CN114820123B - Group purchase commodity recommendation method, device, equipment and storage medium - Google Patents
Group purchase commodity recommendation method, device, equipment and storage mediumInfo
- Publication number
- CN114820123B CN114820123B CN202210432888.0A CN202210432888A CN114820123B CN 114820123 B CN114820123 B CN 114820123B CN 202210432888 A CN202210432888 A CN 202210432888A CN 114820123 B CN114820123 B CN 114820123B
- Authority
- CN
- China
- Prior art keywords
- community
- group
- target terminal
- commodity
- user
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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—Recommending goods or services
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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]
- G06Q30/0639—Locating goods or services, e.g. based on physical position of the goods or services within a shopping facility
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明属于计算机技术领域，公开了一种团购商品推荐方法、装置、设备及存储介质。该方法包括：在接收到目标终端发出的访问请求时，获取目标终端对应的当前位置、用户信息、购买记录以及浏览记录；根据当前位置确定目标终端对应的社区；根据用户信息、购买记录以及浏览记录构建目标终端对应的用户画像；确定用户画像对应的若干商品类型；基于社区和若干商品类型为目标终端推荐合适的团购商品。通过上述方式，确定目标终端对应的用户画像，基于用户画像对应的商品类型和目标终端所在社区推荐团购商品，实现了自动获取用户需求、根据用户需求推荐团购商品，提高了用户购物体验。
The present invention belongs to the field of computer technology and discloses a method, apparatus, device, and storage medium for recommending group-purchased goods. The method includes: upon receiving an access request from a target terminal, obtaining the current location, user information, purchase history, and browsing history corresponding to the target terminal; determining the community corresponding to the target terminal based on the current location; constructing a user profile corresponding to the target terminal based on the user information, purchase history, and browsing history; determining several product types corresponding to the user profile; and recommending suitable group-purchased goods to the target terminal based on the community and several product types. Through the above-mentioned method, the user profile corresponding to the target terminal is determined, and group-purchased goods are recommended based on the product types corresponding to the user profile and the community where the target terminal is located. This realizes automatic acquisition of user needs, recommends group-purchased goods based on user needs, and improves the user shopping experience.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a group purchase commodity recommendation method, apparatus, device, and storage medium.
Background
Currently, users search for desired goods by browsing websites or typing keywords in search engines of websites, thereby confirming whether group purchase of the desired goods is underway on the websites. The conventional group purchase platform cannot timely acquire the demands of users and dynamically recommend group purchase commodities according to the demands of the users, so that the group purchase cannot achieve expected effects.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a group purchase commodity recommending method, device, equipment and storage medium, and aims to solve the technical problems that the conventional group purchase platform cannot timely acquire the demands of users and dynamically recommend group purchase commodities according to the demands of the users.
In order to achieve the above purpose, the present invention provides a group purchase commodity recommending method, which comprises the following steps:
When an access request sent by a target terminal is received, acquiring a current position, user information, a purchase record and a browsing record corresponding to the target terminal;
Determining a community corresponding to the target terminal according to the current position;
constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record;
Determining a plurality of commodity types corresponding to the user images;
and recommending proper group purchase commodities to the target terminal based on the community and the commodity types.
Optionally, before the determining, according to the current position, the community corresponding to the target terminal, the method further includes:
determining position information corresponding to each group purchase user in the group purchase record of each commodity;
reading an initial community dividing grid, and determining an initial community corresponding to the position information according to the initial community dividing grid;
clustering based on the group purchase records and the corresponding multiple initial communities to obtain a target community division grid;
the determining the community corresponding to the target terminal according to the current position comprises the following steps:
Determining a community grid where the current position is located according to the target community division grid;
and determining the community corresponding to the target terminal based on the community grid.
Optionally, the constructing the user portrait corresponding to the target terminal according to the user information, the purchase record and the browse record includes:
Acquiring portrait features from the user information, the purchase records and the browse records;
and constructing the user portrait corresponding to the target terminal based on the portrait features.
Optionally, recommending the appropriate group purchase commodity for the target terminal based on the community and the commodity types comprises:
screening all the group-purchased goods based on the community and the commodity types to obtain a plurality of group-purchased goods;
sequencing the plurality of group-purchased commodities to obtain a commodity recommendation sequence;
and recommending proper group purchase commodities to the target terminal according to the commodity recommendation sequence.
Optionally, the sorting the plurality of group-purchased commodities to obtain a commodity recommendation sequence includes:
Acquiring graphic description information, purchase quantity and good score corresponding to the group-purchased commodities;
determining commodity scores corresponding to all the group-purchased commodities according to the graphic description information, the purchase quantity and the good score;
And sequencing the group-purchased commodities based on the commodity scores to obtain a commodity recommendation sequence.
Optionally, after the user portrait corresponding to the target terminal is constructed according to the user information, the purchase record and the browse record, the method further includes:
And pushing corresponding published life circle content to the target terminal based on the community and the user portrait.
Optionally, the pushing the corresponding published life circle content to the target terminal based on the community and the user portrait includes:
Determining a corresponding number of seller users based on the community;
determining a plurality of buyer users corresponding to the user portraits, wherein the similarity between the target user portraits corresponding to the buyer users and the user portraits is larger than a preset threshold;
and acquiring the published life circle content corresponding to the seller users and the buyer users, and pushing the published life circle content to the target terminal.
In addition, in order to achieve the above object, the present invention also provides a group purchase article recommending apparatus, including:
The acquisition module is used for acquiring the current position, the user information, the purchase record and the browsing record corresponding to the target terminal when receiving the access request sent by the target terminal;
the determining module is used for determining communities corresponding to the target terminals according to the current positions;
the construction module is used for constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record;
the determining module is further used for determining a plurality of commodity types corresponding to the user image;
And the recommending module is used for recommending proper group purchase commodities to the target terminal based on the community and the commodity types.
In addition, in order to achieve the aim, the invention also provides group purchase commodity recommending equipment, which comprises a memory, a processor and a group purchase commodity recommending program stored on the memory and capable of running on the processor, wherein the group purchase commodity recommending program is configured to achieve the group purchase commodity recommending method.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a group purchase article recommendation program which, when executed by a processor, implements the group purchase article recommendation method as described above.
The method comprises the steps of obtaining the current position, user information, purchase records and browsing records corresponding to a target terminal when an access request sent by the target terminal is received, determining communities corresponding to the target terminal according to the current position, constructing user portraits corresponding to the target terminal according to the user information, the purchase records and the browsing records, determining a plurality of commodity types corresponding to the user portraits, and recommending proper group purchase commodities for the target terminal based on the communities and the commodity types. By the method, the user portrait corresponding to the target terminal is determined, the group purchase commodity is recommended based on the commodity type corresponding to the user portrait and the community where the target terminal is located, the user demand is automatically acquired, the group purchase commodity is recommended according to the user demand, and the user shopping experience is improved.
Drawings
FIG. 1 is a schematic diagram of a group purchase article recommendation device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for recommending group-purchased goods according to a first embodiment of the invention;
FIG. 3 is a schematic flow chart of a second embodiment of a group purchase product recommendation method according to the present invention;
Fig. 4 is a block diagram of a group-buying goods recommending apparatus according to the first embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a group purchase article recommendation device in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the group purchase article recommending apparatus may include a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 is not limiting of the group buying goods recommendation device, and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a group purchase goods recommendation program may be included in the memory 1005 as one type of storage medium.
In the group-purchased goods recommending device shown in fig. 1, the network interface 1004 is mainly used for carrying out data communication with a network server, the user interface 1003 is mainly used for carrying out data interaction with a user, and the processor 1001 and the memory 1005 in the group-purchased goods recommending device can be arranged in the group-purchased goods recommending device, and the group-purchased goods recommending device calls the group-purchased goods recommending program stored in the memory 1005 through the processor 1001 and executes the group-purchased goods recommending method provided by the embodiment of the invention.
The embodiment of the invention provides a group purchase commodity recommending method, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the group purchase commodity recommending method.
In this embodiment, the group purchase commodity recommendation method includes the following steps:
And step S10, when an access request sent by a target terminal is received, acquiring the current position, user information, purchase record and browsing record corresponding to the target terminal.
It can be understood that the execution body of the embodiment is a group-purchased commodity recommendation device, which may be a computer, a server, or other devices with the same or similar functions, and the embodiment is not limited thereto.
It should be noted that, taking the execution main body as a server installed with a group purchase platform as an example, the target terminal is installed with a corresponding client, when the target terminal starts the client based on user operation, an access request is sent to the server, the server requests corresponding position information to the target terminal according to the received access request, obtains the current position, and queries a database according to a terminal identifier carried by the access request, so as to obtain user information, purchase records and browsing records corresponding to the target terminal. In a specific implementation, the user information includes gender, age, etc., the purchase record is a plurality of purchase records within a period of time, and the browse record is a plurality of browse records within a period of time.
In a specific implementation, the client initiated by the target terminal includes functions of a home page, community preference, community spelling, local living circle, community good store, personal center and the like. In this embodiment, the "community group" function is aimed at, when the target terminal starts the client and enters the community group page under the operation of clicking the "community group" button by the user, the server obtains the current position, the user information, the purchase record and the browse record according to the access request, and recommends a suitable group purchase commodity for the user based on the obtained information.
And step S20, determining a community corresponding to the target terminal according to the current position.
It should be understood that in this embodiment, a community network divided in advance is provided, and a community corresponding to a current location is determined in the community network.
Further, before the step S20, the method further comprises the steps of determining position information corresponding to each group purchase user in a group purchase record of each commodity, reading an initial community dividing grid, determining an initial community corresponding to the position information according to the initial community dividing grid, clustering based on the group purchase record and a plurality of corresponding initial communities, and obtaining a target community dividing grid;
The step S20 comprises the steps of determining a community grid where the current position is located according to the target community division grid, and determining a community corresponding to the target terminal based on the community grid.
It should be noted that, in order to satisfy the user demand, a part of the commodities may be sold only in a part of the communities, and community users who do not sell the commodities also have commodity purchasing demands. In the embodiment, clustering is performed based on initial communities where all users are in a group purchase record, a plurality of initial communities with high relevance are determined, and the plurality of initial communities with the relevance greater than a preset relevance threshold are divided into the same target communities, so that an adjusted target community division grid is obtained. And determining the community in which the target terminal is located based on the current position, wherein the community comprises a plurality of initial communities with high relevance.
And S30, constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record.
It should be understood that the plurality of commodity keywords of each purchase record are extracted from the plurality of purchase records within a period of time, the plurality of commodity keywords of each browse record are extracted from the plurality of browse records within a period of time, and the plurality of extracted commodity keywords are de-duplicated. Optionally, extracting feature vectors from user information (gender and age) and commodity keywords, and classifying the models by inputting the feature vectors into a pre-trained model for classification, and determining corresponding user portraits. In a specific implementation, the classification result of the pre-trained model corresponds to a plurality of preset feature images, the model outputs the similarity between the feature vector and each feature image, and one or more feature images with the similarity larger than a preset similarity threshold are selected as user images corresponding to the target terminal.
Optionally, the step S30 comprises the steps of acquiring portrait features from the user information, the purchase record and the browse record, and constructing a user portrait corresponding to the target terminal based on the portrait features.
The commodity keywords are extracted from the purchase records and the browse records, the extracted commodity keywords are de-duplicated, corresponding correction weights are given to the commodity keywords according to the occurrence times of the commodity keywords, word vectors corresponding to the user information and the commodity keywords are generated, vector average values are calculated based on the word vectors and the correction weights, and the vector average values are used as image data corresponding to the target terminals.
And S40, determining a plurality of commodity types corresponding to the user images.
It should be understood that, optionally, the server stores a correspondence between each feature image and each commodity type, and specifically, the user sets a correspondence table according to actual situations, for example, "electronic contest young" corresponds to "electronic product". Optionally, the portrait data corresponding to the user portrait is obtained, the portrait data is classified according to a preset classification model, the similarity between the portrait data and each commodity type is determined, and one or more commodity types with the similarity larger than a certain threshold value are selected as commodity types corresponding to the user portrait.
And S50, recommending proper group purchase commodities to the target terminal based on the community and the commodity types.
The group-purchased goods matched with the community and a plurality of goods types are selected from all the group-purchased goods to be recommended.
The method comprises the steps of screening all group-purchased goods based on the community and the commodity types to obtain the group-purchased goods, sorting the group-purchased goods to obtain a commodity recommendation sequence, and recommending proper group-purchased goods for the target terminal according to the commodity recommendation sequence.
It should be understood that, in this embodiment, when the user browses the homepage through the target terminal, the server determines the display number according to the layout information of the target terminal, recommends the group-purchased goods with the corresponding number according to the goods sequence according to the display number, and when the user turns the page on the sliding screen, the server determines the update number according to the sliding instruction, recommends the group-purchased goods with the corresponding number according to the goods sequence according to the update number. Optionally, sorting is performed according to the group assembling progress corresponding to the group purchased goods, for example, the group purchased goods with the most progress of only one person are sorted in the first place.
Further, the ordering of the group-purchased goods to obtain a goods recommendation sequence comprises the steps of obtaining image-text description information, purchase quantity and good score corresponding to the group-purchased goods, determining the goods score corresponding to each group-purchased goods according to the image-text description information, the purchase quantity and the good score, and ordering the group-purchased goods based on the goods scores to obtain the goods recommendation sequence.
It should be noted that the number of the substrates, the purchase amount interval and the grade score corresponding to each purchase grade are divided in advance, and the good score interval and the grade score corresponding to each good grade are divided in advance. And determining a purchase amount interval in which the purchase amounts corresponding to the group-purchased goods are located and a good score interval in which the corresponding good scores are located, so as to determine the purchase grades and the good scores corresponding to the group-purchased goods, and determining the purchase grade scores and the good score according to the purchase grades and the good scores. And evaluating the group-purchased goods on the three layers of the text description integrity, the picture quality and the text and picture conformity degree based on the text description information uploaded by the merchant, so as to obtain corresponding text scores. Determining commodity scores corresponding to all group-purchased commodities according to the purchase grade scores, the good grade scores, the image-text scores and the preset weight ratio, and sequencing the commodity scores according to the order from high to low to obtain commodity recommendation orders.
In one implementation, the server analyzes the purchase records of the target terminal, determines the purchase grade score, the good grade score and the image-text score of the commodity purchased by the user, and takes the average value of the purchase grade scores, the average value of the good grade scores and the average value of the image-text scores corresponding to the purchase records. The method comprises the steps of determining purchase quantity attention corresponding to a target terminal by means of a purchase grade grading average value and a standard purchase grade grading percentage, determining good grade attention corresponding to the target terminal by means of a good grade grading average value and a standard good grade grading percentage, determining image-text description attention corresponding to the target terminal by means of an image-text grading average value and a standard image-text grading percentage, normalizing the purchase quantity attention, the good grade attention and the image-text description attention, and determining a preset weight ratio corresponding to the target terminal. And updating the preset weight ratio of the target terminal at intervals, so as to recommend group-purchased goods meeting the user demands and meeting the shopping habits of the user.
The method comprises the steps of obtaining a current position, user information, purchase records and browsing records corresponding to a target terminal when an access request sent by the target terminal is received, determining a community corresponding to the target terminal according to the current position, constructing a user portrait corresponding to the target terminal according to the user information, the purchase records and the browsing records, determining a plurality of commodity types corresponding to the user portrait, and recommending proper group purchase commodities for the target terminal based on the community and the commodity types. By the method, the user portrait corresponding to the target terminal is determined, the group purchase commodity is recommended based on the commodity type corresponding to the user portrait and the community where the target terminal is located, the user demand is automatically acquired, the group purchase commodity is recommended according to the user demand, and the user shopping experience is improved.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of the group purchase product recommending method according to the present invention.
Based on the above-mentioned first embodiment, the group purchase goods recommendation method of this embodiment further includes, after the step S30:
And step S04, pushing corresponding published life circle content to the target terminal based on the community and the user portrait.
It should be understood that, in this embodiment, the "local life circle" function corresponding to the client is aimed at, when the target terminal starts the client and enters the life circle page under the operation of clicking the "local life circle" button by the user, the server obtains the current position, the user information, the purchase record and the browse record according to the access request, and based on the obtained information, pushes the appropriate published life circle content for the user.
The method comprises the steps of determining a plurality of corresponding seller users based on the community, determining a plurality of buyer users corresponding to the user portraits, wherein the similarity between a target user portraits corresponding to the buyer users and the user portraits is larger than a preset threshold, acquiring published life circle contents corresponding to the plurality of seller users and the plurality of buyer users, and pushing the life circle contents to the target terminal.
Optionally, in this embodiment, the user portrait is one of a plurality of preset feature portraits, a similarity between the plurality of feature portraits is set in advance, a similarity between the user portrait of the target terminal and other feature portraits is determined, and one or more feature portraits (including feature portraits corresponding to the user portraits) with a similarity greater than a preset threshold are selected, so as to determine a plurality of corresponding buyer users. Optionally, in this embodiment, the similarity is calculated based on the portrait data corresponding to the user portrait and the portrait data corresponding to each buyer user, and a plurality of buyer users whose similarity is greater than a preset threshold are selected from the calculated similarity.
It can be understood that in this embodiment, life circle content issued by sellers and buyers with user portrait similarity greater than a preset threshold serving as a corresponding community is pushed to a target terminal, so that hit rate of commodity pushing information is improved, a user can conveniently obtain seller description information and buyer evaluation information of interested commodities, and group purchase experience of the user is improved.
The method comprises the steps of obtaining a current position, user information, purchase records and browsing records corresponding to a target terminal when an access request sent by the target terminal is received, determining a community corresponding to the target terminal according to the current position, constructing a user portrait corresponding to the target terminal according to the user information, the purchase records and the browsing records, and pushing corresponding published life circle content to the target terminal based on the community and the user portrait. In the embodiment, besides providing the commodity recommending function, the living circle content issued by the seller or the buyer is recommended to the user according to the user requirement, so that the user can know the actual condition of the required commodity conveniently, and the group purchase experience of the user is improved.
In addition, the embodiment of the invention also provides a storage medium, wherein a group purchase commodity recommendation program is stored on the storage medium, and the group purchase commodity recommendation method is realized when the group purchase commodity recommendation program is executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
Referring to fig. 4, fig. 4 is a block diagram illustrating a first embodiment of a group-buying goods recommending apparatus according to the present invention.
As shown in fig. 4, the group purchase goods recommending device provided by the embodiment of the invention includes:
And the acquisition module 10 is used for acquiring the current position, the user information, the purchase record and the browsing record corresponding to the target terminal when receiving the access request sent by the target terminal.
And the determining module 20 is configured to determine a community corresponding to the target terminal according to the current position.
And the construction module 30 is used for constructing the user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record.
The determining module 20 is further configured to determine a plurality of commodity types corresponding to the user image.
And the recommending module 40 is used for recommending proper group purchase goods for the target terminal based on the community and the commodity types.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
The method comprises the steps of obtaining a current position, user information, purchase records and browsing records corresponding to a target terminal when an access request sent by the target terminal is received, determining a community corresponding to the target terminal according to the current position, constructing a user portrait corresponding to the target terminal according to the user information, the purchase records and the browsing records, determining a plurality of commodity types corresponding to the user portrait, and recommending proper group purchase commodities for the target terminal based on the community and the commodity types. By the method, the user portrait corresponding to the target terminal is determined, the group purchase commodity is recommended based on the commodity type corresponding to the user portrait and the community where the target terminal is located, the user demand is automatically acquired, the group purchase commodity is recommended according to the user demand, and the user shopping experience is improved.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the group purchase goods recommendation method provided in any embodiment of the present invention, which is not described herein.
In an embodiment, the group purchase commodity recommending device further comprises a community dividing module;
The community dividing module is used for determining the position information corresponding to each group purchase user in the group purchase record of each commodity, reading an initial community dividing grid, determining an initial community corresponding to the position information according to the initial community dividing grid, clustering based on the group purchase record and a plurality of corresponding initial communities, and obtaining a target community dividing grid;
The determining module 20 is further configured to determine a community grid where the current location is located according to the target community division grid, and determine a community corresponding to the target terminal based on the community grid.
In an embodiment, the construction module 30 is further configured to obtain portrait features from the user information, the purchase record and the browsing record, and construct a user portrait corresponding to the target terminal based on the portrait features.
In an embodiment, the recommendation module 40 is further configured to screen all the group-purchased goods based on the community and the plurality of goods types to obtain a plurality of group-purchased goods, order the plurality of group-purchased goods to obtain a goods recommendation order, and recommend suitable group-purchased goods for the target terminal according to the goods recommendation order.
In an embodiment, the recommendation module 40 is further configured to obtain graphic description information, purchase amounts and good scores corresponding to the plurality of group-purchased goods, determine a goods score corresponding to each group-purchased goods according to the graphic description information, the purchase amounts and the good scores, and sort the plurality of group-purchased goods based on the goods scores to obtain a goods recommendation sequence.
In an embodiment, the group purchase commodity recommending device further comprises a message pushing module;
And the message pushing module is used for pushing the corresponding published life circle content to the target terminal based on the community and the user portrait.
In an embodiment, the message pushing module is further configured to determine a plurality of corresponding seller users based on the community, determine a plurality of buyer users corresponding to the user portraits, wherein a similarity between a target user portraits corresponding to the buyer users and the user portraits is greater than a preset threshold, obtain published life circle content corresponding to the plurality of seller users and the plurality of buyer users, and push the published life circle content to the target terminal.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. The group purchase commodity recommending method is characterized by comprising the following steps of:
When an access request sent by a target terminal is received, acquiring a current position, user information, a purchase record and a browsing record corresponding to the target terminal;
Determining a community corresponding to the target terminal according to the current position;
constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record;
Determining a plurality of commodity types corresponding to the user images;
recommending proper group purchase commodities to the target terminal based on the community and the commodity types;
Before the community corresponding to the target terminal is determined according to the current position, the method further comprises the following steps:
determining position information corresponding to each group purchase user in the group purchase record of each commodity;
reading an initial community dividing grid, and determining an initial community corresponding to the position information according to the initial community dividing grid;
clustering based on the group purchase records and the corresponding multiple initial communities to obtain a target community division grid;
Clustering based on the group purchase records and a plurality of corresponding initial communities to obtain a target community division grid, wherein the step of obtaining the target community division grid comprises the steps of dividing the plurality of initial communities with the association degree larger than a preset association degree threshold into the same target community to obtain an adjusted target community division grid;
the determining the community corresponding to the target terminal according to the current position comprises the following steps:
Determining a community grid where the current position is located according to the target community division grid;
and determining communities corresponding to the target terminals based on the community grids, wherein the communities comprise a plurality of initial communities with high relevance.
2. The group purchase commodity recommending method according to claim 1, wherein the constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browse record comprises:
Acquiring portrait features from the user information, the purchase records and the browse records;
and constructing the user portrait corresponding to the target terminal based on the portrait features.
3. The group purchase commodity recommending method according to claim 1, wherein the recommending a suitable group purchase commodity for the target terminal based on the community and the plurality of commodity types includes:
screening all the group-purchased goods based on the community and the commodity types to obtain a plurality of group-purchased goods;
sequencing the plurality of group-purchased commodities to obtain a commodity recommendation sequence;
and recommending proper group purchase commodities to the target terminal according to the commodity recommendation sequence.
4. The method for recommending group-purchased goods according to claim 3, wherein the sorting the plurality of group-purchased goods to obtain a goods recommending order comprises:
Acquiring graphic description information, purchase quantity and good score corresponding to the group-purchased commodities;
determining commodity scores corresponding to all the group-purchased commodities according to the graphic description information, the purchase quantity and the good score;
And sequencing the group-purchased commodities based on the commodity scores to obtain a commodity recommendation sequence.
5. The group purchase commodity recommending method according to claim 1, wherein after the constructing the user portraits corresponding to the target terminals according to the user information, the purchase records and the browsing records, the method further comprises:
And pushing corresponding published life circle content to the target terminal based on the community and the user portrait.
6. The group purchase commodity recommending method according to claim 5, wherein the pushing the corresponding published life circle content to the target terminal based on the community and the user portraits comprises:
Determining a corresponding number of seller users based on the community;
determining a plurality of buyer users corresponding to the user portraits, wherein the similarity between the target user portraits corresponding to the buyer users and the user portraits is larger than a preset threshold;
and acquiring the published life circle content corresponding to the seller users and the buyer users, and pushing the published life circle content to the target terminal.
7. A group-purchased goods recommending device, characterized in that the group-purchased goods recommending device comprises:
The acquisition module is used for acquiring the current position, the user information, the purchase record and the browsing record corresponding to the target terminal when receiving the access request sent by the target terminal;
the determining module is used for determining communities corresponding to the target terminals according to the current positions;
the construction module is used for constructing a user portrait corresponding to the target terminal according to the user information, the purchase record and the browsing record;
the determining module is further used for determining a plurality of commodity types corresponding to the user image;
the recommending module is used for recommending proper group purchase commodities to the target terminal based on the community and the commodity types;
the group purchase commodity recommending device further comprises a community dividing module;
The community dividing module is used for determining the position information corresponding to each group purchase user in the group purchase record of each commodity, reading an initial community dividing grid, determining an initial community corresponding to the position information according to the initial community dividing grid, clustering based on the group purchase record and a plurality of corresponding initial communities to obtain a target community dividing grid, clustering based on the group purchase record and a plurality of corresponding initial communities to obtain the target community dividing grid, wherein the step of dividing the plurality of initial communities with the association degree larger than a preset association degree threshold into the same target community to obtain an adjusted target community dividing grid;
The determining module is further used for determining a community grid where the current position is located according to the target community division grid, and determining communities corresponding to the target terminals based on the community grid, wherein the communities comprise a plurality of initial communities with high relevance.
8. A group purchase commodity recommending apparatus, characterized in that the apparatus comprises a memory, a processor, and a group purchase commodity recommending program stored on the memory and executable on the processor, the group purchase commodity recommending program being configured to implement the group purchase commodity recommending method according to any one of claims 1 to 6.
9. A storage medium having stored thereon a group purchase article recommendation program which, when executed by a processor, implements the group purchase article recommendation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210432888.0A CN114820123B (en) | 2022-04-22 | 2022-04-22 | Group purchase commodity recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210432888.0A CN114820123B (en) | 2022-04-22 | 2022-04-22 | Group purchase commodity recommendation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114820123A CN114820123A (en) | 2022-07-29 |
| CN114820123B true CN114820123B (en) | 2025-09-19 |
Family
ID=82507472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210432888.0A Active CN114820123B (en) | 2022-04-22 | 2022-04-22 | Group purchase commodity recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114820123B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115375414B (en) * | 2022-10-25 | 2023-04-07 | 湖南有态度网络科技有限公司 | Community group purchase commodity recommendation method and device based on big data, electronic equipment and storage medium |
| CN115730970A (en) * | 2022-11-09 | 2023-03-03 | 阿里巴巴（中国）有限公司 | Processing method based on group buying behavior, electronic equipment and storage medium |
| CN115795408B (en) * | 2023-02-06 | 2023-04-25 | 北京师范大学 | Intelligent community commodity big data intelligent bill spelling and settlement method based on blockchain |
| CN116089740B (en) * | 2023-03-11 | 2023-11-07 | 深圳市针线科技有限公司 | Group purchase information retrieval method and system based on social network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945531A (en) * | 2012-10-24 | 2013-02-27 | 江苏乐买到网络科技有限公司 | Group purchase method based on geographic position |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | Product recommendation method and system for e-commerce platform based on user dynamic classification |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120033560A (en) * | 2010-09-30 | 2012-04-09 | 비씨카드(주) | Method for social commerce service and recording media implementing the same |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN112015998B (en) * | 2020-11-02 | 2021-02-09 | 北京值得买科技股份有限公司 | Commodity recommendation method based on user portrait |
-
2022
- 2022-04-22 CN CN202210432888.0A patent/CN114820123B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945531A (en) * | 2012-10-24 | 2013-02-27 | 江苏乐买到网络科技有限公司 | Group purchase method based on geographic position |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | Product recommendation method and system for e-commerce platform based on user dynamic classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114820123A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114820123B (en) | Group purchase commodity recommendation method, device, equipment and storage medium | |
| CN107424043B (en) | Product recommendation method and device and electronic equipment | |
| US11682060B2 (en) | Methods and apparatuses for providing search results using embedding-based retrieval | |
| CN108648058B (en) | Product sorting method and device, electronic equipment and storage medium | |
| US9384278B2 (en) | Methods and systems for assessing excessive accessory listings in search results | |
| US9330071B1 (en) | Tag merging | |
| JP6976207B2 (en) | Information processing equipment, information processing methods, and programs | |
| US20180012284A1 (en) | Information analysis apparatus, information analysis method, and non-transitory computer readable storage medium | |
| CN111654714A (en) | Information processing method, device, electronic equipment and storage medium | |
| CN110737831A (en) | System and method for adapting search results | |
| US9542077B2 (en) | Information processing apparatus, information processing method, information processing program, and recording medium | |
| CN110674391A (en) | Product data pushing method and system based on big data and computer equipment | |
| CN115168700A (en) | Information flow recommendation method, system and medium based on pre-training algorithm | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN113781171A (en) | Information pushing method, device, equipment and storage medium | |
| US12100032B2 (en) | Learning device, computer-readable information storage medium, and learning method | |
| CN109144953B (en) | Search file sorting method, device, equipment, storage medium and search system | |
| CN114971760A (en) | Vehicle type recommendation method and device based on big data, electronic equipment and medium | |
| CN118485493A (en) | Product recommendation method, device and storage medium | |
| CN112328918A (en) | Commodity sorting method, computing device and computer-readable storage medium | |
| CN113902023B (en) | Training sample processing method, computing device and storage medium for sorting model | |
| CN117541350A (en) | Product pushing method, device, computer equipment and storage medium | |
| JP7354329B2 (en) | Information processing device, information processing method, and program | |
| JP6783133B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN113837846A (en) | Commodity recommendation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |