CN109389465B

CN109389465B - E-commerce platform optimization method and device

Info

Publication number: CN109389465B
Application number: CN201811110551.8A
Authority: CN
Inventors: 周雪; 赵锡成; 孟琳琳; 马刚
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2018-09-21
Filing date: 2018-09-21
Publication date: 2021-02-23
Anticipated expiration: 2038-09-21
Also published as: CN109389465A

Abstract

The invention discloses an optimization method and device of an e-commerce platform, relates to the field of internet, and is used for optimizing a shop commodity selling strategy. The method comprises the following steps: acquiring a group of keyword groups input by a user, wherein the keyword groups comprise at least two keywords which are mutually associated, and each keyword is used for describing a commodity; searching each keyword to obtain a plurality of shops selling corresponding commodities and taking an intersection to obtain a shop intersection list; and if the number of shops is not greater than a preset threshold in the obtained shop intersection list, adding the key phrase into a key phrase set, and performing association analysis on the key phrase set to obtain a cross-category association result. The embodiment of the invention is applied to the optimization of the strategy of shop commodity selling in the e-commerce platform.

Description

E-commerce platform optimization method and device

Technical Field

The invention relates to the technical field of internet, in particular to an optimization method and device of an e-commerce platform.

Background

With the development of the e-commerce industry, a large number of B2C e-commerce platforms appear in the market, and the e-commerce platforms can build a connected bridge between a merchant and a consumer, so that the merchant can be provided with business opportunities, and shopping convenience is brought to the consumer. The consumer uses the search engine to select the required goods, and in the prior art, the consumer can only search for and purchase the same kind of goods in one shop, and needs to make orders for the goods in different kinds. In addition, with the prevalence of machine learning in recent years, recommendation systems are also widely applied to e-commerce platforms, so how to accurately grasp the shopping tendency of consumers is an urgent technical problem to be solved for recommending commodities that consumers most probably want to purchase simultaneously.

Disclosure of Invention

The embodiment of the invention provides an optimization method and device of an e-commerce platform, which are used for solving the technical problem that commodities cannot be purchased in the same shop in different categories in the prior art.

In order to solve the technical problem, the embodiment of the invention adopts the following technical scheme:

in a first aspect, an embodiment of the present invention provides a method for optimizing an e-commerce platform, where the method includes:

acquiring a group of keyword groups input by a user, wherein the keyword groups comprise at least two keywords which are mutually associated, and each keyword is used for describing a commodity;

searching each keyword to obtain a plurality of shops selling corresponding commodities and taking an intersection to obtain a shop intersection list;

and if the number of shops is not greater than a preset threshold in the obtained shop intersection list, adding the key phrase into a key phrase set, and performing association analysis on the key phrase set to obtain a cross-category association result.

In a second aspect, an embodiment of the present invention provides an apparatus for optimizing an e-commerce platform, including:

the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a group of key phrases input by a user, the key phrases comprise at least two key words which are mutually associated, and each key word is used for describing a commodity;

the searching unit is used for searching each keyword to obtain a plurality of shops selling corresponding commodities and taking an intersection to obtain a shop intersection list;

and the association unit is used for adding the key phrase into a key phrase set if the number of shops is not greater than a preset threshold in the obtained shop intersection list, and performing association analysis on the key phrase set to obtain a cross-item association result.

In a third aspect, there is provided a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computer, cause the computer to perform the method of optimizing an e-commerce platform of the first aspect.

In a fourth aspect, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method of optimizing an e-commerce platform as described in the first aspect.

In a fifth aspect, an optimization apparatus for an e-commerce platform is provided, including: the system comprises a processor and a memory, wherein the memory is used for storing programs, and the processor calls the programs stored in the memory to execute the optimization method of the E-commerce platform in the first aspect.

The embodiment of the invention provides the optimization method and the device of the E-commerce platform, which realize the method for searching various different types of commodities in the same shop in a combined manner, and meet the requirement of a user for purchasing multiple types of commodities at one time; through reverse analysis of user search behaviors, the relevance among different categories of commodities is mined, and the result is recommended to platform merchants as a sales strategy, so that the merchants are helped to mine the shopping habits of the users, and the commodity sales volume is increased.

Drawings

Fig. 1 is a schematic flow chart of an optimization method for an e-commerce platform according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a relationship among keywords, keyword groups, and a keyword group set according to an embodiment of the present invention;

fig. 3 is a schematic flow chart illustrating a process of determining whether to perform association analysis according to an embodiment of the present invention;

fig. 4 is a schematic flowchart of a method for performing association analysis on a keyword set to obtain cross-category association results according to an embodiment of the present invention;

fig. 5 is a schematic diagram of an optimization apparatus of an e-commerce platform according to an embodiment of the present invention;

fig. 6 is a schematic composition diagram of an association module in an optimization apparatus of an e-commerce platform according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described below with reference to the accompanying drawings.

Referring to fig. 1, an embodiment of the present invention provides a method for optimizing an e-commerce platform, where the method includes steps S100 to S300:

s100, acquiring a group of key phrases input by a user, wherein the key phrases comprise at least two key words which are mutually associated, and each key word is used for describing a commodity.

The keyword group set includes a plurality of keyword groups, each of which includes a plurality of keywords, for example, referring to fig. 2, the keyword group set includes a keyword group 1 and a keyword group 2, where the keyword group 1 includes a keyword 1, a keyword 2 and a keyword 3, and the keyword group 2 includes a keyword 1 and a keyword 4. The user inputs a keyword group in a search engine of the e-commerce platform, the keyword group comprises a plurality of commodity keywords which the user wants to purchase, and preset separators are contained among the keywords of each keyword group and comprise one of commas, pause numbers, spaces and plus numbers.

S200, searching each keyword to obtain a plurality of shops selling corresponding commodities, and taking an intersection to obtain a shop intersection list.

The keyword group is input into the search engine through the step S100, the search engine searches for each keyword, the search engine adopts a full text search mode, the shops and the commodity labels to be searched comprise fields such as shop ID, shop name, commodity ID, commodity name, commodity category and the like, and the commodity names are used as target fields of full text search to construct mapping between the search keywords and the commodity names, so that the query result is quickly returned. The search process includes: firstly, acquiring trade names related to a plurality of keywords input by a user, then searching a plurality of shops corresponding to the trade names according to the shops and commodity labels, taking intersection of the shops corresponding to the searched trade names to obtain a shop intersection list, finally calculating the relevancy and ranking grade of each shop according to the matching degree, appearance position, frequency and link quality of the shops in the list, and returning the shop intersection list to the user according to the relevancy and ranking grade in sequence.

S300, if the number of shops is not larger than a preset threshold in the obtained shop intersection list, adding the key phrase into a key phrase set, and performing association analysis on the key phrase set to obtain a cross-category association result.

Referring to fig. 3, the process of determining whether to perform association analysis on the keyword set includes steps S311 to S315:

and S311, inputting the key phrase in a search engine.

And S312, searching the shop list sold with the commodity through the commodity corresponding to the keyword in the keyword group.

S313, the shops with the intersection are taken from the obtained shop lists to obtain a shop intersection list, and whether the number of the shops in the shop intersection list exceeds a preset threshold or not is judged.

And S314, if so, directly returning the shop intersection list to be presented to the user.

And S315, if not, performing association analysis on the key phrase set.

In the store intersection list returned in step S200 or step S313, if the number of stores is greater than the preset threshold, it is indicated that the multiple commodities purchased by the user at this time may belong to the same category, and therefore, the store intersection list may be directly returned, which does not belong to the research scope of the embodiment of the present invention. If the number of the shops is not greater than the preset threshold, the commodities do not belong to the same category, and most of the shops do not sell the commodities of the categories at the same time currently. Therefore, the keyword set input by the user needs to be added into the keyword set, and the correlation analysis is performed on the keyword set to obtain the cross-category correlation result.

Referring to fig. 4, the process of performing association analysis on the keyword set to obtain cross-category association results includes steps S321 to S323:

s321, selecting a keyword group with an appearance frequency greater than or equal to the support threshold from the keyword group set.

The support degree refers to the probability of one commodity appearing in all transactions, the confidence degree belongs to the conditional probability, and the probability that a user purchases another commodity under the condition of purchasing one commodity is referred to. For example, assuming that the support threshold is 2 and the confidence threshold is 50%, the set of key phrases in the history record includes { I1, I2, I7}, { I3, I4}, { I5, I6, I8}, { I1, I5}, { I2, I4}, { I2, I3}, { I1, I6}, { I1, I3}, { I2, I3}, { I1, I3}, { I1, I3}, { I1, I5}, { I2, I5}, { I3, I5}, and { I2, I3 }.

Firstly, searching commodities with purchase frequency more than or equal to a support degree threshold value to obtain a frequent 1 item set, excluding extreme phrases { I1, I2, I7}, { I3, I4}, { I5, I6 and I8} with occurrence frequency of 1, and in the rest key phrases, the commodities with occurrence frequency more than or equal to a support degree threshold value 2 are { I1} and 6 times respectively; { I2}, 5 times; { I3}, 7 times; { I5}, 4 times, so { I1, I2, I3, I5} is a frequent 1 item set.

Then, the keyword group set containing the commodities in the frequent 1 item set is searched continuously. And respectively judging whether the support degree of each key phrase in the key phrase set is greater than or equal to a support degree threshold value, and removing the key phrases smaller than the support degree threshold value to obtain a frequent 2-item set. Searching key phrases which contain I1, I2, I3 and I5 and have the occurrence frequency greater than or equal to the support threshold value 2 in the key phrase set, namely { I1, I3}, for 3 times; { I1, I5}, 2 times; { I2, I3}, 3 times, and therefore { { I1, I3}, { I1, I5}, { I2, I3} } is a frequent 2-item set.

And similarly, searching a key phrase set containing each key phrase in the frequent 2 item set, comparing the key phrase set with the support threshold, and removing the key phrases smaller than the support threshold to obtain a frequent 3 item set. The search continues until no more key phrases consisting of more items are available. The frequent 3 item set in this example is an empty set, so there is no need to continue the search.

S322, calculating the confidence between each key word in the key word group and the key word group.

After a keyword group with the occurrence frequency of being greater than or equal to the support degree threshold is obtained, the confidence between { I1} and { I1, I3} is calculated in such a way that the support degree of { I1, I3} is divided by the support degree of { I1}, that is, 3/6 ═ 50%, the confidence between { I1} and { I1, I5} is 33.3%, the confidence between { I2} and { I2, I3} is 60%, the confidence between { I3} and { I2, I3} is 42.8%, and the confidence between { I3} and { I1, I3} is 42.8%.

S323, selecting the key phrase of which the confidence coefficient between each key word and the key phrase is greater than or equal to the support threshold as a cross-category correlation result.

The confidence threshold is 50%, so the key phrases with confidence greater than or equal to the support threshold are { I1, I3} and { I2, I3}, { I1, I3} and { I2, I3}, i.e. cross-category correlation results.

Finally, the cross-product type correlation result can be sent to shops in a non-intersection shop list in a plurality of shops selling corresponding commodities, so that the merchants are helped to explore shopping habits of users and increase selling products, and commodity sales volume is further increased.

Referring to fig. 5, an embodiment of the present invention provides an optimization apparatus for an e-commerce platform, which can be applied to the optimization method for an e-commerce platform as described above. The optimization device 123 of the e-commerce platform comprises:

the acquiring unit 100 is configured to acquire a group of keyword groups input by a user, where the keyword group includes at least two keywords related to each other, and each keyword is used to describe a product.

And the searching unit 200 is configured to search each keyword to obtain multiple shops selling corresponding goods and obtain an intersection to obtain a shop intersection list.

Optionally, a preset separator is included between the keywords of each keyword group, and the preset separator includes one of a comma, a pause, a space, and a plus.

And the association unit 300 is configured to, if the number of shops in the obtained shop intersection list is not greater than a preset threshold, add the keyword group to the keyword group set, and perform association analysis on the keyword group set to obtain a cross-item association result.

Further, referring to fig. 6, the association unit 300 includes:

a first selecting module 301, configured to select a keyword group from the keyword group set, where the occurrence frequency is greater than or equal to a support threshold.

A calculating module 302, configured to calculate a confidence between each keyword in the keyword group and the related keyword group.

The second selecting module 303 is configured to select, as the cross-product association result, a keyword group with a confidence level between each keyword and the related keyword group being greater than or equal to a support threshold.

Optionally, the optimizing device 123 of the e-commerce platform further includes: the sending unit (400) is used for sending the data,

the sending unit 400 is configured to send the cross-item-class association result to a store in a non-intersecting store list of multiple stores selling a corresponding product.

Embodiments of the present invention provide a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computer, cause the computer to perform a method of optimizing an e-commerce platform as described in fig. 1, 3 and 4.

Embodiments of the present invention provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of optimizing an e-commerce platform as described in fig. 1, 3 and 4.

The embodiment of the invention provides an optimization device of an e-commerce platform, which comprises: a processor and a memory, the memory for storing a program, the processor calling the program stored in the memory to perform the optimization method of the e-commerce platform as described in fig. 1, fig. 3 and fig. 4.

Since the optimization device, the computer-readable storage medium, and the computer program product of the e-commerce platform in the embodiments of the present invention may be applied to the method described above, the technical effects obtained by the optimization device may also refer to the method embodiments described above, and the details of the embodiments of the present invention are not repeated herein.

The above units may be individually configured processors, or may be implemented by being integrated into one of the processors of the controller, or may be stored in a memory of the controller in the form of program codes, and the functions of the above units may be called and executed by one of the processors of the controller. The processor described herein may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided by the present invention, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

Claims

1. An optimization method for an e-commerce platform is characterized by comprising the following steps:

2. The method for optimizing the e-commerce platform of claim 1, wherein a preset separator is included between the keywords of each keyword group, and the preset separator includes one of commas, pause signs, spaces and plus signs.

3. The method for optimizing an e-commerce platform according to claim 1, wherein the performing correlation analysis on the keyword group set to obtain cross-category correlation results comprises:

selecting a keyword group with the occurrence frequency being more than or equal to a support degree threshold value from the keyword group set;

calculating the confidence between each keyword in the keyword group and the related keyword group;

and selecting the key phrase of which the confidence coefficient between each key word and the key phrase belongs to is greater than or equal to a support degree threshold value as the cross-category correlation result.

4. The method for optimizing an e-commerce platform of claim 1, further comprising:

and sending the cross-product type association result to shops in a non-intersection shop list in the plurality of shops selling the corresponding commodity.

5. An apparatus for optimizing an e-commerce platform, comprising:

6. The e-commerce platform optimization device of claim 5, wherein each keyword group comprises a preset separator between the keywords, and the preset separator comprises one of comma, pause, space and plus.

7. The e-commerce platform optimization device of claim 5, wherein the association unit comprises:

a first selection module, configured to select a keyword group with an occurrence frequency greater than or equal to a support threshold from the keyword group set;

the calculation module is used for calculating the confidence between each keyword in the keyword group and the related keyword group;

and the second selection module is used for selecting the key phrase of which the confidence coefficient between each key word and the key phrase is greater than or equal to the support degree threshold value as the cross-product correlation result.

8. The e-commerce platform optimization device of claim 5, wherein the e-commerce platform optimization device further comprises:

and the sending unit is used for sending the cross-product correlation result to shops in a non-intersection shop list in the multiple shops selling the corresponding commodities.

9. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computer, cause the computer to perform the method of optimizing an e-commerce platform of any one of claims 1-4.

10. An apparatus for optimizing an e-commerce platform, comprising: a processor and a memory, the memory for storing a program, the processor calling the program stored in the memory to perform the method of optimizing an e-commerce platform of any one of claims 1 to 4.