CN107844980A - Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment - Google Patents
Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment Download PDFInfo
- Publication number
- CN107844980A CN107844980A CN201710940939.XA CN201710940939A CN107844980A CN 107844980 A CN107844980 A CN 107844980A CN 201710940939 A CN201710940939 A CN 201710940939A CN 107844980 A CN107844980 A CN 107844980A
- Authority
- CN
- China
- Prior art keywords
- false
- true
- commodity
- characteristic information
- measured
- 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
- 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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The present invention relates to a kind of commercial articles true and false discrimination method and device,Computer-readable storage medium and equipment,Acquisition passes through machine learning method,The commercial articles true and false that machine learning determination is carried out according to the characteristic information storehouse of default sample commodity differentiates model,Obtain the characteristic information of commodity to be measured,Differentiate that the input of model carries out commercial articles true and false discriminating using the characteristic information of commodity to be measured as commercial articles true and false,Model is differentiated using the commercial articles true and false established by presetting machine learning method according to the characteristic information storehouse of sample commodity,True and false discriminating is carried out to commodity to be measured,So as to realize the true and false accurate discriminating of commodity to be measured,And without by manually carrying out true and false discriminating,Avoid due to the problem of human subjective's property influences identification result,Improve commodity and differentiate accuracy,Then further according to data area corresponding to the authentication data and each default true and false grade difference,Determine the true and false grade of the commodity to be measured,It is easy to more intuitively know the true and false degree of commodity to be measured.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of commercial articles true and false discrimination method and device, computer
Storage medium and equipment.
Background technology
With the fast development of ecommerce, shopping online has been come into huge numbers of families, home-confined to enjoy
Market shopping it is convenient.Due to the virtual and limitation of regulator system of network, the commodity of electric business platform are very different,
Substantial amounts of counterfeit and shoddy goods are flooded with, this had both compromised the rights and interests of consumer and regular producer, and was done shopping to consumer network
The difficulty of selection commodity is brought, has had a strong impact on the sound development of ecommerce.Therefore, for ensure ecommerce health hair
Exhibition, it is true and false to commodity progress to discern between right and wrong what is be often necessary.
At present, the common method for carrying out commercial articles true and false identification is that consumer enters according to information such as the introduction of commodity and pictures
Pedestrian's work differentiates, but because artificial discriminating has strong subjectivity, influences identification result, it is impossible to ensures the accuracy differentiated.
The content of the invention
Based on this, it is necessary to for differentiating the problem of accuracy is low, there is provided a kind of commercial articles true and false discrimination method and device, meter
Calculation machine storage medium and equipment.
A kind of commercial articles true and false discrimination method, comprises the following steps：
Acquisition passes through machine learning method, and the business of machine learning determination is carried out according to the characteristic information storehouse of default sample commodity
The true and false discriminating model of product；
Obtain the characteristic information of commodity to be measured；
Differentiate that the input of model carries out commercial articles true and false mirror using the characteristic information of the commodity to be measured as the commercial articles true and false
Not, true and false authentication data is obtained；
According to data area corresponding to the authentication data and each default true and false grade difference, the commodity to be measured are determined
True and false grade.
A kind of commercial articles true and false identification device is also provided, including：
Differentiate model acquisition module, for obtaining by default machine learning device, according to the feature of default sample commodity
The commercial articles true and false that information bank carries out machine learning determination differentiates model；
Fisrt feature data obtaining module, for obtaining the characteristic information of commodity to be measured；
Authentication data acquisition module, for differentiating model using the characteristic information of the commodity to be measured as the commercial articles true and false
Input carry out commercial articles true and false discriminating, obtain true and false authentication data；
True and false identification module, for the data model according to corresponding to the authentication data and each default true and false grade difference
Enclose, determine the true and false grade of the commodity to be measured.
A kind of computer-readable storage medium is also provided, is stored thereon with computer program, the computer program is held by processor
The step of above method is realized during row.
A kind of computer equipment is also provided, including memory, processor and is stored on the memory and can be in institute
The computer program run on processor is stated, realizes above-mentioned method described in the computing device during computer program.
Commercial articles true and false mirror to be measured is carried out by above-mentioned commercial articles true and false discrimination method and device, computer-readable storage medium and equipment
When other, on the one hand, reflected using the commercial articles true and false established by presetting machine learning method according to the characteristic information storehouse of sample commodity
Other model, true and false discriminating is carried out to commodity to be measured, obtains authentication data, so as to realize the true and false accurate discriminating of commodity to be measured, separately
On the one hand, true and false discriminating is carried out by said process, without by manually carrying out true and false discriminating, avoiding again due to human subjective's property
The problem of influenceing identification result, improve commodity and differentiate accuracy, then further according to the authentication data and each default true and false etc.
Data area corresponding to level difference, determines the true and false grade of the commodity to be measured, is easy to more intuitively know commodity to be measured
True and false degree.
Brief description of the drawings
Fig. 1 is the flow chart of the commercial articles true and false discrimination method of an embodiment；
Fig. 2 is the flow chart of the commercial articles true and false discrimination method of another embodiment；
Fig. 3 is the module diagram of the commercial articles true and false identification device of an embodiment；
Fig. 4 is the module diagram of the commercial articles true and false identification device of another embodiment.
Embodiment
Referring to Fig. 1, providing a kind of commercial articles true and false discrimination method of embodiment, comprise the following steps S110 to step
S140。
S110：Acquisition passes through machine learning method, and it is true to carry out machine learning according to the characteristic information storehouse of default sample commodity
Fixed commercial articles true and false differentiates model.
Machine learning method is that a kind of automatically analyzed from given data obtains rule, and assimilated equations enter to unknown data
The method of row prediction, machine learning method are corresponding with initial predicted model, and different machines learning method corresponds to different initial pre-
Model is surveyed, initial predicted model is corresponding with input, procedure parameter and output, exports and is determined by input and procedure parameter, machine
Study is input data known to basis and the continuous makeover process parameter of corresponding output data to obtain optimal process
The process of parameter, will known input of the input data as initial predicted model, it is known that output data is as initial predicted
The output of model, the procedure parameter in initial predicted model is constantly updated, obtains optimal procedure parameter, it is pre- so as to obtain target
Survey model (the true and false discriminating model of corresponding goods in the present embodiment).It is appreciated that the target obtained after machine learning is pre-
It is the corresponding relation between the input and output established using obtained optimal procedure parameter to survey model, that is, above-mentioned known
The rule that input data and output data meet, will be unknown defeated when needing to its corresponding output of Unknown worm data prediction
Enter input of the data as target prediction model obtained above, prediction result can be obtained by being predicted by target prediction model
Export.
In the present embodiment, fixed commercial articles true and false in advance is obtained first and differentiates model, so as to subsequently through true and false mirror
Other model carries out the discriminating of commercial articles true and false.Above-mentioned true and false discriminating model is using machine learning method according to default sample commodity
Characteristic information storehouse carries out what machine learning obtained, and input corresponding to it is the characteristic information of commodity, and corresponding output is true and false mark
Label, the i.e. characteristic information of commodity and the corresponding relation of true and false label to be established according to object procedure parameter.Specifically, will be default
Then the characteristic information storehouse of sample commodity carries out machine learning, found default as the given data needed for machine learning method
The rule that the characteristic information of sample commodity meets is preset in the characteristic information storehouse of sample commodity.
S120：Obtain the characteristic information of commodity to be measured.
After obtaining commercial articles true and false and differentiating model, you can carry out the true and false discriminating of commodity to be measured, then firstly the need of acquisition
The characteristic information of commodity to be measured, differentiate the input of model as commercial articles true and false.In the present embodiment, the feature of single commodity to be measured
Information is identical with the feature quantity of the characteristic information of single sample commodity, and characteristic type is identical.For example, sample commodity include A
Characteristic information corresponding to commodity and B commodity, A commodity and B commodity difference includes A1 features and A2 features, and commodity corresponding to acquisition are true
After vacation differentiates model, commodity C to be measured is predicted, then the commodity C to be measured obtained characteristic information also includes A1 features and A2
Feature, i.e., commodity C to be measured A1 features and A2 features, it is to differentiate that model is carried out very to commodity C to be measured subsequently through commercial articles true and false
Vacation, which differentiates, provides data foundation.
S130：Differentiate that the input of model carries out commercial articles true and false discriminating using the characteristic information of commodity to be measured as commercial articles true and false,
Obtain true and false authentication data.
After the characteristic information of commercial articles true and false discriminating model and commodity to be measured is obtained, you can commodity to be measured are carried out true and false
Prediction, it is true and false authentication data to obtain prediction result.The characteristic information of commodity and true and false mark are being established according to object procedure parameter
After the corresponding relation of label, for the characteristic information of different commodity as the true and false input for differentiating model, the prediction result of output may not
Together, differentiate that the input of model carries out commercial articles true and false discriminating using the characteristic information of commodity to be measured as commercial articles true and false, obtain business to be measured
True and false authentication data (the true and false data for reflecting commodity to be measured) corresponding to product.
S140：According to data area corresponding to authentication data and each default true and false grade difference, commodity to be measured are determined
True and false grade.
Because diversity be present in the size of obtained true and false authentication data, it is impossible to the true and false of commodity to be measured is judged exactly,
The division of true and false grade is carried out in advance, each corresponding data area of true and false grade, according to authentication data and each default true
Data area corresponding to false grade difference, determine the true and false grade of commodity to be measured.Specifically, by the data model belonging to authentication data
True and false grade of the true and false grade as commodity to be measured is preset corresponding to enclosing, in this way, can obtain commodity accurately true and false identification result.And
It can unify intuitively to reflect the true and false of commodity.
When carrying out commercial articles true and false discriminating to be measured by above-mentioned commercial articles true and false discrimination method, on the one hand, use and pass through the machine of presetting
The commercial articles true and false that device learning method is established according to the characteristic information storehouse of sample commodity differentiates model, and true and false mirror is carried out to commodity to be measured
Not, authentication data is obtained, so as to realize that commercial articles true and false to be measured accurately differentiates, on the other hand, true and false mirror is carried out by said process
Not, without by manually carrying out true and false discriminating, avoiding, due to the problem of human subjective's property influences identification result, improving commodity mirror again
Other accuracy, then further according to data area corresponding to the authentication data and each default true and false grade difference, it is determined that described
The true and false grade of commodity to be measured, it is easy to more intuitively know the true and false degree of commodity to be measured.Commodity to be measured can be provided the user
Whether the accurate reference information of counterfeit and shoddy goods, the experience of user electric business shopping is improved, for promoting ecommerce industry to be good for
Kang Fazhan has positive meaning.
Referring to Fig. 2, in one of the embodiments, acquisition passes through machine learning method, according to default sample commodity
Before the step of commercial articles true and false that characteristic information storehouse carries out machine learning determination differentiates model, in addition to step：
S101：Obtain each sample commodity characteristic information and each sample commodity respectively corresponding to true and false label.
Before obtaining above-mentioned commercial articles true and false and differentiating model, first have to determine that commercial articles true and false differentiates model, in the present embodiment
In, determine that commercial articles true and false differentiates in model process, first, obtain the characteristic information and each sample commodity difference of each sample commodity
Corresponding true and false label, wherein, true and false label is used for the information for indicating commercial articles true and false, is pre-established with the true and false label of commodity
Storehouse, store in the true and false tag library of commodity each sample commodity respectively corresponding to true and false label, can be from the true and false tag library of commodity
Obtain true and false label corresponding to each sample commodity difference.For example, label 1 can be used to indicate commodity to be true, business is indicated using label 0
Product are false, true corresponding to sample commodity a if sample commodity a is true commodity for known sample commodity a and sample commodity b
False label is that mark commodity are genuine information, can be 1, sample commodity b is false commodity, then true and false mark corresponding to sample commodity b
It is false information to sign as mark commodity, can be 0.
Further, each sample commodity bundle includes true commodity and false commodity, then the characteristic information of above-mentioned each sample commodity includes
The characteristic information of the characteristic information of true commodity and false commodity, so not only covered true commodity but also covered the characteristic information of false commodity,
Be advantageous to improve the follow-up accuracy for carrying out the commodity that machine learning obtains and differentiating model.
S102：According to true and false label corresponding to the characteristic information of each sample commodity and each sample commodity difference, establish pre-
If the characteristic information storehouse of sample commodity.
After true and false label corresponding to the characteristic information of each sample commodity and each sample commodity difference is obtained, it can be entered
Row combination, the characteristic information storehouse of default sample commodity is established, stored in order to unified, and be easy to subsequently carry out machine-learning process
The acquisition of middle characteristic information and true and false label.The characteristic information storehouse of default sample commodity includes the feature letter of each sample commodity
True and false label corresponding to breath and each sample commodity difference.
S103：By machine learning method, the characteristic informations of each sample commodity in the sample commodity storehouse of foundation with
And true and false label corresponding to each sample commodity difference carries out machine learning, determines that commercial articles true and false differentiates model.
In one specific example, machine learning method may include supporting vector, neutral net, stealthy Markov model with
And Bayesian Decision model, in carrying out commercial articles true and false and differentiating model determination process, it can use in above-mentioned machine learning method and appoint
A kind of method of anticipating corresponds to respectively according to the characteristic information and each sample commodity of each sample commodity in the sample commodity storehouse of foundation
True and false label carry out machine learning.
In one of the embodiments, obtaining the mode of the characteristic information of each sample commodity includes：Grabbed by networking reptile
Sample the characteristic information of this commodity.
Web crawlers is a kind of program or script according to certain rule, the automatically information in crawl networking.
In e-commerce field, diversified commodity are available for purchase, and sample can be rapidly and accurately captured in a network by web crawlers
The characteristic information of this commodity.
In one of the embodiments, obtaining the mode of the characteristic information of commodity to be measured includes：Obtain the net of commodity to be measured
Page address；The webpage of the commodity to be measured is obtained according to web page address, reads the content of the webpage of the commodity to be measured, acquisition is treated
Survey the characteristic information of commodity.
When needing to be predicted commodity to be measured true and false, user can input the web page address of commodity to be measured, you can obtain
The network address of commodity to be measured, then；The webpage of the commodity to be measured is obtained according to web page address, webpage includes commodity to be measured
Relevant information, for example, shelf life, the introduction of merchandise news (such as the information such as material, title, place of production), by reading
State the content of the webpage of commodity to be measured, you can obtain the characteristic information of commodity to be measured.
In one of the embodiments, characteristic information includes name information, manufacturer's information, place of production information, evaluation letter
Breath, pricing information, recommended information and specification information.
By combining above-mentioned name information, manufacturer's information, place of production information, evaluation information, pricing information, recommended information
And specification information, the commercial articles true and false can be used as by features described above information and differentiated corresponding to accurate characterization the characteristics of commodity
When the input of model carries out commercial articles true and false discriminating, the accuracy that commercial articles true and false differentiates the true and false prediction result of model can be improved.
In one of the embodiments, after the true and false grade for determining the commodity to be measured, in addition to step：According to
Default display format shows the true and false grade of the commodity to be measured.
In one specific example, presetting true and false grade may include Absolute truth grade, true grade, General Proper grade, general vacation
Grade, false grade and serious false grade.It is determined that being shown after the true and false grade of commodity to be measured, to be more intuitively
User prompts the true and false of commodity, that is, is easy to user to check the true and false degree of commodity to be measured.In the present embodiment, default display is passed through
Form shown, wherein, default display format includes text importing form and color picture display format.Show for word
Show form, when the true and false grade to commodity to be measured is shown, it is shown that corresponding text information, for example, commodity c to be measured
True and false grade be true grade, it is corresponding to show true grade word.For color picture display format, true and false grade and color picture
Corresponding, the picture color that different true and false grades are shown is different, for example, true and false grade from Absolute truth grade to serious false grade, is schemed
Piece color gradually can be deepened or shoaled, such as, picture color corresponding to true grade is light red, picture corresponding to General Proper grade
Color is red, and commodity c to be measured true and false grade is true grade, then shows red picture, and user is prompted with more intuitive manner.
Referring to Fig. 3, a kind of commercial articles true and false identification device of embodiment is provided, including：
Differentiate model acquisition module 310, for obtaining by default machine learning device, according to the spy of default sample commodity
Levy the commercial articles true and false discriminating model that information bank carries out machine learning determination.
Fisrt feature data obtaining module 320, for obtaining the characteristic information of commodity to be measured.
Authentication data acquisition module 330, for differentiating the defeated of model using the characteristic information of commodity to be measured as commercial articles true and false
Enter to carry out commercial articles true and false discriminating, obtain true and false authentication data.
True and false identification module 340, for according to authentication data and each default true and false grade respectively corresponding to data area,
Determine the true and false grade of commodity to be measured.
When carrying out commercial articles true and false discriminating to be measured by above-mentioned commercial articles true and false identification device, on the one hand, use and pass through the machine of presetting
The commercial articles true and false that device learning method is established according to the characteristic information storehouse of sample commodity differentiates model, and true and false mirror is carried out to commodity to be measured
Not, authentication data is obtained, so as to realize that commercial articles true and false to be measured accurately differentiates, on the other hand, true and false mirror is carried out by said process
Not, without by manually carrying out true and false discriminating, avoiding, due to the problem of human subjective's property influences identification result, improving commodity mirror again
Other accuracy, then further according to data area corresponding to the authentication data and each default true and false grade difference, it is determined that described
The true and false grade of commodity to be measured, it is easy to more intuitively know the true and false degree of commodity to be measured.Commodity to be measured can be provided the user
Whether the accurate reference information of counterfeit and shoddy goods, the experience of user electric business shopping is improved, for promoting ecommerce industry to be good for
Kang Fazhan has positive meaning.
Referring to Fig. 4, in one of the embodiments, above-mentioned commercial articles true and false identification device, in addition to：
Data obtaining module 301, for obtaining corresponding to characteristic information and each sample commodity difference of each sample commodity
True and false label；
Module 302 is established in characteristic information storehouse, is distinguished for the characteristic information according to each sample commodity and each sample commodity
Corresponding true and false label, establish the characteristic information storehouse of default sample commodity；
Differentiate model determining module 303, for by default machine learning device, according in the sample commodity storehouse of foundation
True and false label corresponding to the characteristic information of each sample commodity and each sample commodity difference carries out machine learning, determines commercial articles true and false
Differentiate model.
In one of the embodiments, above- mentioned information acquisition module 301 includes：
Second feature data obtaining module, for the characteristic information by networking crawler capturing sample commodity.
In one of the embodiments, above-mentioned second feature data obtaining module includes：
Web page address acquisition module, for obtaining the web page address of commodity to be measured.
The characteristic information acquisition module of commodity to be measured, for obtaining the net of the commodity to be measured according to the web page address
Page, the content of the webpage of the commodity to be measured is read, obtain the characteristic information of commodity to be measured.
In one of the embodiments, features described above information includes name information, manufacturer's information, place of production information, commented
Valency information, pricing information, recommended information and specification information.
In one of the embodiments, above-mentioned commercial articles true and false identification device, in addition to：
Display module, for showing the true and false grade of the commodity to be measured according to default display format.
A kind of computer-readable storage medium is also provided in one embodiment of the invention, is stored thereon with computer program, the meter
The step of calculation machine program realizes above-mentioned commercial articles true and false discrimination method when being executed by processor.
A kind of computer equipment is also provided in one embodiment of the invention, including memory, processor and is stored in
Above-mentioned commercial articles true and false mirror is realized on reservoir and the computer program that can run on a processor, during computing device computer program
Other method.
Technical characteristic in above-mentioned commercial articles true and false identification device, computer-readable storage medium and computer equipment respectively with it is upper
It is corresponding to state the technical characteristic in commercial articles true and false discrimination method, be will not be repeated here.
Each technical characteristic of above example can be combined arbitrarily, to make description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, lance is not present in the combination of these technical characteristics
Shield, all it is considered to be the scope of this specification record.
Above example only expresses the several embodiments of the present invention, and its description is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for the person of ordinary skill of the art,
On the premise of not departing from present inventive concept, various modifications and improvements can be made, these belong to protection scope of the present invention.
Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of commercial articles true and false discrimination method, it is characterised in that comprise the following steps：
Acquisition passes through machine learning method, and the commodity that machine learning determination is carried out according to the characteristic information storehouse of default sample commodity are true
Vacation differentiates model；
Obtain the characteristic information of commodity to be measured；
Differentiate that the input of model carries out commercial articles true and false discriminating using the characteristic information of the commodity to be measured as the commercial articles true and false, obtain
Obtain true and false authentication data；
According to data area corresponding to the authentication data and each default true and false grade difference, the true of the commodity to be measured is determined
False grade.
2. commercial articles true and false discrimination method according to claim 1, it is characterised in that the acquisition passes through machine learning side
Method, before the step of commercial articles true and false discriminating model of the characteristic information storehouse of default sample commodity progress machine learning determination,
Also include step：
Obtain each sample commodity characteristic information and each sample commodity respectively corresponding to true and false label；
According to the characteristic information of each sample commodity and each sample commodity respectively corresponding to true and false label, described in foundation
The characteristic information storehouse of default sample commodity；
Pass through the machine learning method, the characteristic information of each sample commodity in the sample commodity storehouse of foundation
And true and false label corresponding to each sample commodity difference carries out machine learning, determines that the commercial articles true and false differentiates model.
3. commercial articles true and false discrimination method according to claim 2, it is characterised in that each sample commodity of acquisition
The mode of characteristic information includes：
Pass through the characteristic information of sample commodity described in the crawler capturing of networking.
4. commercial articles true and false discrimination method according to claim 1, it is characterised in that the feature letter for obtaining commodity to be measured
The mode of breath includes：
Obtain the web page address of the commodity to be measured；
The webpage of the commodity to be measured is obtained according to the web page address, reads the content of the webpage of the commodity to be measured, is obtained
The characteristic information of commodity to be measured.
5. the commercial articles true and false discrimination method according to any one in claim 1-4, it is characterised in that the characteristic information
Including name information, manufacturer's information, place of production information, evaluation information, pricing information, recommended information and specification information.
6. commercial articles true and false discrimination method according to claim 1, it is characterised in that described to determine the true of the commodity to be measured
After false grade, in addition to step：
The true and false grade of the commodity to be measured is shown according to default display format.
A kind of 7. commercial articles true and false identification device, it is characterised in that including：
Differentiate model acquisition module, for obtaining by default machine learning device, according to the characteristic information of default sample commodity
The commercial articles true and false that storehouse carries out machine learning determination differentiates model；
Fisrt feature data obtaining module, for obtaining the characteristic information of commodity to be measured；
Authentication data acquisition module, for differentiating the defeated of model using the characteristic information of the commodity to be measured as the commercial articles true and false
Enter to carry out commercial articles true and false discriminating, obtain true and false authentication data；
True and false identification module, for according to the authentication data and each default true and false grade respectively corresponding to data area, really
The true and false grade of the fixed commodity to be measured.
8. commercial articles true and false identification device according to claim 7, it is characterised in that also include：
Data obtaining module, for obtaining corresponding to characteristic information and each sample commodity difference of each sample commodity
True and false label；
Module is established in characteristic information storehouse, for the characteristic information according to each sample commodity and each sample commodity difference
Corresponding true and false label, establish the characteristic information storehouse of the default sample commodity；
Differentiate model determining module, for by the default machine learning device, according in the sample commodity storehouse of foundation
Each sample commodity characteristic information and each sample commodity respectively corresponding to true and false label carry out machine learning, really
The fixed commercial articles true and false differentiates model.
9. a kind of computer-readable storage medium, is stored thereon with computer program, it is characterised in that the computer program is by processor
The step of any one methods described in the claims 1-6 is realized during execution.
10. a kind of computer equipment, including memory, processor and it is stored on the memory and can be in the processor
The computer program of upper operation, it is characterised in that realize such as claim 1-6 described in the computing device during computer program
Method described in middle any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710940939.XA CN107844980A (en) | 2017-09-30 | 2017-09-30 | Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710940939.XA CN107844980A (en) | 2017-09-30 | 2017-09-30 | Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107844980A true CN107844980A (en) | 2018-03-27 |
Family
ID=61662048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710940939.XA Pending CN107844980A (en) | 2017-09-30 | 2017-09-30 | Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107844980A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523908A (en) * | 2020-03-31 | 2020-08-11 | 云南省烟草质量监督检测站 | Packaging machine type tracing method, device and system for identifying authenticity of cigarettes |
| CN112070510A (en) * | 2020-08-12 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for detecting unqualified commodities based on block chain |
| CN112070511A (en) * | 2020-08-12 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for detecting unqualified commodities |
| CN112567419A (en) * | 2018-08-21 | 2021-03-26 | 先讯美资电子有限责任公司 | Self-service product return using computer vision and artificial intelligence |
| CN112633383A (en) * | 2020-12-25 | 2021-04-09 | 百度在线网络技术（北京）有限公司 | Antique identification method and device, electronic equipment and readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6996543B1 (en) * | 1998-04-14 | 2006-02-07 | International Business Machines Corporation | System for protection of goods against counterfeiting |
| CN101820366A (en) * | 2010-01-27 | 2010-09-01 | 南京邮电大学 | Pre-fetching-based phishing web page detection method |
| CN106462549A (en) * | 2014-04-09 | 2017-02-22 | 尹度普有限公司 | Authenticating physical objects using machine learning from microscopic variations |
| CN107194587A (en) * | 2017-05-24 | 2017-09-22 | 暨南大学 | It is a kind of to be circulated based on block chain and the art work of expert system and identification register method |
-
2017
- 2017-09-30 CN CN201710940939.XA patent/CN107844980A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6996543B1 (en) * | 1998-04-14 | 2006-02-07 | International Business Machines Corporation | System for protection of goods against counterfeiting |
| CN101820366A (en) * | 2010-01-27 | 2010-09-01 | 南京邮电大学 | Pre-fetching-based phishing web page detection method |
| CN106462549A (en) * | 2014-04-09 | 2017-02-22 | 尹度普有限公司 | Authenticating physical objects using machine learning from microscopic variations |
| CN107194587A (en) * | 2017-05-24 | 2017-09-22 | 暨南大学 | It is a kind of to be circulated based on block chain and the art work of expert system and identification register method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112567419A (en) * | 2018-08-21 | 2021-03-26 | 先讯美资电子有限责任公司 | Self-service product return using computer vision and artificial intelligence |
| CN111523908A (en) * | 2020-03-31 | 2020-08-11 | 云南省烟草质量监督检测站 | Packaging machine type tracing method, device and system for identifying authenticity of cigarettes |
| CN111523908B (en) * | 2020-03-31 | 2023-04-07 | 云南省烟草质量监督检测站 | Packaging machine type tracing method, device and system for identifying authenticity of cigarettes |
| CN112070510A (en) * | 2020-08-12 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for detecting unqualified commodities based on block chain |
| CN112070511A (en) * | 2020-08-12 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for detecting unqualified commodities |
| CN112633383A (en) * | 2020-12-25 | 2021-04-09 | 百度在线网络技术（北京）有限公司 | Antique identification method and device, electronic equipment and readable medium |
| CN112633383B (en) * | 2020-12-25 | 2023-08-18 | 百度在线网络技术（北京）有限公司 | Ancient game authentication method and device, electronic equipment and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107844980A (en) | Commercial articles true and false discrimination method and device, computer-readable storage medium and equipment | |
| CN106779940B (en) | Method and device for confirming display commodity | |
| US11756092B2 (en) | Flaw analysis of images | |
| CN108846724A (en) | Data analysing method and system | |
| US20150276700A1 (en) | Representing the taste of food | |
| CN108509458B (en) | Business object identification method and device | |
| CN109697786A (en) | Operating method and operating device for vending machine | |
| US20180047007A1 (en) | System and method for paying for goods at a door | |
| CN107784507A (en) | Doubtful infringement commodity method for early warning and device, computer-readable storage medium and equipment | |
| CN113989476A (en) | Object identification method and electronic equipment | |
| US20190114700A1 (en) | Method and system for supplying commodities | |
| CN112839047B (en) | Asset vulnerability scanning method, device, equipment and medium on cloud platform | |
| CN112163872A (en) | Commodity quality identification method, system, equipment and readable storage medium | |
| US11853948B2 (en) | Methods and systems for managing risk with respect to potential customers | |
| CN116010707A (en) | Commodity price anomaly identification method, device, equipment and storage medium | |
| CN116595390A (en) | Commodity information processing method and electronic equipment | |
| CN110619546A (en) | Implementation scheme for solving high throughput of directional ticket issuing | |
| CN113850610A (en) | Method, device and server for identifying false transactions based on logistics data | |
| US20140358635A1 (en) | Making product substitution recommendations | |
| US20170262144A1 (en) | Multiple product attribute visualization | |
| KR20180019939A (en) | Method and apparaturs for purchasing goods in online | |
| CN112950329A (en) | Commodity dynamic information generation method, device, equipment and computer readable medium | |
| KR20220026709A (en) | Method and apparatus for proviDing product-related information for buyer decision-making | |
| CN110782287A (en) | Entity similarity calculation method and device, article recommendation system, medium and equipment | |
| KR101703918B1 (en) | System and method for providing product information |
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: 20180327 |
|
| RJ01 | Rejection of invention patent application after publication |