CN105488696A - Multi-target product material design method - Google Patents
Multi-target product material design method Download PDFInfo
- Publication number
- CN105488696A CN105488696A CN201510874460.1A CN201510874460A CN105488696A CN 105488696 A CN105488696 A CN 105488696A CN 201510874460 A CN201510874460 A CN 201510874460A CN 105488696 A CN105488696 A CN 105488696A
- Authority
- CN
- China
- Prior art keywords
- product
- perceptible
- evaluation
- consumer
- semantic
- 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
- 239000000463 material Substances 0.000 title claims abstract description 134
- 238000013461 design Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims abstract description 3
- 230000001149 cognitive effect Effects 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 7
- 239000004033 plastic Substances 0.000 claims description 5
- 229920003023 plastic Polymers 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 8
- 230000008447 perception Effects 0.000 abstract description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 3
- 230000016776 visual perception Effects 0.000 abstract 3
- 230000002996 emotional effect Effects 0.000 abstract 1
- 238000013139 quantization Methods 0.000 abstract 1
- 238000013507 mapping Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 2
- 235000017491 Bambusa tulda Nutrition 0.000 description 2
- 241001330002 Bambuseae Species 0.000 description 2
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 2
- 238000012356 Product development Methods 0.000 description 2
- 239000011425 bamboo Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011960 computer-aided design Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000036548 skin texture Effects 0.000 description 1
- 238000013456 study Methods 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000005491 wire drawing Methods 0.000 description 1
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-target product material design method. The method comprises: by taking the visual perception and tactile perception of target consumers and the material production costs of enterprises as design and development targets, extracting the visual perception and tactile perception quantization values of the target consumers to product materials through semantic evaluation research, and collecting the material costs of the enterprises; and performing fitting calculation on the visual perception evaluation value, tactile perception evaluation value and cost of each product material and corresponding product material features, constructing an evaluation prediction model of the product material, and performing design by applying a computer aided optimization algorithm on the basis of the prediction model to generate a new material design scheme. According to the method, enterprise designers are helped to more fully mine perceptual demands of consumers in the early stage of material design and development, the generated scheme better conforms to emotional preferences of the consumers, and the material production costs of the enterprises are considered, so that the material design can meet actual conditions of the enterprises while conforming to perceptual preferences of the consumers.
Description
Technical field
The present invention relates to a kind of Computer assistant and optimizing design field, be specifically related to a kind of based on multiobject product material design method.
Background technology
Along with making rapid progress of material category, and the enriching constantly of process of surface treatment, product texture occupies very important effect in the appearance of product.The research launched around product material design at present mainly contains: (one) is cognitive and prediction to product material visual imagery: the solution space first constructing product material feature, then image perception experiment is carried out, next built the quantification mapping relations of material feature and perception image by Mathematical Fitting gimmick, set up and evaluate and forecast model.If the cognitive transformation between material texture key element and consumer's visual preference image is funtcional relationship by paper " product material texture Preference image evolve cognitive algorithm and system ", be used for consumer's hobby of predictably sheet material matter.(2) to cognition and the prediction of product material tactile experience: the solution space constructing product material feature, then material tactile experience perception experiment is carried out, next built the quantification mapping relations of material feature and tactile experience perception by the method such as Conjoint Analysis, quantification one class, set up and evaluate and forecast model.
Current research concentrates on product material vision or the independent cognitive appraisal of sense of touch and prediction substantially, seldom will both joint studyes, and there is no the design generation method of product material and relate to; The emphasis paid close attention to is all launch product material Quality Research with the angle of consumer, and the less angle from product development enterprise launches research.
Summary of the invention
For overcoming the shortcoming of above-mentioned existing product Research on material, the present invention discloses a kind of multiple goal product material design method, helps enterprise to design the material of realistic demand at development.
Carrying out as follows of the technical solution used in the present invention:
(1) collection of product material: determine the product type wanting exploitation and design, from market, network, newpapers and periodicals etc. take pictures and collect such product picture, except the picture high with similarity of deblurring, to remaining product picture numbering; Then gather material sample in kind according to the material type occurred in the picture arranged, and number;
(2) the semantic word of customer segmentation and representativeness extracts: adopt spoken language analysis form to allow consumer write out them and think the semantic word that may be used for describing this series products, select the typical semantic word that the frequency of occurrences is higher; Make semantic questionnaire from the product picture of step (1) the random screening part number of finishing in conjunction with typical semantic word, adopt 7 grades of Scale assessment methods, then invite consumer to fill in semantic questionnaire, then add up questionnaire result; Determine by cluster analysis the number that segments market, then enterprise segments market as target consumer group using one of them, calculates the distance center of semantic word in target segments market, then the semantic word that distance center is nearest is the semantic word of representativeness in target consumer market;
(3) consumer's visually-perceptible cognitive appraisal: sample in kind for the material in representative for step (2) semantic word and step (1) is made semantic evaluation questionnaire, invite consumer to participate in semantic knowledge evaluation experimental, the evaluation score value statistic record of each product material for semantic word is got off;
(4) consumer's tactilely-perceptible is evaluated: sample in kind for the material in step (1) and the sense of touch preference degree of consumer to this series products are made tactilely-perceptible and evaluates questionnaire, allow the consumer in step (3) again participate in tactilely-perceptible evaluation experimental, the evaluation score value statistic record of each product material for sense of touch preference degree is got off;
(5) product material cost gathers: arranged the cost providing the product material collected in step (1) according to practical condition by enterprise;
(6) weight scale: invite cognitive to visually-perceptible, between tactilely-perceptible and material cost three the significance level of industry specialists 9 scaling laws to carry out evaluation marking, then can calculate three's weight separately;
(7) material feature decomposition: candidate's material structural feature of unlike material project elements and each project elements in analytic product material system;
(8) material evaluation maps matching: the visually-perceptible evaluation of estimate of each product material, tactilely-perceptible evaluation of estimate and cost are carried out the Fitting Calculation with this corresponding material feature respectively, constructs the valuation prediction models of this series products material;
(9) multiple goal product material conceptual design generates: application intelligent optimization method generates plastics on new materials scheme, each new departure predicts its visually-perceptible value, tactilely-perceptible value and cost respectively by three evaluation models in step (8), draw the score of material scheme by the weight of three in step (6) again, the material scheme that last fitness value score is the highest may be used in the plastics on new materials exploitation in target segments market.
The beneficial effect that the present invention is compared to the prior art had is:
One, the visually-perceptible of consumer is combined research with tactilely-perceptible, effectively assist enterprise personnel can excavate the perceptual demand of consumer fully in the material of developing new product.
Two, on the basis of excavating consumer's perceptual demand, by the incorporated research of material cost of enterprise, make the material design of new product meet the actual conditions of enterprise, avoid the situation emphasizing merely consumer's perceptual demand or enterprise's rationality cost.
Three, on the basis of material evaluation model, propose the method for product material design, assist enterprise to improve design efficiency.
Four, the product material design method for multiple target is proposed, the new product development in effective auxiliary enterprises surrounding target market.
Accompanying drawing explanation
Fig. 1 cup material objective design method and technology route map.
The bamboo cup full pattern exemplary plot that Fig. 2 gathers.
The material that Fig. 3 collects sample instantiation figure in kind.
7 form scale table sample figure in Fig. 4 questionnaire.
Fig. 5 customer segmentation and the semantic word of representativeness extract shows table sample figure.
Fig. 6 cup material project elements and characteristic element and encoding examples table table sample figure.
Fig. 7 cup material binary coded form sample table master drawing.
Fig. 8 cup material objective design schemes generation process flow diagram.
The cup material scheme phenogram that Fig. 9 computing draws.
Embodiment
For cup material design, the invention will be further described with embodiment by reference to the accompanying drawings below, and Fig. 1 shows concrete Technology Roadmap of the present invention, and the present invention carries out according to the following steps:
(1) product material gathers: need according to the production and operation of enterprise the cup product picture (as Fig. 2) and the corresponding material sample (as Fig. 3) in kind that gather unlike material.Locally from the network media, newspapers and periodicals, supermarket, sales field etc. to collect or the picture of shooting cup, except the picture high with similarity of deblurring, with image processing software by remaining product picture uniform sizes and resolution, and number with arabic numeral; Often plant the sample in kind of material according to the material type collection occurred in the product picture collected, number equally.
(2) the semantic word of customer segmentation and representativeness extracts: allow consumer write out them by spoken language analysis form and think the semantic word that may be used for describing cup, select the typical semantic word that the frequency of occurrences is higher; Make semantic questionnaire from the product picture of step (1) the random screening part number of finishing and typical semantic word, adopt 7 grades of evaluation assessments (scale table sample is shown in Fig. 4), then invite consumer to fill in semantic questionnaire, statistics questionnaire result; As shown in Figure 5, obtain 3 to the data K-mean cluster analysis of questionnaire statistics to segment market, select to segment market 3 for target consumer group, in colony, " modern times " are nearest apart from such centre distance, numerical value is 1.741, therefore can select " modern times " representatively semantic word of property.
(3) consumer's visually-perceptible is evaluated: sample in kind for the material in step (2) " modern times " semantic word and step (1) is made semantic evaluation questionnaire, the same Fig. 4 of scale table sample, target consumer is invited to participate in semantic knowledge evaluation experimental, in evaluation experimental process, sample in kind for material is placed in face of consumer, consumer, according to the direct feel marking of oneself, obtains target consumer and quantizes score value to product material visually-perceptible after statistics.
(4) consumer's tactilely-perceptible is evaluated: sample in kind for the material in step (1) and the sense of touch preference degree of consumer to this series products are made tactilely-perceptible and evaluates questionnaire, consumer is invited to participate in tactilely-perceptible evaluation experimental, across dividing plate between consumer and material sample, can not directly see material sample, but can arbitrarily touch.After evaluation experimental terminates, data are added up, obtain target consumer and quantize score value to by the sense of touch of product material hobby.
(5) product material cost gathers: the cost being provided the unlike material collected by enterprise according to the condition of production, as supposed here, the overall cost of bamboo cup is 3 yuan one.
(6) weight scale: invite industry specialists with 9 scaling laws to visually-perceptible, tactilely-perceptible and material cost significance level assignment, statistics can obtain the numerical value of each target, here suppose that the statistical value of visually-perceptible, tactilely-perceptible and material cost is respectively 5.6,7.8,4.7, so can calculate three's weight separately, as the weights W of visually-perceptible
depending on=X
depending on/ (X
depending on+ X
touch+ X
become), equal 30.9%.
(7) material feature decomposition: the material system of a category product can regard as the candidate's material structural feature by different material project elements and each project elements.Fig. 6 is project elements and the candidate feature key element formation information slip of cup material.
(8) evaluation of product material maps matching: 1. before setting up product material evaluation model, first to encode to product material, binary coding is adopted to encode to product feature key element, as shown in Figure 7, during according to the material featured aspects shown in figure, then the binary coding of this product material is " 0101111100 ";
2. the rear numerical value to obtaining in step (3), (4) and (5) of having encoded is normalized out respectively, is all normalized to by numerical value between (0,1); Because visually-perceptible and tactilely-perceptible are all maximum problem, then need not process further after data normalization process, and material cost is minimum problem, in order to it will be converted into maximum problem by convenience of calculation.
3. the mapping relations of self organizing artificial neural network difference matching product material and " modern times " semantic word, sense of touch preference degree and material cost.Using product material feature as input independent variable, the value after corresponding " modern times " semanteme, sense of touch hobby and the normalization of material cost is as output dependent variable; After setting the parameters such as network hierarchical structure, learning rate, initial weight, initial threshold, just training network can be started, network upgrades weights and threshold value in continuous iterative process, adjust the error between output valve and normalized value reducing network, when network error reaches default fit object, complete material and map the foundation evaluating type.The mapping evaluation model of " modern times " semanteme, sense of touch hobby and material cost three targets will be built altogether.The mapping evaluation model constructed can be evaluated the plastics on new materials scheme that step (9) design generates and predict.
Multiple goal cup material conceptual design generates: adopt genetic algorithm to carry out intelligent Computer Aided Design and to correspond to actual needs cup material scheme, cup material objective design schemes generation process flow diagram is shown in Fig. 8.The first random initial population producing material scheme, " modern times " of the mapping evaluation model numerical procedure that the individuality in population is set up by step (8) are semantic, sense of touch hobby and material cost three desired values, the fitness value of material scheme is gone out again according to step (6) weight gradation calculations, next by selecting, intersect, the genetic manipulations such as variation, produce population of future generation, individual scheme in every generation population all will calculate fitness value, when genetic algebra reaches predetermined iterations, the 1010001000 material schemes that are finally encoded to are the scheme that fitness value is the highest, its material scheme as shown in Figure 9, transparency adopts low transparency, surface coating adopts anodic oxidation, roughness adopts light, skin texture adopts wire drawing, fitness value is 2.48.
Claims (1)
1., based on a multiobject product material design method, it is characterized in that carrying out as follows:
(1), the collection of product material: determine the product type wanting exploitation and design, from market, network, newpapers and periodicals photo information take pictures and collect such product picture, except the picture high with similarity of deblurring, to remaining product picture numbering; Then gather material sample in kind according to the material type occurred in the picture arranged, and number;
(2), the semantic word of customer segmentation and representativeness extracts: adopt spoken language analysis form to allow consumer write out them and think the semantic word that may be used for describing this series products, select the typical semantic word that the frequency of occurrences is higher; Make semantic questionnaire from the product picture of step (1) the random screening part number of finishing in conjunction with typical semantic word, adopt 7 grades of Scale assessment methods, then invite consumer to fill in semantic questionnaire, then add up questionnaire result; Determine by cluster analysis the number that segments market, then enterprise segments market as target consumer group using one of them, calculates the distance center of semantic word in target segments market, and the semantic word that so distance center is nearest is the semantic word of representativeness in target consumer market;
(3), consumer's visually-perceptible cognitive appraisal: sample in kind for the material in representative for step (2) semantic word and step (1) is made semantic evaluation questionnaire, invite target consumer to participate in semantic knowledge evaluation experimental, the evaluation score value statistic record of each product material for semantic word is got off;
(4), consumer's tactilely-perceptible is evaluated: sample in kind for the material in step (1) and the sense of touch preference degree of consumer to this series products are made tactilely-perceptible and evaluates questionnaire, invite target consumer to participate in tactilely-perceptible evaluation experimental, the evaluation score value statistic record of each product material for sense of touch preference degree is got off;
(5), product material cost gathers: arranged the cost providing the product material collected in step (1) according to practical condition by enterprise;
(6), weight scale: invite cognitive to visually-perceptible, between tactilely-perceptible and material cost three the significance level of industry specialists 9 scaling laws to carry out evaluation marking, then can calculate three's weight separately;
(7), material feature decomposition: candidate's material structural feature of unlike material project elements and each project elements in analytic product material system;
(8), material evaluation maps matching: the visually-perceptible evaluation of estimate of each product material, tactilely-perceptible evaluation of estimate and cost are carried out the Fitting Calculation with this corresponding material feature respectively, constructs the valuation prediction models of this series products material;
(9), multiple goal product material conceptual design generates: application intelligent optimization method generates plastics on new materials scheme, each new departure predicts its visually-perceptible value, tactilely-perceptible value and cost respectively by three evaluation models in step (8), draw the score of material scheme by the weight of three in step (6) again, the material scheme that last fitness value is the highest may be used in the plastics on new materials exploitation in target segments market.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510874460.1A CN105488696A (en) | 2015-12-02 | 2015-12-02 | Multi-target product material design method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510874460.1A CN105488696A (en) | 2015-12-02 | 2015-12-02 | Multi-target product material design method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105488696A true CN105488696A (en) | 2016-04-13 |
Family
ID=55675663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510874460.1A Pending CN105488696A (en) | 2015-12-02 | 2015-12-02 | Multi-target product material design method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105488696A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230121A (en) * | 2018-02-09 | 2018-06-29 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on Recognition with Recurrent Neural Network |
| CN110349194A (en) * | 2019-06-19 | 2019-10-18 | 广东工业大学 | A kind of method for selecting and relevant apparatus of furniture material |
| CN115034803A (en) * | 2022-04-13 | 2022-09-09 | 北京京东尚科信息技术有限公司 | New article mining method and device and storage medium |
-
2015
- 2015-12-02 CN CN201510874460.1A patent/CN105488696A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230121A (en) * | 2018-02-09 | 2018-06-29 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on Recognition with Recurrent Neural Network |
| CN110349194A (en) * | 2019-06-19 | 2019-10-18 | 广东工业大学 | A kind of method for selecting and relevant apparatus of furniture material |
| CN115034803A (en) * | 2022-04-13 | 2022-09-09 | 北京京东尚科信息技术有限公司 | New article mining method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948165B (en) | Fine granularity emotion polarity prediction method based on mixed attention network | |
| Le et al. | Interactive boundary prediction for object selection | |
| CN106920243A (en) | The ceramic material part method for sequence image segmentation of improved full convolutional neural networks | |
| CN111538761A (en) | Click rate prediction method based on attention mechanism | |
| CN111008693B (en) | Network model construction method, system and medium based on data compression | |
| CN106529503A (en) | Method for recognizing face emotion by using integrated convolutional neural network | |
| CN107609147B (en) | Method and system for automatically extracting features from log stream | |
| CN111967971A (en) | Bank client data processing method and device | |
| CN110210027B (en) | Fine-grained emotion analysis method, device, equipment and medium based on ensemble learning | |
| KR20200010672A (en) | Smart merchandise searching method and system using deep learning | |
| CN110110372B (en) | Automatic segmentation prediction method for user time sequence behavior | |
| CN106777402A (en) | A kind of image retrieval text method based on sparse neural network | |
| Lin et al. | Intelligent decision support for new product development: a consumer-oriented approach | |
| CN114492191A (en) | Heat station equipment residual life evaluation method based on DBN-SVR | |
| CN105488696A (en) | Multi-target product material design method | |
| CN110569355A (en) | Viewpoint target extraction and target emotion classification combined method and system based on word blocks | |
| CN110503186A (en) | Commodity sequence neural network model training method, device, electronic equipment | |
| CN117152427A (en) | Remote sensing image semantic segmentation method and system based on diffusion model and knowledge distillation | |
| CN114781503A (en) | Click rate estimation method based on depth feature fusion | |
| Patel et al. | Smart adaptive mesh refinement with NEMoSys | |
| Zhu et al. | Predicting google’s stock price with LSTM model | |
| CN115937516B (en) | Image semantic segmentation method and device, storage medium and terminal | |
| CN108596687B (en) | Advertisement targeted delivery method based on Hash learning | |
| CN117194966A (en) | Training method and related device for object classification model | |
| CN114882246A (en) | Image feature recognition method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160413 |
|
| RJ01 | Rejection of invention patent application after publication |