CN112685575A - Information identification method and equipment - Google Patents
Information identification method and equipment Download PDFInfo
- Publication number
- CN112685575A CN112685575A CN202011412578.XA CN202011412578A CN112685575A CN 112685575 A CN112685575 A CN 112685575A CN 202011412578 A CN202011412578 A CN 202011412578A CN 112685575 A CN112685575 A CN 112685575A
- Authority
- CN
- China
- Prior art keywords
- information
- data
- identified
- type data
- information data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an information identification method and equipment, wherein the method comprises the following steps: acquiring first type data of an object to be identified; and identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified, and determining an information tag of the second type data corresponding to the object to be identified according to the information association elements, wherein the second type data and the first type data are information data of the same object in different information dimensions. Therefore, information identification is carried out from a plurality of information dimensions of the object to be identified, the accuracy of the information identification is effectively improved, the information label of the second type data of the object to be identified is accurately judged, limitation caused by identification of the information only from the information dimensions of the second type data is effectively avoided, further, accurate data recommendation and other operations can be carried out according to the information label of the second type data, and the operation accuracy of the data recommendation and other operations is remarkably improved.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to an information identification method and device.
Background
The identification of the media file style is a relatively key technology in a streaming media system, is very important for portraying streaming media users and recommending media files, generally adopts a manual marking mode to identify the media file style, has low efficiency and wastes a large amount of human resources.
In view of the above problems, a scheme for identifying the style of a media file based on audio data of the media file is proposed, but the size of the audio data is usually between hundreds of KB and hundreds of MB, and even compressed audio data has hundreds of KB, so that the acquisition and processing of the audio data requires a lot of computing resources and storage resources. In addition, the music style itself is very abstract, and the recognition accuracy of recognizing the music style by using audio data in the current audio recognition method is very low.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention creatively provide an information identification method and apparatus.
According to a first aspect of the present invention, there is provided an information identifying method, the method comprising: acquiring first type data of an object to be identified; identifying the first type data according to an information identification model to obtain information correlation elements of the first type data and the second type data of the object to be identified; determining an information label of second type data corresponding to the object to be identified according to the information association element; the second type data and the first type data are information data of the same object in different information dimensions.
According to an embodiment of the present invention, the first type data is the image information data of the object phase to be identified, and the second type data is the media information data; correspondingly, the identifying the first type data according to the information identification model to obtain the information associated elements of the first type data and the second type data of the object to be identified includes: and identifying the image information data according to an information identification model to obtain information association elements of the image information data and the media information data of the object to be identified.
According to an embodiment of the present invention, the identifying the image information data according to an information identification model to obtain an information related element between the image information data of the object to be identified and the media information data includes: identifying the image information data through the information identification model, and extracting a feature vector in the image information, wherein the feature vector is related to the media information data; and determining the probability of each information associated element in a plurality of information associated elements of the image information data and the media information data according to the feature vector.
According to an embodiment of the present invention, before extracting, by the information recognition model, a feature vector indicating a style of the object to be recognized in the image information data, the recognizing, by the information recognition model, the image information data to obtain an information related element between the image information data of the object to be recognized and the media information data, further includes: and normalizing the size and/or pixels of the image corresponding to the image information data.
According to an embodiment of the present invention, the determining, according to the information related element, the information tag of the second type data corresponding to the object to be identified includes: and determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the predetermined mapping relation between the information related elements and the information label.
According to the second aspect of the present invention, there is also provided an information identifying apparatus, the apparatus comprising: the data acquisition device is used for acquiring first type data of an object to be identified; the element identification device is used for identifying the first type data according to an information identification model to obtain information associated elements of the first type data and the second type data of the object to be identified; the label determining device is used for determining an information label of the second type data corresponding to the object to be identified according to the information associated element; the second type data and the first type data are information data of the same object in different information dimensions.
According to an embodiment of the present invention, the first type data is the image information data of the object phase to be identified, and the second type data is the media information data; accordingly, the element identifying apparatus includes: and the first identification module is used for identifying the image information data according to an information identification model to obtain the information association elements of the image information data and the media information data of the object to be identified.
