CN110046940A - A kind of Ads on Vehicles personalized push method and device - Google Patents
A kind of Ads on Vehicles personalized push method and device Download PDFInfo
- Publication number
- CN110046940A CN110046940A CN201910322017.1A CN201910322017A CN110046940A CN 110046940 A CN110046940 A CN 110046940A CN 201910322017 A CN201910322017 A CN 201910322017A CN 110046940 A CN110046940 A CN 110046940A
- Authority
- CN
- China
- Prior art keywords
- vehicles
- ads
- scene characteristic
- push
- calculated result
- 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]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0265—Vehicular advertisement
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
Abstract
The present invention relates to advertisements to launch technical field more particularly to a kind of Ads on Vehicles personalized push method and device.Linear model is pushed including establishing, according to push linear model analysis scene characteristic to obtain calculated result, pushes corresponding Ads on Vehicles according to calculated result.In the prior art, the different calculation step of Scenario Design is launched often through to different, so that corresponding advertisement is targetedly launched, but calculation step is many and diverse, it is larger to the demand of calculating.The present invention is by setting up push linear model analysis scene characteristic, calculated result according to push linear model pushes corresponding Ads on Vehicles, without setting up different calculation steps for different scenes, it is on the one hand effectively reduced calculation step, on the other hand effectively reduces the demand of calculating.
Description
Technical field
The present invention relates to advertisements to launch technical field more particularly to a kind of Ads on Vehicles personalized push method and device.
Background technique
Ads on Vehicles is one using abundant in-car entertainment culture life as business division, is aided with the service entry of advertising
Mesh.Ads on Vehicles can provide a covering extensively and contact the high completely new space of consumer's frequency, integrate image, sound,
The mobility of car and the feature that Population Capacity is big are made full use of, the information blank of passenger on the way is filled up.Ads on Vehicles at present
Push is often repeatability, and not for specific crowd and specific scene, pushing effect has randomness, because of this person
Need a kind of advertisement sending method that can be directed to specific crowd and place.
Chinese patent disclose a kind of personalized advertisement supplying system based on recognition of face and method [application number:
CN201810478513.1, publication number: CN108460638A] it include photographing module, processor and display screen, the photographing module
It is connected with the input terminal of processor, the display screen is connected with the output end of processor, and the processor includes image analysis mould
Block, information acquisition module, data analysis module, data memory module, communication module, advertisement matching module, advertising management module
With advertisement playing module.
Although human body face sign can be obtained using face recognition technology, and corresponding for the facial characteristics push obtained
Advertisement cause whole calculating process many and diverse, to calculating but in order to adapt to the different calculation step of different Scenario Designs
Demand is big, and the type for being applicable in scene is less, it can be seen that designs that a kind of operation is easier, is applicable in the type of more scene more
Add extensive advertisement sending method be very it is necessary to.
Summary of the invention
The technical issues of for the prior art, the present invention provides
In order to solve the above technical problems, the present invention provides technical solutions below:
A kind of Ads on Vehicles personalized push method, including push linear model is established, according to push linear model analysis scene
Feature pushes corresponding Ads on Vehicles according to calculated result.
Obtain current geography information, temporal information.It takes pictures to passenger, using artificial intelligence technology to the photograph of acquisition
Piece identified, to obtain the features such as age-sex and the expression of passenger and other features such as dress ornament and belongings.It establishes
Linear model, comprehensive analysis above- mentioned information are pushed, to obtain calculated result, and then are pushed corresponding with calculated result vehicle-mounted
Advertisement is to achieve the purpose that have targetedly advertisement.Compared to the prior art, the present invention pushes linear mould by establishing
Type analyzes current scene, without executing instruction for different Scenario Designs is different, on the one hand greatly reduces fortune
Process is calculated, calculating demand is reduced, is on the other hand effectively increased applicable scene type.
Further, comprising the following steps:
Step 1: contextual data is obtained；
Step 2: scene characteristic is extracted according to the contextual data；
Step 3: the scene characteristic is inputted into push linear model to obtain calculated result；
Step 4: corresponding Ads on Vehicles is pushed according to calculated result.
Further, the scene characteristic includes characteristics of image, geographical feature, temporal characteristics.
Further, the linear model formation of push are as follows:
Wherein xi be characterized label, β i be weight,It is calculated result for sign value, y.
Further, the feature tag includes image tag, geographical labels, time tag.
Further, describedValue be 0 or 1.
Further, using method described in any one of claim 1 to 6 claim.
Further, including scene characteristic acquiring unit, processing unit, advertisement pushing unit；The scene characteristic obtains
Unit obtains scene characteristic, and the scene characteristic that the scene characteristic acquiring unit will acquire is exported to processing unit；The processing
Unit receives the scene characteristic of the scene characteristic acquiring unit input to obtain calculated result；Described in the processing unit output
Calculated result is to the advertisement pushing unit.
Further, the scene characteristic acquiring unit includes contextual data acquiring unit, extraction unit；The scene number
Contextual data is obtained according to acquiring unit, the contextual data acquiring unit exports contextual data to extraction unit；The extraction
Unit receives the contextual data of the contextual data acquiring unit input to extract scene characteristic；Described in the extraction unit output
Scene characteristic is to the processing unit.
Further, push linear model is stored in the processing unit, the processing unit is by the scene characteristic
The push linear model is inputted to obtain calculated result.
Compared to the prior art, the invention has the following advantages that
Using push linear model, calculation step is unified, without designing different calculation steps for different situations, on the one hand
It is effectively simplified operation process, on the other hand effectively reduces calculating demand.
Using push linear model, applicable a variety of different application scenarios have effectively widened application range.
Detailed description of the invention
Fig. 1: Ads on Vehicles method for pushing flow chart.
Specific embodiment
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Embodiment one:
A kind of Ads on Vehicles personalized push method pushes linear model by establishing, according to push linear model analysis scene
Feature pushes corresponding Ads on Vehicles to obtain calculated result, according to calculated result.The following steps are included:
Step 1: contextual data is obtained.
Step 2: scene characteristic is extracted according to contextual data.Wherein scene characteristic includes characteristics of image, geographical feature, time
Feature.
Step 3: scene characteristic is inputted into push linear model to obtain calculated result.
Step 4: corresponding Ads on Vehicles is pushed according to calculated result.
Wherein push linear model formation are as follows:
Xi is characterized label, and feature tag includes image tag, geographical labels, time tag.β i is weight.For sign value,
The value of sign value is 0 or 1.Y is calculated result.
Contextual data includes image data, geodata, time data.By taking pictures passenger to obtain image data,
Image data is extracted to obtain characteristics of image.Such as: by facial recognition techniques identify image data with obtain passenger age,
Gender, expressive features.Image data is identified by image recognition technology to obtain the surface of such as dress ornament, belongings.It is logical
The coordinate of location technology acquisition current vehicle position is crossed to obtain geodata, is stored on local or line by retrieval
Map searches the landmark building in the nearby coordinates of current vehicle position to obtain geographical feature, such as: school, doctor
Institute.By the date and time of calling electronic clock to obtain current time data, the current date in time data is transferred,
And time section corresponding with current time is transferred with acquisition time feature.Wherein time section are as follows: be sometime to put
Starting point divides one section at regular intervals, so that one day time was divided into multiple and different sections, such as: with 8 points early
For starting point, one section was divided into every 3 hours until in 8 points of evening, be followed successively by morning peak, noon, afternoon, evening peak from front to back.
It is night by 8 points to second day of evening early 8 points.
Feature tag library is established before executing step 3, establishes push linear model according to feature tag library.Feature tag
Image tag, geographical labels, time tag are stored in library.Image tag includes the label for indicating passenger's age, such as:
Youth, children, middle age, old age, image tag further include the label for indicating passenger's gender, and image tag further includes for table
Show the label of passenger's expression, such as: it is happy, sad, sad.Geographical labels include the label for indicating landmark building, example
Such as: school, hospital.Time tag includes the label for indicating festivals or holidays, such as: weekend, National Day, time tag further include
For indicating the label of time section, such as: morning peak, noon, afternoon, evening peak, night.
It is stored with multiple and different image tags in feature tag library, is successively denoted as x1, x2, x3 until xi, acquisition
Multiple images feature is successively denoted as A1, A2, A3 until Ai, characteristics of image A1 and x1 is compared, if A1 is not identical as x1, with x1
Corresponding sign value1 is 0, at this time by A1 successively with x2, x3 until xi is compared, until xn identical with A1, then with
The corresponding sign value of xnThe value of n is 1, stops the comparison of characteristics of image A1 at this time, and A2 is compared with image tag one by one, until
X2n identical with A2, then sign value corresponding with x2n2n is 1.A3 can similarly be compared until whole characteristics of image compares
It finishes.If the image tag stored in A1 and feature tag library is all different, sign value is defaulted as 0.Similarly, it can obtain respectively
Sign value corresponding with geographical labels, time tag.Weight is setting value or default value, can be set according to actual demand
To adjust the significance level of feature tag.Sign value1, weight beta 1, the product of feature tag x1 three are denoted as y1, can similarly incite somebody to action
Sign value, weight, the product of feature tag three are successively denoted as y2, y3 until yi.To sum up, calculated result y is that y1, y2, y3 are straight
To the cumulative of yi and.To push corresponding Ads on Vehicles according to calculated result y.
Such as: the scene characteristic of acquisition is followed successively by morning peak, hospital, women, by contrast, these three scene characteristics and feature
Corresponding feature tag is respectively x11, x5, x37 in tag library, then sign value corresponding with these three feature tags respectively
It is 1, remaining feature tag sign value is 0.Weight corresponding with x11, x5, x37 is followed successively by 2,1,1.4, by sign value
It adds up one by one with weight and the product of feature tag three, calculated result y=2x11+x5+1.4x37 can be obtained.According to calculated result
The relevant Ads on Vehicles of retrieval and morning peak, hospital, women, and push corresponding Ads on Vehicles.
If giving up the smallest feature tag of weight currently without corresponding Ads on Vehicles, retrieval is corresponding vehicle-mounted again
Advertisement, if continuing to give up the smallest feature tag of weight still without corresponding Ads on Vehicles, until retrieving corresponding vehicle
Carry advertisement.In this example, if Ads on Vehicles not relevant to morning peak, hospital, women, since the weight of hospital is minimum, then
Give up this feature tag of hospital, thus push Ads on Vehicles corresponding with morning peak, women, if still without vehicle-mounted accordingly
Advertisement, the weight of women becomes minimum at this time, then gives up this feature tag of women, so that push is corresponding with morning peak vehicle-mounted
Advertisement.
Embodiment two:
Weight library is established before executing step 3, establishes push linear model according to weight library.One weighted value can correspond to one
Scene characteristic is also possible to a weighted value and corresponds to multiple scene characteristics.Scene characteristic is inputted into push linear model to call
The sign value of weighted value corresponding with scene characteristic, the then weighted value that is called is 1, and the sign value for being not called upon weighted value is 0,
Calculated result is obtained according to linear model calculation formula is pushed, thus push Ads on Vehicles corresponding with calculated result y.Example
Such as: storing 3 three β 1, β 2, β weighted values in weight library, be followed successively by 2,1,1.Wherein β 1 corresponding morning peak, evening peak, β 2 are right
Answer school, the corresponding male of β 3.Scene characteristic x1, x2, x3 of input are followed successively by noon, school, male.Then sign value be followed successively by 0,
1,1, both called β 2, β 3.Sign value and weight and the product of feature tag three are added up one by one, final acquisition calculated result y=
x2+x3.To push Ads on Vehicles corresponding with school, male.
Embodiment three:
A kind of Ads on Vehicles personalized push device, including scene characteristic acquiring unit, processing unit, advertisement pushing unit.Its
Middle scene characteristic acquiring unit includes contextual data acquiring unit, extraction unit.
Contextual data includes image data, geodata, time data.Contextual data acquiring unit includes for acquisition image
The camera of data is mounted on the top of vehicle seat, alignment lens seat, by taking pictures passenger to obtain picture number
According to.Contextual data acquiring unit further includes vehicle positioning unit, obtains the position of current vehicle by location technology to obtain
Take geodata.Contextual data acquiring unit further includes onboard clock unit, when obtaining the vehicle-mounted time and then obtain current
Between data.Image data that scene acquiring unit will acquire, geodata, time data are exported to extraction unit.
Scene characteristic includes characteristics of image, geographical feature, temporal characteristics.It is defeated that extraction unit receives scene data capture unit
Image data, geodata, the time data entered.Extraction unit includes face recognition unit, is identified by facial recognition techniques
Image data is to extract age, the gender, expressive features of passenger.Extraction unit further includes image identification unit, is known by image
Other technology identifies image data to extract the surface of such as dress ornament, belongings.Extraction unit further includes analytical unit, analysis
Unit analyzes geodata further to obtain the landmark building near present position, such as: school, travels at hospital
Garden etc., to obtain geographical feature.The further analysis time data of analytical unit are to get Date and the period, to obtain
Take temporal characteristics.Extraction unit exports characteristics of image, geographical feature, temporal characteristics to processing unit.
Processing unit includes storage element, computing unit.Model parameter is stored in storage element, computing unit receives figure
As feature, geographical feature, temporal characteristics, and call the model parameter in storage element thus according to push linear model to image
Feature, geographical feature, temporal characteristics carry out calculation processing, and then obtain calculated result.The calculated result that computing unit will acquire
It exports to advertisement pushing unit.
Advertisement pushing unit includes screen, Ads on Vehicles storage element, transfers unit.Screen is mounted on the upper of vehicle seat
Side, and it is directed at vehicle seat.Also may be mounted at vehicle seat leans on back, and is directed at back row seat.Transfer unit receiving area
The calculated result for managing unit input is transferred the Ads on Vehicles stored in Ads on Vehicles storage element according to calculated result, and will be adjusted
The Ads on Vehicles taken is launched on the screen, to push corresponding Ads on Vehicles.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (10)
1. a kind of Ads on Vehicles personalized push method, it is characterised in that: linear model is pushed including establishing, it is linear according to push
Model analysis scene characteristic pushes corresponding Ads on Vehicles to obtain calculated result, according to calculated result.
2. a kind of Ads on Vehicles personalized push method according to claim 1, it is characterised in that: the following steps are included:
Step 1: contextual data is obtained；
Step 2: scene characteristic is extracted according to the contextual data；
Step 3: the scene characteristic is inputted into push linear model to obtain calculated result；
Step 4: corresponding Ads on Vehicles is pushed according to calculated result.
3. a kind of Ads on Vehicles personalized push method according to claim 2, it is characterised in that: the scene characteristic packet
Include characteristics of image, geographical feature, temporal characteristics.
4. a kind of Ads on Vehicles personalized push method according to claim 2, it is characterised in that: the linear mould of push
Type formula are as follows:
Wherein xi be characterized label, β i be weight,It is calculated result for sign value, y.
5. a kind of Ads on Vehicles personalized push method according to claim 4, it is characterised in that: the feature tag packet
Include image tag, geographical labels, time tag.
6. a kind of Ads on Vehicles personalized push method according to claim 4, it is characterised in that: describedValue be 0 or
1。
7. a kind of Ads on Vehicles personalized push device, it is characterised in that: wanted using any one of claim 1 to 6 right
Seek the method.
8. a kind of Ads on Vehicles personalized push device according to claim 7, it is characterised in that: obtained including scene characteristic
Take unit, processing unit, advertisement pushing unit；
The scene characteristic acquiring unit obtains scene characteristic, the scene characteristic output that the scene characteristic acquiring unit will acquire
To processing unit；
The processing unit receives the scene characteristic of the scene characteristic acquiring unit input to obtain calculated result；
The processing unit exports the calculated result to the advertisement pushing unit.
9. a kind of Ads on Vehicles personalized push device according to claim 8, it is characterised in that: the scene characteristic obtains
Taking unit includes contextual data acquiring unit, extraction unit；
The contextual data acquiring unit obtains contextual data, and the contextual data acquiring unit exports contextual data to extraction
Unit；
The extraction unit receives the contextual data of the contextual data acquiring unit input to extract scene characteristic；
The extraction unit exports the scene characteristic to the processing unit.
10. a kind of Ads on Vehicles personalized push device according to claim 8, it is characterised in that: the processing unit
Push linear model is inside stored, the scene characteristic is inputted the push linear model and calculated to obtain by the processing unit
As a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322017.1A CN110046940A (en) | 2019-04-22 | 2019-04-22 | A kind of Ads on Vehicles personalized push method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322017.1A CN110046940A (en) | 2019-04-22 | 2019-04-22 | A kind of Ads on Vehicles personalized push method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110046940A true CN110046940A (en) | 2019-07-23 |
Family
ID=67278131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910322017.1A Pending CN110046940A (en) | 2019-04-22 | 2019-04-22 | A kind of Ads on Vehicles personalized push method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046940A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381574A (en) * | 2020-11-13 | 2021-02-19 | 广州通达汽车电气股份有限公司 | Advertisement putting method and device for public transport vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486680A (en) * | 2014-12-19 | 2015-04-01 | 珠海全志科技股份有限公司 | Video-based advertisement pushing method and system |
| CN104732413A (en) * | 2013-12-20 | 2015-06-24 | 中国科学院声学研究所 | Intelligent individuation video advertisement pushing method and system |
| CN105610929A (en) * | 2015-12-24 | 2016-05-25 | 北京奇虎科技有限公司 | Personalized data pushing method and device |
| CN105759965A (en) * | 2016-02-16 | 2016-07-13 | 广东工业大学 | Mobile advertisement interactive system and method based on Internet of Things |
| CN106445977A (en) * | 2015-08-12 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Picture pushing method and device |
| CN107295361A (en) * | 2017-06-22 | 2017-10-24 | 腾讯科技（深圳）有限公司 | A kind of content delivery method |
| CN108460638A (en) * | 2018-05-18 | 2018-08-28 | 郑州外思创造力文化传播有限公司 | A kind of personalized advertisement supplying system and method based on recognition of face |
| CN108600343A (en) * | 2018-04-09 | 2018-09-28 | 重庆路畅网络科技有限公司 | Ads on Vehicles intelligently pushing system and its control method |
-
2019
- 2019-04-22 CN CN201910322017.1A patent/CN110046940A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732413A (en) * | 2013-12-20 | 2015-06-24 | 中国科学院声学研究所 | Intelligent individuation video advertisement pushing method and system |
| CN104486680A (en) * | 2014-12-19 | 2015-04-01 | 珠海全志科技股份有限公司 | Video-based advertisement pushing method and system |
| CN106445977A (en) * | 2015-08-12 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Picture pushing method and device |
| CN105610929A (en) * | 2015-12-24 | 2016-05-25 | 北京奇虎科技有限公司 | Personalized data pushing method and device |
| CN105759965A (en) * | 2016-02-16 | 2016-07-13 | 广东工业大学 | Mobile advertisement interactive system and method based on Internet of Things |
| CN107295361A (en) * | 2017-06-22 | 2017-10-24 | 腾讯科技（深圳）有限公司 | A kind of content delivery method |
| CN108600343A (en) * | 2018-04-09 | 2018-09-28 | 重庆路畅网络科技有限公司 | Ads on Vehicles intelligently pushing system and its control method |
| CN108460638A (en) * | 2018-05-18 | 2018-08-28 | 郑州外思创造力文化传播有限公司 | A kind of personalized advertisement supplying system and method based on recognition of face |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381574A (en) * | 2020-11-13 | 2021-02-19 | 广州通达汽车电气股份有限公司 | Advertisement putting method and device for public transport vehicle |
| CN112381574B (en) * | 2020-11-13 | 2021-12-03 | 广州通达汽车电气股份有限公司 | Advertisement putting method and device for public transport vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103973968B (en) | Electronic installation and its image synthesis method | |
| CN109064405A (en) | A kind of multi-scale image super-resolution method based on dual path network | |
| CN110489582A (en) | Personalization shows the generation method and device, electronic equipment of image | |
| CN109804357A (en) | Server, client, control method and storage medium | |
| US20210248427A1 (en) | Method and system of neural network object recognition for image processing | |
| CN111108508B (en) | Face emotion recognition method, intelligent device and computer readable storage medium | |
| CN110443120A (en) | A kind of face identification method and equipment | |
| CN102917159A (en) | Mode removal for improved multi-modal background subtraction | |
| CN110414376A (en) | Update method, face recognition cameras and the server of human face recognition model | |
| CN113935435A (en) | Multi-modal emotion recognition method based on space-time feature fusion | |
| CN106529375A (en) | Mobile terminal and object feature identification method for image of mobile terminal | |
| WO2018128015A1 (en) | Suspiciousness estimation model generation device | |
| CN110046940A (en) | A kind of Ads on Vehicles personalized push method and device | |
| CN112016592B (en) | Domain adaptive semantic segmentation method and device based on cross domain category perception | |
| CN111797856B (en) | Modeling method and device, storage medium and electronic equipment | |
| WO2023202006A1 (en) | Systems and methods for task execution | |
| CN115115552B (en) | Image correction model training method, image correction device and computer equipment | |
| CN113362455B (en) | Video conference background virtualization processing method and device | |
| CN109308637A (en) | Entity consumption scene oriented marketing method, device and system | |
| CN111798019A (en) | Intention prediction method, intention prediction device, storage medium and electronic equipment | |
| CN115937938A (en) | Training method of face identity recognition model, face identity recognition method and device | |
| US20220319232A1 (en) | Apparatus and method for providing missing child search service based on face recognition using deep-learning | |
| Lee et al. | Implementation of age and gender recognition system for intelligent digital signage | |
| CN109754319A (en) | Credit score determines system, method, terminal and server | |
| CN113515992A (en) | Object recognition method, device and storage medium |
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: 20190723 |
|
| RJ01 | Rejection of invention patent application after publication |