CN111199439B - Commodity information processing method and device - Google Patents
Commodity information processing method and device Download PDFInfo
- Publication number
- CN111199439B CN111199439B CN201811367534.2A CN201811367534A CN111199439B CN 111199439 B CN111199439 B CN 111199439B CN 201811367534 A CN201811367534 A CN 201811367534A CN 111199439 B CN111199439 B CN 111199439B
- Authority
- CN
- China
- Prior art keywords
- brand
- candidate
- category
- information
- candidate brand
- 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
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a commodity information processing method and a device thereof, wherein the method comprises the following steps: determining candidate brands and candidate brand categories according to the commodity information; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, the candidate brand is determined to be a brand of the good. By adopting the method and the device, the recognition rate of the brand of the commodity can be effectively improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for processing commodity information.
Background
Selling and purchasing goods through the internet has become an integral part of our daily lives. In order to present the goods to the user, the merchant needs to input goods information into the terminal device. However, in the process of inputting commodity information, some merchants have the condition that the commodity brands are wrongly or overlooked, and the commodity brands serve as important commodity information and play a key role in subsequent commodity recommendation and commodity classification, so that the merchants need to ensure that the commodity brands in the commodity information are correct. Further, since the same brand may correspond to different categories, there are cases where the brand does not correspond to the category.
In the prior art, a rule-based method is generally used for extracting brand names and categories of commodities in commodity information, and then, the brand names and the categories are determined by manpower. Therefore, there is a need in the art for a merchandise information processing method that can determine the brand and the category of the merchandise at low cost.
Disclosure of Invention
The present application mainly aims to provide a method and an apparatus for processing merchandise information, which aim to solve the above-mentioned problems of determining the brand and category of the merchandise.
An exemplary embodiment of the present application provides a merchandise information processing method including determining candidate brands and candidate brand categories from merchandise information; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
Another exemplary embodiment of the present application provides a computer-readable storage medium having stored thereon computer instructions, wherein the instructions, when executed, implement the above-described method.
Another exemplary embodiment of the present application provides a commodity information processing apparatus, including a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: determining candidate brands and candidate brand categories according to the commodity information; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
Another exemplary embodiment of the present application provides a commodity information processing method, including: inputting commodity information; and acquiring the commodity brand and the commodity category determined by the text prediction machine learning model component and/or the picture prediction machine learning model component by utilizing the commodity information.
Another exemplary embodiment of the present application provides a merchandise information processing method, the method including determining a candidate brand corresponding to a merchandise from merchandise information; inputting commodity information into the first machine learning model component and/or the second machine learning model component respectively, and determining candidate brand categories of commodities; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
Another exemplary embodiment of the present application provides a computer-readable storage medium having stored thereon computer instructions, wherein the instructions, when executed, implement the above-described method.
Another exemplary embodiment of the present application provides a commodity information processing apparatus, including a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: determining candidate brands according to the commodity information; respectively inputting commodity information into a first machine learning model component and/or a second machine learning model component to obtain a first candidate brand category and/or a second candidate brand category, and determining the candidate brand category of the commodity; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
At least one technical scheme adopted by the exemplary embodiment of the application can be used for mutually determining the candidate brand and the candidate brand category under the condition of determining the candidate brand and the candidate brand category, so that the correctness of the brand and the category thereof is ensured.
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 illustrates a scene diagram to which a commodity processing method according to an exemplary embodiment of the present application is applied;
FIG. 2 is a schematic diagram of time series data stored by rows according to an exemplary embodiment of the present application;
fig. 3 is a block diagram of an apparatus for storing time series data according to an exemplary embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all 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.
Before describing exemplary embodiments of the present application, terms referred to in the present application will be explained first to facilitate better understanding of the present application by those skilled in the art.
Corpora, i.e., linguistic materials, are basic units that constitute a corpus.
Category means the type of commodity, such as drink, digital, fruit, fresh, etc.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 illustrates a scene diagram to which a commodity processing method according to an exemplary embodiment of the present application is applied. As shown in fig. 1, a merchant inputs commodity information by using a terminal device 100, the commodity information may indicate information for describing commodities, including but not limited to literal information represented by characters and pictorial information represented by pictures, furthermore, the terminal device 100 refers to a device used by the merchant for communicating with a website server, and the terminal device according to the present application may include but not limited to any of the following devices: personal Computers (PCs), mobile devices such as cellular phones, personal Digital Assistants (PDAs), digital cameras, portable game consoles, MP3 players, portable/Personal Multimedia Players (PMPs), handheld electronic books, tablet PCs, portable laptop PCs, and Global Positioning System (GPS) navigators, smart TVs, and the like.
The network is a medium for providing communication links between the server 200 and the terminal device 100 and between the server 200 and the mobile terminal 300. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
For example, a merchant may input commodity information "apple gold, mobile telecommunication 4G mobile phone, dual-card dual-standby, new product on the market, larger screen, dual-card dual-standby, and necessary for commerce" on a website for issuing commodities by using a peripheral keyboard of the terminal device 100, and then the terminal device 100 may transmit the commodity information to the server 200 corresponding to the website, and the server 200 may perform processing on the commodity information related to the website, for example, store the commodity information in a certain storage manner, and analyze the commodity information. It should be noted that although only one terminal device 100 is shown in fig. 1, this is merely exemplary, and each merchant may input merchandise information through a different terminal device. Similarly, the number of servers 200 is not limited to that shown in fig. 1, and the user may determine the number of servers according to the requirement.
Then, the user may search for desired goods using the mobile terminal 300, for example, the user may input a keyword "apple" on an interface of a shopping application (e.g., jingdong, naobao, etc.), and then the mobile terminal 300 receives goods recommendations from the server and displays goods information of the goods on the interface. After the commodity information processing method according to the exemplary embodiment of the present application is applied, commodities presented by the mobile terminal 300 include all commodities of the same brand, and there is no problem that the commodities cannot be recommended due to mistake in commodity brand transportation caused by negligence of merchants, and further, after the commodity information processing method according to the exemplary embodiment of the present application is applied, the mobile terminal 300 may display commodity recommendations of the same category.
Fig. 2 is a flowchart illustrating a commodity information processing method according to an exemplary embodiment of the present application. As shown in fig. 2, at step S210, a candidate brand and a category of candidate brands are determined according to commodity information, which is information about a commodity input by a user and includes text information and picture information.
According to an exemplary embodiment of the present application, before performing step S210, the method may store a brand library in advance, and the brands of the commodities and the categories thereof may be stored in the brand library correspondingly, for example, the brand library may include (wara, drinks), (argentina red shrimp, fresh), (guang, milk), (guang, home) (tata, women' S shoes), (tata, wooden doors), and the like. It can be seen that in a brand library, the same category may include a number of different brands, and the same brand may belong to different categories.
Specifically, the text information in the commodity information may be extracted first, where the text information refers to information described in words, and it should be noted that a person skilled in the art may extract the text information by using various text information extraction methods, which will not be described herein again. Then, the text information may be subjected to word segmentation processing to obtain a plurality of words corresponding to the text information, for example, the text information may be "tata" that i particularly like safety and no taste, and the word segmentation processing may be performed on the text information. It should be noted that words without specific meaning, such as word, auxiliary word, etc., may be automatically eliminated when performing the word segmentation process, and "i", "special", "like", "safe", "taste", "tata" may be obtained. Finally, each of the obtained participles is respectively matched with the brand in the brand library, as described in the above example, "me", "special", "like", "safe", "taste", "tata" can be respectively matched with the brand library, and finally the successfully matched brand is "tata", and then "tata" is taken as a candidate brand.
In step S210, in the case where a candidate brand corresponding to the article is determined from the article information, a candidate brand category corresponding to the article may also be determined from the article information. Specifically, text information in the commodity information is extracted; candidate brand category prediction is performed on the textual information using a textual prediction machine learning model component to determine candidate brand categories corresponding to the goods, wherein the textual prediction machine learning model component includes a fast text classifier (FastText) component, a decision tree component, and a Support Vector Machine (SVM) component.
According to an exemplary embodiment of the application, picture information in the commodity information can be extracted, candidate brand category prediction is performed on the picture by using a picture prediction machine learning model component, and therefore candidate brand categories corresponding to the commodity are determined, wherein the picture prediction machine learning model component comprises a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component and a Recurrent Neural Network (RNN) component.
In addition, the candidate commodity category can also be determined from the text information and the picture information respectively according to the method, namely the method can extract the text information and the picture information in the commodity information respectively; performing candidate brand category prediction on the text information by using a text prediction machine learning model component, thereby determining a first candidate brand category corresponding to the commodity; performing candidate brand category prediction on the picture by using the picture prediction machine learning model component so as to determine a second candidate brand category corresponding to the commodity; determining whether the first candidate brand category is the same as the second candidate brand category; and if so, determining the first candidate brand category or the second candidate brand category as the candidate brand category corresponding to the commodity. This may improve the accuracy of the determined candidate categories.
In addition, according to an exemplary embodiment of the present application, candidate brand categories corresponding to the goods may be acquired according to a category acquisition method, where the category acquisition method may include a first category acquisition method and/or a second category acquisition method. Specifically, the text information in the commodity information may be extracted first in the manner described above, and then the candidate brand category may be acquired by using a first category acquisition method, where the first category acquisition method includes: and inputting the text information into a first machine learning model component to obtain candidate brand categories corresponding to the commodities, wherein the first machine learning model component is obtained by performing machine training according to the corresponding relation between the existing text information of the commodities and the categories corresponding to the commodities. According to an exemplary embodiment of the present application, the first machine learning model component includes a fast text classifier (FastText) component, a decision tree component, and a Support Vector Machine (SVM) component.
In addition, the picture information in the commodity information may be extracted by a picture extraction method, for example, the picture information may be extracted by extracting data in various picture formats, and then, the candidate brand category may be acquired by a second category acquisition method, which includes: and inputting the picture information into a second machine learning model component, and acquiring candidate brand categories corresponding to the commodities, wherein the second machine learning model component is obtained by performing machine training according to the corresponding relationship between the existing picture information of the commodities and the categories corresponding to the commodities. According to an exemplary embodiment of the present application, the second machine learning model component includes a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component, and a Recurrent Neural Network (RNN) component.
In addition, when the candidate brand categories of the goods are acquired using the first category acquisition method and the second category acquisition method, the method further includes determining whether the first candidate brand category acquired using the first category acquisition method is the same as the second candidate brand category determined using the second category acquisition method. And if so, determining the first candidate brand category or the second candidate brand category as the candidate brand category corresponding to the commodity.
Subsequently, at step S220, it is determined whether the candidate brand belongs to the category of candidate brands. Specifically, matching the candidate brand category with the candidate category corresponding to the candidate brand in the brand library; if the matching is successful, the candidate brand belongs to the category of candidate brands. For example, when the candidate brand category is milk, the candidate brand is lucent, and the candidate category corresponding to the lucent in the brand library is home and milk, it can be seen that the candidate category corresponding to the lucent in the brand library includes milk.
Finally, in step S230, if the candidate brand belongs to the category of candidate brands, the candidate brand is determined as the brand of the commodity. And according to an exemplary embodiment of the present application, the candidate brand category may be determined as the brand category of the goods, and as the candidate brand definition belongs to the candidate brand category milk, the candidate brand definition may be determined as the brand definition of the goods and the candidate brand category milk is determined as the brand category of the goods, as described above in the example.
And if the candidate brand does not belong to the candidate brand category, the candidate brand is indicated as a commodity brand which cannot be used as the commodity brand, the candidate brand is indicated as an error, the user can set reminding operation, and once the candidate brand does not belong to the candidate brand category, a warning can be sent to the merchant, so that the merchant can change the commodity brand in time.
According to an exemplary embodiment of the present application, there is provided a commodity information processing method including determining a candidate brand corresponding to a commodity from commodity information; respectively inputting commodity information into a first machine learning model component and/or a second machine learning model component to obtain a first candidate brand category and/or a second candidate brand category, and determining the candidate brand category of the commodity; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
Optionally, determining the candidate brand as a brand of the commodity further includes: the candidate brand category is determined as a brand category for the good.
Optionally, the first machine learning model component includes a fast text classifier (FastText) component, a decision tree component, and a Support Vector Machine (SVM) component.
Optionally, the second machine learning model component includes a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component, and a Recurrent Neural Network (RNN) component.
According to an exemplary embodiment of the present application, there is provided a commodity information processing method including: inputting commodity information; and acquiring the commodity brand and the commodity category determined by the text prediction machine learning model component and/or the picture prediction machine learning model component by utilizing the commodity information. It should be noted that the method can be applied on the user side (e.g., merchant, etc.), and the user can know the brand and category of the inputted goods that have been checked after inputting the goods information.
In summary, the merchandise information processing method according to the exemplary embodiment of the present application may determine a brand candidate and a category of a brand candidate by using the brand candidate and the category of the brand candidate to each other, thereby ensuring correctness of the brand, and further, may determine the category of the merchandise to facilitate subsequent operations. When the commodity information processing method according to the exemplary embodiment of the present application is applied to the scenario of fig. 1, a user can view all commodities of the same brand on a display interface without the problem that the commodities cannot be recommended due to the mistake of the brand of the commodity caused by negligence of the merchant, and in addition, the commodities of the same category can be recommended to the user.
In order to more clearly understand the inventive concept of the exemplary embodiment of the present application, a block diagram of a merchandise information processing apparatus of the exemplary embodiment of the present application will be described below with reference to fig. 3. Those of ordinary skill in the art will understand that: the apparatus in fig. 3 shows only components related to the present exemplary embodiment, and common components other than those shown in fig. 3 are also included in the apparatus.
Fig. 3 shows a block diagram of a commodity information processing apparatus of an exemplary embodiment of the present application. Referring to fig. 3, the apparatus includes, at a hardware level, a processor, an internal bus, and a computer-readable storage medium, wherein the computer-readable storage medium includes a volatile memory and a non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory and then runs it. Of course, besides the software implementation, the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Specifically, the processor performs the following operations: determining candidate brands and candidate brand categories according to the commodity information; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, the candidate brand is determined to be a brand of the good.
Optionally, the processor, after implementing the step of determining the candidate brand as a brand of the good, further comprises: the candidate brand category is determined as a brand category for the good.
Optionally, the processor determining, in the implementing step, a candidate brand corresponding to the good according to the good information includes: extracting text information in the commodity information; obtaining a plurality of participles corresponding to the text information by performing participle processing on the text information; matching each word in the multiple words with a brand in a pre-stored brand library respectively; and taking the brand successfully matched as a candidate brand corresponding to the commodity.
Optionally, the processor, in the step of implementing, determining a candidate brand category corresponding to the good according to the good information includes: extracting text information in the commodity information; and performing candidate brand category prediction on the text information by using a text prediction machine learning model component, thereby determining candidate brand categories corresponding to the commodities.
Optionally, the text prediction machine learning model component includes a fast text classifier (FastText) component, a decision tree component, and a Support Vector Machine (SVM) component.
Optionally, the processor determining, in the implementing step, a candidate brand category corresponding to the item according to the item information includes: extracting picture information in the commodity information; and performing candidate brand category prediction on the picture by using the picture prediction machine learning model component, so as to determine candidate brand categories corresponding to the commodities.
Optionally, the picture prediction machine learning model component includes a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component, and a Recurrent Neural Network (RNN) component.
Optionally, the processor, in the step of implementing, determining the category of the candidate brand based on the merchandise information includes: respectively extracting text information and picture information in the commodity information; performing candidate brand category prediction on the text information by using a text prediction machine learning model component, thereby determining a first candidate brand category corresponding to the commodity; performing candidate brand category prediction on the picture by using the picture prediction machine learning model component, thereby determining a second candidate brand category corresponding to the commodity; determining whether the first candidate brand category is the same as the second candidate brand category; and if so, determining the first candidate brand category or the second candidate brand category as the candidate brand category corresponding to the commodity.
Optionally, the processor determining whether the candidate brand belongs to the category of candidate brands in the implementing step includes: matching the candidate brand category with the candidate category corresponding to the candidate brand in the brand library; if the matching is successful, the candidate brand belongs to the category of candidate brands.
According to an exemplary embodiment of the present application, there is provided a commodity information processing apparatus including a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: determining a candidate brand corresponding to the commodity according to the commodity information; respectively inputting commodity information into a first machine learning model component and/or a second machine learning model component to obtain a first candidate brand category and/or a second candidate brand category, and determining the candidate brand category of the commodity; judging whether the candidate brand belongs to the category of the candidate brand; if the candidate brand belongs to the category of candidate brands, the candidate brand is determined to be a brand of the good.
Optionally, the processor implementing the step of determining the candidate brand as a brand of the good further comprises: the candidate brand category is determined as a brand category for the good.
Optionally, the first machine learning model component includes a fast text classifier (FastText) component, a decision tree component, and a Support Vector Machine (SVM) component.
Optionally, the second machine learning model component includes a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component, and a Recurrent Neural Network (RNN) component.
As described above, the commodity information processing apparatus of the exemplary embodiment of the present application can perform determination with respect to each other using a candidate brand and a category of candidate brands in the case of determining the candidate brand and the category of candidate brands, thereby ensuring correctness of brands, and further, can determine the category of commodities for subsequent operations. When the commodity information processing apparatus according to the exemplary embodiment of the present application is applied to the scenario of fig. 1, a user can view all commodities of the same brand on a display interface without the problem that the commodities cannot be recommended due to the mistake of the brand due to negligence of the merchant, and furthermore, commodities of the same category can be recommended to the user.
It should be noted that the execution subjects of the steps of the method provided in embodiment 1 may be the same device, or different devices may be used as the execution subjects of the method. For example, the execution subject of steps 21 and 22 may be device 1, and the execution subject of step 23 may be device 2; for another example, the execution subject of step 21 may be device 1, and the execution subjects of steps 22 and 23 may be device 2; and so on.
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 so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
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 phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.
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.
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 (13)
1. A commodity information processing method, characterized by comprising:
determining candidate brands and candidate brand categories according to the commodity information;
matching the candidate brand category with the candidate category corresponding to the candidate brand in the brand library;
if the matching is successful, the candidate brand belongs to the category of the candidate brand;
if the candidate brand belongs to the category of candidate brands, determining the candidate brand as the brand of the commodity.
2. The method of claim 1, further comprising: the candidate brand category is determined as a brand category for the good.
3. The method of claim 1, wherein determining candidate brands from merchandise information comprises:
extracting text information in the commodity information;
performing word segmentation processing on the text information to obtain a plurality of words corresponding to the text information;
matching each word in the multiple words with a brand in a pre-stored brand library respectively;
and taking the brand successfully matched as a candidate brand.
4. The method of claim 1, wherein determining a category of candidate brands from the merchandise information comprises:
extracting text information in the commodity information;
candidate brand category prediction is performed on the textual information using a textual prediction machine learning model component to determine candidate brand categories.
5. The method of claim 4, wherein the text prediction machine learning model component comprises a fast text classifier FastText component, a decision tree component, and a Support Vector Machine (SVM) component.
6. The method of claim 1, wherein determining a category of candidate brands from the merchandise information comprises:
extracting picture information in the commodity information;
and performing candidate brand category prediction on the picture by utilizing the picture prediction machine learning model component so as to determine the candidate brand category.
7. The method of claim 6, wherein the picture prediction machine learning model components include a Convolutional Neural Network (CNN) component, a Deep Neural Network (DNN) component, and a Recurrent Neural Network (RNN) component.
8. The method of claim 1, wherein determining candidate brand categories from merchandise information comprises:
respectively extracting text information and picture information in the commodity information;
performing candidate brand category prediction on the text information by using a text prediction machine learning model component, thereby determining a first candidate brand category;
performing candidate brand category prediction on the picture by using the picture prediction machine learning model component, thereby determining a second candidate brand category;
determining whether the first candidate brand category is the same as the second candidate brand category;
if so, determining the first candidate brand category or the second candidate brand category as the candidate brand category.
9. An article information processing apparatus characterized by comprising:
a processor; and
a memory for storing computer executable instructions executable by a processor to implement the method of any of claims 1 to 8.
10. A commodity information processing method, characterized by comprising:
determining candidate brands according to the commodity information;
respectively inputting commodity information into a first machine learning model component and/or a second machine learning model component to obtain a first candidate brand category and/or a second candidate brand category, and determining the candidate brand category of the commodity;
matching the candidate brand category with the candidate category corresponding to the candidate brand in the brand library;
if the matching is successful, the candidate brand belongs to the category of candidate brands;
if the candidate brand belongs to the category of candidate brands, the candidate brand is determined to be a brand of the good.
11. The method of claim 10, wherein determining the candidate brand as the brand of the good further comprises: the candidate brand category is determined as a brand category for the good.
12. The method of claim 10, wherein the first machine learning model component comprises a fast text classifier FastText component, a decision tree component, and a Support Vector Machine (SVM) component.
13. The method of claim 10, in which second machine learning model components comprise Convolutional Neural Network (CNN) components, deep Neural Network (DNN) components, and Recurrent Neural Network (RNN) components.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367534.2A CN111199439B (en) | 2018-11-16 | 2018-11-16 | Commodity information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811367534.2A CN111199439B (en) | 2018-11-16 | 2018-11-16 | Commodity information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111199439A CN111199439A (en) | 2020-05-26 |
| CN111199439B true CN111199439B (en) | 2023-04-14 |
Family
ID=70747300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811367534.2A Active CN111199439B (en) | 2018-11-16 | 2018-11-16 | Commodity information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111199439B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989043A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method and device for automatically acquiring trademark in commodity image and searching trademark |
| CN106056133A (en) * | 2016-05-19 | 2016-10-26 | 无线生活（杭州）信息科技有限公司 | Image identification method and device |
| CN107122980A (en) * | 2011-01-25 | 2017-09-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for recognizing the affiliated classification of commodity |
| CN107220876A (en) * | 2017-05-26 | 2017-09-29 | 北京三快在线科技有限公司 | Commodity information management method, device and mobile terminal |
| CN108345620A (en) * | 2017-01-24 | 2018-07-31 | 北京京东尚科信息技术有限公司 | Brand message processing method, device, storage medium and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014032539A (en) * | 2012-08-03 | 2014-02-20 | Toshiba Tec Corp | Object recognition scanner system, dictionary server, object recognition scanner, dictionary server program and control program |
| US9299098B2 (en) * | 2013-08-13 | 2016-03-29 | Ebay Inc. | Systems for generating a global product taxonomy |
| JP6747873B2 (en) * | 2016-05-26 | 2020-08-26 | 東芝テック株式会社 | Information processing device and program |
-
2018
- 2018-11-16 CN CN201811367534.2A patent/CN111199439B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122980A (en) * | 2011-01-25 | 2017-09-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for recognizing the affiliated classification of commodity |
| CN105989043A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method and device for automatically acquiring trademark in commodity image and searching trademark |
| CN106056133A (en) * | 2016-05-19 | 2016-10-26 | 无线生活（杭州）信息科技有限公司 | Image identification method and device |
| CN108345620A (en) * | 2017-01-24 | 2018-07-31 | 北京京东尚科信息技术有限公司 | Brand message processing method, device, storage medium and electronic equipment |
| CN107220876A (en) * | 2017-05-26 | 2017-09-29 | 北京三快在线科技有限公司 | Commodity information management method, device and mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111199439A (en) | 2020-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10929799B2 (en) | Identification of inaccurate addresses for package deliveries | |
| CN110023982B (en) | System, method, storage device, and medium for selecting product title | |
| CN107330752B (en) | Method and device for identifying brand words | |
| US20190311210A1 (en) | Automated extraction of product attributes from images | |
| US11257049B1 (en) | Item identification based on receipt image | |
| CN110020009B (en) | Online question and answer method, device and system | |
| WO2020001106A1 (en) | Classification model training method and store classification method and device | |
| US11615644B2 (en) | Face detection to address privacy in publishing image datasets | |
| CN109816134B (en) | Method and device for predicting delivery address and storage medium | |
| US20150378975A1 (en) | Attribute fill using text extraction | |
| US11741094B2 (en) | Method and system for identifying core product terms | |
| US20150379610A1 (en) | Recommendation information presentation device, recommendation information presentation method, and recommendation information presentation program | |
| CN110569502A (en) | Method and device for identifying forbidden slogans, computer equipment and storage medium | |
| CN112330382B (en) | Item recommendation method, device, computing equipment and medium | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| US20130304539A1 (en) | User recommendation method and device | |
| CN110362702B (en) | Picture management method and equipment | |
| US11068715B1 (en) | Automated detection and extraction of nutrition information for food products | |
| CN111612284B (en) | Data processing method, device and equipment | |
| CN108492112B (en) | Method and device for judging false resource transfer and false transaction and electronic equipment | |
| CN111199439B (en) | Commodity information processing method and device | |
| US10216988B2 (en) | Information processing device, information processing method, and computer program product | |
| CN116010707A (en) | Commodity price anomaly identification method, device, equipment and storage medium | |
| KR20210054021A (en) | Probabilistic item matching and search | |
| US20150347564A1 (en) | Category name extraction device, category name extraction method, and category name extraction program |
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 |