According to an embodiment of the present invention, the first identification module includes: the characteristic extraction submodule is used for identifying the image information data through the information identification model and extracting a characteristic vector in the image information, and the characteristic vector is related to the media information data; and the probability determining submodule is used for determining the probability of each information associated element in a plurality of information associated elements of the image information data and the media information data according to the feature vector.
According to an embodiment of the present invention, the first identification module further includes: and the image processing submodule is used for carrying out normalization processing on the size and/or pixels of the image corresponding to the image information data before extracting the feature vector which is used for showing the style of the object to be recognized in the image information data through the information recognition model.
According to an embodiment of the present invention, the tag determination apparatus includes: and the information mapping module is used for determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the predetermined mapping relation between the information related elements and the information label.
According to a third aspect of the present invention, there is also provided a computer-readable storage medium comprising a set of computer-executable instructions which, when executed, are operable to perform any of the information-recognition methods described above.
The information identification method and equipment of the embodiment of the invention obtain the first type data of the object to be identified; and identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified, and determining an information tag of the second type data corresponding to the object to be identified according to the information association elements, wherein the second type data and the first type data are information data of the same object in different information dimensions. Therefore, information identification is carried out from a plurality of information dimensions of the object to be identified, the accuracy of the information identification is effectively improved, the information label of the second type data of the object to be identified is accurately judged, limitation caused by identification of the information only from the information dimensions of the second type data is effectively avoided, further, accurate data recommendation and other operations can be carried out according to the information label of the second type data, and the operation accuracy of the data recommendation and other operations is remarkably improved.
It is to be understood that the teachings of the present invention need not achieve all of the above-described benefits, but rather that specific embodiments may achieve specific technical results, and that other embodiments of the present invention may achieve benefits not mentioned above.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a schematic diagram illustrating an implementation flow of an embodiment of an information identification method according to an embodiment of the present invention;
FIG. 2 is a first schematic flow chart illustrating implementation of another embodiment of an information identification method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing a second implementation flow of another embodiment of the information identification method according to the embodiment of the present invention;
fig. 4 is a schematic diagram showing a configuration of an information recognition apparatus according to an embodiment of the present invention.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given only to enable those skilled in the art to better understand and to implement the present invention, and do not limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The technical solution of the present invention is further elaborated below with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic diagram illustrating an implementation flow of an embodiment of an information identification method according to an embodiment of the present invention.
Referring to fig. 1, an information identification method according to an embodiment of the present invention at least includes the following operation flows: operation 101, acquiring first type data of an object to be identified; operation 102, identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified; operation 103, determining an information tag of the second type data corresponding to the object to be identified according to the information association element; the second type data and the first type data are information data of the same object in different information dimensions.
In operation 101, first type data of an object to be recognized is acquired;
in an embodiment of the present invention, the object to be identified may be a media file, for example: an album, a music piece, an optical disc containing an image file such as a tv show or a movie, an electronic magazine, and the like. The first type of data of the object to be recognized may be media information data of music, video, magazine, or the like, or image information data of album covers, a composition of a music in a music library, a classic movie of an image file, a cover of a magazine, or the like. Of course other types of data are possible.
For example: the first type data of the object to be recognized is one of the following: the display image information data corresponding to music or songs, the image information data of album covers corresponding to music albums or movie albums, the image information data corresponding to media file short piece MV covers, the image information data of electronic book covers and the like.
And an operation 102 of identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified, wherein the second type data and the first type data are information data of the same object in different information dimensions.
In an embodiment of the present invention, the second type of data may also be the data type of the first type of data listed in operation 101 above. However, the first type data and the second type data are information data of the same object in different information dimensions. For convenience of describing the present invention in detail, the embodiment of the present invention may be described in detail by taking the first type data as the image information data of the object to be recognized, and the second type data as the media information data of the object to be recognized. Of course, in practical applications, the first data type and the second data type are not particularly limited by the present invention.
In an embodiment of the present invention, the information recognition model may be obtained by training according to the collected first type data and second type data of the object to be recognized. For example: the first type data is image information data, the second type data is media information data, and the information association elements of the first type data and the second type data comprise: character types, for example: classical, modern, male, female, child, character complexion, etc.; scene types, for example: farms, villages, cities, buildings, etc.; color systems, for example: obtaining pink system, dark blue hue and the like through RGB analysis; musical instruments, for example: cucurbit flute, violin, piano, etc.; composition style, for example: reduced, dense, etc.
For example, one or more of a neural network algorithm, a logistic regression algorithm, a bayesian algorithm, a decision tree, and the like may be used to perform model training, so as to obtain an information identification model capable of identifying the information associated elements. For example: the cover image information data of the music album is used as the first type data, the media information data of the music album is used as the second type data, and the media information data and the image information data of the music album have strong relevance. Specifically, elegant and quiet music albums are usually matched with a leisure country beauty in the album cover, a music album with a rock motion feeling in the album cover, and heavy colors, heavy metal elements and the like in the album cover.
And determining an information tag of the second type data corresponding to the object to be identified, wherein the information tag can be used for recommending the object which belongs to the same type as the object to be identified according to the identified information tag. For example, the object to be recognized is a music file, and the second type data is media information data of music, such as: audio files such as mp3 and MAV of music can recommend other music to the user as appropriate according to the information tags of the music currently listened to by the user or the music listened to within a set time period. Therefore, the problem of low recognition accuracy in recognition of the audio file of the music listened by the user is effectively avoided, and meanwhile, the problem that a large amount of computing resources and storage resources are consumed for audio signal collection caused by large occupied space of the audio signal file is avoided.
In an embodiment of the present invention, the information related elements may be simply arranged and combined, and an optimization algorithm may be performed according to the information related elements to obtain the information tag of the second type data. In practical application, the selection may be performed according to an application scenario and an accuracy requirement for the information tag, and other suitable methods may be set to process the information-related element to obtain the information tag of the second type of data.
For example, the object to be recognized is a music file, and the first type data is image information data of an electronic cover of the music file, such as: and the second type data is audio data of the music file. And according to the recognition result of the image information data by the information recognition model, obtaining the information associated elements which comprise three of the character types with higher matching probability, three of the scene types with higher matching probability and other information associated elements with higher matching probability, and then carrying out optimization algorithm processing to obtain the comprehensive matching probability of the corresponding music label. And finally, determining the final music labels according to the comprehensive matching probability, wherein the number of the music labels can be one or more, for example: jazz, pop, ethnic, piano, etc. In this way, operations such as recommendation can be performed according to the determined music tag.
For the optimization algorithm processing of the information related elements, the image factor of each information related element to the final information label can be set according to actual needs, a corresponding set threshold value of the matching probability of each information related element obtained according to the information identification model can be set, and the information related elements are ignored when the matching probability of the information related elements is smaller than the corresponding set threshold value.
In an embodiment of the present invention, the object to be identified is an electronic book, for example: children's books, examination books, entertainment periodicals, literary works, domestic literary works, other literary works, etc. The first type data is cover image information data of the electronic book, and the second type data is media information data such as text data of the electronic book. Because more contents need to be acquired when the text of the electronic book is identified, and the tags of the electronic book have higher abstraction, the category tags of the text of the electronic book cannot be well identified when the text of the electronic book is identified. The cover of the electronic book can usually express the type of the electronic book more accurately. Therefore, the information tag of the text content of the electronic book is identified and obtained according to the cover image information data of the electronic book, so that accurate book recommendation and other operations can be performed, and the user experience is remarkably improved.
Fig. 2 shows a first implementation flow diagram of another implementation of the information identification method according to the embodiment of the present invention, and fig. 3 shows a second implementation flow diagram of another implementation of the information identification method according to the embodiment of the present invention.
Referring to fig. 2, another implementation of the information identification method according to the embodiment of the present invention is that, in this implementation, the first type data is image information data of an object to be identified, and the second type data is media information data, and the information identification method at least includes the following operation flows: operation 201, acquiring image information data of an object to be identified; operation 202, according to the information identification model, identifying the image information data to obtain information association elements of the image information data and the media information data of the object to be identified; in operation 203, an information tag of the media information data of the object to be identified is determined according to the information association element.
In operation 201, image information data of an object to be recognized is acquired.
For example, the object to be identified is a music album, and the image information data is image information data of a picture of the album cover.
In operation 202, the image information data is identified according to the information identification model, and information related elements of the image information data and the media information data of the object to be identified are obtained.
In one embodiment of the present invention, first, normalization processing is performed on the size and/or pixels of an image corresponding to image information data.
For example: the album cover picture can be round, square or rectangular, etc. In order to more accurately recognize information included in the image information data, the picture may be processed into a picture of a set size by performing operations such as cropping and scaling. The set size here may be a set size or may be a set pixel. For example: zooming can be done directly for rectangular or circular pictures. For a rectangular picture, the picture can be cut into a square shape based on the pixels or sizes of the short sides of the picture, and it should be noted that since useful information of the picture is usually located in the middle of the picture, the cut areas on the two sides need to be consistent when the rectangular picture is cut. For the cutting of the rectangle, the cutting can be performed to be a circle by taking the intersection point of the perpendicular bisector of the long side and the perpendicular bisector of the short side of the rectangle as the center of a circle and the shortest distance from the center of a circle to the short side as the radius.
In one embodiment of the present invention, the following operation steps are adopted to realize the identification of the image information data according to the information identification model, so as to obtain the information related elements of the image information data and the media information data of the object to be identified: identifying the image information data through an information identification model, and extracting a characteristic vector in the image information, wherein the characteristic vector is related to the media information data; and determining the probability of each information related element in a plurality of information related elements of the image information data and the media information data according to the characteristic vector.
For example, referring to fig. 3, model training is performed by using music style information of a known album as metadata, and model training is performed by using algorithms such as CNN and the like to obtain an information recognition model. Inputting image information data of album cover pictures to be identified into the model, and obtaining a characteristic vector (w) of the image through CNN algorithm processing1，w2，…，wn) The feature vector (w) can be directly mapped1，w2，…，wn) The vector representation, which is the album to be identified in the recommendation system, is used to recommend music or albums of the same genre as the album. In addition, the vector can be further processed to obtain an information tag of the media information data of the object to be identified, and then the information tag is input into the recommendation system.
In operation 203, an information tag of media information data of an object to be identified is determined according to the information association element.
In one embodiment of the present invention, each information-related element in the information-related elements is regarded as an independent element, the image information data conforms to the element, and the value corresponding to the element in the feature vector is represented as 1, otherwise, it is represented as 0. And finally, determining the information label of the media information data according to the mapping of the information association element and the information label of the media information data.
For example, the information associated elements include a, b, c, d, e, and f, the information tags include x, y, and z, the mapping relationship between the information tags and the information associated elements is as shown in table 1 below, the image information of the cover picture of the album to be identified is obtained by identifying, and the image information data of the cover of the album matches b, c, and e in the information associated elements, then the information tags of the media information data of the album are obtained as x and y according to table 1 below.
TABLE 1
In another embodiment of the present invention, the information tag of the album may also be obtained according to the information tag of each song in the album. For example, the music genre information tags for most songs on an album have been determined, but the music genre information tags for the album are missing. For example: album a has songs g1, g2, g3, g4, g5 and g6, wherein the music style information tags of g1, g2, g4 and g5 are (1,1,1,2,3), then the album style can be (1,2,3), and 1,2 and 3 respectively represent a music style information tag.
In an embodiment of the present invention, the following operation steps are adopted to determine the information tag of the second type data corresponding to the object to be identified according to the information association element: and determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the mapping relation between the predetermined information related elements and the information label.
For example, the object to be identified is a music album, the first type data is image information data of an album cover picture, and the second type data is media information data such as an audio file of a music track included in the music album. Album art is identified and information tags for the music tracks within the album are obtained as an overall music genre for the album to provide music recommendations of the same or similar genre to the user of the album.
When receiving the image information data of the album cover picture, firstly, normalizing the image information data of the album cover, including normalizing the size and pixels of the image, and processing the album cover picture into a picture conforming to the predetermined size and pixels, for example: the side length is set to be square, and the side length can be represented by the size of a picture or a pixel of the picture. The image information data of the image is input to the information recognition model as input, and the image information recognition is carried out to obtain the related information elements of the image information data and the media information data. For example: the obtained related information elements are characters: 80% for female, 90% for child, scene: village 80%, evening 60%, color system: 90% pink and 70% blue, wherein the importance ratio of characters in the association mapping relation between the information association elements and the media information is 0.2, the importance ratio of scenes is 0.4, and the importance ratio of color systems is 0.4, and the probability that the information label comprises graceful color (female, country and pink) is 80% 90% 0.576, the probability that the information label comprises melancholy (female, evening and blue) is 80% 60% 70% 0.336, wherein one information label in the information label is greater than 0.45, the information label in the media information data of the album is determined to comprise the information label, and otherwise, the corresponding label is not included. Thus, it is determined that the information label of the album includes graceful pastiness but does not include a feeling of depression.
The association mapping relationship between the information associated elements and the media information may be set according to actual situations, and the embodiments in the above embodiments of the present invention are merely exemplary, and do not form specific limitations on the solution of the present invention.
Other specific implementation processes of operations 201, 202, and 203 are similar to those of operations 101, 102, and 103 in the embodiment shown in fig. 1, and are not described here again.
The information identification method and equipment of the embodiment of the invention obtain the first type data of the object to be identified; and identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified, and determining an information tag of the second type data corresponding to the object to be identified according to the information association elements, wherein the second type data and the first type data are information data of the same object in different information dimensions. Therefore, information identification is carried out from a plurality of information dimensions of the object to be identified, the accuracy of the information identification is effectively improved, the information label of the second type data of the object to be identified is accurately judged, limitation caused by identification of the information only from the information dimensions of the second type data is effectively avoided, further, accurate data recommendation and other operations can be carried out according to the information label of the second type data, and the operation accuracy of the data recommendation and other operations is remarkably improved.
Similarly, based on the above information identification method, an embodiment of the present invention further provides a computer-readable storage medium, in which a program is stored, and when the program is executed by a processor, the processor is caused to perform at least the following operation steps: operation 101, acquiring first type data of an object to be identified; operation 102, identifying the first type data according to the information identification model to obtain information association elements of the first type data and the second type data of the object to be identified; operation 103, determining an information tag of the second type data corresponding to the object to be identified according to the information association element; the second type data and the first type data are information data of the same object in different information dimensions.
Further, based on the above information identification method, an embodiment of the present invention further provides an information identification device, as shown in fig. 4, where the device 40 includes: a data obtaining device 401, configured to obtain first type data of an object to be identified; the element identification device 402 is used for identifying the first type data according to the information identification model to obtain information associated elements of the first type data and the second type data of the object to be identified; a tag determining device 403, configured to determine, according to the information associated element, an information tag of the second type data corresponding to the object to be identified; the second type data and the first type data are information data of the same object in different information dimensions.
In one embodiment of the present invention, the first type data is image information data of an object to be identified, and the second type data is media information data; accordingly, the element recognition means 402 includes: and the first identification module is used for identifying the image information data according to the information identification model to obtain the information association elements of the image information data and the media information data of the object to be identified.
In one embodiment of the present invention, the first identification module includes: the characteristic extraction submodule is used for identifying the image information data through the information identification model and extracting a characteristic vector in the image information, and the characteristic vector is related to the media information data; and the probability determining submodule is used for determining the probability of each information related element in a plurality of information related elements of the image information data and the media information data according to the feature vector.
In an embodiment of the present invention, the first identification module further includes: and the image processing submodule is used for performing normalization processing on the size and/or pixels of the image corresponding to the image information data before extracting the feature vector which is used for showing the style of the object to be recognized in the image information data through the information recognition model.
In one embodiment of the present invention, a tag determination apparatus includes: and the information mapping module is used for determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the predetermined mapping relation between the information related elements and the information label.
Here, it should be noted that: the above description of the embodiment of the information identification device is similar to the description of the method embodiment shown in fig. 1 to 3, and has similar beneficial effects to the method embodiment shown in fig. 1 to 3, and therefore, the description is omitted. For technical details that are not disclosed in the embodiment of the configuration information identifying device of the present invention, please refer to the description of the method embodiment shown in fig. 1 to 3 of the present invention for understanding, and therefore, for brevity, will not be described again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An information identification method, the method comprising:
acquiring first type data of an object to be identified;
identifying the first type data according to an information identification model to obtain information correlation elements of the first type data and the second type data of the object to be identified;
determining an information label of second type data corresponding to the object to be identified according to the information association element;
the second type data and the first type data are information data of the same object in different information dimensions.
2. The method of claim 1, wherein the first type of data is the object phase image information data to be identified, and the second type of data is media information data; accordingly, the number of the first and second electrodes,
the identifying the first type data according to the information identification model to obtain the information association elements of the first type data and the second type data of the object to be identified comprises the following steps:
and identifying the image information data according to an information identification model to obtain information association elements of the image information data and the media information data of the object to be identified.
3. The method according to claim 2, wherein the identifying the image information data according to an information identification model to obtain an information association element between the image information data of the object to be identified and the media information data comprises:
identifying the image information data through the information identification model, and extracting a feature vector in the image information, wherein the feature vector is related to the media information data;
and determining the probability of each information associated element in a plurality of information associated elements of the image information data and the media information data according to the feature vector.
4. The method according to claim 3, wherein before extracting, by the information recognition model, a feature vector showing a style of the object to be recognized in the image information data, the recognizing, by the information recognition model, the image information data to obtain an information-related element of the image information data and the media information data of the object to be recognized further comprises:
and normalizing the size and/or pixels of the image corresponding to the image information data.
5. The method according to claim 3, wherein the determining, according to the information associated element, an information tag of the second type of data corresponding to the object to be identified includes:
and determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the predetermined mapping relation between the information related elements and the information label.
6. An information identifying apparatus, the apparatus comprising:
the data acquisition device is used for acquiring first type data of an object to be identified;
the element identification device is used for identifying the first type data according to an information identification model to obtain information associated elements of the first type data and the second type data of the object to be identified;
the label determining device is used for determining an information label of the second type data corresponding to the object to be identified according to the information associated element;
the second type data and the first type data are information data of the same object in different information dimensions.
7. The apparatus as set forth in claim 6, wherein,
the first type data is the image information data of the object phase to be identified, and the second type data is the media information data;
accordingly, the element identifying apparatus includes:
and the first identification module is used for identifying the image information data according to an information identification model to obtain the information association elements of the image information data and the media information data of the object to be identified.
8. The apparatus of claim 7, the first identification module comprising:
the characteristic extraction submodule is used for identifying the image information data through the information identification model and extracting a characteristic vector in the image information, and the characteristic vector is related to the media information data;
and the probability determining submodule is used for determining the probability of each information associated element in a plurality of information associated elements of the image information data and the media information data according to the feature vector.
9. The apparatus of claim 8, the first identification module further comprising:
and the image processing submodule is used for carrying out normalization processing on the size and/or pixels of the image corresponding to the image information data before extracting the feature vector which is used for showing the style of the object to be recognized in the image information data through the information recognition model.
10. The apparatus of claim 8, the tag determining means comprising:
and the information mapping module is used for determining the information label of the media information data according to the probability of the information related elements of the image information data and the media information data and the predetermined mapping relation between the information related elements and the information label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011412578.XA CN112685575A (en) | 2020-12-04 | 2020-12-04 | Information identification method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011412578.XA CN112685575A (en) | 2020-12-04 | 2020-12-04 | Information identification method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112685575A true CN112685575A (en) | 2021-04-20 |
Family
ID=75446158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011412578.XA Pending CN112685575A (en) | 2020-12-04 | 2020-12-04 | Information identification method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112685575A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091610A (en) * | 2013-11-15 | 2014-10-08 | 腾讯科技（深圳）有限公司 | Audio file managing method and device |
| CN104573132A (en) * | 2015-02-13 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for finding songs |
| CN105912722A (en) * | 2016-05-04 | 2016-08-31 | 广州酷狗计算机科技有限公司 | Song sending method and apparatus |
| CN108153908A (en) * | 2018-01-18 | 2018-06-12 | 逄泽沐风 | Film poster analysis method and system |
| CN109284412A (en) * | 2018-09-20 | 2019-01-29 | 腾讯音乐娱乐科技（深圳）有限公司 | To the method and apparatus of audio data figure |
| CN110555136A (en) * | 2018-03-29 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Video tag generation method and device and computer storage medium |
-
2020
- 2020-12-04 CN CN202011412578.XA patent/CN112685575A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091610A (en) * | 2013-11-15 | 2014-10-08 | 腾讯科技（深圳）有限公司 | Audio file managing method and device |
| CN104573132A (en) * | 2015-02-13 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for finding songs |
| CN105912722A (en) * | 2016-05-04 | 2016-08-31 | 广州酷狗计算机科技有限公司 | Song sending method and apparatus |
| CN108153908A (en) * | 2018-01-18 | 2018-06-12 | 逄泽沐风 | Film poster analysis method and system |
| CN110555136A (en) * | 2018-03-29 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Video tag generation method and device and computer storage medium |
| CN109284412A (en) * | 2018-09-20 | 2019-01-29 | 腾讯音乐娱乐科技（深圳）有限公司 | To the method and apparatus of audio data figure |
Non-Patent Citations (2)
| Title |
|---|
| 柯元黛: "《造花的艺术》", 30 November 1985, pages: 18 - 20 * |
| 陈建军: "《书籍装帧入门 图册》", vol. 7, 31 July 1996, 南宁：广西美术出版社, pages: 18 - 23 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rajaraman | Introduction to information technology | |
| CN113010703B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN109144954B (en) | Resource recommendation method and device for editing document and electronic equipment | |
| CN105512331B (en) | A kind of video recommendation method and device | |
| JP2013541793A (en) | Multi-mode search query input method | |
| WO2013185107A1 (en) | Systems and methods for recognizing ambiguity in metadata | |
| CN111460179A (en) | Multimedia information display method and device, computer readable medium and terminal equipment | |
| US10650814B2 (en) | Interactive question-answering apparatus and method thereof | |
| CN112528053A (en) | Multimedia library classified retrieval management system | |
| CN111723289B (en) | Information recommendation method and device | |
| JP2020005309A (en) | Moving image editing server and program | |
| CN113360768A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN114372172A (en) | Method and device for generating video cover image, computer equipment and storage medium | |
| CN111832826A (en) | Library management method and device based on augmented reality and storage medium | |
| CN114706987B (en) | Text category prediction method, device, equipment, storage medium and program product | |
| US20160259852A1 (en) | Audio file management method, device and storage medium | |
| JP2019220098A (en) | Moving image editing server and program | |
| CN116051192A (en) | Method and device for processing data | |
| CN113672758A (en) | Singing list generation method, device, medium and computing equipment | |
| Poornima et al. | Multi-modal features and correlation incorporated Naive Bayes classifier for a semantic-enriched lecture video retrieval system | |
| Zhao et al. | A novel approach to automatic detection of presentation slides in educational videos | |
| CN117251622A (en) | Method, device, computer equipment and storage medium for recommending objects | |
| CN112685575A (en) | Information identification method and equipment | |
| CN116978028A (en) | Video processing method, device, electronic equipment and storage medium | |
| CN116980646A (en) | Video data processing method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |