CN110232131B - Creative material searching method and device based on creative tag - Google Patents
Creative material searching method and device based on creative tag Download PDFInfo
- Publication number
- CN110232131B CN110232131B CN201910344697.7A CN201910344697A CN110232131B CN 110232131 B CN110232131 B CN 110232131B CN 201910344697 A CN201910344697 A CN 201910344697A CN 110232131 B CN110232131 B CN 110232131B
- Authority
- CN
- China
- Prior art keywords
- label
- creative
- tags
- tag
- confusion
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a creative material searching method and a creative material searching device based on creative tags, wherein the method comprises the following steps: extracting material tags which effectively describe the characteristics of each creative material in the creative material set, classifying the material tags based on a tag type confirmation method, searching a target tag type corresponding to a target keyword in the classified material tag set, and outputting target material data indicated by the target tag type. By adopting the method and the device, the efficient index mode is established through the tag tree, the specific data information can be quickly positioned, and the efficiency of searching the picture data is improved.
Description
Technical Field
The invention relates to the technical field of creative material search, in particular to a creative material search method and device based on creative tags.
Background
In the era of information explosion, as the information production cost is gradually reduced, the consumption cost of information is also increasing. Most of the designed creative materials are in a picture format, effective information contained in the picture format cannot be effectively reflected through keywords, and a large amount of time is consumed for searching the desired picture data from a large amount of pictures, and the searching accuracy is influenced.
Disclosure of Invention
The embodiment of the invention provides a creative material searching method and device based on creative tags, which can quickly locate specific data information by establishing different types of material tag sets and providing an efficient indexing mode based on the sets.
The first aspect of the embodiment of the invention provides a creative material searching method based on creative tags, which comprises the following steps:
extracting material tags which effectively describe the characteristics of each creative material in the creative material set;
performing label classification on the material label based on a label type confirmation method;
and searching a target label type corresponding to the target keyword in the classified material label set, and outputting target material data indicated by the target label type.
Further, the search method further includes:
adding material tags to each creative material in the creative material set based on a deep learning algorithm;
and extracting the added material label and storing the material label into a material label set.
Further, the search method further includes:
and when the material tags belong to at least two tag types, adding and mapping the material tags according to the existing tags, and determining the tag types of the material tags.
Further, the search method further includes:
performing label coincidence analysis on each material label in the material label set to generate a label confusion matrix;
and adjusting the material labels in the material label set according to the label confusion matrix.
Further, when the material tags in the material tag set are adjusted according to the tag mixing matrix, the search method further includes:
calculating the confusion degree value of any two material labels according to the label confusion matrix;
when the confusion degree value is greater than or equal to a preset confusion threshold value, determining that a material label corresponding to the confusion degree value is a coincidence label;
and determining a representative label in the overlapped labels, and replacing the overlapped labels with the representative labels.
Further, the search method further includes:
and when the design carrier/skill corresponding to the coincidence label has correlation with the design style, the original material label of the coincidence label is kept.
In a second aspect of the embodiments of the present invention, a creative material search apparatus based on creative tags is provided, including:
the tag extraction module is used for extracting material tags which effectively describe the characteristics of each creative material in the creative material set;
the label classification module is used for performing label classification on the material label based on a label type confirmation method;
and the material output module is used for searching a target label type corresponding to the target keyword in the classified material label set and outputting target material data indicated by the target label type.
Further, the tag extraction module includes:
the tag adding unit is used for adding material tags to the creative materials in the creative material set based on a deep learning algorithm;
and the label set generating unit is used for extracting the added material labels and storing the material labels into the material label set.
Further, in the above-mentioned case,
and the label-adding classification module is also used for adding and mapping the material labels according to the existing labels when the material labels belong to at least two label types, so as to determine the label types of the material labels.
Further, the above search device further includes:
the matrix generation module is used for carrying out label coincidence analysis on each material label in the material label set to generate a label confusion matrix;
and the label adjusting module is used for adjusting the material labels in the material label set according to the label confusion matrix.
Further, the tag adjustment module includes:
the confusion degree calculating unit is used for calculating the confusion degree value of any two material labels according to the label confusion matrix;
the label confirmation unit is used for determining the material label corresponding to the confusion degree value as a coincidence label when the confusion degree value is greater than or equal to a preset confusion threshold value;
and the label adjusting unit is used for determining a representative label in the overlapped labels and replacing the overlapped labels with the representative label.
Further, the above search device further includes:
and the label keeping module is used for keeping the original material label of the coincidence label when the design carrier/skill corresponding to the coincidence label has correlation with the design style.
In the embodiment of the invention, the material tags are added to the creative materials through the intelligent marking of the pictures, the material tags are classified to establish different types of tag sets, and an efficient index mode is provided based on the set, so that a user can quickly locate specific data information in massive picture data, and further call and use the data information, thereby improving the efficiency of searching the picture data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a creative material search method based on creative tags according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating intelligent labeling of pictures according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a style confusion matrix according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a creative material search apparatus based on creative tags according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a tag extraction module disclosed in an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a tag adjustment module disclosed in an embodiment of the present invention;
fig. 7 is a schematic structural diagram of another creative material search device based on creative tags according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
In the embodiment of the present invention, the creative material search device based on the creative tag (hereinafter, referred to as a search device) may be a terminal device with capabilities of editing and processing images, for example, a portable intelligent terminal, a PC, and the like.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a creative material search method based on creative tags according to an embodiment of the present invention. As shown in fig. 1, the creative material search method based on creative tags described in this embodiment includes the steps of:
s101, extracting material labels which effectively describe the characteristics of each creative material in the creative material set.
Specifically, the search device may extract material tags of the creative material, for example, as shown in fig. 2, after the user inputs a picture, the search device may output tags corresponding to the picture after adding the label through intelligent identification. It is to be understood that the material tags can be specialized vocabularies that effectively describe the category to which a creative material belongs in terms of design style, design carrier/skill, picture meaning, brand, color, depth of field, layout, and industry, for example, the words of children, face, swallow, building, calligraphy, and hand drawing in fig. 2 are tags that depict the creative material in fig. 2.
Optionally, the device may add corresponding material tags to the intelligent picture annotation, for example, material tags may be added to all creative materials in the creative material set based on a deep learning algorithm. Further, all the added material tags can be combined into a material tag set. It is understood that all creative materials in the set of creative materials may be source data obtained by platform deposition, manual tagging, external collection, and the like.
And S102, performing label classification on the material label based on a label type confirmation method.
It should be noted that the design of creative materials is subjective, which results in uncertainty in the quantification of the category of the design works. Optionally, the design category, i.e., the category of the material label, may be divided into three layers, a bottom layer, a middle layer, and a top layer. The high-level layer represents data with strong subjectivity of people (such as atmosphere top grade), the middle-level layer represents data with neutral property, which can be the design style, content characteristics and the like of creative materials (such as cartoons), and the bottom layer represents more objective constituent elements, which can be points and lines, lines and faces, faces and bodies, bodies and colors and the like.
Note that the choice and wording of the labels is more biased toward the design angle, and relatively neutral. Emphasis on classification of style, design vehicle/skill.
Specifically, the search apparatus may perform tag classification on the material tag based on a tag type confirmation method. Optionally, the tag types of the material tags to be classified may be first identified, and then the target type corresponding to the identified tag type is found from all preset tag types and stored in the set corresponding to the target type. It should be noted that some types of tags may not be clearly defined, that is, the category tags corresponding to the material tags in the material tag set at least include two hierarchies, and the search apparatus may add and map the category tags of the at least two hierarchies, and determine the category tag corresponding to the material tag according to the processing result.
In an alternative embodiment, the search apparatus may perform label coincidence analysis on each material label in the label tree to generate a label confusion matrix. Furthermore, material labels in the label tree can be adjusted according to the label confusion matrix. The material labels with higher similarity in the label tree can be combed out by adjusting the material labels in the label tree, and the efficiency of label classification is improved. Preferably, the searching device may calculate the confusion degree value of any two material labels according to the label confusion matrix, determine that the material label corresponding to the confusion degree value is a coincidence label when the confusion degree value is greater than or equal to a preset confusion threshold, then determine a representative label in the coincidence label, and use the representative label to replace the coincidence label.
For example, in the tag confusion matrix shown in fig. 3, the dark color part is the part where the vertical/horizontal coordinate tag data coincide, and represents the confusion degree of the two tags. It should be noted that, by comparison, the labels with the possibility of data confusion do have a certain coincidence of the relation data because there is a stylistic relation between the labels, for example, it is reasonable that the correlation between the web page (web) in the design carrier dimension and the flat (flat) in the style is extremely relevant (the web page design is certainly flatter than other designs), and it can help us to find out the label rule. The style logic in the design scene is more like a label for describing features, and the features have logic relations with all dimensions such as carriers, methods and the like. When the design carrier/skill corresponding to the coincidence label has correlation with the design style, the searching device can keep the original material label of the coincidence label unchanged.
S103, searching a target label type corresponding to the target keyword in the classified material label set, and outputting target material data indicated by the target label type.
Specifically, the searching device can search for a target tag type corresponding to the target keyword in the classified material tag set, and output target material data indicated by the target tag type. For example, when the user inputs a keyword of "picture cut, thumbnail, saturation, freehand, and clean, etc., the search apparatus may output the material picture of fig. 2 and the similar style to fig. 2.
In the embodiment of the invention, the effective information in the creative materials is extracted and classified to the tag tree, and an efficient tag tree index mode is established, so that a user can quickly locate specific data information in massive picture data, further calling and using are carried out, and the picture data searching efficiency is improved.
A creative tag-based creative material search apparatus according to an embodiment of the present invention will be described in detail with reference to fig. 4-6. It should be noted that, the searching apparatus shown in fig. 4-6 is used for executing the method of the embodiment shown in fig. 1-3 of the present invention, for convenience of description, only the portion related to the embodiment of the present invention is shown, and specific technical details are not disclosed, and reference may be made to the embodiment shown in fig. 1-3 of the present invention.
As shown in fig. 4, the search apparatus 10 according to the embodiment of the present invention may include a tag extraction module 101, a tag classification module 102, a material output module 103, a matrix generation module 104, a tag adjustment module 105, and a tag holding module 106, where the tag extraction module 101 includes a tag adding unit 1011 and a tag set generation unit 1012 as shown in fig. 5, and the tag adjustment module 105 may include an obfuscation degree calculation unit 1051, a tag confirmation unit 1052, and a tag adjustment unit 1053 as shown in fig. 6.
A tag extraction module 101, configured to extract material tags that effectively describe characteristics of each creative material in the creative material set.
In a specific implementation, the tag extraction module 101 may extract material tags of the creative material, for example, as shown in fig. 2, after a user inputs a picture, the tag extraction module 101 may output a tag corresponding to the picture after adding a label through intelligent identification. It is to be understood that the material tags can be specialized vocabularies that effectively describe the category to which a creative material belongs in terms of design style, design carrier/skill, picture meaning, brand, color, depth of field, layout, and industry, for example, the words of children, face, swallow, building, calligraphy, and hand drawing in fig. 2 are tags that depict the creative material in fig. 2.
Optionally, the apparatus 10 may add corresponding material tags to the intelligent picture labels, for example, the tag adding unit 1011 may add material tags to all creative materials in the creative material set based on a deep learning algorithm. Further, the tag set generating unit 1012 may compose all the added material tags into a material tag set. It is understood that all creative materials in the set of creative materials may be source data obtained by platform deposition, manual tagging, external collection, and the like.
And the label classification module 102 is used for performing label classification on the material label based on a label type confirmation method.
It should be noted that the design of creative materials is subjective, which results in uncertainty in the quantification of the category of the design works. Optionally, the design category, i.e., the category of the material label, may be divided into three layers, a bottom layer, a middle layer, and a top layer. The high-level layer represents data with strong subjectivity of people (such as atmosphere top grade), the middle-level layer represents data with neutral property, which can be the design style, content characteristics and the like of creative materials (such as cartoons), and the bottom layer represents more objective constituent elements, which can be points and lines, lines and faces, faces and bodies, bodies and colors and the like.
Note that the choice and wording of the labels is more biased toward the design angle, and relatively neutral. Emphasis on classification of style, design vehicle/skill.
In a specific implementation, the tag classification module 102 may perform tag classification on the material tags based on a tag type confirmation method. Optionally, the tag classifying module 102 may first identify tag types of material tags to be classified, then find a target type corresponding to the tag type from all preset tag types, and store the target type into a set corresponding to the target type. It should be noted that some types of tags may not be clearly defined, that is, the category tags corresponding to the material tags in the material tag set at least include two hierarchies, and the search apparatus may add and map the category tags of the at least two hierarchies, and determine the category tag corresponding to the material tag according to the processing result.
In an alternative embodiment, the matrix generation module 104 may perform label coincidence analysis on each material label in the label tree to generate a label confusion matrix. Further, the label adjusting module 105 may adjust the material labels in the label tree according to the label confusion matrix. The material labels with higher similarity in the label tree can be combed out by adjusting the material labels in the label tree, and the efficiency of label classification is improved. Preferably, the confusion degree calculating unit 1051 may calculate the confusion degree value of any two material tags according to the tag confusion matrix, when the confusion degree value is greater than or equal to the preset confusion threshold, the tag confirming unit 1052 may determine that the material tag corresponding to the confusion degree value is a coincidence tag, and then the tag adjusting unit 1053 determines a representative tag in the coincidence tag, and uses the representative tag to replace the coincidence tag.
For example, in the tag confusion matrix shown in fig. 3, the dark color part is the part where the vertical/horizontal coordinate tag data coincide, and represents the confusion degree of the two tags. It should be noted that, by comparison, the labels with the possibility of data confusion do have a certain coincidence of the relation data because there is a stylistic relation between the labels, for example, it is reasonable that the correlation between the web page (web) in the design carrier dimension and the flat (flat) in the style is extremely relevant (the web page design is certainly flatter than other designs), and it can help us to find out the label rule. The style logic in the design scene is more like a label for describing features, and the features have logic relations with all dimensions such as carriers, methods and the like. When the design carrier/skill corresponding to the above-mentioned coincidence label has correlation with the design style, the label holding module 106 may hold the original material label of the coincidence label unchanged.
And the material output module 103 is configured to search for a target tag type corresponding to the target keyword in the categorized material tag set, and output target material data indicated by the target tag type.
In a specific implementation, the material output module 103 may search for a target tag type corresponding to the target keyword in the categorized material tag set, and output target material data indicated by the target tag type. For example, when the user inputs a keyword of "picture cut, thumbnail, saturation, freehand, and clean, etc., the search apparatus may output the material picture of fig. 2 and the similar style to fig. 2.
In the embodiment of the invention, the effective information in the creative materials is extracted and classified to the tag tree, and an efficient tag tree index mode is established, so that a user can quickly locate specific data information in massive picture data, further calling and using are carried out, and the picture data searching efficiency is improved.
Fig. 7 is a schematic structural diagram of a creative material search apparatus based on creative tags according to an embodiment of the present invention. As shown in fig. 7, the search apparatus 1000 may include: at least one processor 1001, such as a CPU, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display) and a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a standard wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 7, the memory 1005, which is a type of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a creative material search application.
In the search apparatus 1000 shown in fig. 7, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; the network interface 1004 is used for data communication with the user terminal; and the processor 1001 may be configured to invoke the creative material search application stored in the memory 1005 and specifically perform the following operations:
extracting material tags which effectively describe the characteristics of each creative material in the creative material set;
performing label classification on the material label based on a label type confirmation method;
and searching a target label type corresponding to the target keyword in the classified material label set, and outputting target material data indicated by the target label type.
In one embodiment, the processor 1001 is further configured to:
adding material tags to each creative material in the creative material set based on a deep learning algorithm;
and extracting the added material label and storing the material label into a material label set.
In one embodiment, the processor 1001 is further configured to:
and when the material tags belong to at least two tag types, adding and mapping the material tags according to the existing tags, and determining the tag types of the material tags.
In one embodiment, the processor 1001 is further configured to:
performing label coincidence analysis on each material label in the label tree to generate a label confusion matrix;
and adjusting the material labels in the label tree according to the label confusion matrix.
In an embodiment, when the processor 1001 adjusts the material tags in the tag tree according to the tag mixing matrix, the following operations are specifically performed:
calculating the confusion degree value of any two material labels according to the label confusion matrix;
when the confusion degree value is greater than or equal to a preset confusion threshold value, determining that a material label corresponding to the confusion degree value is a coincidence label;
and determining a representative label in the coincidental labels, and replacing the coincidental label with the representative label.
In one embodiment, the processor 1001 is further configured to:
and when the design carrier/skill corresponding to the coincidence label has correlation with the design style, keeping the original material label of the coincidence label.
In the embodiment of the invention, the effective information in the creative materials is extracted and classified to the tag tree, and an efficient tag tree index mode is established, so that a user can quickly locate specific data information in massive picture data, further calling and using are carried out, and the picture data searching efficiency is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (6)
1. A creative material searching method based on creative tags is characterized by comprising the following steps:
extracting material tags which effectively describe the characteristics of each creative material in the creative material set;
performing label classification on the material label based on a label type confirmation method;
searching a target label type corresponding to a target keyword in the classified material label set, and outputting target material data indicated by the target label type;
the method further comprises the following steps: performing label coincidence analysis on each material label in the material label set to generate a label confusion matrix;
adjusting material tags in the material tag set according to the tag confusion matrix, including:
calculating the confusion degree value of any two material labels according to the label confusion matrix;
when the confusion degree value is greater than or equal to a preset confusion threshold value, determining that a material label corresponding to the confusion degree value is a coincidence label;
and determining a representative label in the coincidental labels, and replacing the coincidental label with the representative label.
2. The method of claim 1, further comprising:
adding material labels to each creative material in the creative material set based on a deep learning algorithm;
and extracting the added material label and storing the material label into a material label set.
3. The method of claim 1, further comprising:
and when the material tags belong to at least two tag types, adding and mapping the material tags according to the existing tags, and determining the tag types of the material tags.
4. The method of claim 1, further comprising:
and when the design carrier/skill corresponding to the coincidence label has correlation with the design style, keeping the original material label of the coincidence label.
5. A creative material search device based on creative tags, comprising:
the tag extraction module is used for extracting material tags which effectively describe the characteristics of each creative material in the creative material set;
the label classification module is used for performing label classification on the material label based on a label type confirmation method;
the material output module is used for searching a target label type corresponding to the target keyword in the classified material label set and outputting target material data indicated by the target label type;
the device also comprises a matrix generation module, a label confusion matrix generation module and a label confusion matrix generation module, wherein the matrix generation module is used for carrying out label coincidence analysis on each material label in the material label set to generate a label confusion matrix;
the label adjusting module is configured to adjust material labels in the material label set according to the label confusion matrix, and includes: the confusion degree calculating unit is used for calculating the confusion degree value of any two material labels according to the label confusion matrix;
the label confirmation unit is used for determining that the material label corresponding to the confusion degree value is a coincidence label when the confusion degree value is greater than or equal to a preset confusion threshold value;
and the label adjusting unit is used for determining a representative label in the overlapped labels and replacing the overlapped labels with the representative label.
6. The apparatus of claim 5, wherein:
and the label classification module is also used for adding and mapping the material labels according to the existing labels when the material labels belong to at least two label types, and determining the label types of the material labels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910344697.7A CN110232131B (en) | 2019-04-26 | 2019-04-26 | Creative material searching method and device based on creative tag |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910344697.7A CN110232131B (en) | 2019-04-26 | 2019-04-26 | Creative material searching method and device based on creative tag |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110232131A CN110232131A (en) | 2019-09-13 |
| CN110232131B true CN110232131B (en) | 2021-04-27 |
Family
ID=67860962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910344697.7A Active CN110232131B (en) | 2019-04-26 | 2019-04-26 | Creative material searching method and device based on creative tag |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232131B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241342A (en) * | 2020-01-15 | 2020-06-05 | 北京奇艺世纪科技有限公司 | Material file storage management method and device and material file retrieval method and device |
| CN111833099B (en) * | 2020-06-24 | 2021-08-31 | 广州筷子信息科技有限公司 | Method and system for generating creative advertisement |
| CN112732968B (en) * | 2021-01-12 | 2021-08-31 | 特赞（上海）信息科技有限公司 | Case material image retrieval method, device, equipment and storage medium |
| CN112785659A (en) * | 2021-01-28 | 2021-05-11 | 特赞（上海）信息科技有限公司 | Enterprise case material picture detection method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323560A1 (en) * | 2011-06-16 | 2012-12-20 | Asociacion Instituto Tecnologico De Informatica | Method for symbolic correction in human-machine interfaces |
| CN103186538A (en) * | 2011-12-27 | 2013-07-03 | 阿里巴巴集团控股有限公司 | Image classification method, image classification device, image retrieval method and image retrieval device |
| CN103971678A (en) * | 2013-01-29 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Method and device for detecting keywords |
| CN106021364A (en) * | 2016-05-10 | 2016-10-12 | 百度在线网络技术（北京）有限公司 | Method and device for establishing picture search correlation prediction model, and picture search method and device |
-
2019
- 2019-04-26 CN CN201910344697.7A patent/CN110232131B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323560A1 (en) * | 2011-06-16 | 2012-12-20 | Asociacion Instituto Tecnologico De Informatica | Method for symbolic correction in human-machine interfaces |
| CN103186538A (en) * | 2011-12-27 | 2013-07-03 | 阿里巴巴集团控股有限公司 | Image classification method, image classification device, image retrieval method and image retrieval device |
| CN103971678A (en) * | 2013-01-29 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Method and device for detecting keywords |
| CN106021364A (en) * | 2016-05-10 | 2016-10-12 | 百度在线网络技术（北京）有限公司 | Method and device for establishing picture search correlation prediction model, and picture search method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110232131A (en) | 2019-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232131B (en) | Creative material searching method and device based on creative tag | |
| Rigaud et al. | Knowledge-driven understanding of images in comic books | |
| US11704357B2 (en) | Shape-based graphics search | |
| US20140013215A1 (en) | Paragraph Alignment Detection and Region-Based Section Reconstruction | |
| WO2017080007A1 (en) | Intelligent analysis and processing system of identification code and processing method therefor | |
| KR102002024B1 (en) | Method for processing labeling of object and object management server | |
| CN109492168B (en) | Visual tourism interest recommendation information generation method based on tourism photos | |
| Anichini et al. | Developing the ArchAIDE application: a digital workflow for identifying, organising and sharing archaeological pottery using automated image recognition | |
| CN108268510B (en) | Image annotation method and device | |
| CN115564469A (en) | Advertisement creative selection and model training method, device, equipment and storage medium | |
| CN111143555A (en) | Big data-based customer portrait generation method, device, equipment and storage medium | |
| CN114937270A (en) | Ancient book word processing method, ancient book word processing device and computer readable storage medium | |
| CN114022891A (en) | Method, device and equipment for extracting key information of scanned text and storage medium | |
| EP3564833B1 (en) | Method and device for identifying main picture in web page | |
| CN112528610A (en) | Data labeling method and device, electronic equipment and storage medium | |
| CN109857897B (en) | Trademark image retrieval method and device, computer equipment and storage medium | |
| CN111062388A (en) | Advertisement character recognition method, system, medium and device based on deep learning | |
| US9235604B2 (en) | Method, apparatus and system for obtaining location information | |
| US20220301285A1 (en) | Processing picture-text data | |
| CN113591657B (en) | OCR layout recognition method and device, electronic equipment and medium | |
| CN111291758B (en) | Method and device for recognizing seal characters | |
| CN111597368B (en) | Data processing method and device | |
| US20190197346A1 (en) | Methods and systems for applying content aware stickers onto a layout | |
| JP2011118481A (en) | Program and apparatus for processing image | |
| CN111339465A (en) | Picture processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |