CN112036981B - Method, device, equipment and medium for providing target comparison commodities - Google Patents
Method, device, equipment and medium for providing target comparison commodities Download PDFInfo
- Publication number
- CN112036981B CN112036981B CN202010910136.1A CN202010910136A CN112036981B CN 112036981 B CN112036981 B CN 112036981B CN 202010910136 A CN202010910136 A CN 202010910136A CN 112036981 B CN112036981 B CN 112036981B
- Authority
- CN
- China
- Prior art keywords
- commodity
- comparison
- attribute
- commodities
- compared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for providing a target comparison commodity. The method for providing the target comparison commodity comprises the following steps: constructing query conditions according to at least one item of basic commodity information of commodities to be compared, and acquiring query results corresponding to the query conditions and fed back by a plurality of commodity platforms; calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to at least one item of attribute information of the to-be-compared commodity and at least one item of attribute information of the candidate comparison commodity; screening out target comparison commodities from one or more candidate comparison commodities according to the reference similarity; the target comparison commodities are provided for corresponding users, the problem of low commodity comparison efficiency caused by frequent switching of the users on different commodity platforms is solved, the target comparison commodities are screened by calculating the similarity between the candidate comparison commodities and the commodities to be compared, the sequential display of the target comparison commodities is realized, and the commodity comparison efficiency is improved.
Description
Technical Field
The embodiment of the invention relates to the internet technology, in particular to a method, a device, equipment and a medium for providing target comparison commodities.
Background
With the rapid development of the e-commerce industry, a plurality of e-commerce platforms appear, and users can shop online through the e-commerce platforms and complete shopping without going out. However, online shopping has the disadvantages of inconsistent prices and large price fluctuation of the same-quality commodities in different e-commerce platforms, and users need to compare prices and commodity information of similar commodities in different e-commerce platforms when wanting to buy the commodities with the best quality with the least money.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a medium for providing target comparison commodities.
In a first aspect, an embodiment of the present invention provides a method for providing a target comparison product, where the method includes:
constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results corresponding to the query condition and fed back by a plurality of commodity platforms, wherein the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
screening out target comparison commodities from the one or more candidate comparison commodities according to the reference similarity;
and providing the target comparison commodity for a corresponding user.
In a second aspect, an embodiment of the present invention further provides an apparatus for providing a target comparison product, where the apparatus includes:
the system comprises a query result acquisition module, a comparison module and a comparison module, wherein the query result acquisition module is used for constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results which are fed back by a plurality of commodity platforms and correspond to the query condition, the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
the reference similarity calculation module is used for calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
the target comparison commodity screening module is used for screening a target comparison commodity from the one or more candidate comparison commodities according to the reference similarity;
and the target comparison commodity providing module is used for providing the target comparison commodity for a corresponding user.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for providing a target comparison commodity as provided by any of the embodiments of the present invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for providing a target comparison product provided in any embodiment of the present invention.
The technical scheme of the embodiment of the invention comprises the steps of firstly constructing a query condition according to at least one item of commodity basic information of commodities to be compared, obtaining query results corresponding to the query condition and fed back by a plurality of commodity platforms, then calculating the reference similarity between candidate comparison commodities and the commodities to be compared according to at least one item of attribute information of the commodities to be compared and at least one item of attribute information of the candidate comparison commodities, screening target comparison commodities from one or more candidate comparison commodities according to the reference similarity, finally providing the target comparison commodities to corresponding users, solving the problem of low commodity comparison efficiency caused by frequent switching of the users on different commodity platforms, screening the target comparison commodities by calculating the similarity between the candidate comparison commodities and the commodities to be compared, realizing sequential display of the target comparison commodities fed back by different commodity platforms, the commodity comparison efficiency is improved.
Drawings
FIG. 1 is a flow chart of a method for providing a targeted comparison commodity in accordance with one embodiment of the present invention;
FIG. 2 is a flow chart of a method for providing a targeted comparison commodity in accordance with a second embodiment of the present invention;
FIG. 3 is a flow chart of a method for providing a targeted comparison commodity in a third embodiment of the present invention;
FIG. 4 is a schematic diagram of an apparatus for providing a target comparison product according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for providing a target comparison product in a first embodiment of the present invention, where the technical solution of this embodiment is suitable for comparing and sequentially displaying homogeneous products of multiple product platforms, and the method may be executed by a device for providing a target comparison product, where the device may be implemented by software and/or hardware, and may be integrated in various general-purpose computer devices, and specifically includes the following steps:
step 110, constructing a query condition according to at least one item of basic commodity information of the commodities to be compared, and acquiring query results corresponding to the query condition and fed back by the plurality of commodity platforms, wherein the query results include one or more candidate comparison commodities, and the basic commodity information includes at least one item of attribute information of the commodities to be compared.
And the candidate comparison commodities are commodities which are the same as or similar to the commodities to be compared and are obtained by querying other commodity platforms according to the commodity basic information of the commodities to be compared of the current commodity platform. The commodity basic information is information capable of representing commodity basic characteristics of the current commodity to be compared, and comprises at least any one of the following items: at least one item of attribute information of the to-be-compared commodities, pictures of the to-be-compared commodities, and videos of the to-be-compared commodities, wherein in a specific embodiment, the attribute information may be, for example, materials, sizes, applicable scenes, applicable objects, manufacturing processes, and the like of the to-be-compared commodities.
In this embodiment, in order to conveniently and quickly compare a to-be-compared commodity in a current commodity platform with a homogeneous commodity in other commodity platforms, at least one item of commodity basic information of the to-be-compared commodity is first obtained, for example, at least one item of attribute information of the to-be-compared commodity, a to-be-compared commodity picture or a to-be-compared commodity video, then a query condition is constructed according to the commodity picture or the commodity attribute, and a user is simulated to perform commodity search operations on a plurality of commodity platforms, so that at least one item of target comparison commodity corresponding to the query condition and fed back by each commodity platform is obtained. For example, the casual shoes in the e-commerce platform a include 3 attribute items of "applicable scene", "material", and "applicable object", the attribute values corresponding to the attribute items are "casual", "cowhide", and "middle age", respectively, and then the goods including similar attributes and attribute values in the e-commerce platform B are the homogeneous goods.
For example, a user browses a pair of casual shoes in a current goods platform a and needs to compare the goods with homogeneous goods in other goods platforms, first determining basic goods information of the currently browsed casual shoes, for example, at least one item of attribute information of the casual shoes and a picture or a video of the current casual shoes, where the at least one item of attribute information includes that an applicable scene is casual, a material is cowhide, and an applicable object is middle year, and then searching in goods platforms B and C using at least one item of attribute value (e.g., "casual, cowhide") of the casual shoes or the picture of the casual shoes as a query condition to obtain at least one goods that are identical or similar to the casual shoes to be compared currently and are fed back by the goods platforms B and C and meet the query condition. The query condition may be a picture, a video, a material, or an applicable group of the commodity to be compared.
And step 120, calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity.
In this embodiment, in order to display the candidate comparison commodities in a targeted manner, so that the user can see the commodities with higher similarity to the commodities to be compared within a limited time, at least one item of attribute information of the commodities to be compared is determined, including the attribute items of the commodities to be compared and the attribute values corresponding to the attribute items, then the attribute values corresponding to the same attribute items of the candidate comparison commodities are obtained, further, the similarity of the attribute values corresponding to the attribute items is calculated, and the reference similarity between each candidate comparison commodity and the commodities to be compared is calculated according to the similarity of the attribute values corresponding to the attribute items.
Illustratively, at least one item of attribute information of the commodity to be compared in the current commodity platform A, for example, a plurality of items of attribute information of a water cup, is obtained, the material is stainless steel, the applicable scene is outdoor leisure, the style is Chinese, in order to calculate the similarity between the candidate comparison commodity and the commodity to be compared, the attribute value corresponding to the attribute item matching the attribute item in the candidate comparison commodity may be obtained first, for example, the candidate comparison commodity is made of steel, the applicable scene is leisure, the style is European, then calculating the similarity of the attribute values corresponding to the attribute items of the two, for example, respectively calculating the similarity of stainless steel and steel, the similarity of outdoor leisure and outdoor, and the similarity of the Chinese style and the European style, and finally, carrying out weighted summation on the similarity corresponding to each attribute item to obtain the reference similarity between the candidate comparison commodity and the commodity to be compared. The weight of each attribute item may be preset according to the emphasis of the user, for example, for a commodity such as a cup, the user emphasizes the material, and then the weight corresponding to the material is increased.
Optionally, calculating a reference similarity between the candidate comparison commodity and the to-be-compared commodity according to at least one item of attribute information of the to-be-compared commodity and at least one item of attribute information of the post-selection comparison commodity, including:
establishing at least one comparison attribute pair according to the attribute information respectively corresponding to the candidate comparison commodity and the commodity to be compared, wherein the comparison attribute pair comprises at least one attribute value corresponding to the same attribute item;
calculating attribute matching degrees corresponding to the comparison attribute pairs according to a comparison algorithm matched with the attribute items;
and calculating the reference similarity between the candidate comparison commodity and the commodity to be compared according to the attribute weight value of each attribute item and each attribute matching degree.
In this optional embodiment, a specific manner of calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to at least one item of attribute information of the to-be-compared commodity and at least one item of attribute information of the candidate comparison commodity is provided, and first, at least one comparison attribute pair is established according to attribute information respectively corresponding to the candidate comparison commodity and the to-be-compared commodity, where one comparison attribute pair includes at least one attribute value corresponding to the same attribute item, then, according to a preset comparison algorithm corresponding to the attribute item, the attribute matching degree of each comparison attribute pair is calculated, and finally, the reference similarity between the candidate comparison commodity and the to-be-compared commodity is calculated according to the attribute weight value of each attribute item and the attribute matching degree corresponding to each attribute item.
For example, in order to compare, at least one item of attribute information corresponding to the to-be-compared commodity is obtained, for example, the attribute information of the to-be-compared commodity includes that an applicable scene is 'outdoor leisure', a material is 'head layer leather', and a style is 'english'; the attribute information of the candidate comparison commodity comprises that the applicable scene is 'outdoor', the material is 'cortex', and the style is 'Korean', then the comparison attribute pair is formed by the attribute values corresponding to the same attribute item, for example, the two comparison commodities can form 3 comparison attribute pairs, respectively being 'outdoor leisure' and 'outdoor', 'first layer cowhide' and 'cortex', 'English' and 'Korean', after the comparison attribute pair is determined, the attribute matching degree corresponding to each comparison attribute pair is calculated according to the comparison algorithm matched with the attribute item, for example, the attribute matching degree of the two can be calculated according to the number of the same character, finally, the reference similarity between the candidate comparison commodity currently compared and the commodity to be compared is calculated according to the attribute weight value and each attribute matching degree of each attribute, for example, the attribute matching degrees are weighted and summed, wherein, the weight of the material is 50%, the weight of the applicable scene is 30%, and the weight of the style is 20%.
Optionally, the alignment algorithm includes at least one of the following:
when the attribute values contained in the comparison attribute pair are completely the same, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree;
determining the number of the same words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the same words;
determining the number of continuous identical words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the continuous identical words;
and when the attribute value corresponding to the commodity to be compared in the comparison attribute pair is contained in the attribute value corresponding to the candidate comparison commodity, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree.
In this optional embodiment, 4 ways of calculating the attribute matching degree are provided, and the attribute matching degree calculation way corresponding to each attribute item may be selected according to the actual situation. The first type is complete matching, specifically, when two attribute values in the comparison attribute pair are completely the same, it is determined that the attribute matching degree of the current comparison attribute pair is a first matching degree, otherwise, it is a second matching degree, for example, the material attribute may be set to a matching mode of complete matching, where the first matching degree may be set to 1, and the second matching degree is set to 0; the second type is identical character weight matching, specifically, the number of identical characters of an attribute value included in a comparison attribute pair is detected first, and the attribute matching degree of the current comparison attribute pair is calculated according to the number of identical characters, for example, the color attribute of a to-be-compared commodity is "pink", the color attribute of a candidate comparison commodity is "pink", where 2 characters are identical, and the attribute matching degree may be 2/3 ═ 67%; the third is continuous character similarity matching, specifically, the number of continuous same characters in the attribute values included in the comparison attribute pair is detected first, and then the attribute matching degree of the current comparison attribute is calculated according to the number of continuous same characters, for example, if the applicable scene attribute of the to-be-compared commodity is "outdoor leisure sports", and the applicable scene attribute of the candidate comparison commodity is "outdoor leisure", where 4 continuous characters are the same, the attribute matching degree may be 4/6 ═ 67%; and the fourth step is inclusion matching, specifically, when the attribute value corresponding to the to-be-compared commodity is included in the attribute value corresponding to the candidate comparison commodity, determining that the attribute matching degree of the current comparison attribute pair is the first matching degree, otherwise, determining that the attribute matching degree is the second matching degree.
And step 130, screening out target comparison commodities from the one or more candidate comparison commodities according to the reference similarity.
In this embodiment, after the reference similarity between the to-be-compared commodity and the candidate comparison commodity is obtained through calculation, in order to enable a user to see the candidate comparison commodity with a higher similarity to the to-be-compared commodity within a limited time and save the time for browsing homogeneous commodities, a target comparison commodity can be screened from one or more candidate comparison commodities according to the reference similarity between each candidate comparison commodity and the to-be-compared commodity, specifically, the candidate comparison commodities can be sorted from high to low according to the reference similarity, and finally, the top 60% of the candidate comparison commodities are used as the target comparison commodities; and the candidate comparison commodity with the reference similarity higher than the reference similarity threshold value can be used as the target comparison commodity.
Illustratively, the reference similarity threshold is set to be 65%, and finally, according to the reference similarity between each candidate comparison commodity and the commodity to be compared, the candidate comparison commodity with the reference similarity higher than 65% is taken as the target comparison commodity.
And step 140, providing the target comparison commodity for a corresponding user.
In this embodiment, the target comparison commodity is provided to the corresponding user after the target comparison commodity is screened from the candidate comparison commodities according to the reference similarity, specifically, the target comparison commodity can be displayed to the user in a list form, and each list item enters a detail page of the corresponding target comparison commodity after being clicked by the user.
The technical scheme of the embodiment of the invention comprises the steps of firstly constructing a query condition according to at least one item of commodity basic information of commodities to be compared, obtaining query results corresponding to the query condition and fed back by a plurality of commodity platforms, then calculating the reference similarity between candidate comparison commodities and the commodities to be compared according to at least one item of attribute information of the commodities to be compared and at least one item of attribute information of the candidate comparison commodities, screening target comparison commodities from one or more candidate comparison commodities according to the reference similarity, finally providing the target comparison commodities to corresponding users, solving the problem of low commodity comparison efficiency caused by frequent switching of the users on different commodity platforms, screening the target comparison commodities by calculating the similarity between the candidate comparison commodities and the commodities to be compared, realizing sequential display of the target comparison commodities fed back by different commodity platforms, the commodity comparison efficiency is improved.
Example two
Fig. 2 is a flowchart of a method for providing a target comparison product according to a second embodiment of the present invention, which is further detailed on the basis of the above embodiments, and provides a specific step of screening the target comparison product from the one or more candidate comparison products according to the reference similarity. A method for providing a target comparison product according to a second embodiment of the present invention is described below with reference to fig. 2, including the following steps:
step 210, constructing a query condition according to at least one item of basic commodity information of the commodities to be compared, and acquiring query results corresponding to the query condition and fed back by the plurality of commodity platforms, wherein the query results include one or more candidate comparison commodities, and the basic commodity information includes at least one item of attribute information of the commodities to be compared.
Step 220, calculating the reference similarity between each candidate comparison commodity and the commodity to be compared according to at least one item of attribute information of the commodity to be compared and at least one item of attribute information of the candidate comparison commodity.
And step 230, correcting the reference similarity to obtain the similarity between the candidate comparison commodity and the commodity to be compared.
In this embodiment, after the reference similarity between the candidate comparison product and the product to be compared is calculated, in order to make the calculation result more conform to the use habit and expectation of the user, the reference similarity may be corrected according to a preset correction rule, so as to obtain the similarity between the candidate comparison product and the product to be compared.
Illustratively, the reference similarity may be corrected according to a commodity platform of each candidate comparison commodity or a position of the candidate comparison commodity in the matched query result, so as to obtain the similarity between each candidate comparison commodity and the commodity to be compared.
Optionally, the modifying the reference similarity to obtain the similarity between the candidate comparison product and the product to be compared includes:
and correcting the reference similarity according to the commodity platform of the candidate comparison commodity to obtain the similarity.
In this optional embodiment, the reference similarity may be modified according to the commodity platform of the candidate comparison commodity to obtain the similarity, specifically, the reference similarity may be added to the platform weight corresponding to the commodity platform to which the candidate comparison commodity belongs to obtain the final similarity, where the platform weight is set by the user in advance according to an actual situation, for example, the user may set the platform weight according to an importance degree, and for example, if the user attaches importance to the commodity platform B, the platform weight corresponding to the commodity platform B is increased.
Optionally, the modifying the reference similarity to obtain the similarity between the candidate comparison product and the product to be compared includes:
and correcting the reference similarity according to the position of the candidate comparison commodity in the query result to obtain the similarity between the candidate comparison commodity and the commodity to be compared.
In this optional embodiment, the reference similarity may be modified according to the display position of the candidate comparison product on the corresponding product platform to obtain the similarity, specifically, the reference similarity is added to the position weight corresponding to the display position of the candidate comparison product on the corresponding product platform to obtain the final similarity, where the position weight is set by the user in advance according to the actual situation, for example, the position weight may be determined according to the display position of the candidate comparison product on the corresponding product platform, and in general, the more advanced the display position is, the higher the corresponding position weight is.
It should be noted that in this embodiment, the final similarity may also be obtained by performing double correction processing on the reference similarity according to the product platform of the candidate comparison product and the display position of the product platform. For example, after the standard similarity between the to-be-compared commodity and the candidate comparison commodity is calculated to be 70%, a target query result of the candidate comparison commodity is obtained, a candidate commodity platform corresponding to the target query result is determined, a platform weight value of the target commodity platform is further determined, for example, 70%, and a position weight value corresponding to a sorting position of the candidate comparison commodity in the target commodity platform is further determined, for example, the position weight of the displayed 1 st to 15 th commodities is 80%, the position weight of the subsequently displayed commodity is 20%, in this embodiment, the position weight of the candidate comparison commodity is 80% as an example, and finally, the standard similarity is corrected through the platform weight value and the position weight value, and finally, the similarity is obtained as 70% + 70% + 80% + 2.2.
And 240, screening out a target comparison commodity from the one or more candidate comparison commodities according to the similarity.
In this embodiment, after the reference similarity is corrected to obtain the similarity between the to-be-compared commodity and the candidate comparison commodity, in order to enable a user to see the candidate comparison commodity with a higher similarity to the to-be-compared commodity within a limited time and save the time for browsing homogeneous commodities, a target comparison commodity can be screened from one or more candidate comparison commodities according to the similarity between each candidate comparison commodity and the to-be-compared commodity, specifically, the candidate comparison commodities can be sorted from high to low according to the similarity, and finally, the top 60% of the candidate comparison commodities are used as the target comparison commodities; and the candidate comparison commodity with the similarity higher than the reference similarity threshold value can be used as the target comparison commodity.
And step 250, sequencing the target comparison commodities according to the reference similarity.
In this embodiment, after the similarity between each candidate comparison commodity and the commodity to be compared is calculated according to the reference similarity, and the target comparison commodities are obtained by screening from the candidate comparison commodities according to the similarity, each target comparison commodity is displayed in a sequence from high to low according to the similarity, when the similarities of the two target comparison commodities are the same, a commodity with a higher weight corresponding to a platform to which the target comparison commodity belongs can be preferentially displayed, and if the weights corresponding to the platforms are still the same, sequential display is performed according to the sequence of obtaining the target comparison commodities.
And step 260, providing the sorted target comparison commodities to corresponding users.
In the embodiment, after the target comparison commodities are sorted according to the similarity, the target comparison commodities are displayed as corresponding users according to the sorting result, so that the users can preferentially see the target comparison commodities with higher similarity to the commodities to be compared, and the time for the users to browse the same commodities is saved.
The technical scheme of the embodiment of the invention comprises the steps of firstly constructing query conditions according to at least one item of commodity basic information of commodities to be compared, obtaining a plurality of commodity platform feedback candidate comparison commodities, then calculating the reference similarity between the candidate comparison commodities and the commodities to be compared according to at least one item of attribute information of the commodities to be compared and at least one item of attribute information of the candidate comparison commodities, obtaining the commodity platform of each candidate comparison commodity according to query and/or the position of the candidate comparison commodities in a matched query result, correcting the reference similarity to obtain the similarity between each candidate comparison commodity and the commodities to be compared, screening out target comparison commodities from one or more candidate comparison commodities according to the similarity, finally sequencing and displaying the target comparison commodities according to the similarity, wherein on one hand, the comparison information of the target comparison commodities and the commodities is visually displayed, the comparison time of the user is saved, and on the other hand, the similarity is corrected through the commodity platform corresponding to each candidate comparison commodity and the position of the commodity in the query result when the similarity is calculated, so that the effect of adjusting the similarity according to the attention point of the user is realized, and the display result is more in line with the requirement of the user.
EXAMPLE III
Fig. 3 is a flowchart of a method for providing a target comparison product in a third embodiment of the present invention, which is further detailed on the basis of the above embodiment, and provides specific steps for constructing a query condition according to at least one item of product basic information of a product to be compared. A method for providing a target comparison product according to a third embodiment of the present invention is described below with reference to fig. 3, including the following steps:
step 310, constructing a query condition according to at least one item of basic commodity information of the commodities to be compared, and acquiring query results corresponding to the query condition and fed back by the plurality of commodity platforms, wherein the query results include one or more candidate comparison commodities, and the basic commodity information includes at least one item of attribute information of the commodities to be compared.
Optionally, the basic commodity information includes at least one item of attribute information of the commodity to be compared;
constructing a query condition according to at least one item of basic commodity information of commodities to be compared, wherein the query condition comprises the following steps:
and screening at least one item of attribute information of the commodity to be compared to obtain at least one item of key attribute information, and taking the key attribute information as a query condition.
In this optional embodiment, the basic commodity information includes at least one item of attribute information of the commodities to be compared, where the attribute information includes attribute items and attribute values, for example, the casual shoe includes attribute items of "material", "style", and "applicable scene", and the corresponding attribute values are "cowhide", "english", and "outdoor", respectively. Further, the specific step of constructing the query condition according to the basic commodity information may be to obtain at least one piece of key attribute information by screening from at least one piece of attribute information of the commodity to be compared, and use the key attribute information as the query condition, for example, use attribute values "cow leather" and "outdoor" corresponding to attribute items of "material" and "applicable scene" of the casual shoes as the query condition, and perform commodity query on other commodity platforms.
Of course, the commodity picture or the commodity video of the commodity to be compared in the current commodity platform can also be obtained, the commodity picture or the commodity video is used as a query condition, and commodity query is carried out in other commodity platforms supporting picture search.
And step 320, calculating the reference similarity between the candidate comparison commodity and the commodity to be compared according to the at least one item of attribute information of the commodity to be compared and the at least one item of attribute information of the candidate comparison commodity.
And 330, screening a target comparison commodity from the one or more candidate comparison commodities according to the reference similarity.
And step 340, providing the target comparison commodity for a corresponding user.
Step 350, responding to the operation of clicking the target comparison commodity by the user, and displaying the detailed information of the target comparison commodity and the comparison information of the target comparison commodity and the commodity to be compared to the user;
the detailed information comprises at least one item of price, sales volume and comment details of the target comparison commodity;
the comparison information comprises at least one of price comparison, sales comparison and comment detail comparison of the target comparison commodity and the commodity to be compared.
In this embodiment, when the target comparison commodities are displayed in a sorted manner according to the calculated similarity, only basic commodity information is displayed, if a user needs to further check detailed commodity information and comparison information, the target comparison commodities can be clicked, and in response to a user click operation, the detailed information of the target comparison commodities and the comparison information of the target comparison commodities and the commodities to be compared are displayed to the user.
In addition, the comparison of the current information of the to-be-compared commodity and the current information of the target comparison commodity is displayed, the historical price of the to-be-compared commodity and the historical price of the target comparison commodity can be obtained and displayed in the same coordinate system, and the comparison of the commodity prices by a user on the time dimension is facilitated.
And step 360, responding to an attention adding request operation initiated by the user, and adding an attention label to the corresponding target comparison commodity as a key attention commodity.
In this embodiment, when a user needs to pay continuous attention to a certain target comparison commodity, the user can pay additional attention to the commodity, and the system adds an attention tag to the corresponding target comparison commodity according to an attention adding request initiated by the user, so as to serve as a key attention commodity.
and 380, if the price of the important concerned commodity is lower than a set price threshold value, initiating a price reduction prompt message to the user.
In this embodiment, the price of the important commodity is periodically acquired, when the price of the important commodity is lower than a set price threshold, a price reduction prompt message is initiated to the user, specifically, the price of the commodity to be compared can be located at the price threshold, and when the price of the important commodity in the target comparison commodity is lower than the price threshold, information is sent to the user to prompt the user that the price of the homogeneous commodity in other commodity platforms is lower than that of the commodity to be compared.
Optionally, after adding an attention tag to the corresponding target comparison product as a key attention product, the method further includes:
respectively counting first occurrence probabilities of the attribute items in the candidate comparison commodities, second occurrence probabilities of corresponding attribute items in the candidate comparison commodities which serve as target comparison commodities and are clicked and checked by a user, and third occurrence probabilities of corresponding attribute items in the candidate comparison commodities which serve as key attention commodities;
according to a preset commodity weight value, carrying out weighted summation on the first occurrence probability, the second occurrence probability and the third occurrence probability corresponding to each attribute item to obtain a target probability value of each attribute item;
and adjusting the attribute weight value corresponding to each attribute item according to the target probability value of each attribute item.
The first occurrence probability is the occurrence probability of each attribute item in the candidate comparison commodity, the second occurrence probability is the occurrence probability of each attribute item in the commodity clicked by the user in the target comparison commodity, and the third occurrence probability is the occurrence probability of each attribute item in the important commodity.
In this optional embodiment, after adding an attention label to a corresponding target comparison commodity as an important attention commodity, in order to make a result of calculating the similarity more consistent with a habit of a user, an attribute weight value corresponding to each attribute item may be further adjusted according to an occurrence probability of each attribute item in the commodity, specifically, a first occurrence probability of each attribute item in the candidate comparison commodity is respectively counted, for example, 200 items are total for the candidate comparison commodity (casual shoes), and the number of occurrences of the attribute item "material" is 180 times, the first occurrence probability of the attribute item is 180/200 ═ 90%, then a second occurrence probability of each attribute item is calculated in the target comparison commodity clicked and viewed by the user, for example, 20 items of commodities are clicked and viewed by the user, the number of occurrences of the attribute item "material" is 18 times, the second occurrence probability of the attribute item is 90%, in commodities clicked and checked by a user, the number of commodities marked as important attention by the user is 5, wherein the number of times of occurrence of an attribute item 'material' is 5, then the third occurrence probability corresponding to the attribute item is 100%, further, according to a preset commodity weight value, the first occurrence probability, the second occurrence probability and the third occurrence probability corresponding to each attribute item are subjected to weighted summation to obtain a target probability value of the attribute item, and finally, the attribute weight value corresponding to each attribute item is adjusted according to the target probability value, wherein the higher the target probability value of the attribute item is, the higher the corresponding attribute weight is.
The commodity weight values may be weight values corresponding to the first occurrence probability, the second occurrence probability and the third occurrence probability respectively, specifically, since the commodity marked as a focus attention by the user is a commodity focused by the user, the weight value corresponding to the third occurrence probability may be set to be the highest, for example, 60%, the second occurrence probability and the first occurrence probability are sequentially reduced corresponding to the weight values, for example, the second occurrence probability may be 30%, and the first occurrence probability is 10%.
The technical scheme of the embodiment of the invention comprises the steps of firstly constructing query conditions according to at least one item of basic commodity information of commodities to be compared, obtaining candidate comparison commodities fed back by a plurality of commodity platforms, then obtaining the commodity platforms of the candidate comparison commodities according to the query, and/or the positions of the candidate comparison commodities in matched query results, calculating the similarity between the candidate comparison commodities and the commodities to be compared, screening target comparison commodities according to the similarities, sequencing and displaying the target comparison commodities, further responding to the operation of clicking the target comparison commodities by a user, displaying the detailed information of the target comparison commodities and the comparison information of the target comparison commodities and the commodities to be compared to the user, adding attention labels to the commodities concerned by the user, finally adjusting the weight values of the attributes according to the occurrence probability of the attribute items, on one hand, visually displaying the comparison information of the target comparison commodities and the commodities, the comparison time of the user is saved, and on the other hand, the attribute weight value is adjusted according to the occurrence probability of each attribute item, so that the accuracy of calculating the similarity between the target comparison commodity and the commodity to be compared is further improved.
Example four
Fig. 4 is a schematic structural diagram of an apparatus for providing a target comparative commodity according to a fourth embodiment of the present invention, where the apparatus for providing a target comparative commodity includes: a query result obtaining module 410, a reference similarity calculation module 420, a target comparison commodity screening module 430 and a target comparison commodity providing module 440.
A query result obtaining module 410, configured to construct a query condition according to at least one item of basic commodity information of commodities to be compared, and obtain a query result corresponding to the query condition and fed back by multiple commodity platforms, where the query result includes one or more candidate comparison commodities, and the commodity basic information includes at least one item of attribute information of the commodities to be compared;
a reference similarity calculation module 420, configured to calculate a reference similarity between the candidate comparison product and the to-be-compared product according to at least one item of attribute information of the to-be-compared product and at least one item of attribute information of the candidate comparison product;
a target comparison commodity screening module 430, configured to screen a target comparison commodity from the one or more candidate comparison commodities according to the reference similarity;
and the target comparison commodity providing module 440 is configured to provide the target comparison commodity to a corresponding user.
The technical scheme of the embodiment of the invention comprises the steps of firstly constructing a query condition according to at least one item of commodity basic information of commodities to be compared, obtaining query results corresponding to the query condition and fed back by a plurality of commodity platforms, then calculating the reference similarity between candidate comparison commodities and the commodities to be compared according to at least one item of attribute information of the commodities to be compared and at least one item of attribute information of the candidate comparison commodities, screening target comparison commodities from one or more candidate comparison commodities according to the reference similarity, finally providing the target comparison commodities to corresponding users, solving the problem of low commodity comparison efficiency caused by frequent switching of the users on different commodity platforms, screening the target comparison commodities by calculating the similarity between the candidate comparison commodities and the commodities to be compared, realizing sequential display of the target comparison commodities fed back by different commodity platforms, the commodity comparison efficiency is improved.
Optionally, the target comparison goods providing module 440 includes:
the commodity ordering unit is used for ordering the target comparison commodities according to the reference similarity;
and the target comparison commodity providing unit is used for providing the sorted target comparison commodities to corresponding users.
Optionally, the query result obtaining module 410 includes:
and the query condition determining unit is used for screening at least one item of attribute information of the commodities to be compared to obtain at least one item of key attribute information, and taking the key attribute information as the query condition.
Optionally, the apparatus for providing a target comparison product further includes:
the similarity calculation module is used for correcting the reference similarity to obtain the similarity between the candidate comparison commodity and the commodity to be compared;
correspondingly, the target comparison commodity screening module 430 is specifically configured to:
and screening out target comparison commodities from the one or more candidate comparison commodities according to the similarity.
Optionally, the similarity calculation module is specifically configured to:
and correcting the reference similarity according to the commodity platform of the candidate comparison commodity to obtain the similarity.
Optionally, the similarity calculation module is specifically configured to:
and correcting the reference similarity according to the position of the candidate comparison commodity in the query result to obtain the similarity between the candidate comparison commodity and the commodity to be compared. Optionally, the reference similarity calculating module 420 includes:
the comparison attribute pair determining unit is used for establishing at least one comparison attribute pair according to the attribute information respectively corresponding to the candidate comparison commodity and the commodity to be compared, and the comparison attribute pair comprises at least one attribute value corresponding to the same attribute item;
the matching calculation unit is used for calculating the attribute matching degree corresponding to each comparison attribute pair according to a comparison algorithm matched with the attribute items;
and the reference similarity calculation unit is used for calculating the reference similarity between the candidate comparison commodity and the commodity to be compared according to the attribute weight value of each attribute item and each attribute matching degree.
Optionally, the alignment algorithm includes at least one of the following:
when the attribute values contained in the comparison attribute pair are completely the same, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree;
determining the number of the same words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the same words;
determining the number of continuous identical words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the continuous identical words;
and when the attribute value corresponding to the commodity to be compared in the comparison attribute pair is contained in the attribute value corresponding to the candidate comparison commodity, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree.
Optionally, the apparatus for providing a target comparison product further includes:
the information display module is used for responding to the operation of clicking the target comparison commodity by the user, and displaying the detailed information of the target comparison commodity and the comparison information of the target comparison commodity and the to-be-compared commodity to the user;
wherein the detailed information comprises at least one of price, sales volume and comment details of the target comparison commodity;
the comparison information comprises at least one of price comparison, sales comparison and comment detail comparison of the target comparison commodity and the commodity to be compared.
Optionally, the apparatus for providing a target comparison product further includes:
the concerned commodity determining module is used for responding to the operation, adding concerned labels to the corresponding target comparison commodities as key concerned commodities;
the price acquisition module is used for acquiring the price of the key attention commodity;
and the price reduction prompting module is used for initiating a price reduction prompting message to the user if the price of the key attention commodity is lower than a set price threshold value.
Optionally, the apparatus for providing a target comparison product further includes:
the probability calculation module is used for respectively counting first occurrence probabilities of the attribute items in the candidate comparison commodities, second occurrence probabilities of corresponding attribute items in the candidate comparison commodities which serve as the target comparison commodities and are clicked and checked by the user, and third occurrence probabilities of corresponding attribute items in the candidate comparison commodities which serve as the key attention commodities;
the target probability value calculation module is used for weighting and summing the first occurrence probability, the second occurrence probability and the third occurrence probability corresponding to each attribute item according to a preset commodity weight value to obtain a target probability value of each attribute item;
and the attribute weight value adjusting module is used for adjusting the attribute weight value corresponding to each attribute item according to the target probability value of each attribute item.
The device for providing the target comparison commodity provided by the embodiment of the invention can execute the method for providing the target comparison commodity provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, as shown in fig. 5, the electronic device includes a processor 50 and a memory 51; the number of processors 50 in the device may be one or more, and one processor 50 is taken as an example in fig. 5; the processor 50 and the memory 51 in the device may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
The memory 51 serves as a computer-readable storage medium, and may be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a method for providing a target comparison product in the embodiment of the present invention (for example, the query result obtaining module 410, the reference similarity calculation module 420, the target comparison product screening module 430, and the target comparison product providing module 440 in the apparatus for providing a target comparison product). The processor 50 executes various functional applications of the apparatus and data processing by executing software programs, instructions and modules stored in the memory 51, that is, implements the above-described method for providing a target comparison product.
The method comprises the following steps:
constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results corresponding to the query condition and fed back by a plurality of commodity platforms, wherein the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
screening out target comparison commodities from the one or more candidate comparison commodities according to the reference similarity;
and providing the target comparison commodity for a corresponding user.
The memory 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 51 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 51 may further include memory located remotely from the processor 50, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE six
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program for, when executed by a computer processor, performing a method for providing a target comparison commodity, the method comprising:
constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results corresponding to the query condition and fed back by a plurality of commodity platforms, wherein the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
screening out target comparison commodities from the one or more candidate comparison commodities according to the reference similarity;
and providing the target comparison commodity for a corresponding user.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the above embodiment of the apparatus for providing target comparison products, the included units and modules are merely divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (12)
1. A method for providing a targeted comparison product, comprising:
constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results corresponding to the query condition and fed back by a plurality of commodity platforms, wherein the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
screening out target comparison commodities from the one or more candidate comparison commodities according to the reference similarity;
providing the target comparison commodity for a corresponding user;
wherein, the calculating the benchmark similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity comprises:
establishing at least one comparison attribute pair according to the attribute information respectively corresponding to the candidate comparison commodity and the to-be-compared commodity, wherein the comparison attribute pair comprises at least one attribute value corresponding to the same attribute item;
calculating attribute matching degrees respectively corresponding to the comparison attribute pairs according to a comparison algorithm matched with the attribute items;
calculating the reference similarity between the candidate comparison commodity and the commodity to be compared according to the attribute weight value of each attribute item and each attribute matching degree;
respectively counting first occurrence probabilities of the attribute items in the candidate comparison commodities, second occurrence probabilities of corresponding attribute items in the candidate comparison commodities, which serve as the target comparison commodities and are clicked and checked by the user, and third occurrence probabilities of corresponding attribute items in the candidate comparison commodities, which serve as the key attention commodities;
according to a preset commodity weight value, carrying out weighted summation on a first occurrence probability, a second occurrence probability and a third occurrence probability corresponding to each attribute item to obtain a target probability value of each attribute item;
and adjusting the attribute weight value corresponding to each attribute item according to the target probability value of each attribute item.
2. The method of claim 1, wherein providing the target comparison commodity to a corresponding user comprises:
sorting the target comparison commodities according to the reference similarity;
and providing the sorted target comparison commodities to corresponding users.
3. The method as claimed in claim 1, wherein the step of constructing the query condition according to at least one item of basic commodity information of the commodities to be compared comprises:
and screening at least one item of attribute information of the commodity to be compared to obtain at least one item of key attribute information, and taking the key attribute information as the query condition.
4. The method of claim 1, further comprising:
correcting the reference similarity to obtain the similarity between the candidate comparison commodity and the commodity to be compared;
wherein, according to the reference similarity, screening out a target comparison commodity from the one or more candidate comparison commodities, including:
and screening out target comparison commodities from the one or more candidate comparison commodities according to the similarity.
5. The method according to claim 4, wherein the step of correcting the reference similarity to obtain the similarity between the candidate comparison product and the product to be compared comprises:
and correcting the reference similarity according to the commodity platform of the candidate comparison commodity to obtain the similarity.
6. The method according to claim 4, wherein the step of correcting the reference similarity to obtain the similarity between the candidate comparison product and the product to be compared comprises:
and correcting the reference similarity according to the position of the candidate comparison commodity in the query result to obtain the similarity between the candidate comparison commodity and the commodity to be compared.
7. The method of claim 1, wherein the alignment algorithm comprises at least one of:
when the attribute values contained in the comparison attribute pair are completely the same, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree;
determining the number of the same words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the same words;
determining the number of continuous identical words of the attribute values contained in the comparison attribute pair, and calculating the attribute matching degree of the comparison attribute pair according to the number of the continuous identical words;
and when the attribute value corresponding to the commodity to be compared in the comparison attribute pair is contained in the attribute value corresponding to the candidate comparison commodity, determining that the attribute matching degree of the comparison attribute pair is a first matching degree, otherwise, determining that the attribute matching degree is a second matching degree.
8. The method according to any one of claims 1-7, further comprising:
responding to the operation of clicking the target comparison commodity by the user, and displaying the detailed information of the target comparison commodity and the comparison information of the target comparison commodity and the commodity to be compared to the user;
wherein the detailed information comprises at least one of price, sales volume and comment details of the target comparison commodity;
the comparison information comprises at least one of price comparison, sales comparison and comment detail comparison of the target comparison commodity and the commodity to be compared.
9. The method of claim 8, wherein if the operation is an add attention request operation initiated by the user, the method further comprises:
responding to the operation, adding an attention label to the corresponding target comparison commodity as the key attention commodity;
acquiring the price of the key attention commodity;
and if the price of the key attention commodity is lower than a set price threshold value, sending a price reduction prompt message to the user.
10. An apparatus for providing a targeted comparative product, comprising:
the system comprises a query result acquisition module, a comparison module and a comparison module, wherein the query result acquisition module is used for constructing a query condition according to at least one item of commodity basic information of commodities to be compared, and acquiring query results which are fed back by a plurality of commodity platforms and correspond to the query condition, the query results comprise one or more candidate comparison commodities, and the commodity basic information comprises at least one item of attribute information of the commodities to be compared;
the reference similarity calculation module is used for calculating the reference similarity between the candidate comparison commodity and the to-be-compared commodity according to the at least one item of attribute information of the to-be-compared commodity and the at least one item of attribute information of the candidate comparison commodity;
the reference similarity calculation module further includes: a comparison attribute pair determining unit, configured to establish at least one comparison attribute pair according to attribute information corresponding to the candidate comparison product and the product to be compared, where the comparison attribute pair includes at least one attribute value corresponding to the same attribute item; the matching calculation unit is used for calculating the attribute matching degree corresponding to each comparison attribute pair according to a comparison algorithm matched with the attribute items; the reference similarity calculation unit is used for calculating the reference similarity between the candidate comparison commodity and the commodity to be compared according to the attribute weight value of each attribute item and each attribute matching degree;
the target comparison commodity screening module is used for screening a target comparison commodity from the one or more candidate comparison commodities according to the reference similarity;
the target comparison commodity providing module is used for providing the target comparison commodity for a corresponding user;
a probability calculation module, configured to separately count first occurrence probabilities of the attribute items in the candidate comparison commodities, second occurrence probabilities of corresponding attribute items in the candidate comparison commodities, which are used as the target comparison commodity and clicked and viewed by the user, and third occurrence probabilities of corresponding attribute items in the candidate comparison commodities, which are used as the important commodity;
the target probability value calculation module is used for weighting and summing the first occurrence probability, the second occurrence probability and the third occurrence probability corresponding to each attribute item according to a preset commodity weight value to obtain a target probability value of each attribute item;
and the attribute weight value adjusting module is used for adjusting the attribute weight value corresponding to each attribute item according to the target probability value of each attribute item.
11. An electronic device, characterized in that the device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for providing a target comparison commodity as recited in any one of claims 1-9.
12. A computer storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements a method for providing a target comparison article as claimed in any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010910136.1A CN112036981B (en) | 2020-09-02 | 2020-09-02 | Method, device, equipment and medium for providing target comparison commodities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010910136.1A CN112036981B (en) | 2020-09-02 | 2020-09-02 | Method, device, equipment and medium for providing target comparison commodities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112036981A CN112036981A (en) | 2020-12-04 |
| CN112036981B true CN112036981B (en) | 2021-09-17 |
Family
ID=73591174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010910136.1A Active CN112036981B (en) | 2020-09-02 | 2020-09-02 | Method, device, equipment and medium for providing target comparison commodities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112036981B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767090A (en) * | 2021-01-28 | 2021-05-07 | 维沃移动通信有限公司 | Article display method and device and electronic equipment |
| CN112861684A (en) * | 2021-01-29 | 2021-05-28 | 北京电解智科技有限公司 | Article display method and device |
| CN113793191B (en) * | 2021-02-09 | 2024-05-24 | 京东科技控股股份有限公司 | Commodity matching method and device and electronic equipment |
| CN115511014B (en) * | 2022-11-23 | 2023-04-07 | 联仁健康医疗大数据科技股份有限公司 | Information matching method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606089A (en) * | 2013-11-15 | 2014-02-26 | 北京奇虎科技有限公司 | A method and an apparatus used for realizing commodity state change prompting |
| CN106097032A (en) * | 2016-05-26 | 2016-11-09 | 维沃移动通信有限公司 | Commodity price-comparing method and mobile terminal thereof |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN110335109A (en) * | 2019-05-31 | 2019-10-15 | 平安科技（深圳）有限公司 | Take out method of ordering, terminal device, device and computer readable storage medium |
| CN110807482A (en) * | 2019-10-30 | 2020-02-18 | 北京创鑫旅程网络技术有限公司 | Same house source detection method, device and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9699490B1 (en) * | 2015-02-11 | 2017-07-04 | Amazon Technologies, Inc. | Adaptive filtering to adjust automated selection of content using weightings based on contextual parameters of a browsing session |
| CN108038730A (en) * | 2017-12-22 | 2018-05-15 | 联想(北京)有限公司 | Product similarity determination methods, device and server cluster |
| CN110738553A (en) * | 2019-10-18 | 2020-01-31 | 深圳市比量科技传媒有限公司 | method and system for mapping commodity links of different shopping malls to each other |
| CN111400345A (en) * | 2020-02-21 | 2020-07-10 | 北京九州云动科技有限公司 | Commodity searching method and device supporting multiple platforms |
-
2020
- 2020-09-02 CN CN202010910136.1A patent/CN112036981B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606089A (en) * | 2013-11-15 | 2014-02-26 | 北京奇虎科技有限公司 | A method and an apparatus used for realizing commodity state change prompting |
| CN106097032A (en) * | 2016-05-26 | 2016-11-09 | 维沃移动通信有限公司 | Commodity price-comparing method and mobile terminal thereof |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN110335109A (en) * | 2019-05-31 | 2019-10-15 | 平安科技（深圳）有限公司 | Take out method of ordering, terminal device, device and computer readable storage medium |
| CN110807482A (en) * | 2019-10-30 | 2020-02-18 | 北京创鑫旅程网络技术有限公司 | Same house source detection method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112036981A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112036981B (en) | Method, device, equipment and medium for providing target comparison commodities | |
| CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN111523976A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN107644036B (en) | Method, device and system for pushing data object | |
| US9082086B2 (en) | Adaptively learning a similarity model | |
| CN110473040B (en) | Product recommendation method and device and electronic equipment | |
| CN110175895B (en) | Article recommendation method and device | |
| WO2017088496A1 (en) | Search recommendation method, device, apparatus and computer storage medium | |
| CN111695960A (en) | Object recommendation system, method, electronic device and storage medium | |
| US20120296776A1 (en) | Adaptive interactive search | |
| TWI539306B (en) | Information delivery method, processing server and merge server | |
| CN116308684B (en) | Online shopping platform store information pushing method and system | |
| CN112907334B (en) | Object recommendation method and device | |
| US20170287041A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN113837842A (en) | Commodity recommendation method and equipment based on user behavior data | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN113032668A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN113689259A (en) | Commodity personalized recommendation method and system based on user behaviors | |
| US10678878B2 (en) | Method, device and storing medium for searching | |
| CN112488781A (en) | Search recommendation method and device, electronic equipment and readable storage medium | |
| Aprilianti et al. | Implementation of weighted parallel hybrid recommender systems for e-commerce in indonesia | |
| CN116383458B (en) | Information pushing method and device | |
| CN116308683B (en) | Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium | |
| CN113225580A (en) | Live broadcast data processing method and device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 519085 Building 8, No.1, Tangjiawan Harbin Institute of technology, high tech Zone, Zhuhai City, Guangdong Province Applicant after: Zhuhai necessary Industrial Technology Co.,Ltd. Address before: 519085 Building 8, No.1, Tangjiawan Harbin Institute of technology, high tech Zone, Zhuhai City, Guangdong Province Applicant before: ZHUHAI SUIBIAN TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |