CN103258280A - Price comparative method and system - Google Patents

Price comparative method and system Download PDF

Info

Publication number
CN103258280A
CN103258280A CN2012100375728A CN201210037572A CN103258280A CN 103258280 A CN103258280 A CN 103258280A CN 2012100375728 A CN2012100375728 A CN 2012100375728A CN 201210037572 A CN201210037572 A CN 201210037572A CN 103258280 A CN103258280 A CN 103258280A
Authority
CN
China
Prior art keywords
picture
commodity
key parameter
rate
example commodity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN2012100375728A
Other languages
Chinese (zh)
Inventor
余东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHENGQU INFORMATION TECHNOLOGY (SHANGHAI) Co Ltd
Original Assignee
SHENGQU INFORMATION TECHNOLOGY (SHANGHAI) Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by SHENGQU INFORMATION TECHNOLOGY (SHANGHAI) Co Ltd filed Critical SHENGQU INFORMATION TECHNOLOGY (SHANGHAI) Co Ltd
Priority to CN2012100375728A priority Critical patent/CN103258280A/en
Publication of CN103258280A publication Critical patent/CN103258280A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to a price comparative method and system. According to the price comparative method, a server pre-stores text information and pictures of example commodities in a periodicity mode, and analyzes the pictures of the example commodities to obtain key parameters of the example commodities; when price comparison is carried out, a client sends pictures of commodities to be compared in price or URLs of the pictures to the server, the server analyzes the pictures of the commodities to be compared in price to obtain the key parameters of the example commodities, or analyzes the pictures of the commodities to be compared in price to obtain key parameters of the commodities to be compared in price after obtaining the pictures of the commodities to be compared in price according to the URLs of the pictures of the commodities to be compared in price, the server compares the key parameters of all the example commodities and the key parameters of the commodities to be compared in price to obtain final similarity of each example commodity, the server selects the text information and the pictures of the example commodities according to the final similarity and sends the text information and the pictures to the client, and therefore an accurate price comparison result can be obtained according to the pictures of the commodities.

Description

The price comparison method and system
Technical field
The present invention relates to a kind of price comparison method and system.
Background technology
The multiple pricing comparison system has appearred at present; after the user imports specific key word; price comparison system can be mated relevant commodity and be provided the Price Range of each kinds of goods on network; when the user can obtain the definite model of commodity; existing price comparison system can provide accurate relatively Price Range; yet; when the price of user by a certain commodity of a certain keyword query; the more result (even reaching thousands of) who returns through regular meeting; this price comparison system can not well provide the information that the user needs; for example the user browses a skirt at a certain shopping website; the user wish to know this skirt in the price of other businessmans in order to buy in relatively cheap price; but the user obtains a lot of results after importing in rate of exchange net with the name of this skirt; because having that clothes class commodity are born the same name is a lot; cause the result accurate inadequately, can't satisfy customer requirements.
Application number is that 201010177884.X, denomination of invention disclose a kind of method of carrying out price comparison according to the commodity keyword for the Chinese patent application of " a kind of manner of execution of displaying commodity price relative information with computer ", and this method exists the too much problem of return results equally.
Application number is 200710304204.4, denomination of invention is a kind of for the Chinese patent application of " image content recognizing method and recognition system " discloses identifies the method for image content based on the similarity manner of comparison of picture example, but this method is mainly used in the identifying code picture recognition.
Therefore, need a kind of method or system that carries out more accurate price comparison according to the commodity picture at present badly.
Summary of the invention
The object of the present invention is to provide a kind of price comparison method and system, can obtain more accurate price comparison result according to the commodity picture.
For addressing the above problem, the invention provides a kind of price comparison method, comprising:
Service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity;
When carrying out price comparison, comprising:
Client will treat that the URL of rate of exchange commodity picture or picture sends to service end;
The picture that rate of exchange commodity are treated in described service end analysis to be obtaining the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity, obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity;
Service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity;
Word message and picture that service end is chosen the example commodity according to described final similarity send to described client.
Further, in said method, described service end is chosen after the Word message of example commodity and the step that picture sends to described client according to described final similarity, also comprises: described client's section will obtain the Word message of example commodity and picture and be shared with other clients or be distributed on the network.
Further, in said method, described service end is chosen in the Word message of example commodity and the step that picture sends to described client according to described final similarity, and described service end sends to described client with final similarity greater than Word message and the picture of all example commodity of first predetermined threshold value.
Further, in said method, described service end is chosen in the Word message of example commodity and the step that picture sends to described client according to described final similarity, and described service end sends to described client with Word message and the picture of the example commodity of final similarity maximum.
Further, in said method, described Word message comprises trade name and commodity price at least.
Further, in said method, described Word message also comprises descriptive labelling.
Further, in said method, in the step that described service end sends to described client greater than Word message and the picture of all example commodity of first predetermined threshold value with final similarity, described service end from high to low or from low to high sends to described client greater than Word message and the picture of all example commodity of first predetermined threshold value by commodity price with final similarity.
Further, in said method, described periodicity is stored the step of Word message and the picture of example commodity in advance, comprising: select some e-commerce websites in advance;
Grasp the detailed webpage of example commodity from the electronics website and resolve;
Obtain Word message and the picture of example commodity and be stored in the commercial examples storehouse.
Further, in said method, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, comprising:
The picture of analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The picture of analysis example commodity also carries out normalized to picture and obtains color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Further, in said method, describedly picture is carried out normalized comprise with picture consolidation form, resolution and to picture and carry out level and normalization is longitudinally corrected.
Further, in said method, analyze in the step that the picture treat rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, comprising:
Analysis treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
Analysis is treated the picture of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Further, in said method, describedly picture is carried out normalized comprise with picture consolidation form, resolution and to picture and carry out level and normalization is longitudinally corrected.
Further, in said method, described service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares in the step of the final similarity of obtaining each example commodity, comprising:
The final similarity of all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
The key parameter of embedded information, the original color matrix that the key parameter that the color matrices with the embedded information of all unlabelled example commodity, original color matrix, after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively;
Similarity to each key parameter is weighted the final similarity that each unlabelled example commodity is obtained in summation.
The present invention also provides another kind of price comparison method, comprising:
Service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity;
When carrying out price comparison, comprising:
Client will treat that the Word message of rate of exchange commodity and the URL of picture or picture send to service end;
Described service end compares the Word message of commodity and the Word message of all example commodity, obtains the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings greater than second predetermined threshold value,
If the quantity of example commodity of coupling is less than second predetermined threshold value, then Word message and the picture with the example commodity of all couplings sends to client;
If the quantity of the example commodity of coupling is more than or equal to second predetermined threshold value, then described service end analysis treats that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity, service end with the key parameter of the example commodity of all couplings with treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value.
Further, in said method, described Word message comprises trade name and commodity price at least.
Further, in said method, in the step that described service end sends to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value with final similarity, described service end from high to low or from low to high sends to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value by commodity price with final similarity.
Further, in said method, described periodicity is stored the step of Word message and the picture of example commodity in advance, comprising: select some e-commerce websites in advance;
Grasp the detailed webpage of example commodity from the electronics website and resolve;
Obtain Word message and the picture of example commodity and be stored in the commercial examples storehouse.
Further, in said method, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, comprising:
The picture of analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The picture of analysis example commodity also carries out normalized to picture and obtains color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Further, in said method, describedly picture is carried out normalized comprise with picture consolidation form, resolution and to picture and carry out level and normalization is longitudinally corrected.
Further, in said method, analyze in the step that the picture treat rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, comprising:
Analysis treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
Analysis is treated the picture of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
According to another side of the present invention, a kind of price comparison system is provided, comprising:
Service end, be used for periodically storing in advance Word message and the picture of example commodity, the picture of analysis example commodity also obtains the key parameter of example commodity, analysis treats that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity, with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, and send to described client according to Word message and the picture that described final similarity is chosen the example commodity;
Client is used for treating that the URL of rate of exchange commodity picture or picture sends to service end, and shows that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
Further, in said system,
Described service end comprises:
The commercial examples library module is used for Word message and picture that periodicity is stored the example commodity in advance;
First analysis module is used for the picture of analysis example commodity and obtains the key parameter of example commodity;
Second analysis module, be used for analyzing and treat that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or be used for according to the described URL that treats the picture of rate of exchange commodity, obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity;
Comparison module, be used for the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity;
Output module as a result is used for the display module that final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value;
Described client comprises:
Sending module is used for treating that the URL of rate of exchange commodity picture or picture sends to second analysis module;
Display module is used for choosing the Word message of example commodity and the display module that picture sends to described client according to described final similarity.
Further, in said system, described output module as a result is used for display module that final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value, or is used for the Word message of the example commodity of final similarity maximum and the display module that picture sends to described client.
Further, in said system, described Word message comprises trade name and commodity price at least.
Further, in said system, described output module as a result is used for final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value from high to low or from low to high by commodity price.
Further, in said system, described commercial examples library module comprises:
The merchandise news acquiring unit is used for selecting in advance some e-commerce websites, grasps the detailed webpage of example commodity from the electronics website;
The Word message module is used for Word message and the storage of the detailed webpage of example commodity being resolved to obtain the example commodity;
The picture module is for the picture of the detailed webpage of example commodity being resolved to obtain the example commodity
Further, in said system, described first analysis module comprises:
The first parameter unit, the picture that is used for the analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The second parameter unit is used for the picture of analysis example commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Further, in said system, described second analysis module comprises:
The 3rd parameter unit is used for analyzing and treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
The 4th parameter unit be used for to be analyzed the picture for the treatment of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Further, in said system, described comparison module comprises:
First comparing unit, the final similarity that is used for all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
Second comparing unit, the key parameter of embedded information, the original color matrix that the key parameter that be used for embedded information, the original color matrix of all unlabelled example commodity, the color matrices after handling or gray matrix and picture transparency distributes is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively;
Final similarity unit is used for the similarity of each key parameter is weighted the final similarity that each unlabelled example commodity is obtained in summation.
Further, in said system, described service end also comprises a matching module, is used for the Word message of commodity and the Word message of all example commodity are compared, obtain the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value;
Described output module as a result, Word message and picture with the example commodity of all couplings when also being used for quantity when the example commodity of coupling less than second predetermined threshold value send to client, or final similarity are sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value when also being used for quantity when the example commodity that mate more than or equal to second predetermined threshold value;
Described comparison module, when also being used for quantity when the example commodity of coupling more than or equal to second predetermined threshold value with the key parameter of the example commodity of all couplings and treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling
Described sending module also is used for treating that the Word message of rate of exchange commodity sends to matching module.
Further, in said system, described output module as a result is used for final similarity is sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value from high to low or from low to high by commodity price.
Further, in said system, described first comparing unit, the final similarity that also is used for the example commodity of all couplings identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
Described second comparing unit, the key parameter of embedded information, the original color matrix that the key parameter that also be used for embedded information, the original color matrix of the example commodity of all unlabelled couplings, the color matrices after handling or gray matrix and picture transparency distributes is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter of the example commodity that obtain all unlabelled couplings respectively;
Described final similarity unit also is used for the similarity of each key parameter is weighted the final similarity that the example commodity of each unlabelled coupling are obtained in summation.
Compared with prior art, the present invention periodically stores Word message and the picture of example commodity in advance by service end, and the picture of analysis example commodity obtains the key parameter of described example commodity, when carrying out price comparison, described client will treat that earlier the URL of rate of exchange commodity picture or picture sends to service end, described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity then, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, in addition service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, last described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of first predetermined threshold value or final similarity maximum, can obtain accurate price comparison result according to the commodity picture.
In addition, the present invention periodically stores Word message and the picture of example commodity in advance by service end, and the picture of analysis example commodity obtains the key parameter of described example commodity, when carrying out price comparison, described client will treat that earlier the Word message of rate of exchange commodity and the URL of picture or picture send to service end, then the Word message of described service end with the Word message of commodity and all example commodity compared, obtain the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value, if the quantity of the example commodity of coupling is less than second predetermined threshold value, then Word message and the picture with the example commodity of all couplings sends to client, if the quantity of the example commodity of coupling is more than or equal to second predetermined threshold value, then described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, service end with the key parameter of the example commodity of all couplings with treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value, realized carrying out according to the Word message of commodity the result's of price comparison acquisition basis, further the picture according to commodity carries out price comparison in this result, thereby obtains more accurate price comparison result.
Description of drawings
Fig. 1 is the process flow diagram of the price comparison method of the embodiment of the invention one;
Fig. 2 is the process flow diagram of the price comparison method of the embodiment of the invention two;
Fig. 3 is the high-level schematic functional block diagram of the price comparison system of the embodiment of the invention three;
Fig. 4 is the high-level schematic functional block diagram of the price comparison system of the embodiment of the invention four.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
Embodiment one
Fig. 1 is the process flow diagram of the price comparison method of the embodiment of the invention one.
As shown in Figure 1, the invention provides a kind of price comparison method, comprising:
Step S1, service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity, concrete, described Word message comprises trade name and commodity price at least, certainly, described Word message also can comprise descriptive labelling, need a commercial examples storehouse that comprises commodity picture and Word message in service end, in order to realize treating the retrieval of picture analogies degree of rate of exchange commodity and the retrieval of Word message such as key word, the user can upload a pictures or specify the URL of a picture, search engine will return in the commercial examples storehouse and the picture for the treatment of rate of exchange commodity picture analogies, and with Word message such as the model of each picture and commodity, title, prices etc. connect; Preferably, described periodicity is stored in the step of the Word message of example commodity and picture in advance, also select some e-commerce websites in advance, grasp the detailed webpage of example commodity from the electronics website and resolve, with the Word message that obtains the example commodity and the title of picture such as commodity, price, the content of description and picture also is stored in the commercial examples storehouse, wherein, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, analyze essential characteristic such as the form (png of the picture of each example commodity earlier, jpeg, gif or bmp), resolution (long and wide), picture file size and and obtain the MD5 value of this picture, the key parameter of embedded information (meta-data) and original color matrix, the picture of analysis example commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency again, it is described that picture is carried out normalized is with picture consolidation form (as the png form), resolution reaches carries out level and the rectification of normalization longitudinally (being the png form of 200*200 as unification) to picture;
Step S2 when carrying out price comparison, comprising:
Step S21, client will treat that the URL of rate of exchange commodity picture or picture sends to service end, concrete, client can be treated the URL of the picture on the rate of exchange commodity network or the mode of uploading pictures by user's input, transmission treats that the information of rate of exchange commodity is to service end, carry out similarity retrieval, in addition, client also can be by automatic match user browsing webpage the mode of URL of commodity picture, transmission treats that the information of rate of exchange commodity is to service end, carry out similarity retrieval, service end will be returned and the Price Range of importing the picture analogies commodity;
Step S22, described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, concrete, analysis treats that the picture of rate of exchange commodity obtains in the step of the described key parameter for the treatment of rate of exchange commodity, analyze earlier and treat that the picture of rate of exchange commodity obtains the MD5 value of this picture, the key parameter of embedded information and original color matrix, analyze the picture treat rate of exchange commodity again and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency, describedly picture is carried out normalized comprise the picture consolidation form, resolution reaches carries out level and the rectification of normalization longitudinally to picture;
Step S23, service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, concrete, to treat in this step that the commodity image content example of the rate of exchange and the picture of each the example commodity in the commercial examples storehouse compare, obtain the similarity between the picture of each example commodity in this picture for the treatment of rate of exchange commodity and the described picture price case library, this step comprises:
Step S231, the final similarity of all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark, concrete, described complete matching value refers to the highest matching value under the complete match condition of two pictures, for example adopt percentage recently to represent matching value, and the 100%th, the highest matching value, the complete matching value so here is 100%, here at first judge whether in the commercial examples storehouse, to exist the picture of identical example commodity, if have in the commercial examples storehouse and treat the identical MD5 value of rate of exchange picture example, then matching result can join as a result the output module products for further and handles;
Step S232, the key parameter of embedded information, the original color matrix that the key parameter that the color matrices with the embedded information of all unlabelled example commodity, original color matrix, after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively, the similarity of each key parameter all has ripe algorithm to determine that those of ordinary skill in the art can realize relatively at present;
Step S233 is weighted the final similarity that each unlabelled example commodity is obtained in summation to the similarity of each key parameter;
Step S24, Word message and picture that described service end is chosen the example commodity according to described final similarity send to described client, concrete, among the step S24, service end sends to described client with final similarity greater than Word message and the picture of all example commodity of first predetermined threshold value, or described service end sends to described client with Word message and the picture of the example commodity of final similarity maximum, described service end from high to low or from low to high sends to described client greater than Word message and the picture of all example commodity of first predetermined threshold value by commodity price with final similarity, here according to described first predetermined threshold value, can return one with the described rate of exchange image content similarity for the treatment of greater than the example collection of this threshold value, thereby realized obtaining accurate price comparison result according to the commodity picture, after the step S24, can comprise that also described client's section will obtain the Word message of example commodity and the picture mode by SNS and be shared with other clients or be distributed on the network, be published to rate of exchange information on good friend's mobile phone or on the microblogging such as the API of client by third-party mandate.
Embodiment two
Fig. 2 is the process flow diagram of the price comparison method of the embodiment of the invention two.
As shown in Figure 2, the invention provides another kind of price comparison method, the difference of present embodiment and embodiment one is before carrying out price comparison according to the commodity picture, Word message such as commodity keyword according to commodity carries out price comparison earlier, in the result that the price comparison of the Word message of commodity obtains, further carry out price comparison according to the commodity picture, thereby obtain more accurate price comparison result, the method for present embodiment specifically comprises:
Step S51, service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity, concrete, described Word message comprises trade name and commodity price at least, described Word message also can comprise descriptive labelling, described periodicity is stored the step of Word message and the picture of example commodity in advance, comprise: select some e-commerce websites in advance, grasp the detailed webpage of example commodity from the electronics website and resolve, obtain Word message and the picture of example commodity and be stored in the commercial examples storehouse, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, comprise: the picture of analysis example commodity obtains the MD5 value of this picture, the key parameter of embedded information and original color matrix, the picture of analysis example commodity also carries out normalized to picture and obtains color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency, describedly picture is carried out normalized comprises the picture consolidation form, resolution reaches carries out level and the rectification of normalization longitudinally to picture;
Step S52 when carrying out price comparison, comprising:
Step S521, described client will treat that the Word message of rate of exchange commodity and the URL of picture or picture send to service end, concrete, client can be treated the Word message of rate of exchange commodity by user's input, the URL of the picture on the network or the mode of uploading pictures, transmission treats that the information of rate of exchange commodity is to service end, carry out similarity retrieval, in addition, the mode of the URL of commodity picture that client also can be by automatic match user browsing webpage or the Word message of commodity, transmission treats that the information of rate of exchange commodity is to service end, carry out similarity retrieval, service end will be returned and the Price Range of importing the picture analogies commodity;
Step S522, described service end compares the Word message of commodity and the Word message of all example commodity, obtain the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value, if the quantity of the example commodity of coupling is less than second predetermined threshold value, execution in step S523 then, if the quantity of the example commodity of coupling is more than or equal to second predetermined threshold value, execution in step S524 then;
Step S523, Word message and the picture of the example commodity of all couplings are sent to client, concrete, here service end is preferentially carried out Word message such as key word and is mated, if return results appropriateness then show that key word coupling has satisfied user's demand fully exports directly that key word returns the commodity tabulation and Price Range gets final product;
Step S524, described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, concrete, if the user does not import key word, perhaps the key word matching result is too much, such as more than 100, this situation is at clothes, the footwear commodity are very general, up to ten thousand results are often arranged, then enter the image similarity retrieval, analysis treats that the picture of rate of exchange commodity obtains in the step of the described key parameter for the treatment of rate of exchange commodity, comprise: analyze and treat that the picture of rate of exchange commodity obtains the MD5 value of this picture, the key parameter of embedded information and original color matrix, analysis treats the picture of rate of exchange commodity and picture carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency, describedly picture is carried out normalized comprises the picture consolidation form, resolution reaches carries out level and the rectification of normalization longitudinally to picture;
Step S525, service end with the key parameter of the example commodity of all couplings with treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, concrete, step S525 comprises:
Step S5251, the final similarity of the example commodity of all couplings identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
Step S5252, the key parameter of embedded information, the original color matrix that the key parameter that the color matrices with embedded information, the original color matrix of the example commodity of all unlabelled couplings, after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter of the example commodity that obtain all unlabelled couplings respectively;
Step S5253 is weighted the final similarity that the example commodity of each unlabelled coupling are obtained in summation to the similarity of each key parameter;
Step S526, described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value, concrete, can in the example commodity of all couplings, further carry out the retrieval of picture analogies degree according to the picture for the treatment of rate of exchange commodity, return similarity greater than the set of certain threshold value, thereby significantly reduce retrieval time, described service end from high to low or from low to high sends to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value by commodity price with final similarity.
This method can adopt the mode of browser plug-in, namely the mode with plug-in unit is installed on the browser, this plug-in unit url list that prestored, during this url list rule of the web pages conform of browsing as the user, trigger rate of exchange process, client not only matches the title for the treatment of rate of exchange commodity, parameters such as price, also match the picture URL that treats that rate of exchange commodity are associated, and the mode that these parameters one are reinstated ajax sends to service end, the matching process for the treatment of rate of exchange commodity picture concerned URL is similar with the method for the treatment of rate of exchange coupling trade name, the detailed page of the commodity of normal shopping website, its web structure is all fixed, if certain website revision, the web structure may change, client need remove to analyze its webpage source code, find out the source code position of picture correspondence, with common technique means such as regular expression or css3 selector or jquery its URL is matched then, this technology common web developer can realize, in addition, also can adopt the mode of user's manual queries, client can provide the file upload function, the user can upload a picture for the treatment of rate of exchange commodity, also can specify a URL who treats rate of exchange commodity picture, client also has the text input frame simultaneously, the user can import the trade name for the treatment of the rate of exchange, the mode of customer end adopted post or get is sent to service end, the implementation of client is the generic web page form, which kind of scheme no matter, service end obtains one the most at last about treating the picture of rate of exchange commodity, and describe about Word message such as the key word for the treatment of rate of exchange commodity, service end will treat that the picture of rate of exchange commodity and picture and the Word message of Word message and example commodity compare then, return the result of price comparison at last to client.
When for example the user browses a certain concrete commodity page in the e-commerce website, can a rate of exchange bar appear in the browser bottom, show the price of these commodity on other shopping websites, and when the user browses the generic web page of non-e-commerce website, this plug-in unit can not have any demonstration in user interface, on technology realizes, described browser plug-in can adopt the source code of javacript elder generation analyzing web page, analyze the title of commodity that this page comprises, use the mode of ajax that this trade name is sent to rate of exchange server lookup then, server returns in database with the minimum several merchandise newss of money commodity price, this plug-in unit just shows the result by price then, significant color mark of minimum usefulness, whole process is robotization, the user need not import the title of commodity.
Embodiment three
Fig. 3 is the high-level schematic functional block diagram of the price comparison system of the embodiment of the invention three.
As shown in Figure 3, the present invention also provides a kind of price comparison system, comprise service end 1 and client 2, service end 1 is used for periodically storing in advance Word message and the picture of example commodity, the picture of analysis example commodity also obtains the key parameter of example commodity, analysis treats that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity, with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, and send to described client according to Word message and the picture that described final similarity is chosen the example commodity.
Client 2 is used for treating that the URL of rate of exchange commodity picture or picture sends to service end, and shows that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
Wherein, described service end 1 comprises: commercial examples library module 11, first analysis module 12, second analysis module 13, comparison module 14 and output module 15 as a result, and described client 2 comprises: sending module 21 and display module 22, wherein,
Commercial examples library module 11 is used for periodically storing in advance Word message and the picture of example commodity, described Word message comprises trade name and commodity price at least, concrete, described commercial examples library module 11 comprises: merchandise news acquiring unit 111 is used for selecting in advance some e-commerce websites, grasps the detailed webpage of example commodity from the electronics website; Word message module 112 is used for the detailed webpage of example commodity is resolved to obtain the Word message of example commodity and store; Picture module 113 is for the picture of the detailed webpage of example commodity being resolved to obtain the example commodity.
The picture that first analysis module 12 is used for the analysis example commodity obtains the key parameter of described example commodity, concrete, described first analysis module 12 comprises: the picture that the first parameter unit 121 is used for the analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture; The second parameter unit 122 is used for the picture of analysis example commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Second analysis module 13 is used for directly analyzing treating that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or be used for obtaining the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and treat that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, concrete, described second analysis module 13 comprises: the 3rd parameter unit 131 is used for analyzing treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix; The 4th parameter unit 132 is used for analyzing the picture for the treatment of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Comparison module 14 is used for the key parameter of all example commodity and treats that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, concrete, described comparison module 14 comprises: the final similarity that first comparing unit 141 is used for all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark; The key parameter of embedded information, the original color matrix that the key parameter that second comparing unit 142 is used for the embedded information of all unlabelled example commodity, original color matrix, the color matrices after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively; Final similarity unit 143 is used for the similarity of each key parameter is weighted the final similarity that each unlabelled example commodity is obtained in summation.
Output module 15 is used for choosing the Word message of example commodity and the display module 22 that picture sends to described client according to described final similarity as a result, concrete, described output module as a result 15 is used for display module 22 that final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value, or be used for the Word message of the example commodity of final similarity maximum and the display module 22 that picture sends to described client, described output module as a result 15 also can be used for final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value from high to low or from low to high by commodity price, thereby has realized obtaining accurate price comparison result according to the commodity picture.
Sending module 21 is used for treating that the URL of rate of exchange commodity picture or picture sends to second analysis module.
Display module 22 is used for showing that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
Embodiment four
Fig. 4 is the high-level schematic functional block diagram of the price comparison system of the embodiment of the invention four.
As shown in Figure 4, the present invention also provides another kind of price comparison system, this enforcement is to have increased matching module 16 with the difference of embodiment three, thereby be implemented in carry out price comparison according to the commodity picture before, Word message such as commodity keyword according to commodity carries out price comparison earlier, in the result that the price comparison of the Word message of commodity obtains, further carry out price comparison according to the commodity picture, to obtain more accurate price comparison result, the system of present embodiment comprises: service end 1 and client 2, wherein, described service end 1 comprises: commercial examples library module 11, first analysis module 12, second analysis module 13, comparison module 14, output module 15 and matching module 16 as a result, described client 2 comprises: sending module 21 and display module 22, wherein
Commercial examples library module 11 is used for periodically storing in advance Word message and the picture of example commodity, described Word message comprises trade name and commodity price at least, concrete, described commercial examples library module 11 comprises: merchandise news acquiring unit 111 is used for selecting in advance some e-commerce websites; Grasp the detailed webpage of example commodity from the electronics website; Word message module 112 is used for the detailed webpage of example commodity is resolved to obtain the Word message of example commodity and store; Picture module 113 is for the picture of the detailed webpage of example commodity being resolved to obtain the example commodity.
The picture that first analysis module 12 is used for the analysis example commodity obtains the key parameter of described example commodity, concrete, described first analysis module 12 comprises: the picture that the first parameter unit 121 is used for the analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture; The second parameter unit 122 is used for the picture of analysis example commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
Second analysis module 13 is used for directly analyzing treating that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or be used for obtaining the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and treat that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, concrete, described second analysis module 13 comprises: the 3rd parameter unit 131 is used for analyzing treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix; The 4th parameter unit 132 is used for analyzing the picture for the treatment of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
When comparison module 14 is used for quantity when the example commodity of coupling more than or equal to second predetermined threshold value with the key parameter of the example commodity of all couplings and treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, concrete, described comparison module 14 comprises: the final similarity that first comparing unit 141 is used for the example commodity of all couplings identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark, here at first in the commercial examples storehouse, there is the identical picture for the treatment of rate of exchange commodity to judging whether, here can judge with the MD5 value, if have in the commercial examples storehouse and treat the identical MD5 value of rate of exchange picture, then matching result can join as a result output module 15 products for further and handles; The key parameter of embedded information, the original color matrix that the key parameter that second comparing unit 142 is used for the embedded information of the example commodity of all unlabelled couplings, original color matrix, the color matrices after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter of the example commodity that obtain all unlabelled couplings respectively; Final similarity unit 143 is used for the similarity of each key parameter is weighted the final similarity that the example commodity of each unlabelled coupling are obtained in summation.
Word message and picture with the example commodity of all couplings when output module 15 is used for quantity when the example commodity that mate less than second predetermined threshold value as a result send to client, or final similarity is sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value when also being used for quantity when the example commodity that mate more than or equal to second predetermined threshold value, thereby significantly reduce retrieval time, concrete, described output module as a result 15 is used for final similarity is sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value from high to low or from low to high by commodity price.
Matching module 16 is used for the Word message of commodity and the Word message of all example commodity are compared, and obtains the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value.
Sending module 21 is used for treating that the URL of rate of exchange commodity picture or picture sends to described second analysis module, also is used for treating that the Word message of rate of exchange commodity sends to matching module.
Display module 22 is used for showing that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
The present invention periodically stores Word message and the picture of example commodity in advance by service end, and the picture of analysis example commodity obtains the key parameter of described example commodity; When carrying out price comparison, described client will treat that earlier the URL of rate of exchange commodity picture or picture sends to service end, described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity then, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, in addition service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, last described service end sends to described client with final similarity greater than Word message and the picture of all example commodity of first predetermined threshold value, can obtain accurate price comparison result according to the commodity picture.
In addition, the present invention periodically stores Word message and the picture of example commodity in advance by service end, and the picture of analysis example commodity obtains the key parameter of described example commodity; When carrying out price comparison, described client will treat that earlier the Word message of rate of exchange commodity and the URL of picture or picture send to service end, then the Word message of described service end with the Word message of commodity and all example commodity compared, obtain the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value, if the quantity of example commodity of coupling is less than second predetermined threshold value, then Word message and the picture with the example commodity of all couplings sends to client; If the quantity of the example commodity of coupling is more than or equal to second predetermined threshold value, then described service end is directly analyzed and is treated that the picture of rate of exchange commodity obtains the key parameter of described example commodity, or described service end is obtained the picture post analysis for the treatment of rate of exchange commodity according to the described URL that treats the picture of rate of exchange commodity and is treated that the picture of rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, service end with the key parameter of the example commodity of all couplings with treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value, realized carrying out according to the Word message of commodity the result's of price comparison acquisition basis, further the picture according to commodity carries out price comparison in this result, thereby obtains more accurate price comparison result.Each embodiment adopts the mode of going forward one by one to describe in this instructions, and what each embodiment stressed is and the difference of other embodiment that identical similar part is mutually referring to getting final product between each embodiment.For the disclosed system of embodiment, because corresponding with the embodiment disclosed method, so description is fairly simple, relevant part partly illustrates referring to method and gets final product.
The professional can also further recognize, unit and the algorithm steps of each example of describing in conjunction with embodiment disclosed herein, can realize with electronic hardware, computer software or the combination of the two, for the interchangeability of hardware and software clearly is described, composition and the step of each example described in general manner according to function in the above description.These functions still are that software mode is carried out with hardware actually, depend on application-specific and the design constraint of technical scheme.The professional and technical personnel can specifically should be used for using distinct methods to realize described function to each, but this realization should not thought and exceeds scope of the present invention.
Obviously, those skilled in the art can carry out various changes and modification to invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these revise and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these change and modification.

Claims (33)

1. a price comparison method is characterized in that, comprising:
Service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity;
When carrying out price comparison, comprising:
Client will treat that the URL of rate of exchange commodity picture or picture sends to service end;
The picture that rate of exchange commodity are treated in described service end analysis to be obtaining the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity, obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity;
Service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity;
Word message and picture that service end is chosen the example commodity according to described final similarity send to described client.
2. price comparison method as claimed in claim 1, it is characterized in that, described service end is chosen after the Word message of example commodity and the step that picture sends to described client according to described final similarity, also comprises: described client's section will obtain the Word message of example commodity and picture and be shared with other clients or be distributed on the network.
3. price comparison method as claimed in claim 1, it is characterized in that, described service end is chosen in the Word message of example commodity and the step that picture sends to described client according to described final similarity, and described service end sends to described client with final similarity greater than Word message and the picture of all example commodity of first predetermined threshold value.
4. price comparison method as claimed in claim 1, it is characterized in that, described service end is chosen in the Word message of example commodity and the step that picture sends to described client according to described final similarity, and described service end sends to described client with Word message and the picture of the example commodity of final similarity maximum.
5. as each described price comparison method of claim 1 to 4, it is characterized in that described Word message comprises trade name and commodity price at least.
6. price comparison method as claimed in claim 5 is characterized in that, described Word message also comprises descriptive labelling.
7. price comparison method as claimed in claim 5, it is characterized in that, in the step that described service end sends to described client greater than Word message and the picture of all example commodity of first predetermined threshold value with final similarity, described service end from high to low or from low to high sends to described client greater than Word message and the picture of all example commodity of first predetermined threshold value by commodity price with final similarity.
8. price comparison method as claimed in claim 7 is characterized in that, described periodicity is stored the step of Word message and the picture of example commodity in advance, comprising:
Select some e-commerce websites in advance;
Grasp the detailed webpage of example commodity from the electronics website and resolve;
Obtain Word message and the picture of example commodity and be stored in the commercial examples storehouse.
9. price comparison method as claimed in claim 8 is characterized in that, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, comprising:
The picture of analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The picture of analysis example commodity also carries out normalized to picture and obtains color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
10. price comparison method as claimed in claim 9 is characterized in that, describedly picture is carried out normalized comprises with picture consolidation form, resolution and to picture and carries out level and normalization is longitudinally corrected.
11. price comparison method as claimed in claim 10 is characterized in that, analyzes in the step that the picture treat rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, comprising:
Analysis treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
Analysis is treated the picture of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
12. price comparison method as claimed in claim 11 is characterized in that, describedly picture is carried out normalized comprises with picture consolidation form, resolution and to picture and carries out level and normalization is longitudinally corrected.
13. price comparison method as claimed in claim 12 is characterized in that, described service end with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares in the step of the final similarity of obtaining each example commodity, comprising:
The final similarity of all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
The key parameter of embedded information, the original color matrix that the key parameter that the color matrices with the embedded information of all unlabelled example commodity, original color matrix, after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively;
Similarity to each key parameter is weighted the final similarity that each unlabelled example commodity is obtained in summation.
14. a price comparison method is characterized in that, comprising:
Service end is periodically stored Word message and the picture of example commodity in advance, and the picture of analysis example commodity obtains the key parameter of described example commodity;
When carrying out price comparison, comprising:
Client will treat that the Word message of rate of exchange commodity and the URL of picture or picture send to service end;
Described service end compares the Word message of commodity and the Word message of all example commodity, obtains the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings greater than second predetermined threshold value,
If the quantity of example commodity of coupling is less than second predetermined threshold value, then Word message and the picture with the example commodity of all couplings sends to client;
If the quantity of the example commodity of coupling is more than or equal to second predetermined threshold value, then described service end analysis treats that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity, service end with the key parameter of the example commodity of all couplings with treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling, described service end sends to described client with final similarity greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value.
15. price comparison method as claimed in claim 14 is characterized in that described Word message comprises trade name and commodity price at least.
16. price comparison method as claimed in claim 15, it is characterized in that, in the step that described service end sends to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value with final similarity, described service end from high to low or from low to high sends to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value by commodity price with final similarity.
17. price comparison method as claimed in claim 16 is characterized in that, described periodicity is stored the step of Word message and the picture of example commodity in advance, comprising:
Select some e-commerce websites in advance;
Grasp the detailed webpage of example commodity from the electronics website and resolve;
Obtain Word message and the picture of example commodity and be stored in the commercial examples storehouse.
18. price comparison method as claimed in claim 17 is characterized in that, the picture of described analysis example commodity obtains in the step of key parameter of described example commodity, comprising:
The picture of analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The picture of analysis example commodity also carries out normalized to picture and obtains color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
19. price comparison method as claimed in claim 18 is characterized in that, describedly picture is carried out normalized comprises with picture consolidation form, resolution and to picture and carries out level and normalization is longitudinally corrected.
20. price comparison method as claimed in claim 19 is characterized in that, analyzes in the step that the picture treat rate of exchange commodity obtains the described key parameter for the treatment of rate of exchange commodity, comprising:
Analysis treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
Analysis is treated the picture of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
21. price comparison method as claimed in claim 20, it is characterized in that, described service end compares the key parameter of the example commodity of all couplings and the key parameter for the treatment of rate of exchange commodity in the step of final similarity of the example commodity that obtain each coupling, comprising:
The final similarity of the example commodity of all couplings identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
The key parameter of embedded information, the original color matrix that the key parameter that the color matrices with embedded information, the original color matrix of the example commodity of all unlabelled couplings, after handling or gray matrix and picture transparency distribute is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter of the example commodity that obtain all unlabelled couplings respectively;
Similarity to each key parameter is weighted the final similarity that the example commodity of each unlabelled coupling are obtained in summation.
22. a price comparison system is characterized in that, comprising:
Service end, be used for periodically storing in advance Word message and the picture of example commodity, the picture of analysis example commodity also obtains the key parameter of example commodity, analysis treats that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or according to the described URL that treats the picture of rate of exchange commodity obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity, with the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity, and send to described client according to Word message and the picture that described final similarity is chosen the example commodity;
Client is used for treating that the URL of rate of exchange commodity picture or picture sends to service end, and shows that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
23. price comparison system as claimed in claim 22 is characterized in that,
Described service end comprises:
The commercial examples library module is used for Word message and picture that periodicity is stored the example commodity in advance;
First analysis module is used for the picture of analysis example commodity and obtains the key parameter of example commodity;
Second analysis module, be used for analyzing and treat that the picture of rate of exchange commodity is to obtain the key parameter of described example commodity, or be used for according to the described URL that treats the picture of rate of exchange commodity, obtain and analyze treat rate of exchange commodity picture to obtain the described key parameter for the treatment of rate of exchange commodity;
Comparison module, be used for the key parameter of all example commodity with treat that the key parameter of rate of exchange commodity compares the final similarity of obtaining each example commodity;
Output module is used for choosing the Word message of example commodity and the display module that picture sends to described client according to described final similarity as a result;
Described client comprises:
Sending module is used for treating that the URL of rate of exchange commodity picture or picture sends to second analysis module;
Display module is used for showing that final similarity is greater than Word message and the picture of all example commodity of first predetermined threshold value.
24. price comparison system as claimed in claim 23, it is characterized in that, described output module as a result is used for display module that final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value, or is used for the Word message of the example commodity of final similarity maximum and the display module that picture sends to described client.
25. price comparison system as claimed in claim 24 is characterized in that, described Word message comprises trade name and commodity price at least.
26. price comparison system as claimed in claim 25, it is characterized in that, described output module as a result is used for final similarity is sent to described client greater than Word message and the picture of all example commodity of first predetermined threshold value from high to low or from low to high by commodity price.
27. price comparison system as claimed in claim 26 is characterized in that, described commercial examples library module comprises:
The merchandise news acquiring unit is used for selecting in advance some e-commerce websites, grasps the detailed webpage of example commodity from the electronics website;
The Word message module is used for Word message and the storage of the detailed webpage of example commodity being resolved to obtain the example commodity;
The picture module is for the picture of the detailed webpage of example commodity being resolved to obtain the example commodity.
28. price comparison system as claimed in claim 27 is characterized in that, described first analysis module comprises:
The first parameter unit, the picture that is used for the analysis example commodity obtains the key parameter of MD5 value, embedded information and the original color matrix of this picture;
The second parameter unit is used for the picture of analysis example commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
29. price comparison system as claimed in claim 28 is characterized in that, described second analysis module comprises:
The 3rd parameter unit is used for analyzing and treats that the picture of rate of exchange commodity obtains the key parameter of the MD5 value of this picture, embedded information and original color matrix;
The 4th parameter unit be used for to be analyzed the picture for the treatment of rate of exchange commodity and picture is carried out normalized obtain color matrices after this picture is handled or the key parameter of gray matrix and the distributed intelligence of picture transparency.
30. price comparison system as claimed in claim 29 is characterized in that, described comparison module comprises:
First comparing unit, the final similarity that is used for all the example commodity identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
Second comparing unit, the key parameter of embedded information, the original color matrix that the key parameter that be used for embedded information, the original color matrix of all unlabelled example commodity, the color matrices after handling or gray matrix and picture transparency distributes is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter that obtains all unlabelled example commodity respectively;
Final similarity unit is used for the similarity of each key parameter is weighted the final similarity that each unlabelled example commodity is obtained in summation.
31. as each described price comparison system of claim 22 to 30, it is characterized in that, described service end also comprises a matching module, be used for the Word message of commodity and the Word message of all example commodity are compared, obtain the example commodity of all couplings, and whether the quantity of example commodity of judging all couplings is greater than second predetermined threshold value;
Described output module as a result, Word message and picture with the example commodity of all couplings when also being used for quantity when the example commodity of coupling less than second predetermined threshold value send to client, or final similarity are sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value when also being used for quantity when the example commodity that mate more than or equal to second predetermined threshold value;
Described comparison module, when also being used for quantity when the example commodity of coupling more than or equal to second predetermined threshold value with the key parameter of the example commodity of all couplings and treat that the key parameter of rate of exchange commodity compares the final similarity of the example commodity that obtain each coupling
Described sending module also is used for treating that the Word message of rate of exchange commodity sends to matching module.
32. price comparison system as claimed in claim 31, it is characterized in that, described output module as a result is used for final similarity is sent to described client greater than Word message and the picture of the example commodity of all couplings of first predetermined threshold value from high to low or from low to high by commodity price.
33. price comparison system as claimed in claim 32 is characterized in that, described first comparing unit, and the final similarity that also is used for the example commodity of all couplings identical with the MD5 value for the treatment of rate of exchange commodity is set to complete matching value and these example commodity of mark;
Described second comparing unit, the key parameter of embedded information, the original color matrix that the key parameter that also be used for embedded information, the original color matrix of the example commodity of all unlabelled couplings, the color matrices after handling or gray matrix and picture transparency distributes is corresponding with treating rate of exchange commodity, the color matrices after handling or gray matrix and the distribution of picture transparency compares the similarity of each key parameter of the example commodity that obtain all unlabelled couplings respectively;
Described final similarity unit also is used for the similarity of each key parameter is weighted the final similarity that the example commodity of each unlabelled coupling are obtained in summation.
CN2012100375728A 2012-02-17 2012-02-17 Price comparative method and system Pending CN103258280A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012100375728A CN103258280A (en) 2012-02-17 2012-02-17 Price comparative method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012100375728A CN103258280A (en) 2012-02-17 2012-02-17 Price comparative method and system

Publications (1)

Publication Number Publication Date
CN103258280A true CN103258280A (en) 2013-08-21

Family

ID=48962181

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012100375728A Pending CN103258280A (en) 2012-02-17 2012-02-17 Price comparative method and system

Country Status (1)

Country Link
CN (1) CN103258280A (en)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514559A (en) * 2013-09-26 2014-01-15 Opera软件股份公司 On-line shopping price comparison method and device based on mobile terminal browser
CN103927348A (en) * 2014-04-02 2014-07-16 华为技术有限公司 Picture processing method, information acquiring method and device
CN105354770A (en) * 2015-11-16 2016-02-24 南京途牛科技有限公司 Real-time price comparison method for route type tourism product
CN105468730A (en) * 2015-11-20 2016-04-06 广州华多网络科技有限公司 Webpage information extraction method and equipment
CN105843972A (en) * 2016-06-13 2016-08-10 北京京东尚科信息技术有限公司 Method and device for comparing product attribute information
CN105912642A (en) * 2016-04-08 2016-08-31 世纪禾光科技发展(北京)有限公司 Product price data acquisition method and system
CN106097072A (en) * 2016-06-17 2016-11-09 北京京东尚科信息技术有限公司 The control methods of a kind of merchandise news, device and terminal unit
CN106296322A (en) * 2015-05-15 2017-01-04 昆达电脑科技(昆山)有限公司 Purchase method
CN106384264A (en) * 2016-09-22 2017-02-08 深圳市金立通信设备有限公司 Information query method and terminal
CN106408378A (en) * 2016-09-02 2017-02-15 广东聚联电子商务股份有限公司 Price comparison and shopping method applied to electronic commerce
CN107798562A (en) * 2017-10-25 2018-03-13 深圳市宝盒科技有限公司 A kind of self-service commodity preparation method
CN108074172A (en) * 2018-01-09 2018-05-25 北京值得买科技股份有限公司 Electric business merchandise news dissemination method and system
CN109859016A (en) * 2019-02-19 2019-06-07 江苏品德网络科技有限公司 A kind of internet rate of exchange software price comparing method
CN110400201A (en) * 2019-07-30 2019-11-01 中国工商银行股份有限公司 Information displaying method, device, electronic equipment and medium
CN110689407A (en) * 2019-09-29 2020-01-14 杭州洋驼网络科技有限公司 Price comparison method for selected products and computer readable storage medium
CN111513759A (en) * 2020-04-26 2020-08-11 珠海格力电器股份有限公司 Method, device, electronic equipment and computer readable medium for monitoring health state
CN111539765A (en) * 2020-04-20 2020-08-14 广州探途网络技术有限公司 Commodity price data processing method, device and equipment
CN112559788A (en) * 2019-09-10 2021-03-26 江苏易程科技孵化器有限公司 Textile raw material query management system
CN114004796A (en) * 2021-10-26 2022-02-01 未鲲(上海)科技服务有限公司 User evaluation result acquisition method and device, server and storage medium
CN117114803A (en) * 2023-08-17 2023-11-24 湖北光舜科技有限公司 Comparison method for acquiring commodity price information through AI identification

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101196994A (en) * 2007-12-26 2008-06-11 腾讯科技(深圳)有限公司 Image content recognizing method and recognition system
CN201638268U (en) * 2010-05-06 2010-11-17 杭州比比西网络科技有限公司 Air ticket price-relation system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101196994A (en) * 2007-12-26 2008-06-11 腾讯科技(深圳)有限公司 Image content recognizing method and recognition system
CN201638268U (en) * 2010-05-06 2010-11-17 杭州比比西网络科技有限公司 Air ticket price-relation system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KAKA: "用图片也能轻松搜宝贝", 《电脑知识与技术(经验技巧)》 *
TECHWEB.COM.CN: "淘宝图想正式上线 开启图像购物搜索之门", 《HTTP://WWW.TECHWEB.COM.CN/INTERNET/2011-07-12/1064616.SHTML》 *
王晓易: "淘淘搜:图片搜索及导购平台 已获阿里巴巴投资", 《网易科技报道HTTP://TECH.163.COM/10/1104/21/6KM76PR9000938EN.HTML#》 *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514559A (en) * 2013-09-26 2014-01-15 Opera软件股份公司 On-line shopping price comparison method and device based on mobile terminal browser
CN103927348B (en) * 2014-04-02 2018-09-07 华为技术有限公司 Image processing method, information acquisition method and device
CN103927348A (en) * 2014-04-02 2014-07-16 华为技术有限公司 Picture processing method, information acquiring method and device
CN106296322A (en) * 2015-05-15 2017-01-04 昆达电脑科技(昆山)有限公司 Purchase method
CN105354770A (en) * 2015-11-16 2016-02-24 南京途牛科技有限公司 Real-time price comparison method for route type tourism product
CN105468730A (en) * 2015-11-20 2016-04-06 广州华多网络科技有限公司 Webpage information extraction method and equipment
CN105912642A (en) * 2016-04-08 2016-08-31 世纪禾光科技发展(北京)有限公司 Product price data acquisition method and system
CN105843972A (en) * 2016-06-13 2016-08-10 北京京东尚科信息技术有限公司 Method and device for comparing product attribute information
CN106097072A (en) * 2016-06-17 2016-11-09 北京京东尚科信息技术有限公司 The control methods of a kind of merchandise news, device and terminal unit
CN106097072B (en) * 2016-06-17 2020-06-30 北京京东尚科信息技术有限公司 Comparison method and device of commodity information and terminal equipment
CN106408378A (en) * 2016-09-02 2017-02-15 广东聚联电子商务股份有限公司 Price comparison and shopping method applied to electronic commerce
CN106384264A (en) * 2016-09-22 2017-02-08 深圳市金立通信设备有限公司 Information query method and terminal
CN107798562A (en) * 2017-10-25 2018-03-13 深圳市宝盒科技有限公司 A kind of self-service commodity preparation method
CN108074172A (en) * 2018-01-09 2018-05-25 北京值得买科技股份有限公司 Electric business merchandise news dissemination method and system
CN109859016A (en) * 2019-02-19 2019-06-07 江苏品德网络科技有限公司 A kind of internet rate of exchange software price comparing method
CN110400201A (en) * 2019-07-30 2019-11-01 中国工商银行股份有限公司 Information displaying method, device, electronic equipment and medium
CN112559788A (en) * 2019-09-10 2021-03-26 江苏易程科技孵化器有限公司 Textile raw material query management system
CN110689407A (en) * 2019-09-29 2020-01-14 杭州洋驼网络科技有限公司 Price comparison method for selected products and computer readable storage medium
CN111539765A (en) * 2020-04-20 2020-08-14 广州探途网络技术有限公司 Commodity price data processing method, device and equipment
CN111513759A (en) * 2020-04-26 2020-08-11 珠海格力电器股份有限公司 Method, device, electronic equipment and computer readable medium for monitoring health state
CN114004796A (en) * 2021-10-26 2022-02-01 未鲲(上海)科技服务有限公司 User evaluation result acquisition method and device, server and storage medium
CN117114803A (en) * 2023-08-17 2023-11-24 湖北光舜科技有限公司 Comparison method for acquiring commodity price information through AI identification

Similar Documents

Publication Publication Date Title
CN103258280A (en) Price comparative method and system
CN106600343B (en) Video content associated online video advertisement management method and system
CN109903117B (en) Knowledge graph processing method and device for commodity recommendation
CN107220365B (en) Accurate recommendation system and method based on collaborative filtering and association rule parallel processing
US8190556B2 (en) Intellegent data search engine
US11550856B2 (en) Artificial intelligence for product data extraction
CN105022827B (en) A kind of Web news dynamic aggregation method of domain-oriented theme
JP7544791B2 (en) Systems and methods for collecting data relating to fraudulent content in a networked environment - Patents.com
CN104794242B (en) Searching method
CN110827112B (en) Deep learning commodity recommendation method and device, computer equipment and storage medium
CN107193932B (en) Information pushing method and device
CN102375885A (en) Method and device for providing search suggestions corresponding to query sequence
CN103078854B (en) Message filtering method and device
CN103699549B (en) The renewal of a kind of graphic code storehouse, querying method and relevant apparatus
CN105989125B (en) The searching method and system of tag recognition are carried out to no result word
CN103678628B (en) Information-pushing method and system
CN102314494A (en) Method and equipment for processing webpage contents
CN108446333B (en) Big data text mining processing system and method thereof
CN109615437A (en) Sale obtains objective method for tracking and managing
CN103970800A (en) Method and system for extracting and processing webpage related keywords
CN112307352A (en) Content recommendation method, system, device and storage medium
US20200026741A1 (en) Structured search via key-objects
US20230401617A1 (en) Inserting code into a document object model of a graphical user interface (gui) for unified presentation of data
CN113821718A (en) Article information pushing method and device
KR102639788B1 (en) Apparatus for managing health functional food based on artificial intelligence and method thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20130821

RJ01 Rejection of invention patent application after publication