CN113255819A - Method and apparatus for identifying information - Google Patents
Method and apparatus for identifying information Download PDFInfo
- Publication number
- CN113255819A CN113255819A CN202110650616.3A CN202110650616A CN113255819A CN 113255819 A CN113255819 A CN 113255819A CN 202110650616 A CN202110650616 A CN 202110650616A CN 113255819 A CN113255819 A CN 113255819A
- Authority
- CN
- China
- Prior art keywords
- information
- category
- feature
- attribute
- characteristic
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000013528 artificial neural network Methods 0.000 claims description 78
- 230000006870 function Effects 0.000 claims description 41
- 238000012549 training Methods 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000012512 characterization method Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000004927 fusion Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000011176 pooling Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
Embodiments of the present disclosure disclose methods and apparatus for identifying information. One embodiment of the method comprises: acquiring a first attribute feature of information to be identified; acquiring a category feature set, wherein each category feature in the category feature set is respectively used for representing different information categories, and each category feature is obtained by fusing a first attribute feature and a second attribute feature of information in a target information set corresponding to the information category; determining the similarity between the first attribute features of the information to be identified and each category feature in the category feature set respectively to obtain a similarity set; and determining the information category to which the information to be identified belongs according to the similarity set. The implementation mode realizes that the corresponding class representation with higher confidence coefficient is generated by utilizing various attribute characteristics of the information under the information class, thereby being beneficial to realizing the robust and credible identification of the information class under the multi-attribute condition.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method and an apparatus for identifying information.
Background
Classified learning is one of the main application scenarios of artificial intelligence. For example, the corresponding plant category is identified from the plant image. As another example, the item class is identified based on the item image. As another example, a category to which the video content belongs is identified, and so on. At present, classified learning is mainly realized by using a network model based on deep learning. In order to make the network model have better classification capability, a large number of labeled samples are usually required to train the network model.
In some application scenarios, it takes high labor or time cost to obtain a large number of labeled samples, or only a small number of labeled samples can be obtained. In these cases, how to implement classification learning with fewer labeled samples, i.e., small sample learning, is a considerable problem.
Currently, the main method of small sample Learning is Meta-Learning (Meta-Learning). The meta-learning for small samples mainly includes two methods, an optimization-based meta-learning method and a metric-based meta-learning method. The meta-learning method based on optimization generally trains a network model for classification by using a small number of labeled samples, and then optimizes the network model by using a new task in a testing stage. The metric-based meta-learning method generally learns class characterization by using a small number of labeled samples, and then determines the class of the object to be classified according to the relationship between the feature characterization and the class characterization of the object to be classified.
Disclosure of Invention
Embodiments of the present disclosure propose methods and apparatuses for identifying information.
In a first aspect, an embodiment of the present disclosure provides a method for identifying information, the method including: acquiring a first attribute feature of information to be identified; acquiring a category feature set, wherein each category feature in the category feature set is respectively used for representing different information categories, and each category feature is obtained by fusing a first attribute feature and a second attribute feature of information in a target information set corresponding to the information category; determining the similarity between the first attribute features of the information to be identified and each category feature in the category feature set respectively to obtain a similarity set; and determining the information category to which the information to be identified belongs according to the similarity set.
In a second aspect, an embodiment of the present disclosure provides an apparatus for identifying information, the apparatus including: an attribute feature acquisition unit configured to acquire a first attribute feature of information to be identified; the information classification method comprises a classification characteristic acquisition unit, a classification characteristic acquisition unit and a classification characteristic analysis unit, wherein the classification characteristic acquisition unit is configured to acquire a classification characteristic set, each classification characteristic in the classification characteristic set is respectively used for representing different information classes, and each classification characteristic is obtained by fusing a first attribute characteristic and a second attribute characteristic of information in a target information set corresponding to the information class; the similarity determining unit is configured to determine the similarity between the first attribute feature of the information to be identified and each class feature in the class feature set to obtain a similarity set; and the information category determining unit is configured to determine the information category to which the information to be identified belongs according to the similarity set.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, which computer program, when executed by a processor, implements the method as described in any of the implementations of the first aspect.
According to the method and the device for identifying information, the category characteristics corresponding to the information category are determined in advance by fusing at least two attribute characteristics of the information in the target information set corresponding to each information category, and then the information category of the information to be identified can be determined according to the similarity between one attribute characteristic of the information to be identified and the category characteristics corresponding to various information categories. In the method, more accurate category representation can be generated by utilizing various attribute characteristics of the information under each information category, so that the accuracy, robustness and reliability of subsequent category identification aiming at the information to be identified are improved.
Drawings
Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present disclosure may be applied;
FIG. 2 is a flow diagram for one embodiment of a method for identifying information, according to the present disclosure;
FIG. 3 is a flow diagram of one embodiment of a method for determining a category characterization in a method for identifying information according to the present disclosure;
FIG. 4 is a schematic diagram of one application scenario of a method for identifying information in accordance with an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an embodiment of an apparatus for identifying information according to the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary architecture 100 to which embodiments of the method for identifying information or the apparatus for identifying information of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The terminal devices 101, 102, 103 interact with a server 105 via a network 104 to receive or send messages or the like. Various client applications may be installed on the terminal devices 101, 102, 103. Such as search-type applications, browser-type applications, image-processing-type applications, text-processing-type applications, shopping-type applications, and so forth.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server providing various services, such as a server providing back-end support for client applications installed on the terminal devices 101, 102, 103. The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for identifying information provided by the embodiment of the present disclosure is generally performed by the server 105, and accordingly, the apparatus for identifying information is generally disposed in the server 105.
It should be noted that the terminal devices 101, 102, and 103 may also have an information identification application installed therein, and the terminal devices 101, 102, and 103 may also identify the information to be identified based on the information identification application. At this time, the method for identifying information may be executed by the terminal apparatuses 101, 102, 103, and accordingly, the means for identifying information may be provided in the terminal apparatuses 101, 102, 103. At this point, the exemplary system architecture 100 may not have the server 105 and the network 104.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for identifying information in accordance with the present disclosure is shown. The method for identifying information includes the steps of:
In the present embodiment, the information to be identified may be various types of information. For example, the types of information to be identified include, but are not limited to: images, text, video, audio, and so forth.
The first attribute feature may be for characterizing an attribute value of a first attribute of the information. Wherein the first attribute may be any attribute of the information. For example, for an image, the first attribute may be a visual feature of the image (e.g., a texture feature, a shape feature, a spatial relationship feature, a shape feature, etc.).
In the present embodiment, the executing entity (such as the server 105 shown in fig. 1) of the method for identifying information may acquire the first attribute feature of the information to be identified from a local or other storage device (such as a connected database, the terminal devices 101, 102, 103 shown in fig. 1, and the like).
At step 202, a category feature set is obtained.
In this embodiment, the class feature set may be composed of several class features. The category features may be used to characterize the category of information to which the information belongs. Each category feature in the category feature set may correspond to a different information category.
The dividing mode of the information category can be preset according to the actual application scene and the application requirement. For example, in an application scenario of item identification, the information categories may include various item categories. For another example, in an application scenario of plant identification, the information category may include various plant categories.
For each category feature in the category feature set, the category feature may be obtained by fusing a first attribute feature and a second attribute feature of information in the target information set corresponding to the information category. The target information set may refer to a target information set corresponding to an information category characterized by the category feature. The target information set corresponding to an information category may be composed of several pieces of information belonging to the information category.
The second attribute feature may be for characterizing an attribute value of a second attribute of the information. Wherein the second attribute may be any attribute of the information. Generally, the first attribute is different from the second attribute. At this time, the first attribute feature and the second attribute feature are used to describe different attribute features, respectively.
Specifically, various fusion methods can be flexibly adopted to fuse the first attribute feature and the second attribute feature of the information in the target information set to obtain the category representation. For example, the first attribute features respectively corresponding to each piece of information in the target information set may be averaged as the first attribute features after fusion, then the second attribute features respectively corresponding to each piece of information may be averaged as the second attribute features after fusion, and then the first attribute features and the second attribute features may be fused (for example, the first attribute features and the second attribute features are added or multiplied together) as the category representations corresponding to the information categories to which the corresponding target information set belongs.
In this embodiment, the executive may obtain the set of category features from a local or other storage device. The category feature in the category feature set may be obtained by the execution agent by fusing the first attribute feature and the second attribute feature of the information in the target information set corresponding to the information category, or may be obtained by fusing the first attribute feature and the second attribute feature of the information in the target information set corresponding to the information category by another electronic device or the like.
In this embodiment, the first attribute feature and the category feature can be generally represented by using a vector. The similarity between the first attribute feature and the category feature may be determined using various existing similarity calculation methods. For example, the similarity between the first attribute feature and the class feature may be determined according to a euclidean distance and/or a cosine similarity between the first attribute feature and the class feature.
And 204, determining the information category of the information to be identified according to the similarity set.
In this embodiment, after the similarity set corresponding to the information to be identified is obtained, various methods may be used to determine the information category to which the information to be identified belongs according to each similarity in the similarity set and the actual application scenario.
For example, the maximum similarity may be selected from the similarity set, and then the information category corresponding to the maximum similarity is determined as the information category to which the information to be identified belongs. For another example, a plurality of similarity degrees may be selected in descending order, information categories corresponding to the selected similarity degrees are used as candidate information categories of the information to be identified, and then the candidate information categories of the information to be identified are determined comprehensively in combination with identification results of other information category identification methods.
In some optional implementations of the embodiment, the characteristic represented by the first attribute characteristic and the characteristic represented by the second attribute characteristic may be characteristics of different modalities. For example, the feature represented by the first attribute feature and the feature represented by the second attribute feature may include a visual feature and a semantic feature. At this time, the visual feature and the semantic feature of the information can be integrated to accurately represent the category feature.
As an example, the first attribute feature represents a visual feature of the information, and the second attribute feature represents a semantic feature of the information. Alternatively, the first attribute feature represents a semantic feature of the information and the second attribute feature represents a visual feature of the information.
The multi-modal characteristics of the information are utilized to improve the richness of the attribute characteristics of the information, so that relatively accurate category characterization can be obtained by utilizing the richer attribute characteristics, and the accuracy of subsequent information identification based on the category characterization is improved.
In some optional implementation manners of this embodiment, the number of the second attribute features may be one, or may be more than two, and specifically, the second attribute features may be flexibly set according to different application scenarios or actual requirements, so as to accurately represent the category features by combining various effective attribute features.
In some optional implementations of the embodiment, for each class feature in the class feature set, the number of pieces of information included in the target information set for obtaining the class feature is not greater than a preset threshold. The preset threshold value may be preset by a technician according to an actual application scenario.
In some cases, the number of information of each information category that can be acquired is limited. In this case, it is difficult to learn the category standard corresponding to the information category with a small amount of information alone. For this case, the accuracy of the class characterization can be improved from another perspective by augmenting the attribute features of the information.
It should be noted that, in order to facilitate the description of different objects (e.g., different attributes, different attribute features, different neural networks, etc.) in the present disclosure, the first and second objects are used to distinguish the two objects, and those skilled in the art should understand that the first or second object does not constitute a specific limitation for the related object.
The method provided by the above embodiment of the present disclosure expands the types of the attribute features of the information when learning the category characterization of each information category, so as to learn the category characterization of each information category by combining multiple attribute features of the information, thereby solving the problem of unreliable learned category characterization to a certain extent due to the small number of information of each information category that can be used or insufficient information that can be represented by the specified attribute features of the information, and improving the reliability of the category characterization.
With further reference to FIG. 3, a flow 300 of one embodiment of a method for determining a class characterization in a method for identifying information is shown. As shown in fig. 3, for each class feature in the class feature set, the following steps can be performed:
The execution subject for determining the category characterization may be the execution subject of the method for identifying information of the present disclosure, or may be any other electronic device.
In this embodiment, the execution subject determining the category characterization may obtain, from a local or other storage device, the first attribute feature and the second attribute feature corresponding to each piece of information in the target information set.
In this embodiment, for each piece of information in the target information set, various fusion methods may be used to fuse the first attribute feature and the second attribute feature of the piece of information, so as to obtain a fused feature corresponding to the piece of information.
For example, the first attribute feature and the second attribute feature of the information may be directly spliced as the fused feature corresponding to the information. For another example, the first attribute information and the second attribute information of the information may be multiplied to obtain a fused feature corresponding to the information.
Optionally, the first attribute feature and the second attribute feature of the information may be fused using a non-linear fusion method. For example, a weighted sum of the first attribute feature and the second attribute feature of the information is calculated as the fused feature corresponding to the information. And the weights corresponding to the first attribute feature and the second attribute feature respectively belong to the range of 0 to 1, and the sum is 1. Therefore, when the first attribute feature and the second attribute feature are fused, an attention mechanism can be introduced to distinguish the action of different attribute features, so that more accurate class characterization is facilitated.
As an example, the first attribute feature and the second attribute feature of the information may be merged by the following formula:
P′m＝aPm+(1-a)Sm.
where Pm represents the first attribute feature, Sm represents the second attribute feature, P'm represents the fused feature, and a represents the weight.
In this embodiment, after obtaining the fused features corresponding to each information in the target information set, various methods may be used to determine the category characterization of the corresponding information category. For example, the fused features corresponding to each piece of information may be averaged or weighted to obtain a fusion result as the category characterization corresponding to the information category.
When the target information set includes only one piece of information, the fused feature corresponding to the piece of information may be directly used as the category representation of the information category to which the piece of information belongs.
In some optional implementations of this embodiment, for information in the target information, a first attribute feature of the information may be obtained by using a first neural network trained in advance, and a second attribute feature of the information may be obtained by using a second neural network trained in advance.
Wherein, the first neural network and the second neural network can be designed based on the structure of the existing various feature extraction networks. The first neural network and the second neural network may have the same structure or different structures. For example, the first neural network may be a convolutional neural network, a convolutional neural network with pooling, a graph convolution network, a language model, or the like.
As an example, the first or second neural network may be a multi-layer convolutional neural network to achieve feature extraction on an image using the following formula:
where x represents the input to the convolutional neural network,
representing the output of the convolutional neural network, R represents an arbitrary real number, h represents the height of the input image, w represents the width of the input image, c represents the number of channels, d represents the dimension, and θ is a parameter of the convolutional neural network.
As yet another example, a convolutional neural network may include a pooling layer to average pool a feature map of the network layer output in the convolutional neural network using the following formula:
wherein Sm represents a feature map, Pm represents a pooling result, (xi, yi) represents a pixel point in the feature map, theta is a parameter of the pooling layer, and f (x)iAnd θ) represents a representative function of the pooling layer.
As yet another example, the first or second neural network may be a graph convolution network to achieve feature extraction using the following formula:
where Z represents the output of the graph convolution network, ReLU is a nonlinear activation function,
denotes the laplacian matrix, X denotes the input of the graph convolution network, and W1 and W2 are parameters of the graph convolution network.
The first neural network and the second neural network can be obtained by adopting various existing training methods based on machine learning. The first neural network and the second neural network can be obtained by independent training respectively.
In some optional implementations of this embodiment, the first neural network and the second neural network may be obtained through collaborative training. Specifically, the first neural network and the second neural network may be trained by using various existing collaborative training methods so that the first neural network and the second neural network can learn each other in the training process, so as to improve the feature characterization capability of the first neural network and the second neural network.
Optionally, the loss function of the first neural network and the second neural network co-training may include one or more of a first loss function, a second loss function, and a third loss function.
Wherein the first loss function may be used to characterize a difference between an output of the first neural network and a corresponding desired output, and/or to characterize a difference between an output of the second neural network and a corresponding desired output. The output of the neural network may refer to an output result of the neural network on the input sample in the training process, and the corresponding expected output may refer to an output result of the neural network labeled in advance for the input sample. As an example, the first loss function may be designed based on a 2-norm of the output of the neural network and the corresponding desired output.
The second loss function may be used to represent a difference between the information categories determined from the outputs of the first and second neural networks and the labeled information categories. Specifically, in the training process, the output results of the first neural network and the second neural network for the same input sample may be fused, the information category to which the input sample belongs may be predicted according to the fusion result, and the second loss function may be calculated according to the difference between the predicted information and the category pre-labeled for the input sample.
The third loss function may be used to align the first neural network and the second neural network. Specifically, in the training process, a third loss function can be designed by using various existing network alignment methods to align the feature distributions of the vector spaces corresponding to the first neural network and the second neural network, so as to improve the robustness of the overall recognition effect.
As an example, the third loss function may be expressed as the following equation:
wherein L isMARepresents a third loss function, E [ ]]Representing a mathematical expectation. P denotes a first neural network. S represents a second neural network. D (P) represents the output of the discrimination network corresponding to the first neural network. D (S) represents the output of the discrimination network corresponding to the second neural network. D (P) and D (S) both have a value ranging from 0 to 1.
At this time, the first neural network and the second neural network may be aligned based on the generative confrontation network. Specifically, the first neural network and the second neural network may be used as generating models, and the discriminant models corresponding to the first neural network and the second neural network may be respectively constructed at the same time.
In an actual training process, parameters of the first neural network and the second neural network can be adjusted by using one or more of the first loss function, the second loss function and the third loss function so as to complete the training of the first neural network and the second neural network.
With continued reference to fig. 4, fig. 4 is an illustrative application scenario 400 of the method for identifying information according to the present embodiment. In the application scenario of fig. 4, an image 401 to be recognized may be acquired, and then a visual feature 403 of the image 401 to be recognized may be extracted by using a convolutional neural network 402 trained in advance. Then, category representations 404 corresponding to the pre-divided information categories are obtained, similarity between the visual features 403 of the image to be recognized 401 and the characteristics of the categories is calculated to obtain a similarity set 405, and then the information category corresponding to the maximum similarity can be selected from the similarity set to serve as the information category to which the image to be recognized belongs.
The category characterization 404 corresponding to each of the pre-divided information categories may be obtained in advance through a process shown by reference numeral 407 in the figure. Specifically, taking an information category as an example, a sample image set belonging to the information category may be obtained first, and then a knowledge-graph corresponding to the sample images in the sample image set may be obtained.
For a sample image in the sample image set, the sample image can be input to the convolutional neural network to extract visual features of the sample image, and meanwhile, the knowledge graph corresponding to the sample image set is processed by using the graph convolutional network to extract semantic features of nodes representing the sample image in the knowledge graph. Then, the visual features and the semantic features of the sample image can be weighted and summed to obtain the corresponding fusion features of the sample image. Then, the fusion features corresponding to the sample images in the sample image set may be averaged to serve as the category characterization of the information category corresponding to the sample image set.
The method provided by the above embodiment of the present disclosure obtains, for a target information set corresponding to each information category, multiple attribute features of target information, fuses the multiple attribute features of each information, and integrates the fused features corresponding to each information to represent the information category, so that multiple attribute features of information can be sufficiently mined to more accurately represent information, so as to assist in more accurately representing the category representation of the corresponding information category by using the feature representation of each information. Furthermore, the generated class representation with higher confidence coefficient can be used for better identifying the information class of the information to be identified, so that the robust and credible identification of the information class under the multi-attribute condition is realized.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an apparatus for identifying information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable in various electronic devices.
As shown in fig. 5, the apparatus 500 for identifying information provided by the present embodiment includes an attribute feature acquisition unit 501, a category feature acquisition unit 502, a similarity determination unit 503, and an information category determination unit 504. Wherein, the attribute feature acquiring unit 501 is configured to acquire a first attribute feature of the information to be identified; the category feature obtaining unit 502 is configured to obtain a category feature set, where each category feature in the category feature set is used to represent different information categories, and each category feature is obtained by fusing a first attribute feature and a second attribute feature of information in a target information set corresponding to the information category; the similarity determining unit 503 is configured to determine similarity between the first attribute feature of the information to be identified and each category feature in the category feature set, to obtain a similarity set; the information category determination unit 504 is configured to determine an information category to which the information to be identified belongs, according to the similarity set.
In the present embodiment, in the apparatus 500 for identifying information: for specific processing of the attribute feature obtaining unit 501, the category feature obtaining unit 502, the similarity determining unit 503, and the information category determining unit 504 and technical effects thereof, reference may be made to the related descriptions of step 201, step 202, step 203, and step 204 in the corresponding embodiment of fig. 2, and no further description is given here.
In some optional implementations of this embodiment, the target information set includes a number of pieces of information that is not greater than a preset threshold.
In some optional implementations of this embodiment, each class feature in the class feature set is obtained by: acquiring a first attribute characteristic and a second attribute characteristic of information in a target information set corresponding to the category characteristic; for the information in the target information set corresponding to the category characteristics, fusing the first attribute characteristics and the second attribute characteristics of the information to obtain fused characteristics corresponding to the information; and determining the category characteristics according to the fused characteristics corresponding to the information in the target information set corresponding to the category characteristics.
In some optional implementation manners of this embodiment, the obtaining a first attribute feature and a second attribute feature of information in a target information set corresponding to the category feature includes: acquiring a first attribute characteristic of information in a target information set corresponding to the category characteristic by using a pre-trained first neural network; acquiring a second attribute characteristic of the information in the target information set corresponding to the class characteristic by using a pre-trained second neural network; wherein the first neural network and the second neural network are trained cooperatively.
In some optional implementations of the present embodiment, the loss function of the first neural network and the second neural network co-training includes a first loss function, wherein the first loss function is used to characterize a difference between an output of the first neural network and a corresponding desired output, and/or a difference between an output of the second neural network and a corresponding desired output.
In some optional implementations of the embodiment, the loss function of the first neural network and the second neural network co-training includes a second loss function, wherein the second loss function is used to represent a difference between the information category determined from the output of the first neural network and the second neural network and the labeled information category.
In some optional implementations of the embodiment, the loss function of the first neural network and the second neural network co-training includes a third loss function, wherein the third loss function is used to align the first neural network and the second neural network.
In some optional implementations of the embodiment, the feature represented by the first attribute feature and the feature represented by the second attribute feature include a visual feature and a semantic feature.
According to the device provided by the embodiment of the disclosure, the first attribute feature of the information to be identified is acquired through the attribute feature acquisition unit; the method comprises the steps that a category characteristic acquisition unit acquires a category characteristic set, wherein each category characteristic in the category characteristic set is used for representing different information categories, and each category characteristic is obtained by fusing a first attribute characteristic and a second attribute characteristic of information in a target information set corresponding to the information category; the similarity determining unit determines the similarity between the first attribute features of the information to be identified and each category feature in the category feature set respectively to obtain a similarity set; the information category determining unit determines the information category to which the information to be identified belongs according to the similarity set. In the method, more accurate category representation can be generated by utilizing various attribute characteristics of the information under each information category, so that the accuracy, robustness and reliability of subsequent category identification aiming at the information to be identified are improved.
Referring now to FIG. 6, a schematic diagram of an electronic device (e.g., the server of FIG. 1) 600 suitable for use in implementing embodiments of the present disclosure is shown. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure.
It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a first attribute feature of information to be identified; acquiring a category feature set, wherein each category feature in the category feature set is respectively used for representing different information categories, and each category feature is obtained by fusing a first attribute feature and a second attribute feature of information in a target information set corresponding to the information category; determining the similarity between the first attribute features of the information to be identified and each category feature in the category feature set respectively to obtain a similarity set; and determining the information category to which the information to be identified belongs according to the similarity set.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an attribute feature acquisition unit, a category feature acquisition unit, a similarity determination unit, and an information category determination unit. Here, the names of the units do not constitute a limitation to the units themselves in some cases, and for example, the attribute feature acquisition unit may also be described as a "unit that acquires the first attribute feature of the information to be identified".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (11)
1. A method for identifying information, comprising:
acquiring a first attribute feature of information to be identified;
acquiring a category feature set, wherein each category feature in the category feature set is respectively used for representing different information categories, and each category feature is obtained by fusing a first attribute feature and a second attribute feature of information in a target information set corresponding to the information category;
determining the similarity between the first attribute features of the information to be identified and each category feature in the category feature set respectively to obtain a similarity set;
and determining the information category to which the information to be identified belongs according to the similarity set.
2. The method of claim 1, wherein the target set of information includes a number of information not greater than a preset threshold.
3. The method according to claim 1 or 2, wherein each class feature of the set of class features is obtained by:
acquiring a first attribute characteristic and a second attribute characteristic of information in a target information set corresponding to the category characteristic;
for the information in the target information set corresponding to the category characteristics, fusing the first attribute characteristics and the second attribute characteristics of the information to obtain fused characteristics corresponding to the information;
and determining the category characteristics according to the fused characteristics corresponding to the information in the target information set corresponding to the category characteristics.
4. The method according to claim 3, wherein the obtaining of the first attribute feature and the second attribute feature of the information in the target information set corresponding to the category feature comprises:
acquiring a first attribute characteristic of information in a target information set corresponding to the category characteristic by using a pre-trained first neural network;
acquiring a second attribute characteristic of the information in the target information set corresponding to the class characteristic by using a pre-trained second neural network;
wherein the first neural network and the second neural network are trained in coordination.
5. The method of claim 4, wherein the loss function of the first and second neural networks co-training comprises a first loss function, wherein the first loss function is used to characterize a difference between an output of the first neural network and a corresponding desired output, and/or a difference between an output of the second neural network and a corresponding desired output.
6. The method of claim 4, wherein the first and second neural networks co-trained loss functions comprise a second loss function, wherein the second loss function is used to represent a difference between the information categories determined from the outputs of the first and second neural networks and the labeled information categories.
7. The method of claim 4, wherein the loss functions of the first and second neural networks co-training comprise a third loss function, wherein the third loss function is used to align the first and second neural networks.
8. The method of claim 4, wherein the features represented by the first attribute features and the features represented by the second attribute features include visual features and semantic features.
9. An apparatus for identifying information, wherein the apparatus comprises:
an attribute feature acquisition unit configured to acquire a first attribute feature of information to be identified;
the information classification method comprises a classification characteristic acquisition unit, a classification characteristic acquisition unit and a classification characteristic analysis unit, wherein the classification characteristic acquisition unit is configured to acquire a classification characteristic set, each classification characteristic in the classification characteristic set is respectively used for representing different information classes, and each classification characteristic is obtained by fusing a first attribute characteristic and a second attribute characteristic of information in a target information set corresponding to the information class;
the similarity determining unit is configured to determine the similarity between the first attribute feature of the information to be identified and each class feature in the class feature set respectively to obtain a similarity set;
and the information category determining unit is configured to determine the information category to which the information to be identified belongs according to the similarity set.
10. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.
11. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110650616.3A CN113255819B (en) | 2021-06-11 | 2021-06-11 | Method and device for identifying information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110650616.3A CN113255819B (en) | 2021-06-11 | 2021-06-11 | Method and device for identifying information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113255819A true CN113255819A (en) | 2021-08-13 |
| CN113255819B CN113255819B (en) | 2024-04-19 |
Family
ID=77187507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110650616.3A Active CN113255819B (en) | 2021-06-11 | 2021-06-11 | Method and device for identifying information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113255819B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114003188A (en) * | 2021-10-09 | 2022-02-01 | 北京用友薪畴数字科技有限公司 | Information encryption display method and device, electronic equipment and computer readable medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100161524A1 (en) * | 2008-12-19 | 2010-06-24 | International Business Machines Corporation | Method and system for identifying graphical model semantics |
| CN108830334A (en) * | 2018-06-25 | 2018-11-16 | 江西师范大学 | A kind of fine granularity target-recognition method based on confrontation type transfer learning |
| US20190213277A1 (en) * | 2018-01-11 | 2019-07-11 | International Business Machines Corporation | Cognitive retrieve and rank search improvements using natural language for product attributes |
| CN111523574A (en) * | 2020-04-13 | 2020-08-11 | 云南大学 | Image emotion recognition method and system based on multi-mode data |
| CN111598164A (en) * | 2020-05-15 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and device for identifying attribute of target object, electronic equipment and storage medium |
| CN112016601A (en) * | 2020-08-17 | 2020-12-01 | 华东师范大学 | Network model construction method based on knowledge graph enhanced small sample visual classification |
| CN112149699A (en) * | 2019-06-28 | 2020-12-29 | 北京京东尚科信息技术有限公司 | Method and device for generating model and method and device for recognizing image |
| CN112434628A (en) * | 2020-11-30 | 2021-03-02 | 西安理工大学 | Small sample polarization SAR image classification method based on active learning and collaborative representation |
| CN112528058A (en) * | 2020-11-23 | 2021-03-19 | 西北工业大学 | Fine-grained image classification method based on image attribute active learning |
-
2021
- 2021-06-11 CN CN202110650616.3A patent/CN113255819B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100161524A1 (en) * | 2008-12-19 | 2010-06-24 | International Business Machines Corporation | Method and system for identifying graphical model semantics |
| US20190213277A1 (en) * | 2018-01-11 | 2019-07-11 | International Business Machines Corporation | Cognitive retrieve and rank search improvements using natural language for product attributes |
| CN108830334A (en) * | 2018-06-25 | 2018-11-16 | 江西师范大学 | A kind of fine granularity target-recognition method based on confrontation type transfer learning |
| CN112149699A (en) * | 2019-06-28 | 2020-12-29 | 北京京东尚科信息技术有限公司 | Method and device for generating model and method and device for recognizing image |
| CN111523574A (en) * | 2020-04-13 | 2020-08-11 | 云南大学 | Image emotion recognition method and system based on multi-mode data |
| CN111598164A (en) * | 2020-05-15 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and device for identifying attribute of target object, electronic equipment and storage medium |
| CN112016601A (en) * | 2020-08-17 | 2020-12-01 | 华东师范大学 | Network model construction method based on knowledge graph enhanced small sample visual classification |
| CN112528058A (en) * | 2020-11-23 | 2021-03-19 | 西北工业大学 | Fine-grained image classification method based on image attribute active learning |
| CN112434628A (en) * | 2020-11-30 | 2021-03-02 | 西安理工大学 | Small sample polarization SAR image classification method based on active learning and collaborative representation |
Non-Patent Citations (1)
| Title |
|---|
| 孙念;李玉强;刘爱华;刘春;黎威威;: "基于松散条件下协同学习的中文微博情感分析", 浙江大学学报(工学版), no. 08 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114003188A (en) * | 2021-10-09 | 2022-02-01 | 北京用友薪畴数字科技有限公司 | Information encryption display method and device, electronic equipment and computer readable medium |
| CN114003188B (en) * | 2021-10-09 | 2024-02-20 | 北京用友薪畴数字科技有限公司 | Information encryption display method, device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113255819B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108427939B (en) | Model generation method and device | |
| CN111314733B (en) | Method and apparatus for evaluating video sharpness | |
| CN108520220B (en) | Model generation method and device | |
| CN109858445B (en) | Method and apparatus for generating a model | |
| CN109800732B (en) | Method and device for generating cartoon head portrait generation model | |
| CN108280477B (en) | Method and apparatus for clustering images | |
| CN110288049B (en) | Method and apparatus for generating image recognition model | |
| CN108830235B (en) | Method and apparatus for generating information | |
| CN109492128B (en) | Method and apparatus for generating a model | |
| CN109740018B (en) | Method and device for generating video label model | |
| WO2020000879A1 (en) | Image recognition method and apparatus | |
| CN109145828B (en) | Method and apparatus for generating video category detection model | |
| CN111860573A (en) | Model training method, image class detection method and device and electronic equipment | |
| CN109447156B (en) | Method and apparatus for generating a model | |
| CN109376267B (en) | Method and apparatus for generating a model | |
| CN109976997B (en) | Test method and device | |
| CN111523640B (en) | Training method and device for neural network model | |
| CN110009059B (en) | Method and apparatus for generating a model | |
| CN110070076B (en) | Method and device for selecting training samples | |
| CN109961032B (en) | Method and apparatus for generating classification model | |
| CN109800730B (en) | Method and device for generating head portrait generation model | |
| CN109214501B (en) | Method and apparatus for identifying information | |
| CN111368973B (en) | Method and apparatus for training a super network | |
| CN111666416B (en) | Method and device for generating semantic matching model | |
| CN111539903B (en) | Method and device for training face image synthesis model |
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 | ||
| CB02 | Change of applicant information |
Address after: 100176 601, 6th floor, building 2, No. 18, Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing Applicant after: Jingdong Technology Information Technology Co.,Ltd. Address before: 100176 601, 6th floor, building 2, No. 18, Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing Applicant before: Jingdong Shuke Haiyi Information Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant |