CN107357995A - A kind of recommendation method and apparatus of Ceramic Art Design - Google Patents
A kind of recommendation method and apparatus of Ceramic Art Design Download PDFInfo
- Publication number
- CN107357995A CN107357995A CN201710576598.2A CN201710576598A CN107357995A CN 107357995 A CN107357995 A CN 107357995A CN 201710576598 A CN201710576598 A CN 201710576598A CN 107357995 A CN107357995 A CN 107357995A
- Authority
- CN
- China
- Prior art keywords
- design
- ceramic art
- art design
- scheme
- sample
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Adornments (AREA)
Abstract
The present invention proposes a kind of recommendation method and apparatus of Ceramic Art Design, and wherein this method includes:Obtain the request of Ceramic Art Design;Wherein, design needs are included in the request;Extraction design needs from the request;Needed and default Ceramic Art Design neutral net generation recommendation information based on the design;Wherein, the Ceramic Art Design scheme to the design needs is included in the recommendation information.Scheme with this by the embodiment of the present invention, realizes automatic recommendation, improves efficiency, in addition, it is to need to generate recommendation information in Ceramic Art Design neutral net based on design, while efficiency is improved, the effect of recommendation is also assures that, reduces the work of user, ensure that the usage experience of user.
Description
Technical field
The present invention relates to neutral net and data processing field, the recommendation method of more particularly to a kind of Ceramic Art Design and set
It is standby.
Background technology
Existing Ceramic Art Design scheme, if being intended to refer to or expecting a new design, it is all based on artificial
Ceramic exhibition, and the books that Ceramic Art Design is related are seen, and could be generated to carry out reference in a manual manner;It is obvious that this
Kind of mode wastes time and energy, and due to entirely manually, and limited personnel, all already present Ceramic Art Design sides at present can not be used for reference
Case, cause first efficiency it is low, the effect second used for reference cannot also control.
The content of the invention
For in the prior art the defects of, the present invention proposes the recommendation method and apparatus of Ceramic Art Design a kind of, automatic root
According to needing to utilize Ceramic Art Design neural network recommendation Ceramic Art Design, efficiency is improved, and ensure that the effect of recommendation.
Specifically, the present invention proposes embodiment in detail below:
The embodiment of the present invention proposes a kind of recommendation method of Ceramic Art Design, including:
Obtain the request of Ceramic Art Design;Wherein, design needs are included in the request;
Extraction design needs from the request;
Needed and default Ceramic Art Design neutral net generation recommendation information based on the design;Wherein, the recommendation
Include the Ceramic Art Design scheme to the design needs in breath.
In a specific embodiment, the Ceramic Art Design neutral net is to exceed a number of sample by quantity
Ceramic Art Design scheme is trained generation;Wherein described sample Ceramic Art Design scheme include Ceramic Art Design scheme and with pottery
Feedback result corresponding to porcelain design.
In a specific embodiment, in addition to:
Obtain feedback information corresponding with the recommendation information;Wherein, feedback result is included in the feedback information;
The Ceramic Art Design scheme in recommendation information is labeled based on the feedback result, generation sample Ceramic Art Design side
Case;
The Ceramic Art Design neutral net is trained based on the sample Ceramic Art Design scheme generated.
In a specific embodiment, in addition to:
After being trained to the Ceramic Art Design neutral net, the Ceramic Art Design neutral net institute after training is obtained
Corresponding loss function;
If the loss function meets preset requirement, it is determined that the training currently to the Ceramic Art Design neutral net is complete
Into;
If the loss function is unsatisfactory for preset requirement, weight after being adjusted to the default training parameter in training process
Newly the Ceramic Art Design neutral net is trained.
In a specific embodiment, the sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Its
In, the Ceramic Art Design triple data include:The source design that is obtained at random in sample Ceramic Art Design scheme and with institute
The source design of stating belongs to the Top-Down Design scheme of one kind together, adheres to inhomogeneous reverse design scheme separately with the source design;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The consistent design of feedback result;
The reverse design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The inconsistent design of feedback result.
The embodiment of the present invention also proposed a kind of recommendation apparatus of Ceramic Art Design, including:
Acquisition module, for obtaining the request of Ceramic Art Design;Wherein, design needs are included in the request;
Extraction module, for the extraction design needs from the request;
Recommending module, for being needed and default Ceramic Art Design neutral net generation recommendation information based on the design;Its
In, the Ceramic Art Design scheme to the design needs is included in the recommendation information.
In a specific embodiment, the Ceramic Art Design neutral net is to exceed a number of sample by quantity
Ceramic Art Design scheme is trained generation;Wherein described sample Ceramic Art Design scheme include Ceramic Art Design scheme and with pottery
Feedback result corresponding to porcelain design.
In a specific embodiment, in addition to:
Feedback training module, for obtaining feedback information corresponding with the recommendation information;Wherein, in the feedback information
Include feedback result;
The Ceramic Art Design scheme in recommendation information is labeled based on the feedback result, generation sample Ceramic Art Design side
Case;
The Ceramic Art Design neutral net is trained based on the sample Ceramic Art Design scheme generated.
In a specific embodiment, in addition to:
Evaluation module, for after being trained to the Ceramic Art Design neutral net, obtaining the ceramics after training
Design the loss function corresponding to neutral net;
If the loss function meets preset requirement, it is determined that the training currently to the Ceramic Art Design neutral net is complete
Into;
If the loss function is unsatisfactory for preset requirement, weight after being adjusted to the default training parameter in training process
Newly the Ceramic Art Design neutral net is trained.
In a specific embodiment, the sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Its
In, the Ceramic Art Design triple data include:The source design that is obtained at random in sample Ceramic Art Design scheme and with institute
The source design of stating belongs to the Top-Down Design scheme of one kind together, adheres to inhomogeneous reverse design scheme separately with the source design;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The consistent design of feedback result;
The reverse design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The inconsistent design of feedback result.
With this, the embodiment of the present invention proposes a kind of recommendation method and apparatus of Ceramic Art Design, and wherein this method includes:Obtain
Take the request of Ceramic Art Design;Wherein, design needs are included in the request;Extraction design needs from the request;It is based on
The design needs and default Ceramic Art Design neutral net generation recommendation information;Wherein, include in the recommendation information pair
The Ceramic Art Design scheme that the design needs.Scheme with this by the embodiment of the present invention, realizes automatic recommendation, improves effect
Rate, in addition, being to need to generate recommendation information in Ceramic Art Design neutral net based on design, while efficiency is improved, also protect
The effect recommended has been demonstrate,proved, has reduced the work of user, ensure that the usage experience of user.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of the recommendation method for Ceramic Art Design that the embodiment of the present invention proposes;
Fig. 2 is a kind of schematic flow sheet of the recommendation method for Ceramic Art Design that the embodiment of the present invention proposes;
Fig. 3 is a kind of structural representation of the recommendation apparatus for Ceramic Art Design that the embodiment of the present invention proposes;
Fig. 4 is a kind of structural representation of the recommendation apparatus for Ceramic Art Design that the embodiment of the present invention proposes;
Fig. 5 is a kind of structural representation of the recommendation apparatus for Ceramic Art Design that the embodiment of the present invention proposes.
Embodiment
Hereinafter, the various embodiments of the disclosure will be described more fully.The disclosure can have various embodiments, and
It can adjust and change wherein.It should be understood, however, that:It is limited to spy disclosed herein in the absence of by the various embodiments of the disclosure
Determine the intention of embodiment, but the disclosure should be interpreted as covering in the spirit and scope for the various embodiments for falling into the disclosure
All adjustment, equivalent and/or alternatives.
Hereinafter, disclosed in the term " comprising " that can be used in the various embodiments of the disclosure or " may include " instruction
Function, operation or the presence of element, and do not limit the increase of one or more functions, operation or element.In addition, such as exist
Used in the various embodiments of the disclosure, term " comprising ", " having " and its cognate are meant only to represent special characteristic, number
Word, step, operation, the combination of element, component or foregoing item, and be understood not to exclude first one or more other
Feature, numeral, step, operation, element, component or foregoing item combination presence or one or more features of increase, numeral,
Step, operation, element, component or foregoing item combination possibility.
In the various embodiments of the disclosure, stating "or" or " at least one in A or/and B " includes what is listed file names with
Any combinations of word or all combinations.For example, " A or B " or " at least one in A or/and B " may include A, may include for statement
B may include A and B both.
The statement (" first ", " second " etc.) used in the various embodiments of the disclosure can be modified in various implementations
Various element in example, but respective sets can not be limited into element.For example, presented above be not intended to limit the suitable of the element
Sequence and/or importance.The purpose presented above for being only used for differentiating an element and other elements.For example, the first user fills
Put and indicate different user device with second user device, although the two is all user's set.For example, each of the disclosure is not being departed from
In the case of the scope of kind embodiment, the first element is referred to alternatively as the second element, and similarly, the second element is also referred to as first
Element.
It should be noted that:, can be by the first composition member if an element ' attach ' to another element by description
Part is directly connected to the second element, and " connection " the 3rd can be formed between the first element and the second element
Element.On the contrary, when an element " being directly connected to " is arrived into another element, it will be appreciated that be in the first element
And second be not present the 3rd element between element.
The term " user " used in the various embodiments of the disclosure, which may indicate that, to be used the people of electronic installation or uses electricity
The device (for example, artificial intelligence electronic installation) of sub-device.
The term used in the various embodiments of the disclosure is only used for describing the purpose of specific embodiment and not anticipated
In the various embodiments of the limitation disclosure.As used herein, singulative is intended to also include plural form, unless context is clear
Chu it is indicated otherwise.Unless otherwise defined, all terms (including the technical term and scientific terminology) tool being otherwise used herein
There is the implication identical implication that the various embodiment one skilled in the art with the disclosure are generally understood that.The term
(term such as limited in the dictionary typically used) is to be interpreted as having and the situational meaning in correlative technology field
Identical implication and the implication with Utopian implication or overly formal will be not construed as, unless in the various of the disclosure
It is clearly defined in embodiment.
Embodiment 1
The embodiment of the present invention 1 discloses a kind of recommendation method of Ceramic Art Design, as shown in figure 1, including:
Step 101, the request for obtaining Ceramic Art Design;Wherein, design needs are included in the request;
Asked specifically, request can be word, including by word come the design needs that describe, such as color,
The various characteristic informations related to Ceramic Art Design such as shape, school, current popularity degree, directly with picture or can also be regarded
The modes such as frequency are used as request, and the picture or video in subsequently asking this kind are identified, to carry out feature extraction, and then
Extract the needs of design.
Step 102, extraction design needs from the request;
Specifically, request is different, the mode of extraction is different, illustrates, is then divided so that word is asked as an example
Word processing and progress semantics identity, so as to get design needs, in this embodiment, design needs to be with the shape of word
Formula, and the difference asked, the embodiment that the design being subsequently generated needs are different;The embodiment that specific design needs is with asking
Ask and carry out correspondingly.
Specifically, the design needs obtained are more, follow-up recommendation results are more accurate.
The quantity that design needs is more, and follow-up result is more accurate, and in another specific embodiment, each design needs
There can also be different recommendation weights, the specific recommendation weight can be user-defined, or system is given birth to automatically
Into each can also design needs what corresponding recommendation weight was just as.
Step 103, based on it is described design need with default Ceramic Art Design neutral net generation recommendation information;Wherein, institute
State the Ceramic Art Design scheme included in recommendation information to the design needs.
Specifically in one embodiment, in order to further improve the efficiency of processing, design needs can also be converted to
Binary data format, then input in Ceramic Art Design neutral net and handled, because machine language is binary system, thus it is logical
Binary data format is crossed, the process of identification can be accelerated, when being identified, it is not necessary to additionally carries out turning for data again
Change, therefore the efficiency of identification can be effectively improved.
In one embodiment, the Ceramic Art Design neutral net is to be set by quantity more than a number of sample ceramics
Meter scheme is trained generation;Wherein described sample Ceramic Art Design scheme includes Ceramic Art Design scheme and and Ceramic Art Design
Feedback result corresponding to scheme.
In a specific embodiment, as shown in Fig. 2 this method also includes:
Step 104, obtain feedback information corresponding with the recommendation information;Wherein, include in the feedback information anti-
Present result;
Step 105, based on the feedback result Ceramic Art Design scheme in recommendation information is labeled, generation sample pottery
Porcelain design;
Step 106, based on the sample Ceramic Art Design scheme generated the Ceramic Art Design neutral net is trained.
Here, being illustrated with a specific example, such as comment in the feedback effects of the Ceramic Art Design scheme 1 of generation
It is divided into 100 points, in the case, based on the scoring of Ceramic Art Design 1, (which includes ceramics for generation sample Ceramic Art Design scheme 1
Design 1 and corresponding 100 points of scoring), then it is further continued for giving sample Ceramic Art Design scheme 1 and comes to Ceramic Art Design god
It is trained through network, to generate the Ceramic Art Design neutral net of renewal.
After being trained to Ceramic Art Design neutral net, entered using loss function in a specific embodiment
What row was assessed, specifically in the case, this method also includes:
After being trained to the Ceramic Art Design neutral net, the Ceramic Art Design neutral net institute after training is obtained
Corresponding loss function;
If the loss function meets preset requirement, it is determined that the training currently to the Ceramic Art Design neutral net is complete
Into;
If the loss function is unsatisfactory for preset requirement, weight after being adjusted to the default training parameter in training process
Newly the Ceramic Art Design neutral net is trained.
Specifically, by such scheme, constantly Ceramic Art Design neutral net is trained, until Ceramic Art Design nerve net
The loss function that network trains meets preset requirement, then confirms that current Ceramic Art Design neutral net is qualified;As for application
The change of environment etc., preset requirement can also change therewith, be subsequently trained again based on the preset requirement after change.
In a specific embodiment, the sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Its
In, the Ceramic Art Design triple data include:The source design that is obtained at random in sample Ceramic Art Design scheme and with institute
The source design of stating belongs to the Top-Down Design scheme of one kind together, adheres to inhomogeneous reverse design scheme separately with the source design;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The consistent design of feedback result;
The reverse design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The inconsistent design of feedback result.
Specifically, further, illustrated herein with a specific embodiment, Ceramic Art Design triple data example
Such as can be respectively:The successful solution designed by professional Ceramic Art Design personnel obtained at random in sample Ceramic Art Design scheme
(such as corresponding scoring is 100 points, corresponding source design), the layman obtained at random in sample Ceramic Art Design scheme
Designed successful solution (such as corresponding scoring is 70 points, corresponding Top-Down Design scheme) and in sample Ceramic Art Design scheme
In the design (such as corresponding scoring is the corresponding reverse design scheme less than 20 points) of failure that obtains at random, passed through with this
Positive and negative contrast, it more effectively trained the identification accuracy of ceramics identification neutral net.
Embodiment 2
The embodiment of the present invention 2 also discloses a kind of recommendation apparatus of Ceramic Art Design, as shown in figure 3, including:
Acquisition module 201, for obtaining the request of Ceramic Art Design;Wherein, design needs are included in the request;
Extraction module 202, for the extraction design needs from the request;
Recommending module 203, for being needed and default Ceramic Art Design neutral net generation recommendation information based on the design;
Wherein, the Ceramic Art Design scheme to the design needs is included in the recommendation information.
In a specific embodiment, the Ceramic Art Design neutral net is to exceed a number of sample by quantity
Ceramic Art Design scheme is trained generation;Wherein described sample Ceramic Art Design scheme include Ceramic Art Design scheme and with pottery
Feedback result corresponding to porcelain design.
In a specific embodiment, as shown in figure 4, the equipment also includes:
Feedback training module 204, for obtaining feedback information corresponding with the recommendation information;Wherein, the feedback letter
Include feedback result in breath;
The Ceramic Art Design scheme in recommendation information is labeled based on the feedback result, generation sample Ceramic Art Design side
Case;
The Ceramic Art Design neutral net is trained based on the sample Ceramic Art Design scheme generated.
In a specific embodiment, as shown in figure 5, the equipment also includes:
Evaluation module 205, for after being trained to the Ceramic Art Design neutral net, obtaining the pottery after training
Loss function corresponding to porcelain design neutral net;
If the loss function meets preset requirement, it is determined that the training currently to the Ceramic Art Design neutral net is complete
Into;
If the loss function is unsatisfactory for preset requirement, weight after being adjusted to the default training parameter in training process
Newly the Ceramic Art Design neutral net is trained.
In a specific embodiment, the sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Its
In, the Ceramic Art Design triple data include:The source design that is obtained at random in sample Ceramic Art Design scheme and with institute
The source design of stating belongs to the Top-Down Design scheme of one kind together, adheres to inhomogeneous reverse design scheme separately with the source design;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The consistent design of feedback result;
The reverse design scheme to be obtaining with the source design at random in the sample Ceramic Art Design scheme
The inconsistent design of feedback result.
With this, the embodiment of the present invention proposes a kind of recommendation method and apparatus of Ceramic Art Design, and wherein this method includes:Obtain
Take the request of Ceramic Art Design;Wherein, design needs are included in the request;Extraction design needs from the request;It is based on
The design needs and default Ceramic Art Design neutral net generation recommendation information;Wherein, include in the recommendation information pair
The Ceramic Art Design scheme that the design needs.Scheme with this by the embodiment of the present invention, realizes automatic recommendation, improves effect
Rate, in addition, being to need to generate recommendation information in Ceramic Art Design neutral net based on design, while efficiency is improved, also protect
The effect recommended has been demonstrate,proved, has reduced the work of user, ensure that the usage experience of user.
It will be appreciated by those skilled in the art that accompanying drawing is a schematic diagram for being preferable to carry out scene, module in accompanying drawing or
Flow is not necessarily implemented necessary to the present invention.
It will be appreciated by those skilled in the art that the module in device in implement scene can be described according to implement scene into
Row is distributed in the device of implement scene, can also carry out one or more dresses that respective change is disposed other than this implement scene
In putting.The module of above-mentioned implement scene can be merged into a module, can also be further split into multiple submodule.
The invention described above sequence number is for illustration only, does not represent the quality of implement scene.
Disclosed above is only several specific implementation scenes of the present invention, and still, the present invention is not limited to this, Ren Heben
What the technical staff in field can think change should all fall into protection scope of the present invention.
Claims (10)
1. a kind of recommendation method of Ceramic Art Design, it is characterised in that including:
Obtain the request of Ceramic Art Design;Wherein, design needs are included in the request;
Extraction design needs from the request;
Needed and default Ceramic Art Design neutral net generation recommendation information based on the design;Wherein, in the recommendation information
Include the Ceramic Art Design scheme to the design needs.
A kind of 2. recommendation method of Ceramic Art Design as claimed in claim 1, it is characterised in that the Ceramic Art Design neutral net
It is that generation is trained more than a number of sample Ceramic Art Design scheme by quantity;Wherein described sample Ceramic Art Design side
Case includes Ceramic Art Design scheme and feedback result corresponding with Ceramic Art Design scheme.
3. the recommendation method of a kind of Ceramic Art Design as claimed in claim 1, it is characterised in that also include:
Obtain feedback information corresponding with the recommendation information;Wherein, feedback result is included in the feedback information;
The Ceramic Art Design scheme in recommendation information is labeled based on the feedback result, generates sample Ceramic Art Design scheme;
The Ceramic Art Design neutral net is trained based on the sample Ceramic Art Design scheme generated.
4. the recommendation method of a kind of Ceramic Art Design as claimed in claim 3, it is characterised in that also include:
After being trained to the Ceramic Art Design neutral net, obtain corresponding to the Ceramic Art Design neutral net after training
Loss function;
If the loss function meets preset requirement, it is determined that currently the training to the Ceramic Art Design neutral net is completed;
It is again right after being adjusted to the default training parameter in training process if the loss function is unsatisfactory for preset requirement
The Ceramic Art Design neutral net is trained.
A kind of 5. recommendation method of Ceramic Art Design as described in any one in claim 2-4, it is characterised in that
The sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Wherein, the Ceramic Art Design triple packet
Include:The source design that is obtained at random in sample Ceramic Art Design scheme and the forward direction for belonging to one kind together with the source design
Design and the source design adhere to inhomogeneous reverse design scheme separately;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme is anti-with the source design to be obtained at random in the sample Ceramic Art Design scheme
Present the consistent design of result;
The reverse design scheme is anti-with the source design to be obtained at random in the sample Ceramic Art Design scheme
Present the inconsistent design of result.
A kind of 6. recommendation apparatus of Ceramic Art Design, it is characterised in that including:
Acquisition module, for obtaining the request of Ceramic Art Design;Wherein, design needs are included in the request;
Extraction module, for the extraction design needs from the request;
Recommending module, for being needed and default Ceramic Art Design neutral net generation recommendation information based on the design;Wherein, institute
State the Ceramic Art Design scheme included in recommendation information to the design needs.
A kind of 7. recommendation apparatus of Ceramic Art Design as claimed in claim 6, it is characterised in that the Ceramic Art Design neutral net
It is that generation is trained more than a number of sample Ceramic Art Design scheme by quantity;Wherein described sample Ceramic Art Design side
Case includes Ceramic Art Design scheme and feedback result corresponding with Ceramic Art Design scheme.
8. a kind of recommendation apparatus of Ceramic Art Design as claimed in claim 6, it is characterised in that also include:
Feedback training module, for obtaining feedback information corresponding with the recommendation information;Wherein, included in the feedback information
There is feedback result;
The Ceramic Art Design scheme in recommendation information is labeled based on the feedback result, generates sample Ceramic Art Design scheme;
The Ceramic Art Design neutral net is trained based on the sample Ceramic Art Design scheme generated.
9. a kind of recommendation apparatus of Ceramic Art Design as claimed in claim 8, it is characterised in that also include:
Evaluation module, for after being trained to the Ceramic Art Design neutral net, obtaining the Ceramic Art Design after training
Loss function corresponding to neutral net;
If the loss function meets preset requirement, it is determined that currently the training to the Ceramic Art Design neutral net is completed;
It is again right after being adjusted to the default training parameter in training process if the loss function is unsatisfactory for preset requirement
The Ceramic Art Design neutral net is trained.
A kind of 10. recommendation apparatus of Ceramic Art Design as described in any one in claim 7-9, it is characterised in that
The sample Ceramic Art Design scheme includes:Ceramic Art Design triple data;Wherein, the Ceramic Art Design triple packet
Include:The source design that is obtained at random in sample Ceramic Art Design scheme and the forward direction for belonging to one kind together with the source design
Design and the source design adhere to inhomogeneous reverse design scheme separately;
Wherein, the source design is any design obtained at random in the sample Ceramic Art Design scheme;
The Top-Down Design scheme is anti-with the source design to be obtained at random in the sample Ceramic Art Design scheme
Present the consistent design of result;
The reverse design scheme is anti-with the source design to be obtained at random in the sample Ceramic Art Design scheme
Present the inconsistent design of result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710576598.2A CN107357995A (en) | 2017-07-14 | 2017-07-14 | A kind of recommendation method and apparatus of Ceramic Art Design |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710576598.2A CN107357995A (en) | 2017-07-14 | 2017-07-14 | A kind of recommendation method and apparatus of Ceramic Art Design |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107357995A true CN107357995A (en) | 2017-11-17 |
Family
ID=60291935
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710576598.2A Pending CN107357995A (en) | 2017-07-14 | 2017-07-14 | A kind of recommendation method and apparatus of Ceramic Art Design |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107357995A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112287481A (en) * | 2020-10-27 | 2021-01-29 | 上海设序科技有限公司 | Mechanical design scheme searching method and device based on three-dimensional point cloud |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1873648A (en) * | 2005-06-01 | 2006-12-06 | 通用汽车环球科技运作公司 | Casting design optimization system for shape castings |
CN105989510A (en) * | 2015-02-06 | 2016-10-05 | 展讯通信(上海)有限公司 | Online goods recommending system and device based on neural network, and mobile terminal |
CN106778527A (en) * | 2016-11-28 | 2017-05-31 | 中通服公众信息产业股份有限公司 | A kind of improved neutral net pedestrian recognition methods again based on triple losses |
CN106779922A (en) * | 2016-11-30 | 2017-05-31 | 广州市万表科技股份有限公司 | Recommend method and device |
WO2017106977A1 (en) * | 2015-12-23 | 2017-06-29 | Milq Inc. | End-to-end deep collaborative filtering |
-
2017
- 2017-07-14 CN CN201710576598.2A patent/CN107357995A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1873648A (en) * | 2005-06-01 | 2006-12-06 | 通用汽车环球科技运作公司 | Casting design optimization system for shape castings |
CN105989510A (en) * | 2015-02-06 | 2016-10-05 | 展讯通信(上海)有限公司 | Online goods recommending system and device based on neural network, and mobile terminal |
WO2017106977A1 (en) * | 2015-12-23 | 2017-06-29 | Milq Inc. | End-to-end deep collaborative filtering |
CN106778527A (en) * | 2016-11-28 | 2017-05-31 | 中通服公众信息产业股份有限公司 | A kind of improved neutral net pedestrian recognition methods again based on triple losses |
CN106779922A (en) * | 2016-11-30 | 2017-05-31 | 广州市万表科技股份有限公司 | Recommend method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112287481A (en) * | 2020-10-27 | 2021-01-29 | 上海设序科技有限公司 | Mechanical design scheme searching method and device based on three-dimensional point cloud |
CN112287481B (en) * | 2020-10-27 | 2023-11-21 | 上海设序科技有限公司 | Mechanical design scheme searching method and device based on three-dimensional point cloud |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107038765A (en) | A kind of dynamic check class attendance system and method | |
CN107547554A (en) | A kind of smart machine remote assisting system based on augmented reality | |
CN105224665A (en) | A kind of wrong topic management method and system | |
CN106204378A (en) | The processing method of a kind of lesson data arrangement and system | |
CN106910381A (en) | A kind of piano intelligent tutoring system | |
CN108389235A (en) | A kind of intelligence child drawing entertainment systems and its application method | |
Van der Meulen | Between Benjamin and McLuhan: Vilém Flusser's Media Theory | |
CN107423350A (en) | A kind of method and apparatus of technique transfers | |
CN104680277A (en) | Method and system for negotiating and signing electronic contract online | |
CN107871416A (en) | A kind of online course learning system caught based on face recognition expression | |
CN107357995A (en) | A kind of recommendation method and apparatus of Ceramic Art Design | |
CN106411703A (en) | Information synchronization method and apparatus | |
CN106209513A (en) | IEC 61850 multi-client implementation method based on burse mode | |
CN107733971A (en) | A kind of wisdom education big data basic system | |
CN104866361A (en) | System and method for editing, transmitting and downloading school homework | |
CN105303336A (en) | Circuit system and application method used for detecting student attendance and lesson taking statuses | |
CN104933648A (en) | A generation apparatus and a generation method for on-the-Internet on-line courseware | |
CN107705645A (en) | Teaching auxiliary system based on augmented reality | |
CN104363308B (en) | Intelligent the finger ring pairing means of communication and system | |
CN104463736A (en) | System of querying student studies for student parents | |
CN106230928A (en) | A kind of method and device of files passe | |
CN108257437A (en) | A kind of children's long-distance education control system for identifying based on Internet of Things | |
CN110286767A (en) | A method of based on teaching material making virtual display course in kind | |
Kao et al. | The Design of Internet Collaborative Learning System Structure with the Integration of 3D Virtual Instruments | |
CN104980291A (en) | Intelligent conference control system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171117 |
|
RJ01 | Rejection of invention patent application after publication |