CN109858446A - Article register method and device under a kind of new public safety - Google Patents
Article register method and device under a kind of new public safety Download PDFInfo
- Publication number
- CN109858446A CN109858446A CN201910100214.9A CN201910100214A CN109858446A CN 109858446 A CN109858446 A CN 109858446A CN 201910100214 A CN201910100214 A CN 201910100214A CN 109858446 A CN109858446 A CN 109858446A
- Authority
- CN
- China
- Prior art keywords
- goods
- type
- items
- images
- training sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses article register method and devices under a kind of new public safety, this method comprises: obtaining the images of items of article;The images of items is inputted to the feature identification model constructed based on deep learning, extract the characteristic for mapping type of goods in the images of items and is exported in vector form;In the mapping relations of the vector sum type of goods constructed based on the feature identification model, when not finding the corresponding type of goods of vector of feature identification model output, determine the type of goods of the article, and by the corresponding relationship of the vector of determining type of goods and the feature identification model output, it is added in the mapping relations of the vector sum type of goods.The present invention increases the corresponding relationship with type of goods by the vector to unstructured mapping relations, so that can also carry out accurately distinguishing goods categories by the feature identification model to the article of the new registration without the training of feature identification model.
Description
Technical field
The present invention relates to article register method and dresses under article subdivision technical field more particularly to a kind of new public safety
It sets.
Background technique
With greatly developing for scientific and technological network net, in recent years, real economy transition, electric business flow bonus disappear, business mould
Formula is constantly reformed, and the new retail epoch of on-line off-line fusion upgrading are arriving, and new retail is exactly centered on consumer experience
From " goods-field-people " to the transformation of " people-goods-field ", polynary retail form is turned to from single retail, from " article+service " to " object
Product+service+content+other " conversion, allow consumption scene it is ubiquitous, make social experience flexible and convenient, under new public safety
Article is traceable, can optimize data analysis, on-line off-line phase is allowed to melt interpromoting relation in five elements.
Under new public safety, self-service, customer only need to be by cargo automatically scanning image or label, but completes
During retail payment, the prior art can only be realized rough classification to article, such as can recognize that by image or label technique
The affiliated producer of article, affiliated product line, but can not be similar to a large amount of appearances, but the diverse article of actual object carries out essence
True classification such as identifies the specific taste of a certain food under a certain brand, and then pays link in article, is unable to judge accurately out
Specific price of the article under disaggregated classification, and then very important influence is brought to the new public safety of article.
In conclusion in the prior art, under new public safety, existing can not be similar to a large amount of appearances, but actual object
Diverse article carries out the problem of precise classification identification.Meanwhile the existing sorting algorithm based on convolutional network, Zhi Neng
It works, untrained type of goods can not be distinguished in the classification trained.Due to type of merchandize enormous amount, to not
The type of goods of trained mistake is also wanted to accurately distinguish as urgent problem to be solved.
Summary of the invention
The present invention provides article register method and device under a kind of new public safety, solves existing sorting algorithm, only
The problem of capable of working, untrained article can not being distinguished in the classification trained.
In order to solve the above technical problems, the present invention provides article register method and dresses under a kind of new public safety
It sets, specifically includes:
According to first aspect present invention, article register method under a kind of new public safety is provided, this method comprises:
Obtain the images of items of article;
The images of items is inputted to the feature identification model constructed based on deep learning, extracts and is reflected in the images of items
It penetrates the characteristic of type of goods and exports in vector form;
In the mapping relations of the vector sum type of goods constructed based on the feature identification model, the feature is not found
When the corresponding type of goods of vector of identification model output, the type of goods of the article is determined, and by determining type of goods
With the corresponding relationship of the vector of feature identification model output, it is added in the mapping relations of the vector sum type of goods.
In one possible implementation, the prompt information of output instruction user input, and user is received according to described
The type of goods of the article of prompt information input;Alternatively, the images of items of output article receives third root to third party
According to the type of goods for the article that the images of items determines.
In one possible implementation, obtain include multiple training samples training sample set and including multiple tests
The test sample collection of sample, each training sample/test sample include the images of items and the affiliated article kind of the article of article
Class;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, and the prediction is known
Other model includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, current predictive is known
Other model is trained at least once, every time after training, after the test sample concentrated using the test sample is to training
Forecasting recognition model tested, when determining that test result meets default required precision, terminate training process, will remove last
The current Forecasting recognition model output of one feature extraction network layer is the feature identification model.
In one possible implementation, the images of items in the training sample of preset quantity is inputted to current prediction
Identification model exports prediction type of goods corresponding with the images of items;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
In one possible implementation, the sample of training sample set described in current Forecasting recognition model discrimination is utilized
Data, using the training sample set after screening as new training sample set, and trigger model training again.
In one possible implementation, the images of items in the training sample of preset quantity is inputted currently respectively
Forecasting recognition model extracts vector corresponding with the images of items;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;Respectively will
The training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, root
The training sample is assessed according to the vector of Forecasting recognition model output and the mapping relations of the vector sum type of goods
Validity;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new instruction is obtained
Practice sample set.
In one possible implementation, current feature identification model output, the object of the training sample are determined
The corresponding vector of product image;
Determine that the corresponding type of goods of the images of items is corresponding in the mapping relations of the vector sum type of goods
Vector determines the effective of the training sample when being greater than preset value with the vector departure degree that current Forecasting recognition model exports
Property meets preset requirement.
In one possible implementation, the images of items in the training sample of preset quantity is inputted currently respectively
Feature identification model extracts vector corresponding with the images of items;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, structure
Build the mapping relations of the vector sum type of goods.
In one possible implementation, according to based on vector sum type of goods constructed by the feature identification model
Mapping relations, obtain the corresponding type of goods of vector of feature identification model output.
According to second aspect of the present invention, article registers equipment under a kind of new public safety, the equipment include processor and
Memory, wherein the memory stores executable program code, when said program code is performed, so that the processing
Device is for executing following steps:
Obtain the images of items of article;
The images of items is inputted to the feature identification model constructed based on deep learning, extracts and is reflected in the images of items
It penetrates the characteristic of type of goods and exports in vector form;
In the mapping relations of the vector sum type of goods constructed based on the feature identification model, the feature is not found
When the corresponding type of goods of vector of identification model output, the type of goods of the article is determined, and by determining type of goods
With the corresponding relationship of the vector of feature identification model output, it is added in the mapping relations of the vector sum type of goods.
In one possible implementation, the processor is specifically used for:
The prompt information of output instruction user's input, and receive the article that user inputs according to the prompt information
Type of goods;Alternatively, the images of items of output article receives third party according to images of items determination to third party
The type of goods of article.
In one possible implementation, the processor is specifically used for:
Obtain includes the training sample set of multiple training samples and the test sample collection including multiple test samples, Mei Gexun
Practice the images of items and the affiliated type of goods of the article that sample/test sample includes article;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, and the prediction is known
Other model includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, current predictive is known
Other model is trained at least once, every time after training, after the test sample concentrated using the test sample is to training
Forecasting recognition model tested, when determining that test result meets default required precision, terminate training process, will remove last
The current Forecasting recognition model output of one feature extraction network layer is the feature identification model.
In one possible implementation, the processor is specifically used for:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the article
The corresponding prediction type of goods of image;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
In one possible implementation, the processor is specifically used for:
Using the sample data of training sample set described in current Forecasting recognition model discrimination, by the training sample after screening
Collection is as new training sample set, and trigger model training again.
In one possible implementation, the processor is specifically used for:
Images of items in the training sample of preset quantity inputs to current Forecasting recognition model respectively, extract with it is described
The corresponding vector of images of items;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;Respectively will
The training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, root
The training sample is assessed according to the vector of Forecasting recognition model output and the mapping relations of the vector sum type of goods
Validity;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new instruction is obtained
Practice sample set.
In one possible implementation, the processor is specifically used for:
Determine current feature identification model output, the corresponding vector of the images of items of the training sample;
Determine that the corresponding type of goods of the images of items is corresponding in the mapping relations of the vector sum type of goods
Vector determines the effective of the training sample when being greater than preset value with the vector departure degree that current Forecasting recognition model exports
Property meets preset requirement.
In one possible implementation, the processor is specifically used for:
Images of items in the training sample of preset quantity inputs to current feature identification model respectively, extract with it is described
The corresponding vector of images of items;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, structure
Build the mapping relations of the vector sum type of goods.
In one possible implementation, the processor is also used to:
According to the mapping relations based on vector sum type of goods constructed by the feature identification model, the feature is obtained
The corresponding type of goods of vector of identification model output.
According to third aspect present invention, article register device under a kind of new public safety is provided, described device specifically includes:
Image acquisition unit, for obtaining the images of items of article;
Output unit extracts institute for the images of items to be inputted the feature identification model constructed based on deep learning
It states the characteristic for mapping type of goods in images of items and exports in vector form;
Adding unit, in the mapping relations of the vector sum type of goods constructed based on the feature identification model,
When not finding the corresponding type of goods of vector of feature identification model output, the type of goods of the article is determined, and will
The corresponding relationship of determining type of goods and the vector of feature identification model output, is added to the vector sum type of goods
Mapping relations in.
In one possible implementation, the adding unit is specifically used for:
The prompt information of output instruction user's input, and receive the article that user inputs according to the prompt information
Type of goods;Alternatively, the images of items of output article receives third party according to images of items determination to third party
The type of goods of article.
In one possible implementation, the output unit is specifically used for:
Obtain includes the training sample set of multiple training samples and the test sample collection including multiple test samples, Mei Gexun
Practice the images of items and the affiliated type of goods of the article that sample/test sample includes article;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, and the prediction is known
Other model includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, current predictive is known
Other model is trained at least once, every time after training, after the test sample concentrated using the test sample is to training
Forecasting recognition model tested, when determining that test result meets default required precision, terminate training process, will remove last
The current Forecasting recognition model output of one feature extraction network layer is the feature identification model.
In one possible implementation, the output unit is specifically used for:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the article
The corresponding prediction type of goods of image;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
In one possible implementation, the output unit is specifically used for:
Using the sample data of training sample set described in current Forecasting recognition model discrimination, by the training sample after screening
Collection is as new training sample set, and trigger model training again.
In one possible implementation, the output unit is specifically used for:
Images of items in the training sample of preset quantity inputs to current Forecasting recognition model respectively, extract with it is described
The corresponding vector of images of items;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;Respectively will
The training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, root
The training sample is assessed according to the vector of Forecasting recognition model output and the mapping relations of the vector sum type of goods
Validity;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new instruction is obtained
Practice sample set.In one possible implementation, the output unit is specifically used for:
Determine current feature identification model output, the corresponding vector of the images of items of the training sample;
Determine that the corresponding type of goods of the images of items is corresponding in the mapping relations of the vector sum type of goods
Vector determines the effective of the training sample when being greater than preset value with the vector departure degree that current Forecasting recognition model exports
Property meets preset requirement.
In one possible implementation, the output unit is specifically used for:
Images of items in the training sample of preset quantity inputs to current feature identification model respectively, extract with it is described
The corresponding vector of images of items;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, structure
Build the mapping relations of the vector sum type of goods.
In one possible implementation, the output unit is also used to:
According to the mapping relations based on vector sum type of goods constructed by the feature identification model, the feature is obtained
The corresponding type of goods of vector of identification model output.
According to fourth aspect present invention, a kind of computer storage medium is provided, the computer storage medium is stored with meter
Calculation machine program, which, which is performed, realizes above-mentioned method.
Article register method and device compared with prior art, have as follows under a kind of new public safety provided by the invention
Advantages and beneficial effects:
Increase the corresponding relationship with type of goods by the vector of the unstructured mapping relations exported to feature identification model,
So that can also be carried out accurately by the feature identification model to the article of the new registration without the training of feature identification model
Distinguish goods categories.
Detailed description of the invention
Fig. 1 is the flow diagram of article register method under a kind of new public safety that embodiment one provides;
Fig. 2 is that article registers equipment schematic diagram under a kind of new public safety that embodiment two provides;
Fig. 3 is article register device schematic diagram under a kind of new public safety that embodiment three provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.
Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts all
Other embodiments shall fall within the protection scope of the present invention.
The some words occurred in text are explained below:
1, term "and/or" in the embodiment of the present invention describes the incidence relation of affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.Character "/" one
As indicate forward-backward correlation object be a kind of "or" relationship.
2, term " commodity " or " article " in the embodiment of the present invention, refer to acquire above-mentioned quotient using computer vision technique
Product/images of items, and the article that can classify, it is small to arrive fuel, furniture and appliances etc. are arrived greatly.
The application scenarios of description of the embodiment of the present invention are the technical solutions in order to more clearly illustrate the embodiment of the present invention,
The restriction for technical solution provided in an embodiment of the present invention is not constituted, those of ordinary skill in the art are it is found that with newly answering
With the appearance of scene, technical solution provided in an embodiment of the present invention is equally applicable for similar technical problem.Wherein, at this
In the description of invention, unless otherwise indicated, the meaning of " plurality " is two or more.
Above-mentioned new public safety refers to, the scene of the general retail form of the data-driven centered on consumer experience, core
Heart value is will farthest to promote whole society's circulation retail business running efficiency, specifically, new retail is to be with consumer
Center passes through each consumption of data flowing series connection on the basis of the links such as people, commodity and service, supply chain are digitized
Scene, including smart phone, mobile terminal, computer, entity sales field and the following achievable new access etc., utilize digitizing technique
It realizes that entity delivers chain with virtual retail supply chain, transaction, the comprehensive of service chaining is merged, is supplied to consumer and covers full channel
Seamless consumption experience, the efficient general general retail structure of favour type with the characteristics of the substitution entity delivery form of logistics distribution part.
Based on above-mentioned scene, the embodiment of the present invention provides the item identification method and equipment under a kind of public safety.
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
For above-mentioned scene, the embodiment of the present invention is described in further detail with reference to the accompanying drawings of the specification.
Embodiment one
The present invention provides article register method under a kind of new public safety, as shown in Figure 1, specifically includes the following steps:
Step 101, the images of items of article is obtained;
As an alternative embodiment, can with but be not limited to using one/multiple common cameras/rotation camera shooting
Head, is fixed angle/multi-angle to above-mentioned article and takes pictures and obtain the images of items of above-mentioned article.
Step 102, the images of items is inputted to the feature identification model constructed based on deep learning, extracts the article
The characteristic of type of goods is mapped in image and is exported in vector form;
Step 103, it in the mapping relations of the vector sum type of goods constructed based on the feature identification model, does not find
When the corresponding type of goods of the vector of feature identification model output, the type of goods of the article is determined, and will be determining
The corresponding relationship of type of goods and the vector of feature identification model output, is added to the mapping of the vector sum type of goods
In relationship.
It should be understood that the mapping relations of above-mentioned vector sum type of goods preserve different type of goods and corresponding vector
Between mapping relations, different type of goods should respectively correspond different vectors.
It, can be with if what is obtained is the image of multiple angles of article when above-mentioned steps 101 obtain the images of items of article
But be not limited to therefrom to select a pixel it is best/image comprising above-mentioned article appointed part is as input feature vector identification model
Images of items, do not do excessive restriction to this, those skilled in the art can be arranged according to actual needs.
As an alternative embodiment, being based on deep learning construction feature identification model as follows:
1) training sample set including multiple training samples and the test sample collection including multiple test samples are obtained, each
Training sample/test sample includes the images of items and the affiliated type of goods of above-mentioned article of article;
2) model parameter for being randomized deep learning network model obtains initial Forecasting recognition model, above-mentioned Forecasting recognition
Model includes multiple feature extraction network layers;
Excessive restriction is not done to above-mentioned deep learning network model, those skilled in the art can set according to actual needs
Set, in the present embodiment, above-mentioned deep learning network model can with but be not limited to include: convolutional neural networks CNN
(Convolutional Neural Network), Recognition with Recurrent Neural Network RNN (Recurrent Neural Network), depth
Neural network DNN (Deep Neural Networks) etc.;
3) when trigger model training, using the training sample for the preset quantity that above-mentioned training sample is concentrated, to current predictive
Identification model is trained at least once, and every time after training, the test sample concentrated using above-mentioned test sample is to training
Forecasting recognition model afterwards is tested, and when determining that test result meets default required precision, terminates training process, will be removed most
The current Forecasting recognition model output that later feature extracts network layer is features described above identification model.
Excessive restriction is not done to the mode of above-mentioned acquisition training sample set and test sample collection, those skilled in the art can
It is arranged according to actual needs, in the present embodiment, above-mentioned training sample set and test sample collection are acquired greatly in advance by technical staff
The images of items and type of merchandize for measuring article obtain;
Excessive restriction is not done to above-mentioned preset quantity, those skilled in the art can be arranged according to actual needs.
The training sample for the preset quantity concentrated every time using above-mentioned training sample, instructs current predictive identification model
Practice, comprising:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the article
The corresponding prediction type of goods of image;
According to the prediction type of goods of above-mentioned images of items and above-mentioned images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
As an alternative embodiment, by loss function, calculate above-mentioned images of items prediction type of goods and
The departure degree of above-mentioned images of items corresponding type of goods in training sample;
When above-mentioned departure degree is less than default deviation threshold value, that is, think the images of items of above-mentioned Forecasting recognition model output
It predicts type of goods true type of goods close in training sample, terminates training process at this time, the last one feature will be removed
The current Forecasting recognition model output for extracting network layer is features described above identification model;
When above-mentioned departure degree is not less than default deviation threshold value, that is, think the images of items of above-mentioned Forecasting recognition model output
Prediction type of goods and type of goods true in training sample deviate it is excessive, at this time according to parameter preset method of adjustment adjust
The model parameter of current Forecasting recognition model;
Excessive restriction is not done to above-mentioned parameter preset method of adjustment, those skilled in the art can set according to actual needs
Set, can with but be not limited to staged adjusting parameter method;
As an alternative embodiment, can with but be not limited to through loss function, adjustment is worked as follows
The model parameter of preceding Forecasting recognition model:
1) end value and the corresponding method of parameter adjustment calculated in above-mentioned Forecasting recognition model construction loss function, right
When current predictive identification model is trained, according to the above-mentioned Forecasting recognition model of end value adjust automatically of loss function calculating
Model parameter;
2) when being trained to current predictive identification model, the end value that loss function when each training is calculated is defeated
Out, it is investigated by those skilled in the art according to expertise or early period, the model parameter of above-mentioned Forecasting recognition model is carried out
Adjustment.
As an alternative embodiment, determining that test result is unsatisfactory for default required precision every time after training
When, further include, using the training sample of the current above-mentioned training sample set of Forecasting recognition model discrimination, by the training sample after screening
This collection is as new training sample set, and trigger model training again.
As an alternative embodiment, with the training sample of the above-mentioned above-mentioned training sample set of Forecasting recognition model discrimination
This, using the training sample set after screening as new training sample set, comprising:
Images of items in the training sample of preset quantity inputs to current Forecasting recognition model respectively, extract with it is above-mentioned
The corresponding vector of images of items;
Construct the mapping relations of the vector sum type of goods of the training sample of preset quantity;Respectively by above-mentioned training sample set
In each images of items in addition to the training sample of preset quantity input current Forecasting recognition model, according to above-mentioned Forecasting recognition
The vector of model output and the mapping relations of above-mentioned vector sum type of goods assess the validity of above-mentioned training sample;
The training sample that all validity are unsatisfactory for preset requirement is concentrated to delete from above-mentioned training sample and obtains new instruction
Practice sample set.
As an alternative embodiment, determining the article figure of the above-mentioned training sample of above-mentioned Forecasting recognition model output
As corresponding vector;
Determine that the corresponding type of goods of above-mentioned images of items is corresponding in the mapping relations of above-mentioned vector sum type of goods
Vector determines the validity of the training sample when being greater than preset value with the vector departure degree of above-mentioned Forecasting recognition model output
Meet preset requirement.
Preset requirement is met for above-mentioned validity, it should be appreciated that if above-mentioned two images of items (such as A and B) is right
When the vector departure degree answered is not more than preset value, that is, think that the corresponding type of goods of above-mentioned A and B is same class, if A is training
The training sample used when characteristic model then constructs the mapping of above-mentioned vector sum type of goods after obtaining Forecasting recognition model
When relationship, the mapping relations of above-mentioned A and its corresponding type of merchandize in the mapping relations of above-mentioned vector sum type of goods,
Therefore, the training sample comprising article B and its corresponding type of merchandize is the number of redundancy for training Forecasting recognition model
According to needing to delete the training sample comprising article B and its corresponding type of goods when carrying out the screening of above-mentioned training sample set
It removes;
In the above method, using the vector of the training sample of the preset quantity of above-mentioned Forecasting recognition model output, and in advance
If the corresponding type of goods of the training sample of quantity establishes the mapping relations of above-mentioned vector sum type of goods, and utilizes above-mentioned vector
The training sample that mapping relations screening with type of goods is concentrated for the training sample of training pattern, so that the feature trained
The precision of identification model is higher.
As an alternative embodiment, in the training using the above-mentioned above-mentioned training sample set of Forecasting recognition model discrimination
When sample, if the corresponding vector of images of items of the training sample of above-mentioned Forecasting recognition model output is not in above-mentioned vector sum article
When in the mapping relations of type, retain above-mentioned training sample.
As an alternative embodiment, after obtaining features described above identification model, respectively by the training of preset quantity
Images of items in sample inputs current feature identification model, extracts vector corresponding with above-mentioned images of items;
According to the above-mentioned images of items of the corresponding vector sum of above-mentioned images of items corresponding type of goods, structure in training sample
Build the mapping relations of above-mentioned vector sum type of goods.
In above-mentioned steps 103, reflecting for trained feature identification model and vector sum type of goods is stated in use
When penetrating the type of relation recognition article, for the type of goods not new commodity in the mapping relations of above-mentioned vector sum type of goods
The article of type can be obtained above-mentioned by the way that the images of items of above-mentioned article is inputted above-mentioned trained feature identification model
The corresponding vector of images of items that is to say the corresponding vector of above-mentioned new article type, later based on obtained new article type pair
The vector answered adds the mapping relations of the vector sum new article type in the mapping relations of above-mentioned vector sum type of goods
It adds and, the expansion of the mapping relations to above-mentioned vector sum type of goods can be realized, realize the expansion to the type of goods of identification
It fills.
As an alternative embodiment, determining that the type of goods of the new article can be, but not limited to by following two
Kind mode:
Mode one:
In the corresponding type of goods of the vector of not finding feature identification model output, output instruction user's input
Prompt information, and receive the type of goods for the article that user inputs according to the prompt information.User prompt can be with
It is by way of sending the picture of article to user, user determines type of goods according to the picture of article.Herein not to user
The mode of prompt limits.
Mode two:
In the corresponding type of goods of the vector of not finding feature identification model output, the article of the article is exported
For image to the third party that can recognize type of goods, third party's images of items according to object determines type of goods.The third party
Including but not limited to other target identifications detect network, such as the network that can be identified to text in images of items.Herein
Third party is not limited.
By above-mentioned article logon mode, the article of the new registration without the training of feature identification model can also be led to
The feature identification model is crossed to carry out accurately distinguishing goods categories.
Embodiment two
The present embodiment provides articles under a kind of new public safety to register equipment, and the equipment includes processor 201 and storage
Device 202, as shown in Figure 2, wherein the memory stores executable program code, when said program code is performed, so that
The processor is for executing following steps:
Obtain the images of items of article;
The images of items is inputted to the feature identification model constructed based on deep learning, extracts and is reflected in the images of items
It penetrates the characteristic of type of goods and exports in vector form;
In the mapping relations of the vector sum type of goods constructed based on the feature identification model, the feature is not found
When the corresponding type of goods of vector of identification model output, the type of goods of the article is determined, and by determining type of goods
With the corresponding relationship of the vector of feature identification model output, it is added in the mapping relations of the vector sum type of goods.
Optionally, the processor 201 is specifically used for:
The prompt information of output instruction user's input, and receive the article that user inputs according to the prompt information
Type of goods;Alternatively, the images of items of output article receives third party according to images of items determination to third party
The type of goods of article.
Optionally, the processor 201 is specifically used for:
Obtain includes the training sample set of multiple training samples and the test sample collection including multiple test samples, Mei Gexun
Practice the images of items and the affiliated type of goods of the article that sample/test sample includes article;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, and the prediction is known
Other model includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, current predictive is known
Other model is trained at least once, every time after training, after the test sample concentrated using the test sample is to training
Forecasting recognition model tested, when determining that test result meets default required precision, terminate training process, will remove last
The current Forecasting recognition model output of one feature extraction network layer is the feature identification model.
Optionally, the processor 201 is specifically used for:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the article
The corresponding prediction type of goods of image;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
Optionally, the processor 201 is specifically used for:
Using the sample data of training sample set described in current Forecasting recognition model discrimination, by the training sample after screening
Collection is as new training sample set, and trigger model training again.
Optionally, the processor 201 is specifically used for:
Images of items in the training sample of preset quantity inputs to current Forecasting recognition model respectively, extract with it is described
The corresponding vector of images of items;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;Respectively will
The training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, root
The training sample is assessed according to the vector of Forecasting recognition model output and the mapping relations of the vector sum type of goods
Validity;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new instruction is obtained
Practice sample set.
Optionally, the processor 201 is specifically used for:
Determine current feature identification model output, the corresponding vector of the images of items of the training sample;
Determine that the corresponding type of goods of the images of items is corresponding in the mapping relations of the vector sum type of goods
Vector determines the effective of the training sample when being greater than preset value with the vector departure degree that current Forecasting recognition model exports
Property meets preset requirement.
Optionally, the processor 201 is specifically used for:
Images of items in the training sample of preset quantity inputs to current feature identification model respectively, extract with it is described
The corresponding vector of images of items;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, structure
Build the mapping relations of the vector sum type of goods.
Optionally, the processor 201 is also used to:
According to the mapping relations based on vector sum type of goods constructed by the feature identification model, the feature is obtained
The corresponding type of goods of vector of identification model output.
Embodiment three
The present embodiment provides article register devices under a kind of new public safety, and schematic device is as shown in figure 3, above-mentioned apparatus
Include:
Image acquisition unit 301, for obtaining the images of items of article;
Output unit 302 is extracted for the images of items to be inputted the feature identification model constructed based on deep learning
The characteristic of type of goods is mapped in the images of items and is exported in vector form;
Adding unit 303, for the mapping relations in the vector sum type of goods constructed based on the feature identification model
In, when not finding the corresponding type of goods of vector of feature identification model output, determine the type of goods of the article, and
By the corresponding relationship of the vector of determining type of goods and the feature identification model output, it is added to the vector sum article kind
In the mapping relations of class.
Optionally, the adding unit 303 is specifically used for:
The prompt information of output instruction user's input, and receive the article that user inputs according to the prompt information
Type of goods;Alternatively, the images of items of output article receives third party according to images of items determination to third party
The type of goods of article.
Optionally, the output unit 302 is specifically used for:
Obtain includes the training sample set of multiple training samples and the test sample collection including multiple test samples, Mei Gexun
Practice the images of items and the affiliated type of goods of the article that sample/test sample includes article;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, and the prediction is known
Other model includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, current predictive is known
Other model is trained at least once, every time after training, after the test sample concentrated using the test sample is to training
Forecasting recognition model tested, when determining that test result meets default required precision, terminate training process, will remove last
The current Forecasting recognition model output of one feature extraction network layer is the feature identification model.
Optionally, the output unit 302 is specifically used for:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the article
The corresponding prediction type of goods of image;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding article kind
Class adjusts the model parameter of current Forecasting recognition model by loss function.
Optionally, the output unit 302 is specifically used for:
Using the sample data of training sample set described in current Forecasting recognition model discrimination, by the training sample after screening
Collection is as new training sample set, and trigger model training again.
Optionally, the output unit 302 is specifically used for:
Images of items in the training sample of preset quantity inputs to current Forecasting recognition model respectively, extract with it is described
The corresponding vector of images of items;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;Respectively will
The training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, root
The training sample is assessed according to the vector of Forecasting recognition model output and the mapping relations of the vector sum type of goods
Validity;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new instruction is obtained
Practice sample set.
Optionally, the output unit 302 is specifically used for:
Determine current feature identification model output, the corresponding vector of the images of items of the training sample;
Determine that the corresponding type of goods of the images of items is corresponding in the mapping relations of the vector sum type of goods
Vector determines the effective of the training sample when being greater than preset value with the vector departure degree that current Forecasting recognition model exports
Property meets preset requirement.
Optionally, the output unit 302 is specifically used for:
Images of items in the training sample of preset quantity inputs to current feature identification model respectively, extract with it is described
The corresponding vector of images of items;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, structure
Build the mapping relations of the vector sum type of goods.
Optionally, the output unit 302 is also used to:
According to the mapping relations based on vector sum type of goods constructed by the feature identification model, the feature is obtained
The corresponding type of goods of vector of identification model output.
Example IV
The present embodiment is a kind of computer storage medium, and above-mentioned computer storage medium is stored with computer program, the meter
Calculation machine program is performed the content for realizing any one of above-described embodiment one to three.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (11)
1. a kind of method that article is registered under new public safety, which is characterized in that this method comprises:
Obtain the images of items of article;
The images of items is inputted to the feature identification model constructed based on deep learning, extracts in the images of items and maps object
The characteristic of kind class simultaneously exports in vector form;
In the mapping relations of the vector sum type of goods constructed based on the feature identification model, the feature identification is not found
When the corresponding type of goods of vector of model output, the type of goods of the article is determined, and by determining type of goods and institute
The corresponding relationship for stating the vector of feature identification model output, is added in the mapping relations of the vector sum type of goods.
2. the method according to claim 1, wherein determining the type of goods of the article, comprising:
The prompt information of output instruction user's input, and receive the article for the article that user inputs according to the prompt information
Type;Or
The images of items of article is exported to third party, receives the article for the article that third party determines according to the images of items
Type.
3. the method according to claim 1, wherein being based on deep learning construction feature identification model, comprising:
Obtain includes the training sample set of multiple training samples and the test sample collection including multiple test samples, each trained sample
Sheet/test sample includes the images of items and the affiliated type of goods of the article of article;
Model parameter by being randomized deep learning network model obtains initial Forecasting recognition model, the Forecasting recognition mould
Type includes multiple feature extraction network layer;
When trigger model training, using the training sample for the preset quantity that the training sample is concentrated, mould is identified to current predictive
Type is trained at least once, and every time after training, the test sample concentrated using the test sample is to pre- after training
It surveys identification model to be tested, when determining that test result meets default required precision, terminates training process, the last one will be removed
The current Forecasting recognition model output of feature extraction network layer is the feature identification model.
4. according to the method described in claim 3, it is characterized in that, utilizing the preset quantity of training sample concentration every time
Training sample is trained current predictive identification model, comprising:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model, output and the images of items
Corresponding prediction type of goods;
According to the prediction type of goods of the images of items and the images of items in training sample corresponding type of goods, lead to
Cross the model parameter that loss function adjusts current Forecasting recognition model.
5. according to the method described in claim 3, it is characterized in that, it is pre- to determine that test result is unsatisfactory for after training every time
If required precision, further includes:
Using the sample data of training sample set described in current Forecasting recognition model discrimination, the training sample set after screening is made
For new training sample set, and trigger model training again.
6. according to the method described in claim 5, it is characterized in that, utilizing training sample described in current Forecasting recognition model discrimination
The sample data of this collection, using the training sample set after screening as new training sample set, comprising:
Images of items in the training sample of preset quantity is inputted to current Forecasting recognition model respectively, is extracted and the article
The corresponding vector of image;
Construct the mapping relations of the corresponding vector sum type of goods of images of items in the training sample of preset quantity;It respectively will be described
Training sample concentrates each images of items in addition to the training sample of preset quantity to input current Forecasting recognition model, according to institute
The mapping relations of the vector and the vector sum type of goods of stating the output of Forecasting recognition model assess having for the training sample
Effect property;
The training sample that all validity are unsatisfactory for preset requirement is concentrated from the training sample and is deleted, new training sample is obtained
This collection.
7. according to the method described in claim 6, it is characterized in that, according to the vector that current Forecasting recognition model exports, with
And the mapping relations of the vector sum type of goods assess the validity of the training sample, comprising:
Determine current feature identification model output, the corresponding vector of the images of items of the training sample;
Determine the corresponding type of goods of the images of items corresponding vector in the mapping relations of the vector sum type of goods,
When being greater than preset value with the vector departure degree that current Forecasting recognition model exports, determine that the validity of the training sample meets
Preset requirement.
8. method as described in claim 1 or 4, which is characterized in that construct vector sum article based on the feature identification model
The mapping relations of type, comprising:
Images of items in the training sample of preset quantity is inputted to current feature identification model respectively, is extracted and the article
The corresponding vector of image;
According to images of items described in the corresponding vector sum of the images of items in training sample corresponding type of goods, construct institute
State the mapping relations of vector sum type of goods.
9. the method according to claim 1, wherein further include:
According to the mapping relations based on vector sum type of goods constructed by the feature identification model, the feature identification is obtained
The corresponding type of goods of vector of model output.
10. article registers equipment under a kind of new public safety, which is characterized in that the equipment includes processor and memory, wherein
The memory stores executable program code, when said program code is performed, so that the processor executes following step
It is rapid:
Obtain the images of items of article;
The images of items is inputted to the feature identification model constructed based on deep learning, extracts in the images of items and maps object
The characteristic of kind class simultaneously exports in vector form;
In the mapping relations of the vector sum type of goods constructed based on the feature identification model, the feature identification is not found
When the corresponding type of goods of vector of model output, the type of goods of the article is determined, and by determining type of goods and institute
The corresponding relationship for stating the vector of feature identification model output, is added in the mapping relations of the vector sum type of goods.
11. a kind of computer storage medium, which is characterized in that the computer storage medium is stored with computer program, the meter
Calculation machine program, which is performed, realizes method described in any one of claim 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910100214.9A CN109858446A (en) | 2019-01-31 | 2019-01-31 | Article register method and device under a kind of new public safety |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910100214.9A CN109858446A (en) | 2019-01-31 | 2019-01-31 | Article register method and device under a kind of new public safety |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109858446A true CN109858446A (en) | 2019-06-07 |
Family
ID=66897350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910100214.9A Pending CN109858446A (en) | 2019-01-31 | 2019-01-31 | Article register method and device under a kind of new public safety |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109858446A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112270339A (en) * | 2020-06-30 | 2021-01-26 | 上海扩博智能技术有限公司 | Image data generation method, system, device and storage medium for model training |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679573A (en) * | 2017-09-30 | 2018-02-09 | 深圳市锐曼智能装备有限公司 | The article identification system and its method of wisdom counter |
CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
CN108717756A (en) * | 2018-05-16 | 2018-10-30 | 上海集成电路研发中心有限公司 | A kind of intelligent storage cabinet and its lending or the method for being stored in article |
CN108885813A (en) * | 2018-06-06 | 2018-11-23 | 深圳前海达闼云端智能科技有限公司 | Intelligent sales counter, article identification method, apparatus, server and storage medium |
CN109145901A (en) * | 2018-08-14 | 2019-01-04 | 腾讯科技(深圳)有限公司 | Item identification method, device, computer readable storage medium and computer equipment |
JP2019016091A (en) * | 2017-07-05 | 2019-01-31 | 富士ゼロックス株式会社 | Image composition device and program |
WO2019237501A1 (en) * | 2018-06-15 | 2019-12-19 | 广东康云多维视觉智能科技有限公司 | Article display system and method |
-
2019
- 2019-01-31 CN CN201910100214.9A patent/CN109858446A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2019016091A (en) * | 2017-07-05 | 2019-01-31 | 富士ゼロックス株式会社 | Image composition device and program |
CN107679573A (en) * | 2017-09-30 | 2018-02-09 | 深圳市锐曼智能装备有限公司 | The article identification system and its method of wisdom counter |
CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
CN108717756A (en) * | 2018-05-16 | 2018-10-30 | 上海集成电路研发中心有限公司 | A kind of intelligent storage cabinet and its lending or the method for being stored in article |
CN108885813A (en) * | 2018-06-06 | 2018-11-23 | 深圳前海达闼云端智能科技有限公司 | Intelligent sales counter, article identification method, apparatus, server and storage medium |
WO2019237501A1 (en) * | 2018-06-15 | 2019-12-19 | 广东康云多维视觉智能科技有限公司 | Article display system and method |
CN109145901A (en) * | 2018-08-14 | 2019-01-04 | 腾讯科技(深圳)有限公司 | Item identification method, device, computer readable storage medium and computer equipment |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112270339A (en) * | 2020-06-30 | 2021-01-26 | 上海扩博智能技术有限公司 | Image data generation method, system, device and storage medium for model training |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108416902B (en) | Real-time object identification method and device based on difference identification | |
WO2018218860A1 (en) | Commodity recommendation method and device | |
US10628695B2 (en) | Fast item identification for checkout counter | |
CN109190705A (en) | Self-service method, apparatus and system | |
CN108665441A (en) | A kind of Near-duplicate image detection method and device, electronic equipment | |
CN108427927A (en) | Target recognition methods and device, electronic equipment, program and storage medium again | |
CN108921645A (en) | A kind of commodity purchasing determination method, device and user terminal | |
CN109670546B (en) | Commodity matching and quantity regression recognition algorithm based on preset template | |
CN108805644A (en) | The commercial articles vending method and machine for vending of machine for vending | |
CN109919211A (en) | Commodity recognition method, device, system and computer-readable medium | |
CN109858552A (en) | A kind of object detection method and equipment for fine grit classification | |
CN112508132B (en) | Training method and device for identifying SKU | |
CN109754009A (en) | Item identification method, device, vending system and storage medium | |
CN114898249B (en) | Method, system and storage medium for confirming number of articles in shopping cart | |
CN110119914A (en) | Object replenishes processing method, device and system | |
CN112307864A (en) | Method and device for determining target object and man-machine interaction system | |
CN109840503A (en) | A kind of method and device of determining information | |
CN108235114A (en) | Content analysis method and system, electronic equipment, the storage medium of video flowing | |
CN109712324A (en) | A kind of automatic vending machine image-recognizing method, good selling method and vending equipment | |
CN109190706A (en) | Self-service method, apparatus and system | |
CN109858448A (en) | Item identification method and equipment under a kind of public safety | |
CN109858446A (en) | Article register method and device under a kind of new public safety | |
RU2724797C1 (en) | Cash register system and method for identification of courses on tray | |
CN104484745A (en) | City supermarket information publishing system | |
CN110232588A (en) | A kind of solid shop/brick and mortar store management method and solid shop/brick and mortar store management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |