CN114418663A - Commodity information processing method and device, computer equipment and storage medium - Google Patents
Commodity information processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114418663A CN114418663A CN202111509491.9A CN202111509491A CN114418663A CN 114418663 A CN114418663 A CN 114418663A CN 202111509491 A CN202111509491 A CN 202111509491A CN 114418663 A CN114418663 A CN 114418663A
- Authority
- CN
- China
- Prior art keywords
- data
- commodity
- preset
- frequent item
- offline
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a commodity information processing method, a commodity information processing device, computer equipment and a storage medium, wherein the method comprises the steps of acquiring online data and offline data of a commodity; importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data; based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set; importing the online data and the offline data into a commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model; and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information. The association rule and the commodity recommendation information of the commodities are generated by combining the online data and the offline data, the offline commodities can be subjected to inventory management according to the online attention degree, the inventory pressure is reduced, the commodity recommendation can be more accurate, the commodity purchasing experience of a user is greatly optimized, and the commodity sales efficiency is effectively improved.
Description
Technical Field
The present invention relates to the field of commodity information processing technologies, and in particular, to a commodity information processing method and apparatus, a computer device, and a storage medium.
Background
At present, along with the internet development, more and more people select to buy commodities on the internet, although the online shopping provides great convenience for us, but because the user can not see the real object, the commodity information can not be further understood, the user can buy the commodities under the condition that the commodity is not sufficiently understood, and the online store can directly watch and experience the customer, but the online store can not match the demand of the user due to the lack of the understanding of the demand of the user, so that the user can not buy the proper commodities on the online store, and in the past, the stock pressure of the online store is increased.
Disclosure of Invention
In view of the above, it is necessary to provide a commodity information processing method, apparatus, computer device and storage medium in order to solve the above technical problems.
A commodity information processing method comprising:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
In one embodiment, the step of importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating the commodity recommendation information through the commodity recommendation model includes:
preprocessing the online data and the offline data to obtain preprocessed data;
importing the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data;
detecting whether the error of each active neuron is smaller than a preset error threshold value or not;
when the error of the active neuron is smaller than the preset error threshold value, eliminating the active neuron; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold;
and constructing the commodity recommendation model based on the fused plurality of active neurons.
In one embodiment, the step of importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data includes:
classifying the online data and the offline data according to a preset classification rule to obtain classified data;
and importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
In one embodiment, the step of importing the classification data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classification data includes:
counting the occurrence frequency of each classification data;
calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion;
screening the classified data with the data proportion larger than a preset proportion to obtain screened data;
and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
In one embodiment, the step of calculating the association rule of each commodity according to the frequent item set based on a preset association rule algorithm includes:
calculating an imbalance factor of each commodity by using an imbalance factor algorithm;
rejecting the commodities with the unbalance factors larger than preset factors;
and calculating to obtain the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
In one embodiment, the preset frequent item set mining algorithm includes an FP Tree algorithm and an Apriori algorithm.
In one embodiment, the offline data of the commodity is acquired through a preset sensor.
A commodity information processing apparatus comprising:
the commodity data acquisition module is used for acquiring online data and offline data of commodities;
a frequent item set calculation obtaining module, configured to import the online data and the offline data into a preset frequent item set mining algorithm, so as to obtain frequent item sets of the online data and the offline data;
the association rule obtaining module is used for calculating and obtaining the association rule of each commodity according to the frequent item set based on a preset association rule algorithm;
the recommendation information obtaining module is used for importing the online data and the offline data into a pre-constructed commodity recommendation model and calculating commodity recommendation information through the commodity recommendation model;
and the commodity recommendation scheme generating module is used for generating a commodity recommendation scheme based on the association rule and the commodity recommendation information and outputting the commodity recommendation scheme.
A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
According to the commodity information processing method, the commodity information processing device, the computer equipment and the storage medium, the association rule and the commodity recommendation information of the commodity are generated by combining the online data and the offline data, so that the commodity sold online can be recommended according to the attention degree of the offline user, the commodity sold offline can also be subjected to inventory management according to the attention degree of the online user, the inventory pressure is reduced, the commodity recommendation can be more accurate, the commodity purchasing experience of the user is greatly optimized, and the commodity sales efficiency is effectively improved.
Drawings
FIG. 1 is a flowchart illustrating a method for processing merchandise information according to an embodiment;
FIG. 2 is a block diagram showing a configuration of a commodity information processing apparatus according to an embodiment;
FIG. 3 is a diagram of the internal structure of a computer device in one embodiment;
FIG. 4A is a diagram illustrating a process for generating association rules for a good according to one embodiment;
FIG. 4B is a diagram illustrating a process of constructing a product recommendation model for a product according to an embodiment;
fig. 4C is a schematic diagram of a process of generating a commodity recommendation scheme for a commodity in one 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.
Example one
In this embodiment, as shown in fig. 1, a commodity information processing method is provided, which includes:
and step 110, acquiring online data and offline data of the commodity.
In this embodiment, the online data is data corresponding to a commodity sold on an online network platform, and the online data at least includes browsing data, click data, sales data, and positioning data, for example, the browsing data includes the number of times that a user browses a commodity page and the browsing duration of a single user, the click data includes the number of times that a link of the commodity is clicked, the sales data includes the sales volume of the commodity, and the positioning data includes the position of the user browsing the commodity page or purchasing the commodity.
The offline data is data corresponding to commodities sold by the offline pads, the offline data at least comprises attention data and purchase data, the attention data is data of a user paying attention to a certain commodity, and the attention data can comprise average staying time of the user before staying in the commodity and times of the user before going to and fro the commodity. The focus data reflects the degree of interest of the user in the merchandise. The purchase data is an amount of the item purchased by the user.
In this embodiment, the online data of the commodity can be acquired by acquiring data of the network platform, the offline data can be acquired by the sensor, and in one embodiment, the offline data of the commodity is acquired by the preset sensor. The preset sensor may include an infrared sensor, an iris sensor, and a photosensitive element, where the sensory element includes a camera, for example, the infrared sensor is used to detect the user staying in front of the commodity and passing through the commodity, the iris sensor is used to detect whether the users who go back and forth many times are the same user, and accordingly, the number of times the user goes back and forth is counted, and the camera is used to obtain a face image of the user or to detect the number of users staying in or passing through the commodity.
And 120, importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data.
In this embodiment, the preset frequent item set mining algorithm is used to calculate a frequent item set of each commodity, where the frequent item set is a set of commodities with a support degree greater than or equal to a minimum support degree.
In one embodiment, the preset frequent item set mining algorithm includes a FP Tree algorithm and an Apriori algorithm.
In this embodiment, a preset frequent item set mining algorithm is further explained as an FP (frequency pattern) Tree algorithm, the FP Tree algorithm is also called an FP-growth or FP growth algorithm, the online data and the offline data respectively construct an FP Tree of commodity information through the FP Tree algorithm, and then the FP Tree searches for a condition pattern, so as to construct a creation condition FP Tree, and finally a frequent item set is obtained.
In one embodiment, the step of importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data includes: classifying the online data and the offline data according to a preset classification rule to obtain classified data; and importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
Specifically, the classification data respectively construct an FP Tree of the commodity information through an FP Tree algorithm, and then the FP Tree searches for a condition pattern, so as to construct a condition creating FP Tree, and finally a frequent item set is obtained.
And step 130, calculating to obtain association rules of the commodities according to the frequent item set based on a preset association rule algorithm.
In one embodiment, the preset association rule algorithm is an algorithm based on the Kulc criterion.
In this embodiment, the association relationship between the commodities is calculated by an algorithm based on the Kulc criterion according to the different frequent item sets obtained in the previous step, so as to obtain the association rule of the commodities. The association rule is used to reflect the association relationship between the commodities, for example, after the user purchases the commodity a, the user also typically purchases the commodity B, and there is an association relationship between the commodity a and the commodity B, so as to serve as a commodity recommendation scheme, after the user purchases the commodity a, the user can recommend the commodity B or the similar product of the commodity B.
And 140, importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model.
In this embodiment, a large amount of online data and offline data are imported into a pre-constructed commodity recommendation model, and commodity recommendation information is obtained through calculation, and is used for recommending commodities and recommending commodities with high demand and high heat to a user.
And 150, generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
In the embodiment, the commodity recommendation scheme is generated by combining the association rule of the commodity and the commodity recommendation information, and is output to the online network platform and the offline store, so that the online network platform can push the commodity to the user according to the commodity recommendation scheme, the offline store can manage the inventory according to the commodity recommendation scheme, the inventory overstock is reduced, and the shopping guide screen can display the information of the recommended commodity, thereby greatly optimizing the commodity purchasing experience of the user, and effectively improving the commodity sales efficiency.
In the embodiment, the association rule and the commodity recommendation information of the commodity are generated by combining the online data and the offline data, so that the commodity sold online can be recommended according to the attention degree of the offline user, the commodity sold offline can also be subjected to inventory management according to the attention degree of the online user, the inventory pressure is reduced, the commodity recommendation is more accurate, the commodity purchasing experience of the user is greatly optimized, and the commodity sales efficiency is effectively improved.
In one embodiment, the step of importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating the commodity recommendation information through the commodity recommendation model includes: preprocessing the online data and the offline data to obtain preprocessed data; importing the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data; detecting whether the error of each active neuron is smaller than a preset error threshold value or not; when the error of the active neuron is smaller than the preset error threshold value, eliminating the active neuron; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold; and constructing the commodity recommendation model based on the fused plurality of active neurons.
In the embodiment, on-line data and off-line data of history are preprocessed on the premise of being based on a large amount of historical data, and the preprocessed on-line data comprise browsed commodity information, commodity browsing duration, whether a shopping cart is added, mobile phone positioning, historical purchasing records and commodity evaluation information; the preprocessed offline data comprise browsed commodity information, commodity browsing duration, commodity satisfaction of a user, commodity evaluation, the number of people entering a store every day and purchasing records.
In this embodiment, the commodity recommendation model is implemented by using a GMDH (Group Method of Data Handling) neural network learning algorithm, preprocessing Data is used as an input source, a series of active neurons are generated by pairwise cross combination of the input preprocessing Data, an error and a mean square error of the active neurons are calculated and compared with a preset error threshold, the active neurons are eliminated and merged, and an optimal recommendation model, that is, a commodity recommendation model, is finally constructed through multiple iterations. Thus, the commodity recommendation model is more accurate.
In one embodiment, the step of importing the classification data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classification data includes: counting the occurrence frequency of each classification data; calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion; screening the classified data with the data proportion larger than a preset proportion to obtain screened data; and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
In this embodiment, the number of times of occurrence of each piece of classification data, referred to as the number of times of occurrence of a frequent set for short, is first calculated according to the classification data, and data with a minimum support degree greater than a preset ratio is screened according to the number of times of occurrence of each piece of classification data, in this embodiment, the preset ratio is 20%, the minimum support degree is a ratio of classification data to total data, and finally, the selected data is used to construct a FP Tree through a FP Tree algorithm, and the FP Tree can obtain a sorted frequent item set.
In one embodiment, the step of calculating the association rule of each commodity according to the frequent item set based on a preset association rule algorithm includes: calculating an imbalance factor of each commodity by using an imbalance factor algorithm; rejecting the commodities with the unbalance factors larger than preset factors; and calculating to obtain the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
In this embodiment, the imbalance factor RI of the associated commodity is calculated by the imbalance factor algorithm, and the data with RI >0.6 is filtered out, so that the commodity association rule is finally obtained.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
Example two
According to the method and the device, data mining is carried out on the data acquired online and offline, and the commodity recommendation schemes are provided for online and offline respectively through the model constructed through machine learning. Effectively improve the exposure rate of the hot goods of the off-line shop on-line and the exposure rate of the on-line hot goods of the off-line shop, improve the shopping experience of the user, and improve the economic benefit of the company.
The specific process is as follows:
first, commodity association analysis, as shown in fig. 4A:
1. browsing, exposure and commodity sales data of the online commodities are acquired through a program on line; the attention (heat) information of the commodities, the commodity sales information of the offline store and the offline store position information are collected through a sensor and a shopping guide large screen offline.
2. And filtering invalid data according to the data acquired online and offline, and classifying the filtered data according to the date, the sales area, the commodity category and the sales channel (online and offline).
3. And (3) respectively constructing an FP Tree of the commodity information by the classified data through an FP Tree algorithm, searching a condition pattern base by the FP Tree, constructing and creating the condition FP Tree, and finally obtaining a frequent item set (a set with the support degree greater than or equal to the minimum support degree, and the main meaning is to record the frequency of different data occurrence).
The specific process of obtaining the frequent item set is as follows:
1. calculating the occurrence frequency of each data (frequency of occurrence of frequent set for short) according to the classification data
2. And (3) screening out data with the minimum support degree (the proportion of the data to the total data) of more than 20% from the data obtained in the step (1).
3. And (3) constructing the FP tree by the data obtained in the step (2) through an algorithm, and obtaining the ordered frequent item set by the FP tree.
4. And calculating the association relation among the commodities according to the obtained different frequent item sets through a Kulc criterion (algorithm implementation). The specific flow is that the imbalance factor RI of the related commodity is calculated by the imbalance factor algorithm. And screening data with RI >0.6 (the data can be manually adjusted in the actual process), and finally obtaining the commodity association rule.
Secondly, constructing a recommendation model, as shown in fig. 4B:
1. on the premise of being based on a large amount of historical data, preprocessing historical online data and historical offline data, wherein the processed online data comprises browsed commodity information, commodity browsing duration, whether a shopping cart is added, mobile phone positioning (informed by user consent), historical purchasing records and commodity evaluation information; the processed offline data comprises browsed commodity information, commodity browsing time, commodity satisfaction of users, commodity evaluation, the number of people entering a store every day and purchase records.
2. The recommendation model is realized by using a GMDH neural network learning algorithm, a series of active neurons are generated by pairwise crossing and combining input data according to the data preprocessed in the step 1 as an input source, the mean square error of the error is calculated and is compared with a specified threshold (the threshold is set manually, and the threshold needs to be adjusted continuously in the recommendation model building process so as to select an optimal threshold, generally speaking, the threshold can be selected to be 0.6 or 0.45), the neurons are eliminated and fused, and the optimal recommendation model is built through continuous iteration.
Thirdly, generating a commodity display and associated commodity recommendation scheme, as shown in fig. 4C:
and generating a commodity display and associated commodity recommendation scheme through a recommendation model based on the commodity association rule, the historical data and the real-time data, wherein the scheme comprises two parts which respectively correspond to an online scheme and an offline scheme.
The on-line scheme specifically comprises the following contents:
1. by analyzing hot goods data under the line, according to the difference of regions, the goods with high attention of stores under the line and high user satisfaction in different regions and the related goods are pushed to the APP on the line.
2. If the online APP user agrees to obtain the positioning information, the commodities provided in the scheme are recommended in addition to the commodities with high online popularity, and the store address with the commodity displayed in the nearest distance below the line and the evaluation of the commodities by the offline user are provided for the user when the commodities are checked.
The specific content of the offline scheme is as follows:
1. by analyzing the data of the online hot commodities, the online browsing click rate is high, the order quantity is large, the user satisfaction degree is high, and the associated commodities are pushed to an online offline store intelligent shopping guide large screen, and meanwhile, a store can manage warehouse inventory according to the scheme, so that the inventory backlog is reduced, the commodities in the scheme are displayed in the store, and the shopping experience of the user is improved.
2. When a user browses commodities on a large screen by using an online store intelligent shopping guide, the commodities are displayed to the user in a subtitle or voice mode according to an evaluation label provided in the scheme, so that the user can buy commodities with ease; meanwhile, after the user finishes watching the commodity (sample), the commodity can be evaluated in a shopping guide large screen in a tag or self-defined mode, and in addition, the user can recommend the associated commodity for the user to select after finishing watching the commodity.
EXAMPLE III
In the present embodiment, as shown in fig. 2, there is provided a product information processing apparatus including:
a commodity data acquiring module 210, configured to acquire online data and offline data of a commodity;
a frequent item set calculation obtaining module 220, configured to import the online data and the offline data into a preset frequent item set mining algorithm, so as to obtain frequent item sets of the online data and the offline data;
an association rule obtaining module 230, configured to calculate, based on a preset association rule algorithm, an association rule of each commodity according to the frequent item set;
a recommendation information obtaining module 240, configured to import the online data and the offline data into a pre-constructed commodity recommendation model, and calculate commodity recommendation information through the commodity recommendation model;
and a commodity recommendation scheme generating module 250, configured to generate a commodity recommendation scheme based on the association rule and the commodity recommendation information, and output the commodity recommendation scheme.
In one embodiment, the commodity information processing apparatus further includes:
the preprocessing module is used for preprocessing the online data and the offline data to obtain preprocessed data;
the neuron generation module is used for leading the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data;
the error detection module is used for detecting whether the error of each active neuron is smaller than a preset error threshold value or not;
the neuron elimination fusion module is used for eliminating the active neurons when the error of the active neurons is smaller than the preset error threshold; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold;
and the recommendation model building module is used for building the commodity recommendation model for the plurality of the activity neurons based on fusion.
In one embodiment, the frequent item set calculation module includes:
the classification unit is used for classifying the online data and the offline data according to a preset classification rule to obtain classified data;
and the frequent item set obtaining unit is used for importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
In one embodiment, the frequent item set obtaining unit is further configured to count the occurrence frequency of each classification data; calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion; screening the classified data with the data proportion larger than a preset proportion to obtain screened data; and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
In one embodiment, the association rule obtaining module includes:
the unbalance factor acquisition unit is used for calculating the unbalance factor of each commodity by using an unbalance factor algorithm;
the rejecting unit is used for rejecting the commodities with the imbalance factors larger than preset factors;
and the association rule obtaining unit is used for calculating and obtaining the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
In one embodiment, the preset frequent item set mining algorithm includes a FP Tree algorithm and an Apriori algorithm.
In one embodiment, the offline data of the commodity is acquired through a preset sensor.
For specific limitations of the product information processing device, reference may be made to the above limitations of the product information processing method, which are not described herein again. Each unit in the above-described commodity information processing apparatus may be entirely or partially realized by software, hardware, and a combination thereof. The units can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the units.
Example four
In this embodiment, a computer device is provided. The internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and is deployed with a database for storing online data and offline data of goods. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with other computer devices that deploy application software. The computer program is executed by a processor to implement a commodity information processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
preprocessing the online data and the offline data to obtain preprocessed data;
importing the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data;
detecting whether the error of each active neuron is smaller than a preset error threshold value or not;
when the error of the active neuron is smaller than the preset error threshold value, eliminating the active neuron; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold;
and constructing the commodity recommendation model based on the fused plurality of active neurons.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
classifying the online data and the offline data according to a preset classification rule to obtain classified data;
and importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
counting the occurrence frequency of each classification data;
calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion;
screening the classified data with the data proportion larger than a preset proportion to obtain screened data;
and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
calculating an imbalance factor of each commodity by using an imbalance factor algorithm;
rejecting the commodities with the unbalance factors larger than preset factors;
and calculating to obtain the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
In one embodiment, the preset frequent item set mining algorithm includes a FP Tree algorithm and an Apriori algorithm.
In one embodiment, the offline data of the commodity is acquired through a preset sensor.
EXAMPLE five
In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, the computer program realizing the following steps when executed by a processor:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
In one embodiment, the computer program when executed by the processor further performs the steps of:
preprocessing the online data and the offline data to obtain preprocessed data;
importing the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data;
detecting whether the error of each active neuron is smaller than a preset error threshold value or not;
when the error of the active neuron is smaller than the preset error threshold value, eliminating the active neuron; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold;
and constructing the commodity recommendation model based on the fused plurality of active neurons.
In one embodiment, the computer program when executed by the processor further performs the steps of:
classifying the online data and the offline data according to a preset classification rule to obtain classified data;
and importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
counting the occurrence frequency of each classification data;
calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion;
screening the classified data with the data proportion larger than a preset proportion to obtain screened data;
and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating an imbalance factor of each commodity by using an imbalance factor algorithm;
rejecting the commodities with the unbalance factors larger than preset factors;
and calculating to obtain the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
In one embodiment, the preset frequent item set mining algorithm includes a FP Tree algorithm and an Apriori algorithm.
In one embodiment, the offline data of the commodity is acquired through a preset sensor.
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. A commodity information processing method, characterized by comprising:
acquiring online data and offline data of a commodity;
importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data;
based on a preset association rule algorithm, calculating to obtain an association rule of each commodity according to the frequent item set;
importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information through the commodity recommendation model;
and generating a commodity recommendation scheme based on the association rule and the commodity recommendation information, and outputting the commodity recommendation scheme.
2. The method of claim 1, wherein the step of importing the online data and the offline data into a pre-constructed commodity recommendation model, and calculating commodity recommendation information by the commodity recommendation model comprises:
preprocessing the online data and the offline data to obtain preprocessed data;
importing the preprocessed data into a neural network for learning, and constructing a plurality of active neurons based on pairwise crossing combination of the preprocessed data;
detecting whether the error of each active neuron is smaller than a preset error threshold value or not;
when the error of the active neuron is smaller than the preset error threshold value, eliminating the active neuron; fusing the active neurons when the error of the active neurons is greater than or equal to the preset error threshold;
and constructing the commodity recommendation model based on the fused plurality of active neurons.
3. The method of claim 1, wherein the step of importing the online data and the offline data into a preset frequent item set mining algorithm to obtain frequent item sets of the online data and the offline data comprises:
classifying the online data and the offline data according to a preset classification rule to obtain classified data;
and importing the classified data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of the classified data.
4. The method according to claim 3, wherein the step of importing the classified data into a preset frequent item set mining algorithm for calculation to obtain the frequent item set of the classified data comprises:
counting the occurrence frequency of each classification data;
calculating the proportion of each classification data in all classification data based on the occurrence frequency of each classification data to obtain a data proportion;
screening the classified data with the data proportion larger than a preset proportion to obtain screened data;
and importing the screened data into a preset frequent item set mining algorithm for calculation to obtain a frequent item set of each screened data.
5. The method according to claim 1, wherein the step of calculating the association rule of each commodity according to the frequent item set based on a preset association rule algorithm comprises:
calculating an imbalance factor of each commodity by using an imbalance factor algorithm;
rejecting the commodities with the unbalance factors larger than preset factors;
and calculating to obtain the association rule of each commodity after being eliminated according to the frequent item set based on a preset association rule algorithm.
6. The method of claim 1, wherein the pre-set frequent item set mining algorithm comprises a FP Tree algorithm and an Apriori algorithm.
7. The method of any one of claims 1-6, wherein the offline data of the commodity is obtained by a preset sensor.
8. An article information processing apparatus characterized by comprising:
the commodity data acquisition module is used for acquiring online data and offline data of commodities;
a frequent item set calculation obtaining module, configured to import the online data and the offline data into a preset frequent item set mining algorithm, so as to obtain frequent item sets of the online data and the offline data;
the association rule obtaining module is used for calculating and obtaining the association rule of each commodity according to the frequent item set based on a preset association rule algorithm;
the recommendation information obtaining module is used for importing the online data and the offline data into a pre-constructed commodity recommendation model and calculating commodity recommendation information through the commodity recommendation model;
and the commodity recommendation scheme generating module is used for generating a commodity recommendation scheme based on the association rule and the commodity recommendation information and outputting the commodity recommendation scheme.
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 7 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 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111509491.9A CN114418663A (en) | 2021-12-10 | 2021-12-10 | Commodity information processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111509491.9A CN114418663A (en) | 2021-12-10 | 2021-12-10 | Commodity information processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114418663A true CN114418663A (en) | 2022-04-29 |
Family
ID=81265148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111509491.9A Pending CN114418663A (en) | 2021-12-10 | 2021-12-10 | Commodity information processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114418663A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983921A (en) * | 2022-12-29 | 2023-04-18 | 广州市玄武无线科技股份有限公司 | Offline store commodity association combination method, device, equipment and storage medium |
-
2021
- 2021-12-10 CN CN202111509491.9A patent/CN114418663A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983921A (en) * | 2022-12-29 | 2023-04-18 | 广州市玄武无线科技股份有限公司 | Offline store commodity association combination method, device, equipment and storage medium |
| CN115983921B (en) * | 2022-12-29 | 2023-11-14 | 广州市玄武无线科技股份有限公司 | Off-line store commodity association combination method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509054B (en) | Commodity recommendation method under mass data, electronic device and storage medium | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| CN107169806B (en) | Method and device for determining influence degree of commodity attribute on purchase decision | |
| US10860634B2 (en) | Artificial intelligence system and method for generating a hierarchical data structure | |
| US20110004509A1 (en) | Systems and methods for predicting sales of item listings | |
| CN107622427A (en) | The method, apparatus and system of deep learning | |
| CN110276495A (en) | Commercial articles ordering method, apparatus, computer and storage medium based on artificial intelligence | |
| Kabir et al. | Analysis of different predicting model for online shoppers’ purchase intention from empirical data | |
| KR102321987B1 (en) | Petition System based on Petition History and Petitioner Profile Analysis | |
| CN109300003A (en) | Enterprise's recommended method, device, computer equipment and storage medium | |
| CN113362126A (en) | Order data detection method and system applied to online business | |
| CN115311042A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| CN114418663A (en) | Commodity information processing method and device, computer equipment and storage medium | |
| Wiradinata et al. | Online Measuring Feature for Batik Size Prediction using Mobile Device: A Potential Application for a Novelty Technology | |
| KR102311107B1 (en) | Customer exit prevention method that provides a solution to prevent customer from leaving the deep learning solution platform that automatically creates a deep learning model, perfomred by a system to avoid leaving the customer | |
| Mandala et al. | Recognition of E-Commerce through Big Data Classification and Data Mining Techniques Involving Artificial Intelligence | |
| US20230334553A1 (en) | Systems and methods for garment size recommendation | |
| CN117422306A (en) | Cross-border E-commerce risk control method and system based on dynamic neural network | |
| KR102319997B1 (en) | Machine learning based clothing fit recommending apparatus | |
| CN116595390A (en) | Commodity information processing method and electronic equipment | |
| US11861882B2 (en) | Systems and methods for automated product classification | |
| CN114757630A (en) | Storage management model determining method and device and computer equipment | |
| KR102582813B1 (en) | Method and apparatus for providing personalized recommendation service for offline purchase | |
| WO2018144695A1 (en) | In-store display with selective display of products based on visibility metric | |
| CN114971083A (en) | Method for purchasing, predicting and selling goods |
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 |