CN113435936A - Online and offline consumer goods recommendation method and system based on big data - Google Patents

Online and offline consumer goods recommendation method and system based on big data Download PDF

Info

Publication number
CN113435936A
CN113435936A CN202110753673.4A CN202110753673A CN113435936A CN 113435936 A CN113435936 A CN 113435936A CN 202110753673 A CN202110753673 A CN 202110753673A CN 113435936 A CN113435936 A CN 113435936A
Authority
CN
China
Prior art keywords
data
commodity
recommendation
offline
online
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
Application number
CN202110753673.4A
Other languages
Chinese (zh)
Other versions
CN113435936B (en
Inventor
朱霖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Haoman Technology Co ltd
Original Assignee
Shenzhen Haoman Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Haoman Technology Co ltd filed Critical Shenzhen Haoman Technology Co ltd
Priority to CN202110753673.4A priority Critical patent/CN113435936B/en
Publication of CN113435936A publication Critical patent/CN113435936A/en
Application granted granted Critical
Publication of CN113435936B publication Critical patent/CN113435936B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an online and offline consumer goods recommendation method and system based on big data, which comprises the steps of obtaining a trigger instruction of selecting a preset offline consumer goods shopping recommendation option, calling a prestored Apriori algorithm based on the trigger instruction to obtain online goods purchase type data and online goods consumption amount data; generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses; and generating an off-line commodity recommendation interface. In order to improve convenience, the recommended commodity store path address is generated, so that a consumer can quickly and efficiently acquire the relevant store address, the recommendation accuracy of the consumer commodity is improved, and the use experience of the shopping consumer can be improved.

Description

Online and offline consumer goods recommendation method and system based on big data
Technical Field
The application relates to the technical field of consumer goods recommendation, in particular to an online and offline consumer goods recommendation method and system based on big data.
Background
Big data, a data set mainly characterized by large capacity, multiple types, high access speed and high application value, is applied to the IT industry for the first time, and is rapidly developed into a new generation of information technology and service industry for acquiring, storing and performing association analysis on data with huge quantity, dispersed sources and various formats, discovering new knowledge, creating new value and improving new capability. The big data needs to adopt a distributed architecture to carry out distributed data mining on mass data, so distributed processing, a distributed database, cloud storage and virtualization technologies of cloud computing need to be relied on.
With the development of big data technology, the big data technology is gradually applied to consumer product recommendation, for example, in a patent document with application number CN201910727785.5, an intelligent recommendation system based on big data is disclosed, which includes a big data cloud storage system, a user uploading system and a user recommendation system; the big data cloud storage system is used for automatically storing recommended data with a large amount of praise according to the amount of praise clicked by the user and automatically deleting recommended data with a small amount of praise; the user uploading system is used for compressing various network users according to the materials to be uploaded to upload the cloud system; the user recommendation system is used for intelligently decompressing the recommendation data uploaded by the cloud end and intelligently recommending recommended users.
Although the technical scheme can effectively reduce the memory occupation of the pushed data by uniformly compressing the uploaded pushed data, and can confirm whether the pushed data with small praise number is deleted according to the praise number of the user, the space of the system memory can be well released, and the retrieval efficiency of the user on the recommended data is improved, many technologies are the same, and efficient and accurate recommendation cannot be realized, for example, accurate recommendation on-line and off-line consumer goods cannot be realized.
Obviously, the current recommendation method based on big data has the problem of low efficiency.
Disclosure of Invention
In view of the above, it is necessary to provide a big data-based online and offline consumer goods recommendation method and system capable of improving the consumer goods recommendation accuracy.
The technical scheme of the invention is as follows:
a big data based online and offline consumer goods recommendation method, the method comprising:
acquiring a trigger instruction of selecting a preset off-line consumer goods shopping recommendation option, and acquiring on-line consumer goods shopping process data of a current consumer in a specific time period based on a prestored Apriori algorithm called by the trigger instruction, wherein the consumer goods shopping process data at least comprises on-line goods purchase type data and on-line goods consumption amount data;
generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses;
and generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, wherein the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
Specifically, offline commodity shopping recommendation demand data is generated according to the online commodity purchase type data and the online commodity consumption amount data, and the offline commodity shopping recommendation demand data at least comprises offline shopping recommended commodities and recommended commodity store path addresses; the method specifically comprises the following steps:
according to the online commodity purchasing type data, acquiring current season fire-heat commodity data at the current time, and then generating similar type line commodity store data based on the online commodity purchasing type data and the current season fire-heat commodity data;
according to the online commodity consumption amount data, acquiring consumption amount range data formed after floating a specific amount by taking the online commodity consumption amount data as a center, and then generating the same type of consumption amount offline commodity store data according to the consumption amount range data;
after the commodity store data under the same type of lines and the commodity store data under the same type of consumption quota lines are obtained, an offline store data merging instruction is generated in real time;
according to the offline shop data merging instruction, data merging is carried out on the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption money, and first type shop data and second type shop data are generated;
and sequentially arranging the first type of store data and the second type of store data, and generating commodity store data under the same type of lines.
Specifically, according to the on-line commodity consumption amount data, consumption amount range data formed after floating a specific amount with the on-line commodity consumption amount data as a center is obtained, and then the same type of consumption amount off-line commodity store data is generated according to the consumption amount range data; the method specifically comprises the following steps:
acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the online commodity consumption amount data, and recording the growth ratio value as a floating amount reference ratio value;
generating an increase floating amount of the online commodity consumption amount data according to the floating amount reference proportional value;
generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data;
and generating commodity store data under the same type of consumption money line according to the consumption money range data.
Specifically, an offline commodity recommendation interface is generated according to the offline shopping recommended commodities and the recommended commodity store path addresses, and the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses, and then the method further includes:
acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data;
generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop, and setting the current commodity dissatisfaction data set as first re-recommendation reference information;
generating a current commodity link dissatisfaction data set according to the purchase failure recommended shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information;
generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information;
importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model based on the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information, and generating an upgraded consumer goods recommendation model;
and importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate the autonomous design user main body data.
Specifically, importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model based on the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information, and generating an upgraded consumer goods recommendation model; the method specifically comprises the following steps:
generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation;
classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values, and generating a priority training sequence arrangement table;
and leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model for training according to the priority training sequence arrangement table, and generating an upgraded consumer goods recommendation model.
In summary, the present invention sequentially obtains a trigger instruction selecting a preset offline shopping recommendation option of a consumable commodity, and obtains online shopping process data of the consumable commodity of a current consumer in a specific time period based on a trigger instruction invoking a prestored Apriori algorithm, wherein the shopping process data of the consumable commodity at least includes online commodity purchase type data and online commodity consumption amount data; the Apriori algorithm is a frequent item set algorithm for mining association rules, and the frequent item set is mined through two stages of candidate set generation and downward closed detection of plot, namely, shopping data of online consumer goods shopping of a current consumer in a specific time period is collected based on the Apriori algorithm, the frequent item set is mined, further, the consumer goods shopping process data is realized, the acquisition of data of online purchased goods is realized efficiently and accurately, then, online goods shopping recommendation demand data is generated according to the online goods purchase type data and the online goods consumption amount data, and the offline goods shopping recommendation demand data at least comprises offline shopping recommendation goods and recommended goods path store addresses; then, an offline commodity recommendation interface is generated according to the offline shopping recommended commodity and the recommended commodity store path address, the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodity and the recommended commodity store path address, namely, through online purchasing habits, when a purchasing body needs to purchase commodities offline, on one hand, the online commodity shopping recommendation demand data which accords with the online purchasing habits of the consuming body can be used for recommending the commodities, and meanwhile, in order to improve convenience, the recommended commodity store path address is generated, so that the consuming body can quickly and efficiently acquire the relevant store addresses, further, the recommendation accuracy of the consumer commodities is improved, and meanwhile, the use experience of the shopping consuming body can be improved.
Specifically, a big data based online and offline consumer goods recommendation system, the system comprising:
the system comprises an offline consumption module, an online consumption module and an online consumption module, wherein the offline consumption module is used for acquiring a trigger instruction of a preset offline consumption commodity shopping recommendation option, calling a prestored Apriori algorithm based on the trigger instruction to acquire online consumption commodity shopping process data of a current consumption main body in a specific time period, and the online consumption commodity shopping process data at least comprises online commodity purchase type data and online commodity consumption amount data;
the commodity purchasing module is used for generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, and the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses;
and the shopping recommending module is used for generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, and the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
Specifically, the system further comprises:
the module is used for acquiring the current-time in-season hot commodity data according to the online commodity purchasing type data, and then generating similar type line under-commodity store data based on the online commodity purchasing type data and the current-season hot commodity data;
the expense amount module is used for acquiring expense amount range data formed after floating a specific amount by taking the online commodity expense amount data as a center according to the online commodity expense amount data, and then generating the same type of expense amount off-line commodity store data according to the expense amount range data;
the shop data module is used for generating an offline shop data merging instruction in real time after acquiring the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption rates;
the data merging module is used for performing data merging on the commodity store data under the same type of lines and the commodity store data under the same type of consumption rating lines according to the off-line store data merging instruction and generating first type store data and second type store data;
and the offline type module is used for sequentially arranging the first type of store data and the second type of store data and generating similar offline commodity store data.
Specifically, the system further comprises:
the amount data module is used for acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the consumption amount data of the online commodity, and recording the growth ratio value as a floating amount reference ratio value;
the floating amount module is used for generating an increasing floating amount of the online commodity consumption amount data according to the floating amount reference proportion value;
the range data module is used for generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data;
the same type generation module is used for generating the same type of off-line commodity store data of the expense amount according to the expense amount range data;
the consumption main body module is used for acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data;
the failure commodity module is used for generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop and setting the current commodity dissatisfaction data set as first re-recommendation reference information;
the system comprises a failure purchase module, a recommendation module and a recommendation module, wherein the failure purchase module is used for generating a current commodity link dissatisfaction data set according to the purchase failure recommendation shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information;
the data set module is used for generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information;
the recommendation reference module is used for importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model and generating an upgraded consumer goods recommendation model;
the user main body module is used for importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate autonomous design user main body data;
the entropy operation module is used for generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation;
the information entropy module is used for classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values and generating a priority training sequence arrangement table;
and the priority training module is used for sequentially leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model according to the priority training sequence arrangement table for training and generating an upgraded consumer goods recommendation model.
Specifically, the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the online and offline consumer goods recommendation method based on big data when executing the computer program.
Specifically, a computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the above-described big data based online and offline consumer goods recommendation method.
The invention has the following technical effects:
the online and offline consumer goods recommendation method and system based on big data sequentially acquire a trigger instruction selecting a preset offline consumer goods shopping recommendation option, and acquire online consumer goods shopping process data of a current consumer in a specific time period based on a prestored Apriori algorithm called by the trigger instruction, wherein the consumer goods shopping process data at least comprises online goods purchase type data and online goods consumption amount data; the Apriori algorithm is a frequent item set algorithm for mining association rules, and the frequent item set is mined through two stages of candidate set generation and downward closed detection of plot, namely, shopping data of online consumer goods shopping of a current consumer in a specific time period is collected based on the Apriori algorithm, the frequent item set is mined, further, the consumer goods shopping process data is realized, the acquisition of data of online purchased goods is realized efficiently and accurately, then, online goods shopping recommendation demand data is generated according to the online goods purchase type data and the online goods consumption amount data, and the offline goods shopping recommendation demand data at least comprises offline shopping recommendation goods and recommended goods path store addresses; then, an offline commodity recommendation interface is generated according to the offline shopping recommended commodity and the recommended commodity store path address, the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodity and the recommended commodity store path address, namely, through online purchasing habits, when a purchasing body needs to purchase commodities offline, on one hand, the online commodity shopping recommendation demand data which accords with the online purchasing habits of the consuming body can be used for recommending the commodities, and meanwhile, in order to improve convenience, the recommended commodity store path address is generated, so that the consuming body can quickly and efficiently acquire the relevant store addresses, further, the recommendation accuracy of the consumer commodities is improved, and meanwhile, the use experience of the shopping consuming body can be improved.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a big data based online and offline consumer goods recommendation method;
FIG. 2 is a block diagram of an embodiment of a big data based online and offline consumer goods recommendation system;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, an application scenario of an online and offline consumer goods recommendation method based on big data is provided, in the application scenario, when a current consumer needs offline shopping, a terminal is triggered to acquire a trigger instruction selecting a preset offline consumer goods shopping recommendation option, the trigger instruction is sent to a server, the server calls a prestored Apriori algorithm based on the trigger instruction to acquire online consumer goods shopping process data of the current consumer within a specific time period, wherein the consumer goods shopping process data at least comprises online goods purchase type data and online goods consumption amount data; then, the server generates offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommended commodities and recommended commodity store path addresses; then, the terminal generates an offline commodity recommending interface according to the offline shopping recommended commodity and the recommended commodity store path address, and the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodity and the recommended commodity store path address.
Further, in this embodiment, the terminal is an input/output device connected to the computer system, and is usually far from the computer. Depending on the function, there are several categories of terminals with certain processing functions, called smart terminals or intelligent terminals, which have their own microprocessor and control circuits, while those without this function are called dumb terminals, which do not have a microprocessor. The terminal in the present application also includes a terminal supporting conversation or processing with a computer, i.e. an interactive terminal or an online terminal.
In one embodiment, as shown in fig. 1, there is provided a big data based online and offline consumer goods recommendation method, the method comprising:
step S100: acquiring a trigger instruction of selecting a preset off-line consumer goods shopping recommendation option, and acquiring on-line consumer goods shopping process data of a current consumer in a specific time period based on a prestored Apriori algorithm called by the trigger instruction, wherein the consumer goods shopping process data at least comprises on-line goods purchase type data and on-line goods consumption amount data;
specifically, in this step, the trigger instruction is obtained, that is, the user selects an offline consumable item shopping recommendation option, the offline consumable item shopping recommendation option is preset, a starting connection association relationship is pre-established for the offline consumable item shopping recommendation option, and after the trigger instruction is obtained, a pre-stored Apriori algorithm is immediately called to obtain online consumable item shopping process data of the current consumption subject in a specific time period through the starting connection association relationship.
Specifically, the Apriori algorithm is a frequent item set algorithm for mining association rules, and the frequent item set is mined through two stages of candidate set generation and downward closed detection of plot, that is, shopping data of online consumer goods shopping of a current consumer in a specific time period is collected based on the Apriori algorithm, and the frequent item set is mined, so that the consumer goods shopping process data is realized, and the acquisition of data of the online consumer goods is realized efficiently and accurately.
Further, the specific time period is preset, such as three months, half a year or a year. That is, the shopping process data of the consumer goods is a set of all data in a longer time, so that the data is more comprehensive and more conforms to the purchasing habits of current consumer bodies.
The online commodity purchase type data is data formed by purchased commodity types, such as a set of data formed by clothing commodities, living goods commodities and office goods commodities.
The online commodity consumption amount data is data of the amount spent by the current consumption main body when purchasing various types of commodities, and the online commodity consumption amount data represents the purchasing ability of the current consumption main body in a certain degree.
Step S200: generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses;
specifically, in this step, the offline commodity shopping recommendation requirement data is generated based on the online commodity purchase type data and the online commodity consumption amount data, that is, the offline commodity shopping recommendation requirement data is realized according to the online commodity purchase type data and the online commodity consumption amount data, so that the recommended offline shopping recommended commodities and the recommended commodity store path addresses are ensured to conform to the commodity purchase habit and the commodity purchasing power purchased by the current consuming body, and meanwhile, the current consuming body can timely acquire addresses of the related commodities which can be purchased by the current consuming body by generating the recommended commodity store path addresses, so that the going-ahead is facilitated, and the use experience is greatly improved.
Step S300: and generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, wherein the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
Specifically, in this step, in order to improve user experience, convenience is provided for the current consuming body, and therefore, an offline commodity recommendation interface is generated according to the offline shopping recommended commodities and the recommended commodity store path addresses, that is, the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses, so that the current consuming body can dynamically see the offline shopping recommended commodities and the recommended commodity store path addresses according to actual needs, convenience in offline shopping is improved, and efficiency in offline shopping is improved.
In one embodiment, step S200: generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses; the method specifically comprises the following steps:
step S210: according to the online commodity purchasing type data, acquiring current season fire-heat commodity data at the current time, and then generating similar type line commodity store data based on the online commodity purchasing type data and the current season fire-heat commodity data;
specifically, in this step, after the online commodity purchase type data is acquired, the commodity type with the largest purchase amount at the current time is acquired based on a big data technology, the current season hot commodity data is generated, meanwhile, commodities with commodity similarity of more than 90% in the online commodity purchase type data and the current season hot commodity data are extracted, and commodity data corresponding to the commodities are generated into similar type offline commodity store data.
Step S220: according to the online commodity consumption amount data, acquiring consumption amount range data formed after floating a specific amount by taking the online commodity consumption amount data as a center, and then generating the same type of consumption amount offline commodity store data according to the consumption amount range data;
specifically, in this step, the consumption amount range data is acquired based on the consumption amount data of the online commodity, so that purchasing power range data is generated according to purchasing power habits of the user, the flexibility of the data is ensured, and the recommendation accuracy is improved.
Therefore, the same type of consumption amount off-line commodity store data is generated according to the consumption amount range data, the purchasing power of the current consumption main body is better met, and the off-line commodity store which is more suitable for the purchasing power of the current consumption main body can be recommended.
Step S230: after the commodity store data under the same type of lines and the commodity store data under the same type of consumption quota lines are obtained, an offline store data merging instruction is generated in real time;
step S240: according to the offline shop data merging instruction, data merging is carried out on the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption money, and first type shop data and second type shop data are generated;
specifically, in this step, by generating an offline shop data merging instruction, data merging is performed on the offline commodity shop data of the same type and the offline commodity shop data of the same type of consumption price according to the offline shop data merging instruction, that is, by data processing, a shop with the same type of offline commodity shop data and the same type of offline commodity shop data in the offline commodity shop data of the same type is screened.
Further, the first type of store data is data corresponding to the same store in the same type of offline commercial store data and the same type of consuming fee offline commercial store data.
And for the second type of store data, the first stores which accord with the consumption habits of the current consumption subjects in the similar type of offline commodity store data and the similar type of consumption fee offline commodity store data are set according to actual requirements, and are not limited specifically.
Step S250: and sequentially arranging the first type of store data and the second type of store data, and generating commodity store data under the same type of lines.
Specifically, in this step, efficient and orderly display of data is realized by sequential arrangement, and then generation of commodity store data under the same type of lines is realized.
In one embodiment, step S220: according to the online commodity consumption amount data, acquiring consumption amount range data formed after floating a specific amount by taking the online commodity consumption amount data as a center, and then generating the same type of consumption amount offline commodity store data according to the consumption amount range data; the method specifically comprises the following steps:
step S221: acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the online commodity consumption amount data, and recording the growth ratio value as a floating amount reference ratio value;
step S222: generating an increase floating amount of the online commodity consumption amount data according to the floating amount reference proportional value;
step S223: generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data;
step S224: and generating commodity store data under the same type of consumption money line according to the consumption money range data.
Specifically, in this step, according to the online commodity consumption amount data, a growth ratio value of the consumption amount of the current consumption subject in a specific time period is obtained, taking the specific time period as 6 months as an example, the single-month growth ratio between two adjacent months is calculated step by step, and then an average value of the single-month growth ratios is obtained and recorded as the growth ratio value. Then, the growth rate value is recorded as a floating amount reference rate value.
Then, if the reference proportion value of the floating amount is 13%, calculating an average monthly consumption amount within a specific time period, for example 10000, according to the reference proportion value of the floating amount and the increase floating amount for generating the data of the online commodity consumption amount, and multiplying the average monthly consumption amount by the reference proportion value of the floating amount, wherein the average monthly consumption amount is 1300. Further, generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data, wherein the consumption amount range data is 10000-13000.
Furthermore, commodity store data under the same type of consumption money line is generated according to the consumption money range data, namely, the corresponding store is recommended according to the grade of the purchasing power of 10000 + 13000.
In one embodiment, step S300: generating an offline commodity recommendation interface according to the offline shopping recommended commodity and the recommended commodity store path address, wherein the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodity and the recommended commodity store path address, and then the method further comprises the following steps:
step S410: acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data;
step S420: generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop, and setting the current commodity dissatisfaction data set as first re-recommendation reference information;
step S430: generating a current commodity link dissatisfaction data set according to the purchase failure recommended shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information;
step S440: generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information;
step S450: importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model based on the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information, and generating an upgraded consumer goods recommendation model;
step S460: and importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate the autonomous design user main body data.
Specifically, in this step, the purchase failure product data is a data set of products that have been recommended but not currently purchased by the consuming body. The purchase failure recommendation store is a data set of stores that are recommended but not currently consumed by the consuming body. The data of the unsatisfied purchasing link is a link which is made by the shop and enables the current consuming main body to be unsatisfied in the process of purchasing the commodities and fed back by the current consuming main body, such as poor service attitude in a fitting link. The purchase path dissatisfaction data is a set of dissatisfaction information which is considered by current consumers to be caused by insufficient convenience according to the recommended path.
Therefore, a current commodity dissatisfaction data set is generated according to the purchase failure commodity data and the purchase failure recommended store, a current commodity link dissatisfaction data set is generated according to the purchase failure recommended store and the purchase dissatisfaction link data, and a current commodity path dissatisfaction data set is generated according to the purchase failure recommended store and the purchase path dissatisfaction data, namely the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information are respectively obtained.
Further, the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information are imported into a preset original consumer goods recommendation model, an upgraded consumer goods recommendation model is generated, training of the original consumer goods recommendation model according to actual feedback data information is achieved, the intelligent degree of the original consumer goods recommendation model is improved, and the original consumer goods recommendation model is preset.
In addition, the current main body basic data information of the current consumption main body is imported into the upgraded consumption commodity recommendation model, and the independently designed user main body data is generated, so that each user main body corresponds to one data, and the privacy of the user is improved.
In one embodiment, step S450: importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model based on the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information, and generating an upgraded consumer goods recommendation model; the method specifically comprises the following steps:
step S451: generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation;
step S452: classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values, and generating a priority training sequence arrangement table;
step S453: and leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model for training according to the priority training sequence arrangement table, and generating an upgraded consumer goods recommendation model.
Specifically, in this step, the first actual information entropy, the second actual information entropy, and the third actual information entropy are classified according to the magnitude of entropy values, a priority training sequence arrangement table is generated, and then the first actual information entropy, the second actual information entropy, and the third actual information entropy are sequentially led into a preset original consumer goods recommendation model according to the priority training sequence arrangement table for training, so as to achieve training orderliness.
In summary, the present invention sequentially obtains a trigger instruction selecting a preset offline shopping recommendation option of a consumable commodity, and obtains online shopping process data of the consumable commodity of a current consumer in a specific time period based on a trigger instruction invoking a prestored Apriori algorithm, wherein the shopping process data of the consumable commodity at least includes online commodity purchase type data and online commodity consumption amount data; the Apriori algorithm is a frequent item set algorithm for mining association rules, and the frequent item set is mined through two stages of candidate set generation and downward closed detection of plot, namely, shopping data of online consumer goods shopping of a current consumer in a specific time period is collected based on the Apriori algorithm, the frequent item set is mined, further, the consumer goods shopping process data is realized, the acquisition of data of online purchased goods is realized efficiently and accurately, then, online goods shopping recommendation demand data is generated according to the online goods purchase type data and the online goods consumption amount data, and the offline goods shopping recommendation demand data at least comprises offline shopping recommendation goods and recommended goods path store addresses; then, an offline commodity recommendation interface is generated according to the offline shopping recommended commodity and the recommended commodity store path address, the offline commodity recommendation interface is used for dynamically displaying the offline shopping recommended commodity and the recommended commodity store path address, namely, through online purchasing habits, when a purchasing body needs to purchase commodities offline, on one hand, the online commodity shopping recommendation demand data which accords with the online purchasing habits of the consuming body can be used for recommending the commodities, and meanwhile, in order to improve convenience, the recommended commodity store path address is generated, so that the consuming body can quickly and efficiently acquire the relevant store addresses, further, the recommendation accuracy of the consumer commodities is improved, and meanwhile, the use experience of the shopping consuming body can be improved.
In one embodiment, as shown in FIG. 2, a big data based online and offline consumer goods recommendation system, the system comprising:
the system comprises an offline consumption module, an online consumption module and an online consumption module, wherein the offline consumption module is used for acquiring a trigger instruction of a preset offline consumption commodity shopping recommendation option, calling a prestored Apriori algorithm based on the trigger instruction to acquire online consumption commodity shopping process data of a current consumption main body in a specific time period, and the online consumption commodity shopping process data at least comprises online commodity purchase type data and online commodity consumption amount data;
the commodity purchasing module is used for generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, and the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses;
and the shopping recommending module is used for generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, and the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
Specifically, the system further comprises:
the module is used for acquiring the current-time in-season hot commodity data according to the online commodity purchasing type data, and then generating similar type line under-commodity store data based on the online commodity purchasing type data and the current-season hot commodity data;
the expense amount module is used for acquiring expense amount range data formed after floating a specific amount by taking the online commodity expense amount data as a center according to the online commodity expense amount data, and then generating the same type of expense amount off-line commodity store data according to the expense amount range data;
the shop data module is used for generating an offline shop data merging instruction in real time after acquiring the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption rates;
the data merging module is used for performing data merging on the commodity store data under the same type of lines and the commodity store data under the same type of consumption rating lines according to the off-line store data merging instruction and generating first type store data and second type store data;
and the offline type module is used for sequentially arranging the first type of store data and the second type of store data and generating similar offline commodity store data.
In one embodiment, the system further comprises:
the amount data module is used for acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the consumption amount data of the online commodity, and recording the growth ratio value as a floating amount reference ratio value;
the floating amount module is used for generating an increasing floating amount of the online commodity consumption amount data according to the floating amount reference proportion value;
the range data module is used for generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data;
the same type generation module is used for generating the same type of off-line commodity store data of the expense amount according to the expense amount range data;
the consumption main body module is used for acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data;
the failure commodity module is used for generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop and setting the current commodity dissatisfaction data set as first re-recommendation reference information;
the system comprises a failure purchase module, a recommendation module and a recommendation module, wherein the failure purchase module is used for generating a current commodity link dissatisfaction data set according to the purchase failure recommendation shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information;
the data set module is used for generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information;
the recommendation reference module is used for importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model and generating an upgraded consumer goods recommendation model;
the user main body module is used for importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate autonomous design user main body data;
the entropy operation module is used for generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation;
the information entropy module is used for classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values and generating a priority training sequence arrangement table;
and the priority training module is used for sequentially leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model according to the priority training sequence arrangement table for training and generating an upgraded consumer goods recommendation model.
In one embodiment, as shown in fig. 3, a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the big data based online and offline consumer goods recommendation method when executing the computer program.
In one embodiment, the processor is configured to perform the steps of:
acquiring a trigger instruction of selecting a preset off-line consumer goods shopping recommendation option, and acquiring on-line consumer goods shopping process data of a current consumer in a specific time period based on a prestored Apriori algorithm called by the trigger instruction, wherein the consumer goods shopping process data at least comprises on-line goods purchase type data and on-line goods consumption amount data; generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses; and generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, wherein the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses. According to the online commodity purchasing type data, acquiring current season fire-heat commodity data at the current time, and then generating similar type line commodity store data based on the online commodity purchasing type data and the current season fire-heat commodity data; according to the online commodity consumption amount data, acquiring consumption amount range data formed after floating a specific amount by taking the online commodity consumption amount data as a center, and then generating the same type of consumption amount offline commodity store data according to the consumption amount range data; after the commodity store data under the same type of lines and the commodity store data under the same type of consumption quota lines are obtained, an offline store data merging instruction is generated in real time; according to the offline shop data merging instruction, data merging is carried out on the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption money, and first type shop data and second type shop data are generated; and sequentially arranging the first type of store data and the second type of store data, and generating commodity store data under the same type of lines. Acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the online commodity consumption amount data, and recording the growth ratio value as a floating amount reference ratio value; generating an increase floating amount of the online commodity consumption amount data according to the floating amount reference proportional value; generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data; and generating commodity store data under the same type of consumption money line according to the consumption money range data.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described big-data-based online-offline consumer goods recommendation method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. An online and offline consumer goods recommendation method based on big data is characterized by comprising the following steps:
acquiring a trigger instruction of selecting a preset off-line consumer goods shopping recommendation option, and acquiring on-line consumer goods shopping process data of a current consumer in a specific time period based on a prestored Apriori algorithm called by the trigger instruction, wherein the consumer goods shopping process data at least comprises on-line goods purchase type data and on-line goods consumption amount data; generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, wherein the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses; and generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, wherein the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
2. The big-data-based online-offline consumer goods recommendation method according to claim 1, wherein offline commodity shopping recommendation demand data is generated according to the online commodity purchase type data and the online commodity consumption amount data, the offline commodity shopping recommendation demand data including at least an offline shopping recommended commodity and a recommended commodity store path address; the method specifically comprises the following steps:
according to the online commodity purchasing type data, acquiring current season fire-heat commodity data at the current time, and then generating similar type line commodity store data based on the online commodity purchasing type data and the current season fire-heat commodity data; according to the online commodity consumption amount data, acquiring consumption amount range data formed after floating a specific amount by taking the online commodity consumption amount data as a center, and then generating the same type of consumption amount offline commodity store data according to the consumption amount range data; after the commodity store data under the same type of lines and the commodity store data under the same type of consumption quota lines are obtained, an offline store data merging instruction is generated in real time; according to the offline shop data merging instruction, data merging is carried out on the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption money, and first type shop data and second type shop data are generated; and sequentially arranging the first type of store data and the second type of store data, and generating commodity store data under the same type of lines.
3. The big-data-based online and offline consumer goods recommendation method according to claim 2, wherein according to the online goods consumption amount data, consumption amount range data formed by floating a specific amount with the online goods consumption amount data as a center is acquired, and then the same type of consumption amount offline commodity store data is generated according to the consumption amount range data; the method specifically comprises the following steps:
acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the online commodity consumption amount data, and recording the growth ratio value as a floating amount reference ratio value; generating an increase floating amount of the online commodity consumption amount data according to the floating amount reference proportional value; generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data; and generating commodity store data under the same type of consumption money line according to the consumption money range data.
4. The big-data-based online and offline consumer goods recommendation method according to any one of claims 1 to 3, wherein an offline goods recommendation interface is generated according to the offline shopping recommended goods and the recommended goods store path address, the offline goods recommendation interface is used for dynamically displaying the offline shopping recommended goods and the recommended goods store path address, and then the method further comprises:
acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data; generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop, and setting the current commodity dissatisfaction data set as first re-recommendation reference information; generating a current commodity link dissatisfaction data set according to the purchase failure recommended shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information; generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information; importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model based on the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information, and generating an upgraded consumer goods recommendation model; and importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate the autonomous design user main body data.
5. The online and offline consumer goods recommendation method based on big data as claimed in claim 4, wherein the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information are imported into a preset original consumer goods recommendation model, and an upgraded consumer goods recommendation model is generated; the method specifically comprises the following steps:
generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation; classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values, and generating a priority training sequence arrangement table; and leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model for training according to the priority training sequence arrangement table, and generating an upgraded consumer goods recommendation model.
6. An online-offline consumer goods recommendation system based on big data, the system comprising:
the system comprises an offline consumption module, an online consumption module and an online consumption module, wherein the offline consumption module is used for acquiring a trigger instruction of a preset offline consumption commodity shopping recommendation option, calling a prestored Apriori algorithm based on the trigger instruction to acquire online consumption commodity shopping process data of a current consumption main body in a specific time period, and the online consumption commodity shopping process data at least comprises online commodity purchase type data and online commodity consumption amount data;
the commodity purchasing module is used for generating offline commodity shopping recommendation demand data according to the online commodity purchasing type data and the online commodity consumption amount data, and the offline commodity shopping recommendation demand data at least comprises offline shopping recommendation commodities and recommended commodity store path addresses;
and the shopping recommending module is used for generating an offline commodity recommending interface according to the offline shopping recommended commodities and the recommended commodity store path addresses, and the offline commodity recommending interface is used for dynamically displaying the offline shopping recommended commodities and the recommended commodity store path addresses.
7. The big-data based online-offline consumer goods recommendation system according to claim 6, further comprising:
the module is used for acquiring the current-time in-season hot commodity data according to the online commodity purchasing type data, and then generating similar type line under-commodity store data based on the online commodity purchasing type data and the current-season hot commodity data;
the expense amount module is used for acquiring expense amount range data formed after floating a specific amount by taking the online commodity expense amount data as a center according to the online commodity expense amount data, and then generating the same type of expense amount off-line commodity store data according to the expense amount range data;
the shop data module is used for generating an offline shop data merging instruction in real time after acquiring the offline commodity shop data of the same type of lines and the offline commodity shop data of the same type of consumption rates;
the data merging module is used for performing data merging on the commodity store data under the same type of lines and the commodity store data under the same type of consumption rating lines according to the off-line store data merging instruction and generating first type store data and second type store data;
and the offline type module is used for sequentially arranging the first type of store data and the second type of store data and generating similar offline commodity store data.
8. The big-data based online-offline consumer goods recommendation system according to claim 6, further comprising:
the amount data module is used for acquiring a growth ratio value of the consumption amount of the current consumption subject in a specific time period according to the consumption amount data of the online commodity, and recording the growth ratio value as a floating amount reference ratio value;
the floating amount module is used for generating an increasing floating amount of the online commodity consumption amount data according to the floating amount reference proportion value;
the range data module is used for generating consumption amount range data according to the increase floating amount and the average consumption amount value in the online commodity consumption amount data;
the same type generation module is used for generating the same type of off-line commodity store data of the expense amount according to the expense amount range data;
the consumption main body module is used for acquiring an unsatisfactory information data set of the current consumption main body after purchasing the off-line shopping recommended commodity according to the recommended commodity store path address, wherein the unsatisfactory information data set comprises purchase failure commodity data, purchase failure recommended stores, purchase unsatisfactory link data and purchase path unsatisfactory data;
the failure commodity module is used for generating a current commodity dissatisfaction data set according to the purchase failure commodity data and the purchase failure recommendation shop and setting the current commodity dissatisfaction data set as first re-recommendation reference information;
the system comprises a failure purchase module, a recommendation module and a recommendation module, wherein the failure purchase module is used for generating a current commodity link dissatisfaction data set according to the purchase failure recommendation shop and the purchase dissatisfaction link data, and setting the current commodity link dissatisfaction data set as second re-recommendation reference information;
the data set module is used for generating a current commodity path dissatisfaction data set according to the purchase failure recommended shop and the purchase path dissatisfaction data, and setting the current commodity path dissatisfaction data set as third re-recommendation reference information;
the recommendation reference module is used for importing the first re-recommendation reference information, the second re-recommendation reference information and the third re-recommendation reference information into a preset original consumer goods recommendation model and generating an upgraded consumer goods recommendation model;
the user main body module is used for importing the current main body basic data information of the current consumption main body into the upgraded consumption commodity recommendation model to generate autonomous design user main body data;
the entropy operation module is used for generating a first actual information entropy according to the first re-recommendation reference information through preset entropy operation, generating a second actual information entropy according to the second re-recommendation reference information through preset entropy operation, and generating a third actual information entropy according to the third re-recommendation reference information through preset entropy operation;
the information entropy module is used for classifying the first actual information entropy, the second actual information entropy and the third actual information entropy according to the magnitude of entropy values and generating a priority training sequence arrangement table;
and the priority training module is used for sequentially leading the first actual information entropy, the second actual information entropy and the third actual information entropy into a preset original consumer goods recommendation model according to the priority training sequence arrangement table for training and generating an upgraded consumer goods recommendation model.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
CN202110753673.4A 2021-07-02 2021-07-02 Online and offline consumer goods recommendation method and system based on big data Active CN113435936B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110753673.4A CN113435936B (en) 2021-07-02 2021-07-02 Online and offline consumer goods recommendation method and system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110753673.4A CN113435936B (en) 2021-07-02 2021-07-02 Online and offline consumer goods recommendation method and system based on big data

Publications (2)

Publication Number Publication Date
CN113435936A true CN113435936A (en) 2021-09-24
CN113435936B CN113435936B (en) 2022-09-06

Family

ID=77758880

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110753673.4A Active CN113435936B (en) 2021-07-02 2021-07-02 Online and offline consumer goods recommendation method and system based on big data

Country Status (1)

Country Link
CN (1) CN113435936B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117710034A (en) * 2023-12-12 2024-03-15 贵州果卡科技有限公司 Advertisement pushing method and system for online fruit mall
CN117745338A (en) * 2024-02-20 2024-03-22 山东浪潮数字商业科技有限公司 Wine consumption prediction method based on curvelet transformation, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107767154A (en) * 2016-08-18 2018-03-06 中国电信股份有限公司 Information-pushing method, platform and system
CN107862585A (en) * 2017-12-04 2018-03-30 谷德嘉 On-line off-line purchase method and purchase system
CN108876526A (en) * 2018-06-06 2018-11-23 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device and computer readable storage medium
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN109636454A (en) * 2018-12-05 2019-04-16 广州市弹弹旦电子商务有限公司 A kind of commodity method for pushing based on zone user habit big data
CN112200636A (en) * 2020-10-24 2021-01-08 朱丽勤 Intelligent shopping recommendation method based on big data
KR102234751B1 (en) * 2020-08-18 2021-03-31 최우석 Customer-specific cosmetic recommendation system that analyzes the customer's cosmetic purchase history with artificial intelligence and makes personalized recommendations

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107767154A (en) * 2016-08-18 2018-03-06 中国电信股份有限公司 Information-pushing method, platform and system
CN107862585A (en) * 2017-12-04 2018-03-30 谷德嘉 On-line off-line purchase method and purchase system
CN108876526A (en) * 2018-06-06 2018-11-23 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device and computer readable storage medium
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN109636454A (en) * 2018-12-05 2019-04-16 广州市弹弹旦电子商务有限公司 A kind of commodity method for pushing based on zone user habit big data
KR102234751B1 (en) * 2020-08-18 2021-03-31 최우석 Customer-specific cosmetic recommendation system that analyzes the customer's cosmetic purchase history with artificial intelligence and makes personalized recommendations
CN112200636A (en) * 2020-10-24 2021-01-08 朱丽勤 Intelligent shopping recommendation method based on big data

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117710034A (en) * 2023-12-12 2024-03-15 贵州果卡科技有限公司 Advertisement pushing method and system for online fruit mall
CN117745338A (en) * 2024-02-20 2024-03-22 山东浪潮数字商业科技有限公司 Wine consumption prediction method based on curvelet transformation, electronic equipment and storage medium
CN117745338B (en) * 2024-02-20 2024-05-03 山东浪潮数字商业科技有限公司 Wine consumption prediction method based on curvelet transformation, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN113435936B (en) 2022-09-06

Similar Documents

Publication Publication Date Title
CN113435936B (en) Online and offline consumer goods recommendation method and system based on big data
CN108205768B (en) Database establishing method, data recommending device, equipment and storage medium
CN111080413A (en) E-commerce platform commodity recommendation method and device, server and storage medium
CN107332910B (en) Information pushing method and device
AU2017268629A1 (en) Collaborative filtering method, apparatus, server and storage medium in combination with time factor
CN111445134A (en) Commodity sales prediction method, commodity sales prediction apparatus, computer device, and storage medium
CN109300003A (en) Enterprise's recommended method, device, computer equipment and storage medium
CN111738805B (en) Behavior log-based search recommendation model generation method, device and storage medium
CN111127152A (en) Commodity recommendation method, device and equipment based on user preference prediction and readable medium
CN111737418A (en) Method, apparatus and storage medium for predicting relevance of search term and commodity
CN109254980A (en) Method, apparatus, computer equipment and the storage medium of Customer Score sequence
KR20180113111A (en) Apparatus and method for generating prediction information based on a keyword search volume
CN110880127A (en) Consumption level prediction method and device, electronic equipment and storage medium
CN113689259A (en) Commodity personalized recommendation method and system based on user behaviors
CN111160566A (en) Sample generation method and device, computer readable storage medium and computer equipment
CN110858377B (en) Information processing method, page display method, system and equipment
CN114219376A (en) Household appliance large-scale customized service resource scheduling method based on knowledge graph
CN111523914A (en) User satisfaction evaluation method, device and system and data display platform
CN114579843A (en) Personalized search method and device, computer equipment and storage medium
CN110889748B (en) Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium
CN117194764A (en) Goods display method, equipment and medium based on multi-platform fusion mall
CN115760275A (en) Intelligent product sale recommendation method and system for e-commerce platform
CN114565422A (en) Warehouse sales prediction method and device, storage medium and equipment
CN114820113A (en) E-commerce platform recommendation adjustment method and system based on block chain
CN112488771B (en) Method, apparatus, device and storage medium for automatically setting commodity price

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