CN107766394B - Service data processing method and system - Google Patents
Service data processing method and system Download PDFInfo
- Publication number
- CN107766394B CN107766394B CN201610711264.7A CN201610711264A CN107766394B CN 107766394 B CN107766394 B CN 107766394B CN 201610711264 A CN201610711264 A CN 201610711264A CN 107766394 B CN107766394 B CN 107766394B
- Authority
- CN
- China
- Prior art keywords
- image
- business
- determining
- keywords
- business object
- 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 OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a service data processing method and a system thereof, wherein the method comprises the following steps: extracting image description characteristics of images corresponding to a plurality of business objects; determining an image-related business object in the plurality of business objects according to the image description features; extracting the text description information of the business object related to the image, and determining the key words of the business object related to the image according to the text description information; determining a business object related to the business type according to the keywords of the business object related to the image; and determining the description information of the business object related to the business type. By the method and the device, the precision and the recall rate of the data mining result can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and a system for processing service data.
Background
Currently, the e-commerce platform contains a large number of (billions) of commodities, and information of the commodities is mostly edited and added by a user of a seller. Due to the fact that the uniform standard does not exist, the correctness of the text information such as the title, the attribute and the detailed description of the commodity filled by the seller is uneven, and therefore the effect obtained by directly using the information provided by the seller is poor; meanwhile, the accuracy of the similar commodity relation graph established by using the information is low.
Moreover, due to the limitation of the existing image algorithm, the accuracy of the similar commodity relation graph which can be constructed only by using the image information is higher than that of the similar commodity relation graph which is established based on characters, but the recall rate is also lower.
In view of the above, it is necessary to provide improved technical means to solve the above problems, because the information corresponding to the business object such as the product is not accurate in the prior art.
Disclosure of Invention
The present application mainly aims to provide a method and a system for processing service data, so as to solve the above problems in the prior art.
In order to solve the above problem, an embodiment according to the present application provides a service data processing method, which includes: extracting image description characteristics of images corresponding to a plurality of business objects; determining an image-related business object in the plurality of business objects according to the image description features; extracting the text description information of the business object related to the image, and determining the key words of the business object related to the image according to the text description information; determining a business object related to the business type according to the keywords of the business object related to the image; and determining the description information of the business object related to the business type.
Wherein the step of determining an image-related business object among the plurality of business objects according to the image description features comprises: and calculating the image similarity of the corresponding business object according to the image description characteristics, and determining the business object with the image similarity larger than a preset threshold value as the business object related to the image.
Wherein, the step of determining the keywords of the business object related to the image according to the text description information comprises the following steps: performing word segmentation on the word description information, and matching each word obtained by word segmentation with a preset keyword dictionary to obtain a keyword; and counting the occurrence frequency of the keywords, and determining the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the business object related to the image.
Wherein, the step of determining the business object related to the business type according to the keyword of the business object related to the image comprises the following steps: and comparing the similarity of the keywords of the business objects related to the plurality of images, and determining the business objects with the similarity larger than a preset threshold as the business objects related to the business types.
Wherein the description information of the business object comprises: text description information; the step of determining the description information of the service object related to the service type includes: counting the occurrence frequency of the keywords of the service objects related to the service types, and determining the keywords with the occurrence frequency larger than a preset threshold value as the text description information of the service objects related to the service types;
wherein the description information of the business object comprises: image description information; the step of determining the description information of the service object related to the service type includes: extracting image description characteristics of an image corresponding to the service object related to the service type; and calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
Wherein the image description features include: SIFT features, CNN features, SURF features, color features, texture histogram features.
According to an embodiment of the present application, there is also provided a service data processing system, including: the image description feature extraction module is used for extracting image description features of images corresponding to the plurality of business objects; the same-image business object determining module is used for determining the business object related to the image in the plurality of business objects according to the image description characteristics; the keyword determining module is used for extracting the text description information of the business object related to the image and determining the keywords of the business object related to the image according to the text description information; the same-class business object determining module is used for determining the business object related to the business type according to the keywords of the business object related to the image; and the description information determining module is used for determining the description information of the service object related to the service type.
The same-image business object determining module is further used for calculating the image similarity of the corresponding business object according to the image description characteristics, and determining the business object with the image similarity larger than a preset threshold value as the business object related to the image.
The keyword determining module is further used for performing word segmentation processing on the text description information, and matching each word obtained through word segmentation processing with a preset keyword dictionary to obtain a keyword; and counting the occurrence frequency of the keywords, and determining the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the business object related to the image.
The similar business object determining module is further used for comparing the similarity of the keywords of the business objects related to the plurality of images and determining the business object with the similarity larger than a preset threshold as the business object related to the business type.
Wherein the description information of the business object comprises: text description information; the description information determination module includes: the text description information determining module is used for counting the occurrence frequency of the keywords of the service object related to the service type and determining the keywords with the occurrence frequency larger than a preset threshold value as the text description information of the service object related to the service type;
wherein the description information of the business object comprises: image description information; the description information determination module includes: the image description information determining module is used for extracting the image description characteristics of the image corresponding to the business object related to the business type; and calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
Wherein the image description features include: SIFT features, CNN features, SURF features, color features, texture histogram features.
According to the technical scheme of the application, the same-image service is established by utilizing the image information, the character key words with higher confidence coefficient are screened according to the same-image service relationship, the similar service relationship based on the characters is established by utilizing the determined character key words, and the description information with higher confidence coefficient is mined according to the established similar service relationship by a statistical method, so that the precision and the recall rate of the data mining result are effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow diagram of a business data processing method according to one embodiment of the present application;
fig. 2 is a flowchart of a service data processing method according to another embodiment of the present application;
fig. 3 is a block diagram of a business data processing system according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a service data processing method according to an embodiment of the present application, and as shown in fig. 1, the method includes:
step S102, extracting image description characteristics of images corresponding to a plurality of business objects.
In the embodiment of the present application, the image corresponding to the business object may be all corresponding images such as a presentation image and a blueprint. Wherein the image description features can represent essential features of an image, including but not limited to: SIFT features, CNN features, SURF features, color features, texture histogram features.
And extracting image description characteristics of an image corresponding to the service data, and creating a same-image service relationship according to the image description characteristics.
Step S104, determining the business object related to the image in the plurality of business objects according to the image description characteristics.
Specifically, the image similarity of the corresponding business object is calculated according to the image description characteristics of the business object, and the business object with the image similarity larger than a preset threshold value is determined as the business object related to the image. That is, the business objects with similar images are gathered together, and the same-image business relationship is established for the business objects. In this application, an image-related business object may also be referred to as a map-like business object.
And step S106, extracting the text description information of the business object related to the image, and determining the key words of the business object related to the image according to the text description information.
Firstly, extracting the caption information of the same-figure service object, wherein the caption information comprises the caption information of the service object, attribute information, brief introduction, options and the like; then, performing word segmentation processing on the extracted word description information, and performing matching processing on each word obtained after the word segmentation processing and a preset keyword dictionary respectively to obtain a preselected keyword from the word description information; then, counting the occurrence frequency of the preselected keywords, and taking the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the same-image service object.
Step S108, determining the business object related to the business type according to the keywords of the business object related to the image.
After determining the keywords of the same-image business objects, comparing the similarity of the keywords of the same-image business objects, and if the similarity is greater than a preset threshold value, judging that the same-image business objects are business objects related to business types. In this application, business objects related to business types may also be referred to as homogeneous business objects.
Step S110, determining description information of the business object related to the business type.
In the embodiment of the present application, the description information of the homogeneous service object includes: the text description information and the image description information are described below separately. The step of determining the text description information of the similar service object comprises the following steps: counting the occurrence frequency of the keywords of the similar service objects, and determining the keywords with the occurrence frequency larger than a preset threshold value as the character description information of the similar service objects; determining the image description information of the homogeneous service object comprises the following steps: extracting image description characteristics of the image corresponding to the service object related to the service type, calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
Details of the above process are described in detail below in conjunction with fig. 2. Fig. 2 is a flowchart of a business data processing method according to another embodiment of the present application, and in this embodiment, a commodity of an e-commerce website is taken as an example for description. As shown in fig. 2, the method comprises the steps of:
in step S202, image description features of images corresponding to a plurality of products are extracted.
In the embodiment of the present application, the image corresponding to the business object may be an image displayed corresponding to a commodity of an e-commerce website, an image corresponding to all commodities such as a coupon of a buyer, and the like. Wherein the image description features include, but are not limited to: CNN (Convolutional Neural Network) Features, SIFT (Scale-invariant feature transform), SURF (Speed-Up Robust Features), color Features, texture histogram Features.
And step S204, determining the commodity with the same image according to the image description characteristics.
In practical applications, one or more description features of an image may be extracted for calculation, and the following description will take the extraction of CNN features and SIFT features of an image as an example. Firstly, calculating similarity values based on CNN features and SIFT (scale invariant feature transform) image similarity values between different images; then, the result of the weighted CNN similarity value and the SIFT similarity value is used as the final result of the similarity between the images, and the commodity with the image similarity larger than a preset threshold value is determined as the commodity of the same image. The weighting coefficient is not limited in the present application.
Step S206, extracting corresponding descriptive information from the determined group of same-drawing commodities, where the descriptive information includes but is not limited to: title, attribute information, brief introduction, options, and other descriptive information.
And step S208, determining keywords of the commodity in the same picture according to the caption information of the commodity in the same picture.
Specifically, word segmentation is performed on the word description information, then each word obtained after word segmentation is matched with a preset keyword dictionary, the occurrence frequency of each keyword is counted, and the keywords with the occurrence frequencies larger than a certain threshold are regarded as the keywords with higher confidence and serve as the keywords of the same-image commodity. Wherein, the keywords of the commodity with the same picture can be one or more.
In practical application, when each word obtained after word segmentation processing is compared with the keyword dictionary, the edit distance of the two words or the cosine distance mode after word2vec coding can be compared, and the two words can also be compared word by word, which is not limited in the application.
Step S210, calculating the similarity of the keywords of a plurality of same-image commodities, and determining the commodities with the similarity larger than a certain threshold value as the same-class commodities.
In practical application, for the determined keywords of the same-image commodity (the keywords with higher confidence), the keywords can be encoded by using a preset encoding mode, the similarity of the obtained encoding result is judged, and the commodity with the similarity larger than a certain threshold value is determined as the same-type commodity.
Step S212, for the determined similar product, counting the occurrence frequencies of all the keywords obtained in step S208 and counting the occurrence frequencies of all the keywords in step S210, and using the keywords with the occurrence frequencies greater than a certain threshold as the final high-confidence character description, that is, determining the character description information of the similar product.
For example, the occurrence frequency of the keyword a in step S210 is a, the occurrence frequency of the keyword a in step S212 is B, and the final weighted score may be C ═ a × a + B × B, where values a and B are manually selected empirical values, for example, 0.5, or 0.3, 0.7, and the like, which is not limited in the present application.
Step S216 is to extract image features of all images (such as the display image, the buyer solarization image, and other related images) included in the determined similar commodities, calculate similarity between the images in the similar commodities, measure a result of the similarity, and use the image with the image similarity greater than a threshold as a high-confidence image description of the similar commodity, that is, determine image description information of the similar commodity.
Fig. 3 is a block diagram of a service data processing system according to an embodiment of the present application, and as shown in fig. 3, the system includes:
and an image description feature extraction module 310, configured to extract image description features of images corresponding to the multiple business objects. In the embodiment of the present application, the image corresponding to the business object may be all corresponding images such as a presentation image and a blueprint. Wherein the image description features can represent essential features of an image, including but not limited to: SIFT features, CNN features, SURF features, color features, texture histogram features.
And the map-associated business object determining module 320 is configured to determine a business object associated with an image from the plurality of business objects according to the image description feature. Specifically, the same-image service object determining module 320 calculates the image similarity of the corresponding service object according to the image description feature, and determines the service object with the image similarity greater than a preset threshold as the service object related to the image.
The keyword determining module 330 is configured to extract the text description information of the business object related to the image, and determine the keyword of the business object related to the image according to the text description information. Specifically, the keyword determining module 330 performs word segmentation on the caption information, and matches each word obtained by word segmentation with a preset keyword dictionary to obtain a keyword; and counting the occurrence frequency of the keywords, and determining the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the business object related to the image.
The homogeneous service object determining module 340 is configured to determine a service object related to a service type according to the keyword of the service object related to the image. Specifically, the same-class service object determining module 340 compares the similarity of the keywords of the service objects related to the plurality of images, and determines the service object with the similarity greater than a preset threshold as the service object related to the service type.
A description information determining module 350, configured to determine description information of the service object related to the service type. Wherein the description information of the business object comprises: the description information determining module 350 includes:
a text description information determining module (not shown) configured to count occurrence frequencies of keywords of the service object related to the service type, and determine the keywords with the occurrence frequencies greater than a preset threshold as text description information of the service object related to the service type; the description information of the business object comprises: image description information; the description information determination module includes:
an image description information determining module (not shown) for extracting image description features of an image corresponding to the business object related to the business type; and calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
The operation steps of the method correspond to the structural features of the system, and can be referred to one another, which is not described in detail.
In summary, according to the above technical solution of the present application, the same-graph service is constructed by using image information, the text keywords with higher confidence are screened according to the same-graph service relationship, the similar service relationship based on text is established by using the determined text keywords, and the description information with higher confidence is mined according to the established similar service relationship by a statistical method, so that the precision and recall rate of the data mining result are effectively improved. In addition, the method and the device can greatly improve the effect of final retrieval recommendation by mining correct information such as titles, attributes, character descriptions and image descriptions from data containing a large amount of noise.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (12)
1. A method for processing service data is characterized by comprising the following steps:
extracting image description characteristics of images corresponding to a plurality of business objects;
determining an image-related business object in the plurality of business objects according to the image description features;
extracting the text description information of the image-related business object from the image-related business object, and determining the key word of the image-related business object according to the text description information;
determining a business object related to a business type in the business objects related to the images according to the comparison result of the similarity between the keywords of the business objects related to the images and a preset threshold;
counting the occurrence frequency of each keyword in the step of determining the keywords of the image-related service object according to the text description information aiming at the service object related to the determined service type to obtain a first statistical result; counting the occurrence frequency of each keyword in the step of determining the business object related to the business type in the business objects related to the image to obtain a second statistical result;
weighting the first statistical result and the second statistical result to obtain a weighted score;
and determining the keywords with the weighted scores larger than a preset threshold value of the keywords as the character description information of the service object related to the service type.
2. The method of claim 1, wherein the step of determining an image-related business object among the plurality of business objects according to the image description features comprises:
and calculating the image similarity of the corresponding business object according to the image description characteristics, and determining the business object with the image similarity larger than a preset threshold value as the business object related to the image.
3. The method of claim 1, wherein the step of determining the keywords of the image-related business object according to the caption information comprises:
performing word segmentation on the word description information, and matching each word obtained by word segmentation with a preset keyword dictionary to obtain a keyword;
and counting the occurrence frequency of the keywords, and determining the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the business object related to the image.
4. The method according to claim 1, wherein the step of determining the business object related to the business type from the business objects related to the images according to the comparison result of the similarity between the keywords of the business objects related to the images and the preset threshold comprises:
and comparing the similarity of the keywords of the business objects related to the plurality of images, and determining the business objects with the similarity larger than a preset threshold as the business objects related to the business types.
5. The method according to claim 1, wherein after the step of determining the business object related to the business type in the business objects related to the images is executed according to the comparison result between the similarity between the keywords of the plurality of business objects related to the images and the preset threshold, the method further comprises:
extracting image description characteristics of an image corresponding to the service object related to the service type;
and calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
6. The method of any of claims 1 to 5, wherein the image description feature comprises: SIFT features, CNN features, SURF features, color features, texture histogram features.
7. A business data processing system, comprising:
the image description feature extraction module is used for extracting image description features of images corresponding to the plurality of business objects;
the same-image business object determining module is used for determining the business object related to the image in the plurality of business objects according to the image description characteristics;
the keyword determining module is used for extracting the text description information of the image-related business object from the image-related business object and determining the keyword of the image-related business object according to the text description information;
the similar business object determining module is used for determining business objects related to business types in the business objects related to the images according to the comparison result of the similarity between the keywords of the business objects related to the images and a preset threshold value;
the frequency counting module is used for counting the occurrence frequency of each keyword in the step of determining the keywords of the image-related business object according to the text description information aiming at the business object related to the determined business type to obtain a first counting result; counting the occurrence frequency of each keyword in the step of determining the business object related to the business type in the business objects related to the image to obtain a second statistical result;
the weighting processing module is used for weighting the first statistical result and the second statistical result to obtain a weighting score;
and the text description information determining module is used for determining the keywords with the weighted scores larger than a preset keyword threshold value as the text description information of the service object related to the service type.
8. The system according to claim 7, wherein the same-image business object determining module is further configured to calculate an image similarity of the corresponding business object according to the image description feature, and determine the business object with the image similarity greater than a preset threshold as the image-related business object.
9. The system of claim 7, wherein the keyword determination module is further configured to perform word segmentation on the caption information, and match each word obtained by the word segmentation with a preset keyword dictionary to obtain a keyword; and counting the occurrence frequency of the keywords, and determining the keywords with the occurrence frequency larger than a preset threshold value as the keywords of the business object related to the image.
10. The system according to claim 7, wherein the homogeneous service object determining module is further configured to compare similarity of keywords of the service objects related to the plurality of images, and determine the service object with the similarity greater than a preset threshold as the service object related to the service type.
11. The system of claim 7, further comprising:
the image description information determining module is used for extracting the image description characteristics of the image corresponding to the business object related to the business type; and calculating the image similarity of the corresponding service object according to the image description characteristics, and determining the image with the image similarity larger than a preset threshold value as the image description information of the service object related to the service type.
12. The system of any of claims 7 to 11, wherein the image description feature comprises: SIFT features, CNN features, SURF features, color features, texture histogram features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610711264.7A CN107766394B (en) | 2016-08-23 | 2016-08-23 | Service data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610711264.7A CN107766394B (en) | 2016-08-23 | 2016-08-23 | Service data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107766394A CN107766394A (en) | 2018-03-06 |
| CN107766394B true CN107766394B (en) | 2021-12-21 |
Family
ID=61264791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610711264.7A Active CN107766394B (en) | 2016-08-23 | 2016-08-23 | Service data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107766394B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119624950A (en) * | 2025-02-11 | 2025-03-14 | 重庆医科大学绍兴柯桥医学检验技术研究中心 | Intelligent fundus image analysis method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034116A (en) * | 2010-05-07 | 2011-04-27 | 大连交通大学 | Commodity image classifying method based on complementary features and class description |
| CN102194013A (en) * | 2011-06-23 | 2011-09-21 | 上海毕佳数据有限公司 | Domain-knowledge-based short text classification method and text classification system |
| CN102193936A (en) * | 2010-03-09 | 2011-09-21 | 阿里巴巴集团控股有限公司 | Data classification method and device |
| CN102254043A (en) * | 2011-08-17 | 2011-11-23 | 电子科技大学 | Semantic mapping-based clothing image retrieving method |
| US8296188B2 (en) * | 2008-07-31 | 2012-10-23 | Fujifilm Corporation | Image display system, server apparatus, and terminal apparatus |
| CN104142946A (en) * | 2013-05-08 | 2014-11-12 | 阿里巴巴集团控股有限公司 | Method and system for aggregating and searching service objects of same type |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334796B (en) * | 2008-02-29 | 2011-01-12 | 浙江师范大学 | A Personalized and Collaborative Online Multimedia Retrieval and Query Method |
| CN101996191B (en) * | 2009-08-14 | 2013-08-07 | 北京大学 | Method and system for searching for two-dimensional cross-media element |
| US8612441B2 (en) * | 2011-02-04 | 2013-12-17 | Kodak Alaris Inc. | Identifying particular images from a collection |
| CN102929937B (en) * | 2012-09-28 | 2015-09-16 | 福州博远无线网络科技有限公司 | Based on the data processing method of the commodity classification of text subject model |
| CN104111933B (en) * | 2013-04-17 | 2017-08-04 | 阿里巴巴集团控股有限公司 | Obtain business object label, set up the method and device of training pattern |
| CN104021228B (en) * | 2014-06-25 | 2017-05-24 | 厦门大学 | Method for matching trademark image fused with object semantic |
| CN104166982A (en) * | 2014-06-30 | 2014-11-26 | 复旦大学 | Image optimization clustering method based on typical correlation analysis |
| CN104199931B (en) * | 2014-09-04 | 2018-11-20 | 厦门大学 | A kind of consistent semantic extracting method of trademark image and trade-mark searching method |
| CN104317827B (en) * | 2014-10-09 | 2017-06-30 | 深圳码隆科技有限公司 | A kind of picture air navigation aid of commodity |
-
2016
- 2016-08-23 CN CN201610711264.7A patent/CN107766394B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8296188B2 (en) * | 2008-07-31 | 2012-10-23 | Fujifilm Corporation | Image display system, server apparatus, and terminal apparatus |
| CN102193936A (en) * | 2010-03-09 | 2011-09-21 | 阿里巴巴集团控股有限公司 | Data classification method and device |
| CN102034116A (en) * | 2010-05-07 | 2011-04-27 | 大连交通大学 | Commodity image classifying method based on complementary features and class description |
| CN102194013A (en) * | 2011-06-23 | 2011-09-21 | 上海毕佳数据有限公司 | Domain-knowledge-based short text classification method and text classification system |
| CN102254043A (en) * | 2011-08-17 | 2011-11-23 | 电子科技大学 | Semantic mapping-based clothing image retrieving method |
| CN104142946A (en) * | 2013-05-08 | 2014-11-12 | 阿里巴巴集团控股有限公司 | Method and system for aggregating and searching service objects of same type |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107766394A (en) | 2018-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359244B (en) | Personalized information recommendation method and device | |
| US9348898B2 (en) | Recommendation system with dual collaborative filter usage matrix | |
| CN107194430B (en) | Sample screening method and device and electronic equipment | |
| CN105975459B (en) | A kind of the weight mask method and device of lexical item | |
| CN110019792A (en) | File classification method and device and sorter model training method | |
| CN111078842A (en) | Method, device, server and storage medium for determining query result | |
| CN106598999B (en) | Method and device for calculating text theme attribution degree | |
| CN111046904B (en) | Image description method, image description device and computer storage medium | |
| US10055741B2 (en) | Method and apparatus of matching an object to be displayed | |
| CN110825894A (en) | Data index establishing method, data index retrieving method, data index establishing device, data index retrieving device, data index establishing equipment and storage medium | |
| CN112580637B (en) | Text information identification method, text information extraction method, text information identification device, text information extraction device and text information extraction system | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| CN111651981A (en) | Data auditing method, device and equipment | |
| CN112632396A (en) | Article recommendation method and device, electronic equipment and readable storage medium | |
| CN106033455B (en) | Method and equipment for processing user operation information | |
| CN107332905A (en) | Information-pushing method, device and server | |
| CN110796505B (en) | Business object recommendation method and device | |
| CN107133811A (en) | The recognition methods of targeted customer a kind of and device | |
| CN106997350B (en) | Data processing method and device | |
| CN106933878B (en) | Information processing method and device | |
| CN107766394B (en) | Service data processing method and system | |
| CN114741489A (en) | Document retrieval method, device, storage medium, and electronic device | |
| CN108255880B (en) | Data processing method and device | |
| CN106294765A (en) | Process the method and device of news data | |
| CN107766373B (en) | Method and system for determining categories to which pictures belong |
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 |