-generation individual;With institute
The next-generation individual of at least one obtained updates the individual in the population;The cross and variation operation is continued to execute until meeting
Preset stopping condition;
Technique determination unit is configured to for the processing technology information in the maximum individual of fitness in the population being determined as most
Excellent processing technology information.
9. device according to claim 8, wherein described device further include:
Unit is processed, is configured to according to processing technology indicated by the optimal processing technology information to the target raw material
Raw material indicated by information are processed in the processing environment indicated by the target processing environment information.
10. device according to claim 8, wherein the product quality score computation model is by following training step
What rapid training in advance obtained:
The model structure and the initialization initial product mass fraction for determining initial product mass fraction computation model calculate
The model parameter of model;
Obtain training sample set, wherein training sample includes sample raw material information, sample processing environment information, sample processing
Technique information and corresponding mark product quality score;
Sample raw material information, sample processing environment information and sample processing in the training sample that the training sample is concentrated
Input of the technique information as the initial product mass fraction computation model, and by the mark product in corresponding training sample
Desired output of the mass fraction as the initial product mass fraction computation model, it is described just using machine learning method training
Beginning product quality score computation model;
The initial product mass fraction computation model that training obtains is determined as the product quality score trained in advance
Computation model.
11. device according to claim 10, wherein the product quality score computation model is neural network.
12. device according to claim 11, wherein the preset stopping condition, which includes at least one of the following:, executes institute
The number for stating cross and variation operation is more than or equal to preset times threshold value, and it is small that this cross and variation operates corresponding fitness changing value
In default fitness change threshold, wherein this cross and variation operates corresponding fitness changing value as this cross and variation behaviour
The maximum value and last time cross and variation made in the fitness for each individual of the population being calculated operate the institute being calculated
The difference of the maximum value in the fitness of each individual of population is stated, the population that the operation of this cross and variation is calculated is each
Maximum value in the fitness of individual is greater than default fitness threshold value.
13. device according to claim 12, wherein the target raw material information includes target tobacco leaf information, described
Target processing environment information includes at least one of the following: environment dry-bulb temperature, wet-bulb temperature, air humidity, height above sea level, oven class
Type, the processing technology information include that curve is toasted composed by baking time and baking temperature.
14. device according to claim 8, wherein described device further include:
Output unit is configured to export the optimal processing technology information.
15. a kind of electronic equipment, comprising:
One or more processors;
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize the method as described in any in claim 1-7.
16. a kind of computer readable storage medium, is stored thereon with computer program, wherein the computer program is by one
Or multiple processors realize the method as described in any in claim 1-7 when executing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910165217.0A CN109886500A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for determining processing technology information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910165217.0A CN109886500A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for determining processing technology information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109886500A true CN109886500A (en) | 2019-06-14 |
Family
ID=66930713
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910165217.0A Pending CN109886500A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for determining processing technology information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109886500A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111507677A (en) * | 2020-03-13 | 2020-08-07 | 益萃网络科技(中国)有限公司 | Commodity processing method and device, computer equipment and storage medium |
CN111842922A (en) * | 2020-06-04 | 2020-10-30 | 深圳市人工智能与机器人研究院 | Material synthesis parameter adjusting method and device, computer equipment and storage medium |
CN112949704A (en) * | 2021-02-24 | 2021-06-11 | 北京优创新港科技股份有限公司 | Tobacco leaf maturity state identification method and device based on image analysis |
CN113112101A (en) * | 2020-01-10 | 2021-07-13 | 北京百度网讯科技有限公司 | Method and device for monitoring production process, electronic equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101391268A (en) * | 2008-11-07 | 2009-03-25 | 东北大学 | Reverse optimization method of steel plate rolling and cooling controlling-process temperature institution |
CN102058012A (en) * | 2010-11-03 | 2011-05-18 | 广东海洋大学 | Oyster sapidity peptide controllable enzymolysis process based on optimization of nerve network system |
CN106295795A (en) * | 2016-08-09 | 2017-01-04 | 衢州学院 | A kind of copper pipe interior whorl forming qualitative forecasting method based on BP neural network algorithm |
-
2019
- 2019-03-05 CN CN201910165217.0A patent/CN109886500A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101391268A (en) * | 2008-11-07 | 2009-03-25 | 东北大学 | Reverse optimization method of steel plate rolling and cooling controlling-process temperature institution |
CN102058012A (en) * | 2010-11-03 | 2011-05-18 | 广东海洋大学 | Oyster sapidity peptide controllable enzymolysis process based on optimization of nerve network system |
CN106295795A (en) * | 2016-08-09 | 2017-01-04 | 衢州学院 | A kind of copper pipe interior whorl forming qualitative forecasting method based on BP neural network algorithm |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113112101A (en) * | 2020-01-10 | 2021-07-13 | 北京百度网讯科技有限公司 | Method and device for monitoring production process, electronic equipment and storage medium |
CN113112101B (en) * | 2020-01-10 | 2023-07-25 | 北京百度网讯科技有限公司 | Method and device for monitoring production process, electronic equipment and storage medium |
CN111507677A (en) * | 2020-03-13 | 2020-08-07 | 益萃网络科技(中国)有限公司 | Commodity processing method and device, computer equipment and storage medium |
CN111842922A (en) * | 2020-06-04 | 2020-10-30 | 深圳市人工智能与机器人研究院 | Material synthesis parameter adjusting method and device, computer equipment and storage medium |
CN112949704A (en) * | 2021-02-24 | 2021-06-11 | 北京优创新港科技股份有限公司 | Tobacco leaf maturity state identification method and device based on image analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886500A (en) | Method and apparatus for determining processing technology information | |
US11420115B2 (en) | Automated dynamic custom game content generation | |
CN109582982A (en) | Method and apparatus for translated speech | |
US11673049B2 (en) | Operator interface for automated game content generation | |
CN107153496A (en) | Method and apparatus for inputting emotion icons | |
CN109101919A (en) | Method and apparatus for generating information | |
US11465052B2 (en) | Game definition file | |
CN107273436A (en) | The training method and trainer of a kind of recommended models | |
US11724193B2 (en) | Automated prediction of user response states based on traversal behavior | |
CN108734557A (en) | Methods, devices and systems for generating dress ornament recommendation information | |
US11957982B2 (en) | Parametric player modeling for computer-implemented games | |
CN110188719A (en) | Method for tracking target and device | |
US12083436B2 (en) | Automated assessment of custom game levels | |
US11806624B2 (en) | On device game engine architecture | |
US11738272B2 (en) | Automated generation of custom content for computer-implemented games | |
CN108985228A (en) | Information generating method and device applied to terminal device | |
CN109242043A (en) | Method and apparatus for generating information prediction model | |
CA3127835A1 (en) | System and method for updating objects in a simulated environment | |
CN109144729A (en) | The data processing method and distributed system of distributed system | |
CN110472558A (en) | Image processing method and device | |
CN108509041A (en) | Method and apparatus for executing operation | |
WO2022231824A1 (en) | Audio reactive augmented reality | |
CN109598344A (en) | Model generating method and device | |
CN109670579A (en) | Model generating method and device | |
CN106530377A (en) | Method and device for operating three-dimensional animated character |
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 |