CN106951516B

CN106951516B - Decoration selection intelligent sorting method based on big data

Info

Publication number: CN106951516B
Application number: CN201710162522.5A
Authority: CN
Inventors: 王国彬; 胡鹏; 胡少雄; 鲁四喜
Original assignee: Shenzhen Bincent Technology Co Ltd
Current assignee: Tubatu Group Co Ltd
Priority date: 2017-03-18
Filing date: 2017-03-18
Publication date: 2020-07-17
Anticipated expiration: 2037-03-18
Also published as: CN106951516A

Abstract

The invention discloses a decoration option intelligent sorting method based on big data, relates to the technical field of decoration option search matching under the big data, and solves the problem of low search matching degree in the prior art. The method comprises the following steps: the client uploads a list of the currently selected commodities containing at least two commodity attributes to the server; the server analyzes the list of the selected commodities, respectively obtains the arrangement sequence of two commodity attributes of the selected commodities after intelligent analysis, matches the corresponding commodity attributes of the current to-be-selected commodities with the obtained ordering result of the selected commodities, and obtains the increasing sequence arrangement result of the current to-be-selected commodities based on the corresponding commodity attributes; and the server sends the sequencing increasing result to the client for display. The invention solves the problems that the commodity display ordering is single and the intelligent ordering cannot be realized in the prior art, realizes the intelligent ordering of the commodities based on the analysis of big data, and reduces and avoids the selection difficulty and the selection error when a user decorates and selects the commodities.

Description

Decoration selection intelligent sorting method based on big data

Technical Field

The invention relates to the technical field of decoration option search and matching under big data, in particular to a decoration option intelligent sorting method based on big data.

Background

With the advancement and development of science and technology, in the hard-clothing and soft-clothing industries, many home decoration sales personnel introduce and select commodities for customers through mobile equipment, and the display sequence of the furniture decoration commodities on the existing website and App is single. On one hand, the existing websites and apps can only sort according to the brand, price and popularity of commodities generally, and intelligent sorting cannot be realized; on the other hand, the online commodities are full of line and various in variety, and under the restriction of comprehensive factors in two aspects, customers often hold the chess with variable or no choices of furniture brands and furniture styles in the commodity selection process, and much time is wasted.

In another aspect, although the existing websites and apps can perform customized search and matching, they are all search and matching based on the individual preferences and opinions of customers, and the style of the search and matching is not good due to the wrong selection of the customers. For the complete decoration of a blank room, the whole style of the selected product can be mastered and the brand and the like can be preliminarily coordinated and unified at the beginning of purchasing the complete furniture and the decorative material. And for the conditions that partial decoration or later-stage rearrangement decoration is finished and home decoration furniture is added in the later stage, the way that the style and the brand of newly added furniture are coordinated and unified with the original integral decoration becomes a prominent problem.

According to survey data, a great number of customers purchase newly-added furniture according to products pushed by the existing website or App or fraudulently mislead by a shopping guide in a furniture city, and the newly-added furniture has strong randomness in the shopping process. Due to the technical limitations of the existing websites and some apps and misleading of customers caused by the fact that shopping guide members in furniture cities do not know the style and brand of furniture in houses of the customers, compared with existing indoor furniture, the style of the furniture selected by the customers is different, so that the furniture selected by the customers is more obtrusive, and lacks coordination and aesthetic feeling. Meanwhile, the existing technology cannot respectively push furniture with corresponding decoration styles aiming at different indoor decoration styles, and the judgment and selection of individuals are still mainstream, which wastes time and energy for customers with selection difficulty.

Disclosure of Invention

In order to solve the technical problems, the invention provides an intelligent decoration option sequencing method based on big data, and the method provided by the invention can intelligently sequence commodities by analyzing the big data and analyzing the big data based on the existing furniture list, thereby reducing and avoiding the selection difficulty and the selection error of customers during decoration options.

The technical scheme adopted by the invention for realizing the technical effects is as follows:

a decoration selected product intelligent sorting method based on big data comprises the following steps:

s1, the client uploads a list of the current selected commodities containing at least two commodity attributes to the server;

s2, the server analyzes the list of the selected commodity, obtains the arrangement sequence of the two commodity attributes of the selected commodity after intelligent analysis, matches the corresponding commodity attribute of the current commodity to be selected with the obtained arrangement result of the selected commodity, and obtains the increasing sequence arrangement result of the current commodity to be selected based on the corresponding commodity attribute;

and S3, the server sends the increasing sequence arrangement result of the current commodity to be selected to the client side for display in a passive request mode/active pushing mode.

Further, the server comprises an analysis module, a matching module and a data module, the client comprises an uploading module, a sequencing analysis module and a display module, the uploading module is connected with the analysis module, the analysis module is connected with the matching module, the matching module is connected with the sequencing analysis module, the sequencing analysis module is connected with the display module, and the matching module is in two-way connection with the data module.

Furthermore, the client uploads the list to the analysis module of the server through the uploading module, the server analyzes the list through the analysis module, then intelligent matching and sorting are carried out through an intelligent matching module in the matching module and matching data in the data module, and after the matching module finishes matching, the sorting data are transmitted back to the display module of the client for sorting and displaying.

Further, in the step S1, the two product attributes of the selected product are a brand attribute of the selected product and a style attribute of the selected product, respectively.

Further, in the step S1, a decoration space attribute corresponding to a space where the selected merchandise is located is further included.

Further, in step S2, the sorting result is displayed in a partitioned manner according to different decoration spaces.

Further, the step S2 further includes the following steps:

s201, the server analyzes the list of the selected commodities, calculates brand attribute ratios and style attribute ratios of the commodities in the current list, and stores the style attribute and the brand attribute with the highest ratio in the list;

s202, the server matches the similar commodities with the current commodities to be selected with matching data of the existing popular commodities according to style attributes and brand attributes, and then sorts the commodities from high to low according to the usage amount;

and S203, the server sends the sequencing data acquired in the step S202 to the client, and the client performs commodity sequencing display according to the sequencing data.

Furthermore, the collocation data in the data module is from collocation data successfully placed and collocation data preset by a designer.

Further, the collocation data in the data module is from data captured by a webpage.

Further, the matching rule of the intelligent matching module is as follows:

1) calculating the style attribute ratio and the brand attribute ratio in the list of the current selected commodity, and obtaining the style attribute and the brand attribute with the highest ratio;

2) the server matches the style attribute and the brand attribute of the commodities with the existing popular matching data, and sorts the commodities from high to low according to the usage amount.

The invention has the beneficial effects that: the invention can perform intelligent sorting of commodities based on analysis of big data, and reduces selection difficulty and selection error when a user decorates and selects commodities. Through the list analysis of the selected commodities, furniture corresponding to decoration styles can be respectively pushed for spaces with different indoor decoration styles, and the furniture pushing method has strong pertinence and can assist customers to flexibly unify the decoration styles.

Drawings

FIG. 1 is a flow chart of a first embodiment of the present invention;

FIG. 2 is a block diagram of a first embodiment of the present invention;

FIG. 3 is a flowchart illustrating a detailed procedure of step S2 according to the second embodiment of the present invention;

FIG. 4 is a schematic block diagram illustrating a collaborative matching ordering of an intelligent matching module and a data module according to a second embodiment of the present invention;

FIG. 5 is a list of currently selected products including attributes of brand and style according to the second embodiment of the present invention;

fig. 6 is matching data generated by server parsing according to the second embodiment of the present invention;

FIG. 7 is a list of currently selected products including triple attributes of brand, style, and decoration space according to a third embodiment of the present invention;

fig. 8 is matching data generated by server parsing according to the third embodiment of the present invention;

fig. 9 is a sequencing interface diagram of the current selected commodity sofa on the client according to the invention.

Detailed Description

In order to make the present invention more clearly and completely explained, the technical solutions of the present invention are further explained below with reference to the accompanying drawings and the specific embodiments of the present invention.

The first embodiment is as follows:

as shown in fig. 1 and 2, the method for intelligently sorting decoration options based on big data provided by the invention comprises the following steps:

step S1, the client uploads a list of the current selected commodities containing at least two commodity attributes to the server;

step S2, the server analyzes the list of the selected commodity, obtains the arrangement sequence of two commodity attributes of the selected commodity after intelligent analysis, matches the corresponding commodity attribute of the current commodity to be selected with the obtained arrangement result of the selected commodity, and obtains the increasing order arrangement result of the current commodity to be selected based on the corresponding commodity attribute;

and step S3, the server sends the increasing order arrangement result of the current commodity to be selected to the client side for display in a passive request mode/active pushing mode.

The server comprises an analysis module, a matching module and a data module, and the client comprises an uploading module, a sequencing analysis module and a display module. The uploading module is connected with the analysis module, the analysis module is connected with the matching module, the matching module is connected with the sequencing analysis module, the sequencing analysis module is connected with the display module, and the matching module is in bidirectional connection with the data module. The client uploads the list to the analysis module of the server through the upload module, the server analyzes the list through the analysis module, then intelligent matching and sorting are carried out on the matched data in the data module and the intelligent matching module in the matching module, and after the matching module finishes matching, the sorted data are transmitted back to the display module of the client for sorting and displaying. As shown in fig. 9, after the current goods to be selected take the sofa as an example and the data is analyzed and the big data in the data module is matched, the ordering of the similar sofa optimization selection schemes on the client is as shown in the interface diagram of fig. 9.

Preferably, the matching data in the data module is from matching data successfully placed and matching data preset by a designer, or may be from data captured by a web page, or a combination thereof. The matching data successfully ordered comprises matching schemes purchased and selected by each existing customer, serving as successful case samples and supplemented into the data module, and matching schemes stored in the data module and preset by a designer, and the two aspects of data sources ensure that a sample library in the data module has rich excellent matching schemes. As another supplementary way, the collocation data in the data module may also come from web page captured data. Particularly, a matching scheme with more approval, more favorable comment and better comment is obtained from a plurality of excellent home decoration online platforms or home decoration designer forums or home decoration designer websites with a large number of users and resident designers. Through the collocation scheme selected by the customer, the collocation scheme stored by the pre-set of the designer and the collocation scheme captured on the network, the sample library in the data module can store abundant and massive excellent collocation scheme data, and under the support of the excellent collocation scheme data, the matching degree of the current goods to be selected can reach a higher level, and the matching with the original furniture can be more harmonious and uniform.

According to the invention, by analyzing the list and combining with the matching of a large amount of data, the intelligent sorting of commodities can be carried out on the specific attributes of the commodities, so that matching combinations with consistent and harmonious attributes are provided for users, and the selection difficulty and selection errors of the users during decoration and selection are reduced.

Example two:

referring to fig. 1 to 6, the method for intelligently sorting decoration options based on big data provided by the invention includes the following steps:

step S1, the client uploads the list of the currently selected merchandise including the style attribute and the brand attribute to the server, as shown in fig. 5, and lists the two attributes of the currently existing merchandise according to the style and the brand.

Step S2, as shown in fig. 6, the server parses the list of the selected merchandise, obtains the arrangement order of the style attribute and the brand attribute of the selected merchandise after intelligent analysis, and matches the corresponding merchandise attribute of the current merchandise to be selected with the obtained arrangement result of the selected merchandise, to obtain the increasing order arrangement result of the current merchandise to be selected based on the corresponding merchandise attribute;

and step S3, the server sends the increasing order arrangement result of the current commodity to be selected to the client side for display in a passive request mode/active pushing mode. Specifically, as shown in fig. 9, after the current goods to be selected take the sofa as an example and data analysis and big data matching in the data module are performed, the same type of sofa optimization selection schemes are sorted on the client as shown in the interface diagram of fig. 9.

Specifically, step S2 further includes the following steps:

s202, matching the similar commodities with the current commodities to be selected with matching data of the existing popular commodities according to style attributes and brand attributes by a server, and then sequencing the commodities according to the usage amount from high to low;

The server comprises an analysis module, a matching module and a data module, and the client comprises an uploading module, a sequencing analysis module and a display module. The uploading module is connected with the analysis module, the analysis module is connected with the matching module, the matching module is connected with the sequencing analysis module, the sequencing analysis module is connected with the display module, and the matching module is in bidirectional connection with the data module. The client uploads the list to the analysis module of the server through the upload module, the server analyzes the list through the analysis module, then intelligent matching and sorting are carried out on the matched data in the data module and the intelligent matching module in the matching module, and after the matching module finishes matching, the sorted data are transmitted back to the display module of the client for sorting and displaying.

The collocation data in the data module is from collocation data successfully placed and collocation data preset by a designer, or can be from data captured by a webpage, and the combination of the modes. The matching data successfully ordered comprises matching schemes purchased and selected by each existing customer, serving as successful case samples and supplemented into the data module, and matching schemes stored in the data module and preset by a designer, and the two aspects of data sources ensure that a sample library in the data module has rich excellent matching schemes. As another supplementary way, the collocation data in the data module may also come from web page captured data. Particularly, a matching scheme with more approval, more favorable comment and better comment is obtained from a plurality of excellent home decoration online platforms or home decoration designer forums or home decoration designer websites with a large number of users and resident designers. Through the collocation scheme selected by the customer, the collocation scheme stored by the pre-set of the designer and the collocation scheme captured on the network, the sample library in the data module can store abundant and massive excellent collocation scheme data, and under the support of the excellent collocation scheme data, the matching degree of the current goods to be selected can reach a higher level, and the matching with the original furniture can be more harmonious and uniform.

The specific matching rule of the intelligent matching module is as follows:

1) the style attribute ratio accounting unit and the brand ratio accounting unit respectively calculate the style attribute ratio and the brand attribute ratio in the list of the current selected commodities to obtain the style attribute and the brand attribute with the highest ratio;

As shown in fig. 4, the intelligent matching module includes a style attribute ratio accounting unit and a brand ratio accounting unit, after the list is imported and analyzed, the style attribute ratio accounting unit calculates respective ratios of different style attributes of various commodities in the list, the brand ratio accounting unit calculates respective ratios of different brand attributes of various commodities in the list, and obtains respective attributes with the highest ratios, then matching is performed according to the matching data with higher matching utilization rate stored in the data module, and the commodities with higher matching rate are associated as the recommendation to be selected according to the attributes with the highest ratios. As shown in FIG. 5, the 27 items of furniture in the list collectively share two stylistic attributes of "American" and "modern", and three branded attributes of "Guest", "Yi-Home", and "Lihao". After the analysis, as shown in fig. 6, the total amount of furniture in the list is 27, wherein the number of furniture with the "modern" style attribute is 19, and the number of furniture with the "american" style attribute is 8, then the "modern" style attribute duty ratio of the 27 selected commodities calculated by the style attribute duty ratio accounting unit is 19/27, and the "american" style attribute duty ratio is 8/27, according to the highest duty ratio rule, the intelligent matching module stores the "modern" style attribute, the collocation data of the same type of commodities with higher collocation utilization rate and higher collocation utilization rate stored in the data module establish a one-to-many mapping relationship with the "modern" style attribute, and are arranged in a descending order according to the height of the collocation utilization rate. Similarly, the ordering rule of the brand attribute is consistent with the ordering rule of the style attribute, and the description is omitted here.

Example three:

as shown in fig. 1 to 4, and fig. 7 and 8, the third embodiment is characterized in that the inventory data of the currently selected merchandise also includes a decoration space attribute corresponding to a space in which the currently selected merchandise is located. Specifically, as shown in fig. 7, the attributes in the manifest include three attributes of space, style, and brand. In step S2, the sorted results are displayed in different partitions according to different decoration spaces, and the highest ratio of style attribute and brand attribute is calculated in each partition. Specifically, as shown in fig. 8, the data generated by parsing is generated in a partitioned manner according to three spaces (a dining room, a bedroom, and a study room) of the list in fig. 7, wherein the style attribute and the brand attribute of each region are synchronously generated in the corresponding partition, so that reference suggestions for collocation of different spaces are provided for the user, and flexibility and unification of intelligent matching are achieved. Specifically, as shown in fig. 9, after the current goods to be selected take the sofa as an example and data analysis and big data matching in the data module are performed, the same type of sofa optimization selection schemes are sorted on the client as shown in the interface diagram of fig. 9.

The invention can perform intelligent sorting of commodities based on analysis of big data, and reduces selection difficulty and selection error when a user decorates and selects commodities. Through the list analysis of the selected commodities, furniture corresponding to decoration styles can be respectively pushed for spaces with different indoor decoration styles, and the furniture pushing method has strong pertinence and can assist customers to flexibly unify the decoration styles.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims

1. An intelligent decoration option sequencing method based on big data is characterized by comprising the following steps:

s3, the server sends the increasing order arrangement result of the current commodity to be selected to the client side in a passive request mode/active pushing mode for display;

the step S2 further includes the steps of:

2. The intelligent decoration option sequencing method based on big data as claimed in claim 1, wherein the server comprises an analysis module, a matching module and a data module, the client comprises an uploading module, a sequencing analysis module and a display module, the uploading module is connected with the analysis module, the analysis module is connected with the matching module, the matching module is connected with the sequencing analysis module, the sequencing analysis module is connected with the display module, and the matching module is bidirectionally connected with the data module.

3. The intelligent decoration option sequencing method based on big data as claimed in claim 2, wherein the client uploads the list to the parsing module of the server through the uploading module, the server parses the list through the parsing module, then intelligently matches and sequences the matched data in the data module through an intelligent matching module in the matching module, and after the matching module completes matching, the sequenced data is transmitted back to the display module of the client for sequencing and display.

4. A decoration option intelligent sorting method based on big data according to claim 1, wherein in the step S1, the two commodity attributes of the selected commodity are a brand attribute of the selected commodity and a style attribute of the selected commodity, respectively.

5. A decoration option intelligent sorting method based on big data according to claim 4, wherein in the step S1, the method further comprises a decoration space attribute corresponding to the space where the selected commodity is located.

6. A decoration option intelligent sorting method based on big data as claimed in claim 5, wherein in step S2, the sorting result is displayed in different partitions according to different decoration spaces.

7. A decoration option intelligent sorting method based on big data according to claim 3, wherein the collocation data in the data module is from collocation data successfully placed and collocation data preset by designers.

8. The intelligent big data-based decoration option sequencing method of claim 3, wherein the collocation data in the data module is from web crawl data.

9. The intelligent decoration option sequencing method based on big data as claimed in claim 3, wherein the matching rule of the intelligent matching module is: