CN115578163A - Personalized pushing method and system for combined commodity information - Google Patents
Personalized pushing method and system for combined commodity information Download PDFInfo
- Publication number
- CN115578163A CN115578163A CN202211274426.7A CN202211274426A CN115578163A CN 115578163 A CN115578163 A CN 115578163A CN 202211274426 A CN202211274426 A CN 202211274426A CN 115578163 A CN115578163 A CN 115578163A
- Authority
- CN
- China
- Prior art keywords
- data
- commodity
- combined
- time
- combined commodity
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012216 screening Methods 0.000 claims description 35
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000005236 sound signal Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a personalized pushing method and system for combined commodity information, and relates to the technical field of information pushing. According to the method and the device, potential combined commodities of the users are mined based on historical purchasing data of the users, the users are classified on the basis of the potential combined commodities, similar group sets with similar purchasing potential requirements are obtained, then combined commodity data corresponding to the similar group sets are used as the basis, and the current operation data of the target customers are added to determine a combined commodity recommendation table based on self preference of the commodities, and the commodities are recommended to the target customers according to the combined commodity recommendation table, so that the target users can be helped to quickly locate the targets, a large amount of time is saved, user experience is improved, personalized recommendation based on the preference requirements of the target users is achieved, and commodity recommendation quality and recommendation accuracy are improved.
Description
Technical Field
The invention relates to the technical field of information pushing, in particular to a personalized pushing method and system for combined commodity information.
Background
In recent years, with the rapid popularization and development of computers, internet technology has also been rapidly applied. Meanwhile, with the steady increase of the disposable income of residents, online shopping has become one of indispensable consumption channels of netizens in China. The internet provides a huge amount of commodity choices, but the quantity of commodities is so large that consumers need to spend a great deal of time and energy to identify the commodities needed by the consumers, namely, the problem of information overload is caused.
While random commodity combined sales is a common commodity sales mode, when combined commodities are sold on line, a merchant usually puts one or more commodities in a good bag to give a total price for consumers to choose, and the commodity combined sales is more adopted by various e-commerce platforms.
However, in the early stage of the development of the e-commerce shopping guide platform, flow guidance and commodity recommendation are mainly provided for the user, so that the targeted shopping requirements of the user cannot be met in all aspects, the recommendation accuracy is low, and the user experience is poor.
Disclosure of Invention
The invention aims to provide a personalized pushing method and a personalized pushing system for combined commodity information, so as to improve the problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for personalized push of combined commodity information, including:
respectively acquiring historical purchase data of each user and current operation data of a target customer based on the big data;
screening based on the historical purchase data of each user to obtain combined commodity data;
calculating all the users by utilizing a collaborative filtering algorithm based on all the combined commodity data to obtain a similar group set;
obtaining a combined commodity recommendation table based on the target customer, the current operation data and the similar group set;
and carrying out personalized pushing on the combined commodity information to the target customer based on the combined commodity recommendation table.
In a second aspect, the present application further provides an individualized push system for combined commodity information, including an obtaining module, a screening module, a sorting module, an ordering module, and a push module, wherein:
an acquisition module: the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for respectively acquiring historical purchase data of each user and current operation data of a target customer based on big data;
a screening module: the combined commodity data is obtained by screening based on the historical purchase data of each user;
a classification module: the system is used for calculating all the users by utilizing a collaborative filtering algorithm based on all the combined commodity data to obtain a similar group set;
a sorting module: the combined commodity recommendation table is obtained based on the target customer, the current operation data and the similar group set;
a pushing module: and the combined commodity recommendation table is used for carrying out personalized pushing on the combined commodity information to the target customer.
The invention has the beneficial effects that:
according to the method and the device, potential combined commodities of the users are mined based on historical purchasing data of the users, the users are classified on the basis of the potential combined commodities, similar group sets with similar purchasing potential requirements are obtained, then combined commodity data corresponding to the similar group sets are used as the basis, and current operation data of the target customer are added to further determine a combined commodity recommendation table based on self preference of the commodities, and the combined commodity recommendation table is recommended to the target customer according to the combined commodity recommendation table, so that the target user can be helped to quickly locate the target, a large amount of time is saved, user experience is improved, personalized recommendation based on preference requirements of the target user is achieved, and commodity recommendation quality and recommendation accuracy are improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a block diagram of a personalized push method for combined commodity information described in this embodiment;
fig. 2 is a block diagram of the personalized delivery system for combined commodity information described in this embodiment;
fig. 3 is a block diagram of the personalized push device for combined commodity information described in this embodiment.
In the figure: 710-an acquisition module; 720-a screening module; 721-a statistical unit; 722-a first judgment unit; 723-a second determination unit; 724-a first obtaining unit; 725-a third judging unit; 7251-a second obtaining unit; 7252-a fourth judging unit; 7253-a fifth judging unit; 7254-sixth judging unit; 730-a classification module; 740-a sorting module; 741 — a first arrangement unit; 742-a retrieval unit; 743-a calculation unit; 744-a second arrangement unit; 750-a push module; 800-personalized push equipment for combined commodity information; 801-a processor; 802-a memory; 803-multimedia components; 804 — an I/O interface; 805-communication component.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.
Example 1:
referring to fig. 1, fig. 1 is a block diagram of a personalized push method for combined commodity information in this embodiment. Fig. 1 shows that the method comprises a step S1, a step S2, a step S3, a step S4 and a step S5.
And S1, respectively acquiring historical purchase data of each user and current operation data of a target customer based on the big data.
It can be understood that, in this step, purchase data corresponding to each user in the purchase platform is extracted based on the big data, including all the information of the goods, the information of the shop, the purchase quantity, the purchase time, and the like included in the same purchase behavior. And meanwhile, acquiring current operation data corresponding to a target client with a purchase demand, such as searching, clicking browsing, collecting, purchasing and the like, based on the big data.
And S2, screening based on the historical purchase data of each user to obtain combined commodity data.
It is understood that, in this step, the historical purchase data of the users are mined to obtain the combined product data of each user, and the combined product data may be the purchase list of all products purchased by the user each time (the single purchase product type exceeds the purchase list of 2) or the purchase list of all products purchased within a limited time (for example, within the same day).
However, when the historical purchase data of the user is less or the user is a new online shopping user, the combined commodity data of the user cannot be accurately mined due to the fact that the purchase data of the user is too little, the real potential requirements of the user cannot be really obtained, and the experience of the user is poor. Therefore, the method and the device divide the users, and mine the potential demands of the users in different modes aiming at different users (different purchase historical data amount), so that the problems of data sparseness and cold start in commodity recommendation are solved, the recommendation platform helps the users to make decisions, and the commodity selection probability of the users is improved. The mining method aiming at the user preference with less data comprises a step S21, a step S22 and a step S23.
And S21, counting the total purchase times of the historical purchase data of each user.
Step S22, judging whether the total purchase frequency is smaller than a first preset threshold value, and if the total purchase frequency is smaller than the first preset threshold value, acquiring purchase time corresponding to each commodity based on the historical purchase data; the first preset threshold is the minimum value of the historical purchase times of the user.
It can be understood that, in this step, when the total purchase number of the user is less than the first preset threshold, it indicates that the historical purchase data of the user is less, and the potential demand information of the user cannot be mined from the current historical purchase data, the purchase time corresponding to each commodity is obtained based on the historical purchase data.
Step S23, based on the purchase time, judging whether the interval between the two adjacent purchase times is smaller than a second preset threshold value, if the interval between the two adjacent purchase times is smaller than the second preset threshold value, the commodities corresponding to the two adjacent purchase times are combined commodity data; the second preset threshold is the maximum value of the adjacent two-time purchasing time interval.
It can be understood that in this step, based on the timeliness of the user to the commodity purchasing behavior, the commodity combination recommendation information based on the potential demand of the user is formed, the problems of data sparseness and cold start existing due to less data are solved, meanwhile, the user is helped to quickly obtain the commodity with the potential demand, and the shopping experience of the user is improved. In this embodiment, the shorter the time difference between two adjacent purchased commodities is, the commodity is the article required by the user in the current time, and all commodities corresponding to the interval between two adjacent purchased times of the user, which is smaller than a second preset threshold (for example, the second preset threshold is set to 48 hours in this embodiment, and may be adjusted in other embodiments, and specific numerical values are not limited), are taken as the combined commodity data.
When the total purchase frequency of the user is greater than or equal to a first preset threshold, which indicates that the potential demand information of the user can be mined through the historical purchase data of the user, screening is performed based on the historical purchase data of the user to obtain combined commodity data, wherein the combined commodity data obtaining method comprises the step S24 and the step S25.
And S24, respectively acquiring operation time data corresponding to each commodity based on the historical purchase data.
It can be understood that, in this step, the purchase time corresponding to each product is acquired according to the products involved in the historical purchase data.
S25, ordering the transaction orders in the historical purchase data based on the time sequence, judging whether the two adjacent purchased commodities are the same or not, and if the two adjacent purchased commodities are different, screening according to the absolute value of the difference between the two adjacent purchased commodities and the operation time data and a preset screening condition to obtain combined commodity data; the preset screening condition is a time difference parameter corresponding to the purchased commodity.
It can be understood that, in this step, the purchase list is obtained by sorting the purchase time corresponding to each product based on the time sequence. Based on the purchase list, the absolute value of the time difference between two adjacent purchases records is calculated, and all the commodities within a limited time are screened based on a preset screening condition (for example, 24 hours in the embodiment), so as to obtain combined commodity data.
Further, step S25 includes step S251, step S252, step S253, and step S254.
And step S251, acquiring the corresponding shop data based on the purchased products.
It can be understood that, in this step, the shop corresponding to each item is acquired from two adjacent purchased items.
Step S252 is to determine whether the store data corresponding to the two adjacent purchased products is the same store.
It is understood that, in this step, it is determined whether or not the two adjacent purchased products are from the same store.
Step S253, if the store data is not the same store, determining whether the absolute value is smaller than a first time parameter, and if the absolute value is smaller than the first time parameter, determining that the two adjacent purchased commodities are combined commodity data, where the first time parameter is a maximum time interval parameter of combined consumption in the same store.
It can be understood that, in this step, when the commodities purchased twice next to each other do not come from the same store, it is further determined whether an absolute value of a time difference between two commodity purchases is smaller than a first time parameter, and if so, it is determined that all the commodities purchased by the user within the time are potentially required commodities of the user, and the potentially required commodities are taken as combined commodity data. And if the absolute value of the time difference between the two times of commodity purchase is greater than or equal to the first time parameter, which indicates that the time interval corresponding to the commodity purchase is long and combined consumption is impossible, the combination relation of the commodity is abandoned.
Step S254, if the store data is the same store, determining whether the absolute value is smaller than a second time parameter, if the absolute value is smaller than the second time parameter, the two adjacent purchased commodities are combined commodity data, and the second time parameter is a maximum time interval parameter of combined consumption of different stores.
It can be understood that, in this step, when the commodities purchased twice next to each other come from the same store, it is further determined whether an absolute value of a time difference between the two commodity purchases is smaller than a second time parameter, and if so, it is determined that all the commodities purchased by the user within the time are potentially required commodities of the user, and the potentially required commodities are taken as combined commodity data. And if the absolute value of the time difference between the two times of commodity purchasing is greater than or equal to the second time parameter, which indicates that the corresponding time of the purchased commodities is long and combined consumption is impossible, the combination relation of the commodities is abandoned.
In the above steps S251 to S254, the product purchase is divided into the same-store purchase and the different-store purchase, and different time difference parameters are set on the divided purchase behavior (the time difference between two adjacent combined purchases corresponding to the store is smaller than that of the different store) to obtain the combined product data, so as to improve the accuracy of the combined product data, and further improve the recommendation quality of the later-stage combined product information.
And S3, calculating all the users by utilizing a collaborative filtering algorithm based on all the combined commodity data to obtain a similar group set.
It can be understood that, in this step, the similarity between the current user and other users is calculated according to the formula (1), all users corresponding to similarity values higher than a similarity threshold (preset similarity threshold is 0.5, which is adjustable and not limited) are classified into the same class, and all users are classified based on the above method to obtain a similar group set. Equation (1) is as follows:
wherein: r is a radical of hydrogen ij Is the similarity; h (i) combined commodity data purchased by the user i; h (j) is the combined commodity data purchased by the user j.
And S4, obtaining a combined commodity recommendation table based on the target customer, the current operation data and the similar group set.
It can be understood that, in this step, a similar group set to which the target client belongs is determined according to the target client, the combined commodity data corresponding to the users in the similar group set is taken as a basis, the screening user including the current operation data is determined according to the current operation data (such as the searched commodity) of the user, and then the combined commodity data including the current operation data is sorted in a descending order based on the similarity of the screening user, so as to obtain a combined commodity recommendation table. The calculation method of the similarity between the current commodity and other commodities comprises a Pearson correlation coefficient algorithm or a Manhattan distance and the like.
Further, the acquisition method of the combined product recommendation table includes step S41, step S42, step S43, and step S44.
And S41, performing descending order arrangement based on the similarity of the similar group set and the target client to obtain a neighbor user list.
It can be understood that, in this step, based on the similar group set to which the target client belongs, the similarity (similarity between the user and the target client) corresponding to each user in the similar group set is sorted in a descending order to obtain the neighbor user list.
And S42, respectively determining the target commodity corresponding to each neighbor user based on the coincidence data of each neighbor user in the neighbor user list and the current operation data.
It can be understood that, in this step, according to the combined commodity data corresponding to the neighboring user, the user including the current operation data and the purchase data corresponding to the user are found, and the purchase data corresponding to the user is taken as the target commodity.
And S43, calculating based on all the target commodities, the current operation data and a preset weight to obtain a favorite value corresponding to each commodity.
It can be understood that, in this step, the target product is set as a first preset weight, the products corresponding to the current operation data such as click, collection and purchase are respectively set as a second preset weight, a third preset weight and a fourth preset weight, and the favorite value corresponding to each product is calculated according to the formula (2):
W i ＝ρ 1 θ+ρ 2 λ+ρ 3 α+ρ 4 β (2)
wherein: w is a group of i The favorite value corresponding to the commodity i; rho 1 、ρ 2 、ρ 3 And ρ 4 Respectively a first preset weight, a second preset weight, a third preset weight and a fourth preset weight; theta is the browsing frequency of the target commodity; lambda is the browsing times of clicking the commodity; alpha is the browsing times of the collected commodities; beta is the browsing times of purchased goods.
And S44, performing descending order arrangement on the target commodities based on the favorite values to obtain a combined commodity recommendation table.
And S5, performing personalized pushing of combined commodity information to the target customer based on the combined commodity recommendation table.
It can be understood that, in this step, the list of products with the greatest similarity to the target customer is recommended to the target customer based on the combined product recommendation table, so as to improve the recommendation quality of the combined products.
Example 2:
fig. 2 is a block diagram of the personalized push system of combined commodity information in this embodiment, which includes an obtaining module 710, a screening module 720, a classifying module 730, an ordering module 740, and a pushing module 750, where:
the obtaining module 710: the method is used for respectively acquiring historical purchase data of each user and current operation data of a target customer based on the big data.
The screening module 720: and the combined commodity data is obtained by screening based on the historical purchase data of each user.
Preferably, the screening module 720 includes a statistical unit 721, a first judging unit 722 and a second judging unit 723, wherein:
the statistical unit 721: counting the total purchase times of the historical purchase data of each user;
the first determination unit 722: the system is used for judging whether the total purchase frequency is smaller than a first preset threshold value or not, and if the total purchase frequency is smaller than the first preset threshold value, acquiring the purchase time corresponding to each commodity based on the historical purchase data; the first preset threshold value is the minimum value of the historical purchase times of the user;
second determination unit 723: the commodity combination module is used for judging whether the interval between two adjacent times of purchasing time is smaller than a second preset threshold value or not based on the purchasing time, and if the interval between two adjacent times of purchasing time is smaller than the second preset threshold value, the commodity corresponding to the two adjacent times of purchasing time is combined commodity data; the second preset threshold is the maximum value of the adjacent two-time purchasing time interval.
Further, the screening module 720 further includes a first obtaining unit 724 and a third determining unit 725, wherein:
the first acquisition unit 724: the system is used for respectively acquiring operation time data corresponding to each commodity based on the historical purchase data;
the third judgment unit 725: the commodity-purchasing-time-sequence-based combined commodity data processing system is used for sequencing the transaction orders in the historical purchasing data based on the time sequence, judging whether the two adjacent purchasing commodities are the same or not, and if the two adjacent purchasing commodities are different, screening according to the absolute value of the difference between the two adjacent purchasing commodities and the operation time data and a preset screening condition to obtain combined commodity data; the preset screening condition is a time difference parameter corresponding to the purchased commodity.
Preferably, the third judging unit 725 includes a second acquiring unit 7251, a fourth judging unit 7252, a fifth judging unit 7253 and a sixth judging unit 7254, wherein:
second acquisition unit 7251: the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring corresponding shop data based on the purchased commodities respectively;
fourth determination unit 7252: the system comprises a database, a database and a database, wherein the database is used for storing shop data corresponding to two adjacent purchased commodities;
fifth judging unit 7253: the system is used for judging whether the absolute value is smaller than a first time parameter if the store data is not the same store, and if the absolute value is smaller than the first time parameter, the purchased commodities in two adjacent times are combined commodity data, and the first time parameter is a maximum time interval parameter of combined consumption of the same store;
sixth determination unit 7254: and the time parameter is a maximum time interval parameter of the different-shop combined consumption.
The classification module 730: the system is used for calculating all the users by utilizing a collaborative filtering algorithm based on all the combined commodity data to obtain a similar group set;
the sorting module 740: the combined commodity recommendation table is obtained based on the target customer, the current operation data and the similar group set;
preferably, the sorting module 740 includes a first sorting unit 741, a retrieving unit 742, a calculating unit 743 and a second sorting unit 744, wherein:
the first arrangement unit 741: the system is used for carrying out descending order arrangement on the basis of the similarity of the similar group set and the target client to obtain a neighbor user list;
the search unit 742: the target commodity corresponding to each neighbor user is respectively determined based on the coincidence data of each neighbor user in the neighbor user list and the current operation data;
the calculation unit 743: the system is used for calculating based on all the target commodities, the current operation data and a preset weight to obtain a favorite value corresponding to each commodity;
the second arranging unit 744: and the combined commodity recommendation table is used for performing descending order arrangement on the target commodities based on the favorite values to obtain the combined commodity recommendation table.
The push module 750: and the combined commodity recommendation table is used for carrying out personalized pushing on the combined commodity information to the target customer.
It should be noted that, with regard to the system in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
Example 3:
corresponding to the above method embodiment, the present embodiment further provides an individualized pushing device for combined commodity information, and the individualized pushing device for combined commodity information described below and the individualized pushing method for combined commodity information described above may be referred to correspondingly.
Fig. 3 is a block diagram illustrating a personalized push device 800 for combined merchandise information, according to an example embodiment. As shown in fig. 3, the personalized push device 800 for combined commodity information may include: a processor 801, a memory 802. The personalized push device 800 of combined merchandise information may also include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control overall operations of the personalized pushing device 800 for combined commodity information, so as to complete all or part of the steps in the above personalized pushing method for combined commodity information. The memory 802 is used to store various types of data to support the operation of the personalized push device 800 for the combined merchandise information, which may include, for example, instructions for any application or method operating on the personalized push device 800 for the combined merchandise information, as well as application related data. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the personalized push device 800 for the combined merchandise information and other devices. Wireless communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the personalized push Device 800 for combined commodity information may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, for performing the above-mentioned personalized push method for combined commodity information.
Example 4:
corresponding to the above method embodiment, a storage medium is also provided in this embodiment, and a storage medium described below and the above personalized push method for combined merchandise information may be referred to correspondingly.
A storage medium, on which a computer program is stored, and when being executed by a processor, the computer program implements the steps of the personalized push method for combined commodity information of the above method embodiments.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other storage media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A personalized pushing method for combined commodity information is characterized by comprising the following steps:
respectively acquiring historical purchase data of each user and current operation data of a target customer based on the big data;
screening based on the historical purchase data of each user to obtain combined commodity data;
based on all the combined commodity data, calculating all the users by utilizing a collaborative filtering algorithm to obtain a similar group set;
obtaining a combined commodity recommendation table based on the target customer, the current operation data and the similar group set;
and performing personalized pushing of combined commodity information to the target customer based on the combined commodity recommendation table.
2. The method for personalized delivery of combined commodity information according to claim 1, wherein the screening based on the historical purchase data of each user to obtain combined commodity data comprises:
counting the total purchase times of the historical purchase data of each user;
judging whether the total purchase frequency is smaller than a first preset threshold value or not, and if the total purchase frequency is smaller than the first preset threshold value, acquiring the purchase time corresponding to each commodity based on the historical purchase data; the first preset threshold value is the minimum value of the historical purchase times of the user;
judging whether the interval between two adjacent times of purchase time is smaller than a second preset threshold value or not based on the purchase time, and if the interval between two adjacent times of purchase time is smaller than the second preset threshold value, determining that the commodities corresponding to the two adjacent times of purchase time are combined commodity data; the second preset threshold is the maximum value of the time interval between two adjacent purchases.
3. The method for personalized delivery of combined commodity information according to claim 2, wherein the step of pushing the total number of purchases greater than or equal to a first preset threshold value comprises:
respectively acquiring operation time data corresponding to each commodity based on the historical purchase data;
ordering the transaction orders in the historical purchase data based on the time sequence, judging whether the two adjacent purchased commodities are the same or not, if the two adjacent purchased commodities are different, screening according to the absolute value of the difference between the two adjacent purchased commodities and the operation time data and a preset screening condition to obtain combined commodity data; the preset screening condition is a time difference parameter corresponding to the purchased commodity.
4. The method for personalized delivery of combined commodity information according to claim 3, wherein the screening according to an absolute value of a difference between the two adjacent purchased commodities and the operation time data and a preset screening condition to obtain combined commodity data comprises:
respectively acquiring corresponding shop data based on the purchased commodities;
judging whether the shop data corresponding to the purchased commodities adjacent to each other twice is the same shop;
if the store data is not the same store, judging whether the absolute value is smaller than a first time parameter, if the absolute value is smaller than the first time parameter, the purchased commodities in two adjacent times are combined commodity data, and the first time parameter is a maximum time interval parameter of combined consumption of the same store;
and if the store data is the same store, judging whether the absolute value is smaller than a second time parameter, if the absolute value is smaller than the second time parameter, determining that the purchased commodities adjacent to each other twice are combined commodity data, and the second time parameter is a maximum time interval parameter of different store combined consumption.
5. The method for personalized delivery of combined commodity information according to claim 1, wherein the obtaining of the combined commodity recommendation table based on the target customer, the current operation data and the similar group set comprises:
performing descending order on the basis of the similarity of the similar group set and the target client to obtain a neighbor user list;
respectively determining a target commodity corresponding to each neighbor user based on the coincidence data of each neighbor user in the neighbor user list and the current operation data;
calculating based on all the target commodities, the current operation data and a preset weight to obtain a favorite value corresponding to each commodity;
and performing descending order arrangement on the target commodities based on the favorite values to obtain a combined commodity recommendation table.
6. A personalized push system for combined commodity information is characterized by comprising:
an acquisition module: the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for respectively acquiring historical purchase data of each user and current operation data of a target customer based on big data;
a screening module: the combined commodity data is obtained by screening the historical purchase data of each user;
a classification module: the system is used for calculating all the users by utilizing a collaborative filtering algorithm based on all the combined commodity data to obtain a similar group set;
a sorting module: the combined commodity recommendation table is obtained based on the target customer, the current operation data and the similar group set;
a pushing module: and the combined commodity recommendation table is used for carrying out personalized pushing on the combined commodity information to the target customer.
7. The system for personalized delivery of combined merchandise information according to claim 6, wherein the screening module comprises:
a statistic unit: counting the total purchase times of the historical purchase data of each user;
a first judgment unit: the system is used for judging whether the total purchase frequency is smaller than a first preset threshold value or not, and if the total purchase frequency is smaller than the first preset threshold value, acquiring the purchase time corresponding to each commodity based on the historical purchase data; the first preset threshold value is the minimum value of the historical purchase times of the user;
a second judgment unit: the commodity combination module is used for judging whether the interval between two adjacent times of purchasing time is smaller than a second preset threshold value or not based on the purchasing time, and if the interval between two adjacent times of purchasing time is smaller than the second preset threshold value, the commodity corresponding to the two adjacent times of purchasing time is combined commodity data; the second preset threshold is the maximum value of the adjacent two-time purchasing time interval.
8. The system for personalized delivery of combined commodity information according to claim 7, wherein the screening module further comprises:
a first acquisition unit: the system is used for respectively acquiring operation time data corresponding to each commodity based on the historical purchase data;
a third judging unit: the commodity transaction ordering system is used for ordering the transaction orders in the historical purchase data based on the time sequence, judging whether the two adjacent purchased commodities are the same or not, and if the two adjacent purchased commodities are different, screening according to the absolute value of the difference between the two adjacent purchased commodities and the operation time data and a preset screening condition to obtain combined commodity data; the preset screening condition is a time difference parameter corresponding to the purchased commodity.
9. The system for personalized delivery of combined commodity information according to claim 8, wherein the third judging unit comprises:
a second acquisition unit: the system is used for respectively acquiring corresponding shop data based on the purchased commodities;
a fourth judging unit: the system comprises a database, a database and a database, wherein the database is used for storing shop data corresponding to two adjacent purchased commodities;
a fifth judging unit: the system is used for judging whether the absolute value is smaller than a first time parameter if the store data is not the same store, and if the absolute value is smaller than the first time parameter, the purchased commodities in two adjacent times are combined commodity data, and the first time parameter is a maximum time interval parameter of combined consumption of the same store;
a sixth judging unit: and the time parameter is a maximum time interval parameter of the different-shop combined consumption.
10. The system for personalized delivery of combined merchandise information of claim 6, wherein the ranking module comprises:
a first arranging unit: the system is used for carrying out descending order arrangement on the basis of the similarity of the similar group set and the target client to obtain a neighbor user list;
the retrieval unit: the target commodity corresponding to each neighbor user is respectively determined based on the coincidence data of each neighbor user in the neighbor user list and the current operation data;
a calculation unit: the system is used for calculating based on all the target commodities, the current operation data and a preset weight to obtain a favorite value corresponding to each commodity;
a second arrangement unit: and the commodity recommending table is used for carrying out descending order arrangement on the target commodities based on the favorite values to obtain a combined commodity recommending table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211274426.7A CN115578163A (en) | 2022-10-18 | 2022-10-18 | Personalized pushing method and system for combined commodity information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211274426.7A CN115578163A (en) | 2022-10-18 | 2022-10-18 | Personalized pushing method and system for combined commodity information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115578163A true CN115578163A (en) | 2023-01-06 |
Family
ID=84585068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211274426.7A Pending CN115578163A (en) | 2022-10-18 | 2022-10-18 | Personalized pushing method and system for combined commodity information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115578163A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205675A (en) * | 2023-04-28 | 2023-06-02 | 华南师范大学 | Data acquisition method and device based on thread division |
| CN116596640A (en) * | 2023-07-19 | 2023-08-15 | 国网山东省电力公司营销服务中心(计量中心) | Recommendation method, system, equipment and storage medium for electric power retail electric charge package |
| CN117391823A (en) * | 2023-12-11 | 2024-01-12 | 广州宇中网络科技有限公司 | User preference information automatic pushing method based on self-learning |
| CN117649256A (en) * | 2024-01-29 | 2024-03-05 | 贵州师范大学 | Ecological product sales information analysis method suitable for karst region |
-
2022
- 2022-10-18 CN CN202211274426.7A patent/CN115578163A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205675A (en) * | 2023-04-28 | 2023-06-02 | 华南师范大学 | Data acquisition method and device based on thread division |
| CN116205675B (en) * | 2023-04-28 | 2023-09-08 | 华南师范大学 | Data acquisition method and device based on thread division |
| CN116596640A (en) * | 2023-07-19 | 2023-08-15 | 国网山东省电力公司营销服务中心(计量中心) | Recommendation method, system, equipment and storage medium for electric power retail electric charge package |
| CN117391823A (en) * | 2023-12-11 | 2024-01-12 | 广州宇中网络科技有限公司 | User preference information automatic pushing method based on self-learning |
| CN117391823B (en) * | 2023-12-11 | 2024-05-10 | 广州宇中网络科技有限公司 | User preference information automatic pushing method based on self-learning |
| CN117649256A (en) * | 2024-01-29 | 2024-03-05 | 贵州师范大学 | Ecological product sales information analysis method suitable for karst region |
| CN117649256B (en) * | 2024-01-29 | 2024-04-02 | 贵州师范大学 | Ecological product sales information analysis method suitable for karst region |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115578163A (en) | Personalized pushing method and system for combined commodity information | |
| CN100594496C (en) | Information processing device and method | |
| US8407104B2 (en) | Catalog based price search | |
| CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
| CN104239338A (en) | Information recommendation method and information recommendation device | |
| CN102163211A (en) | Information processing device, importance calculation method, and program | |
| CN104216881A (en) | Method and device for recommending individual labels | |
| CN116823409B (en) | Intelligent screening method and system based on target search data | |
| CN116452261B (en) | Advertisement delivery data processing method based on cross-border E-commerce service platform | |
| Lin et al. | Personalized hotel recommendation using text mining and mobile browsing tracking | |
| CN116431931B (en) | Real-time incremental data statistical analysis method | |
| KR102279210B1 (en) | Electronic device for determining similarity between sequences considering item classification scheme and control method thereof | |
| Hemalatha | Market basket analysis–a data mining application in Indian retailing | |
| CN110647679A (en) | Search result comprehensive ordering method under o2o scene | |
| CN114581175A (en) | Commodity pushing method and device, storage medium and electronic equipment | |
| US7949576B2 (en) | Method of providing product database | |
| CN117557306B (en) | Management system for classifying consumers based on behaviors and characteristics | |
| CN107515942A (en) | In non-Frequent episodes excavate can decision-making negative sequence pattern buying behavior analysis method | |
| CN115131108A (en) | E-commerce commodity screening system | |
| Pinto et al. | Hybrid recommendation system based on collaborative filtering and fuzzy numbers | |
| CN114169965A (en) | Commodity similarity matching method and device, equipment, medium and product thereof | |
| Meena et al. | Product recommendation system using distance measure of product image features | |
| CN112734511A (en) | Commodity search recommendation method based on e-commerce system and application | |
| Jadhav et al. | Customer Segmentation and Buyer Targeting Approach | |
| Yang et al. | Consumers’ Purchase Behavior Preference in E-Commerce Platform Based on Data Mining Algorithm |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20230106 |
|
| WD01 | Invention patent application deemed withdrawn after publication |