CN114897576A - Commodity pushing method based on data analysis - Google Patents
Commodity pushing method based on data analysis Download PDFInfo
- Publication number
- CN114897576A CN114897576A CN202210478960.3A CN202210478960A CN114897576A CN 114897576 A CN114897576 A CN 114897576A CN 202210478960 A CN202210478960 A CN 202210478960A CN 114897576 A CN114897576 A CN 114897576A
- Authority
- CN
- China
- Prior art keywords
- information
- search
- data
- user
- coefficient
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims description 23
- 238000013139 quantization Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
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]
- G06Q30/0631—Item recommendations
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a commodity pushing method based on data analysis, which comprises the steps of receiving first search information of a user after receiving login information of the user; constructing a search range, finishing the first search in the search range according to the first search information, and acquiring a first data set based on the first search information; adjusting the search range according to the amount of data in the first data set. Through setting up multiple commodity introduction explanation to calling different search information, the user of being convenient for more accurately fixes a position the commodity that will search more, realizes the accurate propelling movement to search information.
Description
Technical Field
The invention relates to the technical field of e-commerce sales, in particular to a commodity pushing method based on data analysis.
Background
With the advent of the big data age, the amount of information in the network is exponentially increased, and the problem of information overload is brought. The recommendation system is one of the most effective ways to solve the information overload, and the big data recommendation system has gradually become a research hotspot in the information field. The big data based recommendation system derives the interest preference of the user by studying the historical information of the user, so that the user can be recommended with items that they may like now and in the future. The effectiveness and accuracy of the recommended data become important indexes for measuring the recommendation system, and how to ensure the accuracy of the recommended data becomes a problem to be considered by technicians firstly.
Patent document No. CN106021337A discloses an intelligent recommendation method based on big data analysis, which extracts behavior data (browsing, clicking, collecting, searching, etc.) of a user on an e-commerce application or an information platform (PC website, APP), and stores the behavior data in a big data platform; analyzing user behavior data stored in a big data platform, portraying a user, specifically, searching and obtaining a quantization value of each dimension space of a commodity concerned by the user according to a preset quantization value of the dimension space, and obtaining a weight value corresponding to each quantization value according to a click rate of the user to the dimension space; and performing matching operation with the data of the single commodity according to the quantization values of the dimension spaces of the concerned commodities of the user and the weight values corresponding to the quantization values, so as to obtain the recommendation index of the single commodity. And setting a certain recommendation index threshold, and adding the single commodity into a recommended commodity list when the recommendation index of the single commodity is greater than the recommendation index threshold.
However, when the recommendation index of any single commodity is not greater than the recommendation index threshold, the recommended commodity list for the user is empty, and the collected user data cannot be well matched with the commodity, so that the commodity recommendation pushing efficiency is affected.
Disclosure of Invention
Therefore, the invention provides a commodity pushing method based on data analysis, which can solve the technical problem that a recommendation algorithm is not matched with commodities in the prior art.
In order to achieve the above object, the present invention provides a commodity pushing method based on data analysis, including:
after receiving login information of a user, receiving first search information of the user;
constructing a search range, finishing the first search in the search range according to the first search information, and acquiring a first data set based on the first search information;
adjusting the search range according to the data amount in the first data set;
if the first data set matched with the first search information is empty in the search range, the fact that relevant commodity information is not found according to the search information of the current user is indicated, at the moment, secondary processing needs to be carried out on the first search information to form second search information, and the second search information is composed of the first search information and substitute information of the first search information;
when the second search information is formed, the number of the alternative information is determined according to the requirement of the alternative information, and a first number n1, a second number n2 and a third number n3 are preset, wherein the first number n1< the second number n2< the third number n 3;
the determining the amount of the alternative information according to the requirement on the alternative information comprises:
if the similarity degree of the semantics of the substitute information and the first search information is required to be high, selecting a first number n1 of substitute information;
if the similarity of the semantics of the required alternative information and the first search information is medium, selecting a second number n2 of alternative information;
if the similarity degree of the semantics of the required alternative information and the first search information is low, selecting a third number n3 of alternative information;
for any number of alternative information, determining the increment of the data quantity in the second data set relative to the data quantity in the first data set, which is formed by searching based on the second search information, and adjusting the search range according to the increment of the data quantity in the second data set;
if the increment of the data volume in the second data set is less than or equal to 20% of the data volume in the first data set, adjusting the search range to be 120% of the original search range;
if 80% of the data volume in the first data set is more than or equal to the increment of the data volume in the second data set and more than 20% of the data volume in the first data set, adjusting the original search range to be 180% of the original search range;
if the increment of the data amount in the second data set is greater than 80% of the data amount in the first data set, the original search range is adjusted to 200% of the original search range.
Further, when the first search information is processed for the second time, the method further comprises the steps of converting according to the language of the first search information to increase the number of the alternative information of the first search information, and then determining an adjustment coefficient of a search range according to the structure of the alternative information in the second search information;
if the number of the alternative information adopting the semantic conversion is the same as that of the alternative information adopting the language conversion in the second search information, increasing the original search range by adopting a first increment coefficient I1;
if the number of the alternative information adopting the semantic conversion is greater than the number of the alternative information adopting the language conversion, adopting the original search range;
if the number of the alternative information adopting the semantic conversion is less than the number of the alternative information adopting the language conversion, the original search range is increased by adopting a second increment coefficient I2.
Further, identity information of the user is determined according to the input login information, and the data volume of the data set in the next search period is determined according to the identity information of the user and the data volume in the current search period.
Further, a plurality of search periods are set, and the data volume of the first data set in the next search period is adjusted under the actual search condition in the current search period;
when the number of the first data sets of the next search period needs to be adjusted, a first coefficient k1, a second coefficient k2 and a third coefficient k3 are set in advance, wherein 0< k1< k2< k3<1,
and selecting a coefficient for adjusting the first data set quantity according to the age information in the user identity information.
Further, when the age information of the user is less than or equal to 18, a first coefficient k1 is selected as an adjustment coefficient of the data amount in the first data set;
when the age information of the user is more than or equal to 60 and is more than 18, selecting a second coefficient k2 as an adjusting coefficient of the data volume in the first data set;
when the age information of the user is >60, the third coefficient k2 is selected as the adjustment coefficient for the amount of data in the first data set.
Further, when the data amount D1 in the first data set is adjusted by the first coefficient k1, the adjusted data amount is D11' = D1 × (1+ k 1);
when the data amount D1 in the first data set is adjusted by the second coefficient k2, the adjusted data amount is D12' = D1 × (1+ k 2);
when the data amount D1 in the first data set is adjusted by the third coefficient k3, the adjusted data amount is D13' = D1 × (1+ k 3).
Further, the first coefficient k1= n 1/(n 1+ n2+ n 3);
the second coefficient k2= n 2/(n 1+ n2+ n 3);
the third coefficient k3= n 3/(n 1+ n2+ n 3).
Furthermore, the login information of the user is a user name and a password of the user, the login page of the user and the search page of the user are arranged on the same page, or the login information of the user is received and then the user enters the search page in different page settings, so that the login page and the search page belong to different pages, the page settings have a chronological precedence relationship, when the user enters the search page, a search frame is arranged in the search page to receive the search information input by the user, after the search information of the user is received, the search information is stored, and the search information is stored in the storage unit.
Further, the commodity benchmarking list is a corresponding relation of various language expressions of the commodity, and if the user inputs the Chinese of the first search information, the Chinese of the first search information is converted into English during secondary processing of the first search information.
Furthermore, the actual number of the search information is one, and after the corresponding page is logged in, when the search is needed, only one first search information needs to be input, wherein the first search information is a common name of a commodity.
Compared with the prior art, the method and the device have the advantages that different search information is called by setting various commodity introduction descriptions, so that a user can quickly and accurately position the commodity to be searched, and accurate pushing of the search information is realized.
Particularly, the search range is enlarged by carrying out secondary processing on the search information, so that matching based on the search information in the search range is more accurate, the push success rate of the commodities is improved, the defect that the suitable commodities cannot be matched is effectively avoided, and the search efficiency of the target product is greatly improved.
Particularly, the secondary processing of the search information is completed through the input of the primary search information of the user, the secondary processing is carried out on the search information, and the number of the alternative information with the same or similar semanteme with the search information is increased.
Particularly, the quantity of the alternative information is determined through semantic similarity conversion, effective supplement of the search information is achieved, effective matching in a search range is improved, and commodity recommendation efficiency is improved.
In particular, by determining the age information of the user, determining the section in which the age information of the user is located, and adaptively adjusting the data amount of the first data set according to the section in which the actual age of the user is located, in practical applications, the age of the user is 18 to 60 years old, the network used is frequent, and therefore the data amount generated in the age section is large, and therefore, the adjustment is performed using the second coefficient k2, achieving an effective increase in the data amount in the first data set, the network data generated by the user is relatively small for the age of the user less than 18, and the age at which the network data is generated is small, and therefore, the data information related to the user is small during the search based on the search information, and therefore, the data amount in the first data set is adjusted using the first coefficient k1, and when the age information of the user is greater than 60 years old, at this moment, the age span of the user is large, so that the time span of related information search of the user is large, the data volume D1 in the first data is adjusted by adopting the third coefficient k3, effective determination of the first data sets of the users in different age groups is effectively improved, and further matching information in a user search range is determined according to the search information, so that an accurate first data set is determined, the search accuracy of the user is improved, and the effectiveness and recommendation efficiency of commodity pushing are improved.
Particularly, the data volume D1 in the first data set is adjusted by adopting different coefficients, so that the data volume in the first data set is effectively adjusted, effective search based on search information in a search range is realized, commodity information related to the search information in the first data set is conveniently promoted, effective display and search of the commodity information are completed, the recommendation accuracy of the commodity information is improved, and the effectiveness and convenience of commodity pushing are improved.
Drawings
Fig. 1 is a schematic flow chart of a commodity pushing method based on data analysis according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1, a commodity pushing method based on data analysis according to an embodiment of the present invention includes:
step S100: after receiving login information of a user, receiving first search information of the user;
step S200: constructing a search range, finishing the first search in the search range according to the first search information, and acquiring a first data set based on the first search information;
step S300: adjusting the search range according to the amount of data in the first data set.
Specifically, the login information of the user is the user name and password of the user, the login page of the user and the search page of the user can be set on the same page, and can also be set on different pages, in practical application, the login information of the user is usually received, and then the user enters the search page, so the login page and the search page belong to different pages, the setting of the pages has a chronological precedence relationship, when the user enters the search page, a search frame is arranged in the search page to receive the search information input by the user, after the search information of the user is received, the search information is stored, and the search information is stored in a storage unit, in practical application, the search information can be Chinese or English, or any other language, the search range in the embodiment of the invention is preset according to the language of the search information, in practical application, when the data search range is determined, if the search information is Chinese, a commodity library containing Chinese introduction is selected for searching, the commodities in the commodity library contain introduction descriptions of multiple languages, and by setting multiple commodity introduction descriptions, different search information is called, so that a user can more quickly and accurately position the commodity to be searched, and accurate pushing of the search information is realized.
If the first data set matched with the first search information is empty in the search range, the fact that relevant commodity information is not found according to the search information of the current user is indicated, at the moment, secondary processing needs to be carried out on the first search information to form second search information, and the second search information is composed of the first search information and substitute information of the first search information;
when the second search information is formed, the number of the alternative information is determined according to the requirement of the alternative information, and a first number n1, a second number n2 and a third number n3 are preset, wherein the first number n1< the second number n2< the third number n 3;
the determining the amount of the alternative information according to the requirement on the alternative information comprises:
if the similarity degree of the semantics of the substitute information and the first search information is required to be high, selecting a first number n1 of substitute information;
if the similarity of the semantics of the required alternative information and the first search information is medium, selecting a second number n2 of alternative information;
if the similarity degree of the semantics of the required alternative information and the first search information is low, selecting a third number n3 of alternative information;
for any number of alternative information, determining the increment of the data quantity in the second data set relative to the data quantity in the first data set, which is formed by searching based on the second search information, and adjusting the search range according to the increment of the data quantity in the second data set;
if the increment of the data volume in the second data set is less than or equal to 20% of the data volume in the first data set, adjusting the search range to be 120% of the original search range;
if 80% of the data volume in the first data set is more than or equal to the increment of the data volume in the second data set and more than 20% of the data volume in the first data set, adjusting the original search range to be 180% of the original search range;
if the increment of the data amount in the second data set is greater than 80% of the data amount in the first data set, the original search range is adjusted to 200% of the original search range.
Specifically, the second search information in the embodiment of the present invention is composed of the first search information and the substitute information of the first search information, where the substitute information is obtained by converting according to the first search information, the requirement for the substitute information in the actual application is different, the number of conversions according to the first search information is also different, if the requirement for the substitute information is higher and the degree of similarity to the first search information must be higher, the first number n1 is selected as the number of the substitute information, if the degree of similarity to the first search information is lower, the number of the substitute information may be increased, the third number n3 is selected as the number of the substitute information, in the actual application, the degree of similarity to the semantic meaning may be determined according to the derivation relationship with the first search information, if a certain substitute information is directly derived according to the first search information, the similarity degree of the substitute information and the first search information is high, if a certain substitute information is obtained according to other substitute information, the semantic similarity degree of the substitute information and the first search information is not high, in practical application, a relationship network chart based on each search information is stored in advance, a plurality of levels of word information are arranged in the relationship network chart, the relationship network chart in the embodiment of the invention is constructed according to information such as the category and the brand of a commodity name and is formed according to information such as the commodity name, the function and the brand in an electronic website, when the search information is a sound box, the similar words as the sound box comprise a computer sound box, a notebook sound box, a HiFi sound box and the like, and the similar words as the sound box are used as first level information of the search information, and for the computer sound box in the first level information, the computer sound box of each brand is also included, such as an apple and a walker, as information of the second hierarchy, the information is searched for and searched for alternative information based on the first search information, and related goods can be efficiently searched for and efficiently pushed.
If the first data set matched with the first search information is empty in the search range, the fact that related commodity information is not found according to the search information of the current user is indicated, at the moment, secondary processing needs to be carried out on the first search information, the search range is increased, in the embodiment of the invention, in the secondary processing of the first search information, the increased search range is selected according to a preset commodity target list, in practical application, the commodity target list is in correspondence expressed by various languages of commodities, if Chinese of the first search information is input by a user, in the secondary processing of the search information, the Chinese of the search information is converted into an expression mode of English or other languages, in the embodiment of the invention, the search range is increased by carrying out secondary processing on the first search information, so that the matching based on the search information in the search range is more accurate, the success rate of pushing the commodities is improved, the defect that the suitable commodities cannot be matched is effectively avoided, and the searching efficiency of the target product is greatly improved.
Specifically, when the first search information is subjected to secondary processing, the method further comprises the steps of converting according to the language of the first search information to increase the number of the alternative information of the first search information, and then determining the adjustment coefficient of the search range according to the structure of the alternative information in the second search information;
if the number of the alternative information adopting the semantic conversion is the same as that of the alternative information adopting the language conversion in the second search information, increasing the original search range by adopting a first increment coefficient I1;
if the number of the alternative information adopting the semantic conversion is greater than the number of the alternative information adopting the language conversion, adopting the original search range;
if the number of the alternative information using the semantic conversion is less than the number of the alternative information using the language conversion, the original search range is increased by using the second increment coefficient I2.
Specifically, in the embodiment of the present invention, the user only inputs the first search information once to complete the secondary processing of the first search information, the first search information is processed twice, and the number of alternative information having the same or similar semantics as the search information is increased, in practical applications, when the first search information is processed twice, the information having the semantics similar to that of the first search information may be used as the alternative information of the first search information to form the second search information, and the first search information may also be language-converted, and obviously, after the language of the first search information is converted, the formed second search information includes the first search information and the alternative information after semantic conversion and language conversion, when the second search information is searched twice, if there are more alternative information with semantic conversion in the alternative information, the original search range may be selected for searching, if the information system of language transformation in the substitute information is more, the database, such as a foreign language database, needs to be increased by using the first incremental coefficient at this time to perform secondary search, so as to implement pushing based on the first search information, and if the number of language transformation and semantic transformation used in the substitute information is the same, the original search range is increased by using the first incremental coefficient I2.
Specifically, in the embodiment of the present invention, a sound box is taken as an example for explanation, words with close sound box semantics are taken as speakers, and when a commodity in a website is searched, and when the search is performed based on keywords, the search difference is often large due to inconsistency of publicity terms.
Specifically, in the embodiment of the invention, the matching based on the second search information and the search range is realized by adjusting the number of the alternative information and the search range, so that the optimized search result can be conveniently and quickly given, the situation of no-result display is effectively avoided, the user can be guided to consume, and the pushing efficiency of commodity pushing is improved.
Specifically, the actual quantity of the first search information is one, after a corresponding page is logged in, when a search is needed, only one search information needs to be input, in practical application, the search information can be a common name of a commodity, the embodiment of the invention increases the determination of the substitute information similar to the commodity semantics by effectively converting the semantics of the name, and after the substitute information is determined, the search information and the substitute information are all used as new search information to complete effective matching in a search range according to the new search information, so that accurate pushing of the commodity is realized.
Specifically, the embodiment of the invention determines the identity information of the user according to the input login information, and determines the data volume of the data set in the next search period according to the identity information of the user and the data volume in the current search period.
Specifically, the embodiment of the invention is provided with a plurality of search periods, and the data volume of the first data set in the next search period is adjusted under the actual search condition in the current search period;
when the number of the first data sets of the next search period needs to be adjusted, a first coefficient k1, a second coefficient k2 and a third coefficient k3 are set in advance, wherein 0< k1< k2< k3<1,
selecting a coefficient for adjusting the number of the first data sets according to age information in the user identity information;
when the age information of the user is less than or equal to 18, selecting a first coefficient k1 as an adjusting coefficient of the data amount in the first data set;
when the age information of the user is more than or equal to 60 and is more than 18, selecting a second coefficient k2 as an adjusting coefficient of the data volume in the first data set;
when the age information of the user is >60, the third coefficient k2 is selected as the adjustment coefficient for the amount of data in the first data set.
Specifically, in the embodiment of the present invention, by determining the age information of the user, determining the section where the age information of the user is located, and adaptively adjusting the data amount of the first data set according to the section where the actual age of the user is located, in practical applications, the age of the user is 18 to 60 years old, the network used is frequent, and therefore the data amount generated in the age section is large, and therefore, the adjustment is performed by using the second coefficient k2, so that the effective increase of the data amount in the first data set is achieved, and for the age of the user less than 18, the network data generated by the user is relatively small, and the age of generating the network data is small, and therefore, the data information related to the user is small during the search based on the search information, and therefore, the data amount in the first data set is adjusted by using the first coefficient k1, and when the age information of the user is larger than 60 years old, at this moment, the age span of the user is large, so that the time span of related information search of the user is large, the data volume D1 in the first data is adjusted by adopting the third coefficient k3, effective determination of the first data sets of the users in different age groups is effectively improved, and further matching information in a user search range is determined according to the search information, so that an accurate first data set is determined, the search accuracy of the user is improved, and the effectiveness and recommendation efficiency of commodity pushing are improved.
Specifically, when the data amount D1 in the first data set is adjusted by the first coefficient k1, the adjusted data amount is D11' = D1 × (1+ k 1);
when the data amount D1 in the first data set is adjusted by the second coefficient k2, the adjusted data amount is D12' = D1 × (1+ k 2);
when the data amount D1 in the first data set is adjusted by the third coefficient k3, the adjusted data amount is D13' = D1 × (1+ k 3).
In particular, the first coefficient k1= n 1/(n 1+ n2+ n 3);
the second coefficient k2= n 2/(n 1+ n2+ n 3);
the third coefficient k3= n 3/(n 1+ n2+ n 3).
Specifically, according to the embodiment of the invention, the data volume D1 in the first data set is adjusted by adopting different coefficients, so that effective adjustment of the data volume in the first data set is realized, effective search based on search information in a search range is realized, commodity information related to the search information in the first data set is conveniently promoted, effective display and search of the commodity information are completed, the recommendation precision of the commodity information is improved, and the effectiveness and convenience of commodity pushing are improved.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A commodity pushing method based on data analysis is characterized by comprising the following steps:
after receiving login information of a user, receiving first search information of the user;
constructing a search range, finishing the first search in the search range according to the first search information, and acquiring a first data set based on the first search information;
adjusting the search range according to the data amount in the first data set;
if the first data set matched with the first search information is empty in the search range, the fact that relevant commodity information is not found according to the search information of the current user is indicated, at the moment, secondary processing needs to be carried out on the first search information to form second search information, and the second search information is composed of the first search information and substitute information of the first search information;
when the second search information is formed, the number of the alternative information is determined according to the requirement of the alternative information, and a first number n1, a second number n2 and a third number n3 are preset, wherein the first number n1< the second number n2< the third number n 3;
the determining the amount of the alternative information according to the requirement on the alternative information comprises:
if the similarity degree of the semantics of the substitute information and the first search information is required to be high, selecting a first number n1 of substitute information;
if the similarity of the semantics of the required alternative information and the first search information is medium, selecting a second number n2 of alternative information;
if the similarity degree of the semantics of the required alternative information and the first search information is low, selecting a third number n3 of alternative information;
for any number of alternative information, determining the increment of the data quantity in the second data set relative to the data quantity in the first data set, which is formed by searching based on the second search information, and adjusting the search range according to the increment of the data quantity in the second data set;
if the increment of the data quantity in the second data set is less than or equal to 20 percent of the data quantity in the first data set, adjusting the search range to be 120 percent of the original search range;
if 80% of the data volume in the first data set is more than or equal to the increment of the data volume in the second data set and more than 20% of the data volume in the first data set, adjusting the original search range to be 180% of the original search range;
if the increment of the data amount in the second data set is greater than 80% of the data amount in the first data set, the original search range is adjusted to 200% of the original search range.
2. The data analysis-based commodity pushing method according to claim 1,
when the first search information is processed for the second time, the method also comprises the steps of converting according to the language of the first search information so as to increase the number of the alternative information of the first search information, and then determining the adjustment coefficient of the search range according to the structure of the alternative information in the second search information;
if the number of the alternative information adopting the semantic conversion is the same as that of the alternative information adopting the language conversion in the second search information, increasing the original search range by adopting a first increment coefficient I1;
if the number of the alternative information adopting the semantic conversion is larger than the number of the alternative information adopting the language conversion, adopting an original search range;
if the number of the alternative information using the semantic conversion is less than the number of the alternative information using the language conversion, the original search range is increased by using the second increment coefficient I2.
3. The data analysis-based commodity pushing method according to claim 2, wherein the identity information of the user is determined according to the input login information, and the data volume of the data set in the next search period is determined according to the identity information of the user and the data volume in the current search period.
4. The data analysis-based commodity pushing method according to claim 3,
setting a plurality of search periods, and adjusting the data volume of the first data set in the next search period under the actual search condition in the current search period;
when the number of the first data sets of the next search period needs to be adjusted, a first coefficient k1, a second coefficient k2 and a third coefficient k3 are set in advance, wherein 0< k1< k2< k3<1,
and selecting a coefficient for adjusting the first data set quantity according to the age information in the user identity information.
5. The data analysis-based commodity pushing method according to claim 4,
when the age information of the user is less than or equal to 18, selecting a first coefficient k1 as an adjusting coefficient of the data amount in the first data set;
when the age information of the user is more than or equal to 60 and is more than 18, selecting a second coefficient k2 as an adjusting coefficient of the data volume in the first data set;
when the age information of the user >60, the third coefficient k2 is selected as the adjustment coefficient for the amount of data in the first data set.
6. The commodity pushing method based on data analysis according to claim 5,
when the data amount D1 in the first data set is adjusted by the first coefficient k1, the adjusted data amount is D11' = D1 × (1+ k 1);
when the data amount D1 in the first data set is adjusted by the second coefficient k2, the adjusted data amount is D12' = D1 × (1+ k 2);
when the data amount D1 in the first data set is adjusted by the third coefficient k3, the adjusted data amount is D13' = D1 × (1+ k 3).
7. The data analysis-based merchandise pushing method according to claim 6,
the first coefficient k1= n 1/(n 1+ n2+ n 3);
the second coefficient k2= n 2/(n 1+ n2+ n 3);
the third coefficient k3= n 3/(n 1+ n2+ n 3).
8. The commodity pushing method based on data analysis according to claim 7, wherein the login information of the user is a user name and a password of the user, the login page of the user and the search page of the user are set on the same page, or the login information of the user is received at different page settings and then the user enters the search page, so that the login page and the search page belong to different pages, the page settings have a chronological precedence relationship, when the user enters the search page, a search box is provided in the search page to receive the search information input by the user, the search information is stored after the search information of the user is received, and the search information is stored in the storage unit.
9. The data analysis-based merchandise pushing method according to claim 8,
the commodity benchmarking list is a corresponding relation of various languages of the commodity, and if the first search information input by the user is Chinese, the Chinese of the first search information is converted into English during secondary processing of the first search information.
10. The commodity pushing method based on data analysis according to claim 9, wherein the actual number of the search information is one, and after the corresponding page is logged in, when a search is required, only one first search information needs to be input, where the first search information is a common name of a commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210478960.3A CN114897576B (en) | 2022-05-05 | 2022-05-05 | Commodity pushing method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210478960.3A CN114897576B (en) | 2022-05-05 | 2022-05-05 | Commodity pushing method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114897576A true CN114897576A (en) | 2022-08-12 |
| CN114897576B CN114897576B (en) | 2024-04-19 |
Family
ID=82719075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210478960.3A Active CN114897576B (en) | 2022-05-05 | 2022-05-05 | Commodity pushing method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114897576B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
| US20120030226A1 (en) * | 2005-05-09 | 2012-02-02 | Surfwax, Inc. | Systems and methods for using lexically-related query elements within a dynamic object for semantic search refinement and navigation |
| WO2012143839A1 (en) * | 2011-04-19 | 2012-10-26 | Greyling Abraham Carel | A computerized system and a method for processing and building search strings |
| KR101485940B1 (en) * | 2013-08-23 | 2015-01-27 | 네이버 주식회사 | Presenting System of Keyword Using depth of semantic Method Thereof |
| US20160260152A1 (en) * | 2015-03-03 | 2016-09-08 | Amazon Technologies, Inc. | Model-based replacement part system |
| CN106484721A (en) * | 2015-08-28 | 2017-03-08 | 深圳市世强先进科技有限公司 | A kind of intelligent searching system and method |
| CN108346073A (en) * | 2017-01-23 | 2018-07-31 | 北京京东尚科信息技术有限公司 | A kind of voice purchase method and device |
| US20200089808A1 (en) * | 2018-09-17 | 2020-03-19 | Ebay Inc. | Search system for providing search results using query understanding and semantic binary signatures |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| US10706450B1 (en) * | 2018-02-14 | 2020-07-07 | Amazon Technologies, Inc. | Artificial intelligence system for generating intent-aware recommendations |
| CN113129060A (en) * | 2021-04-19 | 2021-07-16 | 深圳市极客智能科技有限公司 | Offline commodity recommendation display system, method, device, equipment and storage medium |
| CN113609319A (en) * | 2021-07-26 | 2021-11-05 | 阿里巴巴（中国）有限公司 | Commodity searching method, device and equipment |
| CN113792209A (en) * | 2021-08-13 | 2021-12-14 | 唯品会(广州)软件有限公司 | Search word generation method, system and computer readable storage medium |
-
2022
- 2022-05-05 CN CN202210478960.3A patent/CN114897576B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120030226A1 (en) * | 2005-05-09 | 2012-02-02 | Surfwax, Inc. | Systems and methods for using lexically-related query elements within a dynamic object for semantic search refinement and navigation |
| KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
| WO2012143839A1 (en) * | 2011-04-19 | 2012-10-26 | Greyling Abraham Carel | A computerized system and a method for processing and building search strings |
| KR101485940B1 (en) * | 2013-08-23 | 2015-01-27 | 네이버 주식회사 | Presenting System of Keyword Using depth of semantic Method Thereof |
| US20160260152A1 (en) * | 2015-03-03 | 2016-09-08 | Amazon Technologies, Inc. | Model-based replacement part system |
| CN106484721A (en) * | 2015-08-28 | 2017-03-08 | 深圳市世强先进科技有限公司 | A kind of intelligent searching system and method |
| CN108346073A (en) * | 2017-01-23 | 2018-07-31 | 北京京东尚科信息技术有限公司 | A kind of voice purchase method and device |
| US10706450B1 (en) * | 2018-02-14 | 2020-07-07 | Amazon Technologies, Inc. | Artificial intelligence system for generating intent-aware recommendations |
| US20200089808A1 (en) * | 2018-09-17 | 2020-03-19 | Ebay Inc. | Search system for providing search results using query understanding and semantic binary signatures |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| CN113129060A (en) * | 2021-04-19 | 2021-07-16 | 深圳市极客智能科技有限公司 | Offline commodity recommendation display system, method, device, equipment and storage medium |
| CN113609319A (en) * | 2021-07-26 | 2021-11-05 | 阿里巴巴（中国）有限公司 | Commodity searching method, device and equipment |
| CN113792209A (en) * | 2021-08-13 | 2021-12-14 | 唯品会(广州)软件有限公司 | Search word generation method, system and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 孙明: "基于语义的信息检索与关联推荐关键技术研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 03, 15 March 2016 (2016-03-15), pages 138 - 7990 * |
| 张延玲: "基于Android的社区购物系统的设计与实现", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 01, pages 138 - 293 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114897576B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663254B2 (en) | System and engine for seeded clustering of news events | |
| CN109947909B (en) | Intelligent customer service response method, equipment, storage medium and device | |
| Mazandu et al. | Gene ontology semantic similarity tools: survey on features and challenges for biological knowledge discovery | |
| US9171078B2 (en) | Automatic recommendation of vertical search engines | |
| US7783630B1 (en) | Tuning of relevancy ranking for federated search | |
| US9846841B1 (en) | Predicting object identity using an ensemble of predictors | |
| US20120166438A1 (en) | System and method for recommending queries related to trending topics based on a received query | |
| KR101681109B1 (en) | An automatic method for classifying documents by using presentative words and similarity | |
| US8589231B2 (en) | Sensitivity categorization of web pages | |
| CN106383836B (en) | Attributing actionable attributes to data describing an identity of an individual | |
| WO2008144444A1 (en) | Ranking online advertisements using product and seller reputation | |
| Gomez et al. | A survey of automated hierarchical classification of patents | |
| CA2956627A1 (en) | System and engine for seeded clustering of news events | |
| CN114201598B (en) | Text recommendation method and text recommendation device | |
| KR101753768B1 (en) | A knowledge management system of searching documents on categories by using weights | |
| WO2020095357A1 (en) | Search needs assessment device, search needs assessment system, and search needs assessment method | |
| TW201243627A (en) | Multi-label text categorization based on fuzzy similarity and k nearest neighbors | |
| CN114445043B (en) | Open ecological cloud ERP-based heterogeneous graph user demand accurate discovery method and system | |
| CN115062135B (en) | Patent screening method and electronic equipment | |
| CN114897576B (en) | Commodity pushing method based on data analysis | |
| US10482128B2 (en) | Scalable approach to information-theoretic string similarity using a guaranteed rank threshold | |
| CN113571198A (en) | Conversion rate prediction method, device, equipment and storage medium | |
| CN116610853A (en) | Search recommendation method, search recommendation system, computer device, and storage medium | |
| JP2020109689A (en) | Retrieval need evaluation device, retrieval need evaluation system, and retrieval need evaluation method | |
| Huang et al. | Rough-set-based approach to manufacturing process document retrieval |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |