CN113313545A - Information recommendation method and device, computer equipment and storage medium - Google Patents

Information recommendation method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN113313545A
CN113313545A CN202110417980.5A CN202110417980A CN113313545A CN 113313545 A CN113313545 A CN 113313545A CN 202110417980 A CN202110417980 A CN 202110417980A CN 113313545 A CN113313545 A CN 113313545A
Authority
CN
China
Prior art keywords
information
user
commodity
portrait data
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110417980.5A
Other languages
Chinese (zh)
Other versions
CN113313545B (en
Inventor
陈智鑫
邓华武
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Zhumang Information Technology Co ltd
Original Assignee
Shenzhen Zhumang Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Zhumang Information Technology Co ltd filed Critical Shenzhen Zhumang Information Technology Co ltd
Priority to CN202110417980.5A priority Critical patent/CN113313545B/en
Publication of CN113313545A publication Critical patent/CN113313545A/en
Application granted granted Critical
Publication of CN113313545B publication Critical patent/CN113313545B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/0042—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an information recommendation method, an information recommendation device, computer equipment and a storage medium, wherein when a shared article is leased, user portrait data are obtained according to a user identifier; and obtaining a rental cabinet identifier; then, searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information; predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction popularization information; and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal. The method and the system increase the function of the lending system, and can carry out targeted information recommendation to the user when the shared article is lent.

Description

Information recommendation method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to an information recommendation method and apparatus, a computer device, and a storage medium.
Background
With the development of science and technology, although the use of the mobile power supply is more and more extensive, the mobile power supply still has inconvenience for users because the mobile power supply occupies a certain storage space and has a certain weight, and therefore, a shared mobile power supply for providing a mobile power supply leasing service for the users is produced.
In order to facilitate renting of users, a shared mobile power supply enterprise often performs product release in multiple places. However, in the conventional technology, the utilization rate of the shared mobile power source is affected by the functional singleness of the shared mobile power source leasing system.
Disclosure of Invention
In view of the above, it is necessary to provide an information recommendation method, an apparatus, a computer device, and a storage medium capable of diversifying the functions of the shared portable power source leasing system in order to solve the above technical problems.
An information recommendation method, the method comprising:
when the shared article is rented, user portrait data is obtained according to the user identification;
acquiring a rental cabinet identifier; the rental cabinet is used for providing the shared goods for the user;
searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information;
predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction popularization information;
and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal.
In one embodiment, the obtaining user representation data based on the user identifier includes:
collecting user behavior data and user attribute data according to the user identification;
and generating the user portrait data according to the user behavior data and the user attribute data.
In one embodiment, the rental cabinet is associated with a sales cabinet; the method comprises the following steps of searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information, and comprises the following steps:
and searching according to the user portrait data to obtain preset popularization information including at least one of a target sales counter and discount information matched with the user portrait data.
In one embodiment, the method further comprises:
acquiring crowd portrait information of user crowds corresponding to the preset popularization information;
and adjusting the preset popularization information according to the crowd portrait information.
In one embodiment, the manner of generating the people portrait information includes:
acquiring user portrait data of a plurality of users in the user crowd;
extracting keywords from the portrait data of each user to obtain a feature tag of each user;
and clustering the feature labels of the users to obtain the crowd portrait information.
In one embodiment, the method further comprises:
and responding to the renting instruction of the shared article, controlling the shared article to be ejected out of the renting cabinet, and simultaneously placing the commodity into the goods taking port position of the target sales cabinet.
In one embodiment, the searching according to the user portrait data and/or the rental cabinet identifier to obtain corresponding preset popularization information includes:
acquiring preset popularization information of an operation area where the rental cabinet is located according to the rental cabinet identifier;
and determining preset popularization information corresponding to the user portrait data in the preset popularization information of the operation area.
In one embodiment, the predicting the commodity of interest to the user according to the user portrait data to obtain corresponding prediction popularization information includes:
inputting the user portrait data into a logistic regression model to obtain the recommendation probability of each commodity;
and determining the commodity with the recommendation probability meeting the preset condition as the commodity interested by the user, and obtaining the prediction popularization information corresponding to the user portrait data.
In one embodiment, the position information corresponding to the predicted promotion information is shop position information of a commodity which is interested by the user; the store position information of the product in which the user is interested is determined by the corresponding relation between the product information and the store position information.
In one embodiment, a generation manner of the correspondence between the commodity information and the store location information includes:
acquiring information of each commodity and shop position information of each commodity, wherein the shop position information comprises an identifier of a rental cabinet identifier;
and establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities.
An information recommendation apparatus, the apparatus comprising:
the portrait data acquisition module is used for acquiring user portrait data according to the user identification when the shared article is rented;
the rental cabinet identification acquisition module is used for acquiring the rental cabinet identification; the rental cabinet is used for providing the shared goods for the user;
the preset information searching module is used for searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information;
the promotion information prediction module is used for predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction promotion information;
and the position information recommending module is used for recommending the position information corresponding to the prediction popularization information to the user terminal if the preset popularization information is matched with the prediction popularization information.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the information recommendation method, the information recommendation device, the computer equipment and the storage medium, when the shared article is leased, the user portrait data are obtained according to the user identification; and obtaining a rental cabinet identifier; then, searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information; predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction popularization information; and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal. The method and the system increase the function of the lending system, and can carry out targeted information recommendation to the user when the shared article is lent.
Drawings
FIG. 1 is a diagram of an application environment of a method for information recommendation in one embodiment;
FIG. 2 is a flow diagram illustrating a method for information recommendation in one embodiment;
FIG. 3 is a flowchart illustrating step S210 according to an embodiment;
FIG. 4 is a flowchart illustrating an information recommendation method according to another embodiment;
FIG. 5 is a flow diagram illustrating a method for generating people profile information in accordance with one embodiment;
FIG. 6 is a diagram illustrating the relationship between rental containers and sales containers in one embodiment;
FIG. 7 is a flowchart illustrating step S230 according to an embodiment;
FIG. 8 is a flowchart illustrating step S240 according to an embodiment;
FIG. 9 is a flowchart illustrating a method of generating correspondence between merchandise information and store location information according to an embodiment;
FIG. 10 is a block diagram showing a schematic configuration of an information recommendation apparatus according to an embodiment;
FIG. 11 is a diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The information recommendation method provided by the application can be applied to the application environment shown in fig. 1. The system comprises a plurality of leasing cabinets 110, a server 120 and a terminal 130, wherein each leasing cabinet 110 is in communication connection with the server 120, and the server 120 is in communication connection with the terminal 130. Rental cabinet 110 is used to hold a number of shared items to provide the shared items to the user. When the shared goods in any rental cabinet 110 are rented by the user, the user terminal sends the user identification to the server 120, and the rental cabinet 110 sends the rental cabinet identification to the server 120. The server 120 acquires user portrait data according to the user identification, acquires a rental cabinet identification, and searches according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information. If the server 120 can be deployed with a prediction model, predicting the commodity interested by the user according to the user portrait data based on the prediction model to obtain corresponding prediction popularization information; and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal.
It should be noted that the shared article may be a shared article of daily use, such as a shared umbrella, a shared charger baby, a shared book, and the like. The terminal 130 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 120 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, an information recommendation method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s210, when the shared goods are leased, user portrait data are obtained according to the user identification.
And S220, acquiring the rental cabinet identifier.
Wherein the rental cabinet is used for providing the shared goods for the user. When the user needs to use the shared article, the shared article is rented from the rental cabinet, the rental cabinet can send the rental cabinet identifier to the server, and the user terminal sends the user identifier to the server. In some embodiments, the database of the server may store the user portrait data in advance, and the server obtains the user portrait data from the database according to the user identification after receiving the user identification. In other embodiments, user representation data is stored on a computer device communicatively coupled to a server, and the server retrieves the user representation data from the computer device based on a user identification.
And S230, searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information.
The preset promotion information is promotion information stored in the server or computer equipment in communication connection with the server in advance. The preset promotion information may be commodity type information (men's clothing, tableware, restaurants, living goods, cosmetics, skin care products, etc.), shop location information, commodity preference information, etc., and the preset promotion information may also be advertisement information, movie publicity information, etc. The preset promotion information can also lease the geographic position of a retail sales counter associated with the counter or preferential information and the like. Specifically, in one embodiment, the user portrait data may reflect interests of the user or needs of the user, and thus, corresponding preset popularization information is searched according to the user portrait data. In another embodiment, the rental cabinet is placed at a fixed geographic location, and the server stores that the rental cabinet identification has a corresponding relationship with the geographic location of the rental cabinet. Various types of shops or various types of sales counter corresponding to the renting cabinet are distributed around the geographic position of the renting cabinet, the corresponding relation between the renting cabinet identification and the preset popularization information can be stored in the server in advance, and the corresponding preset popularization information can be obtained by searching according to the renting cabinet identification. In other embodiments, the server stores the corresponding relationship between the user portrait data, the rental cabinet identifier and the preset popularization information in advance, and the server can search according to the user portrait data and the rental cabinet identifier to obtain the corresponding preset popularization information.
S240, predicting the commodity interested by the user according to the user portrait data to obtain corresponding prediction popularization information.
The predicted promotion information is promotion information obtained by predicting commodities which are interested by the user, for example, the predicted promotion information can be restaurants with 'suo side dishes' by predicting that the user is likely to be interested in the suo side dishes according to the user portrait data. For another example, if it is predicted that the user may be interested in early education according to the user portrait data, the predicted popularization information may be an early education mechanism of "XX baby". Specifically, the server side can be deployed with a prediction model, user portrait data is input into the prediction model, a series of commodities is obtained, the probability that the user is interested in the commodities is obtained, the commodities which the user is interested in are determined from the commodities according to the probability of each commodity, and corresponding prediction popularization information is obtained. It should be noted that there are many ways to implement the prediction model, such as a content-based recommendation algorithm, a collaborative filtering-based recommendation algorithm, an association rule-based recommendation algorithm, a utility-based recommendation algorithm, a knowledge-based recommendation algorithm, and the like. In some embodiments, a collaborative filtering recommendation algorithm may be adopted, and a prediction model is established through a machine learning algorithm, so as to predict the commodity of interest to the user. Machine learning algorithms suitable for collaborative filtering recommendation are various, such as Aspect Model, PLSA, LDA, clustering, SVD, Matrix Factorization, LR, and GBDT.
And S250, if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal.
Specifically, preset popularization information is compared with predicted popularization information, and if the preset popularization information is matched with the predicted popularization information, position information corresponding to the predicted popularization information is recommended to a user terminal. For example, if the predicted promotion information is french fries, and the preset promotion information includes a certain brand fast food restaurant, the french fries are matched with the brand fast food restaurant, and the position information of the brand fast food restaurant is recommended to the user terminal, so that the user is guided to go to the brand fast food restaurant for consumption. If the predicted promotion information is fried chicken, when the preset promotion information is a nail shop, the fried chicken may not be matched with the nail shop.
In the embodiment, when the shared article is rented, user portrait data is acquired according to the user identification; and obtaining a rental cabinet identifier; then, searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information; predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction popularization information; and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal. On one hand, the function of the renting system is added, and information recommendation can be conducted on the shared goods in a targeted mode to the user when the shared goods are rented. On the other hand, the enthusiasm of the user for using the leasing system is improved through diversifying the functions of the leasing system, so that the utilization rate of shared articles is improved.
In one embodiment, as shown in FIG. 3, in step S210, the obtaining user portrait data according to the user identifier includes:
s310, collecting user behavior data and user attribute data according to the user identification.
And S320, generating the user portrait data according to the user behavior data and the user attribute data.
The user behavior data may include data related to user shopping (such as user shopping habit data, online shopping order data, offline transaction data, and the like), webpage data browsed by the user, and other operation behavior data of the user at the user terminal. The user attribute data may be information such as gender and age of the user, or the user attribute data may be data such as young, middle, 80 th, 90 th, and the like. The user attribute data may be user data filled in by the user when registering the application, or may be user attribute data obtained by predicting the user data. Specifically, user behavior data and user attribute data such as user shopping habits are collected according to the user identification, the user attribute data are collected according to the user identification, and the user behavior data and the user attribute data are analyzed to obtain user portrait data. The user representation data may reflect user preferences or user interests.
In this embodiment, user behavior data and user attribute data are collected according to the user identifier. And generating the user portrait data according to the user behavior data and the user attribute data. The user portrait data provides an accurate data base for follow-up prediction of commodities which are interested in the user, and the user retention rate can be improved through accurate information recommendation.
In one embodiment, the rental cabinet is associated with a sales cabinet; in step S230, the searching according to the user portrait data and/or the rental cabinet identifier to obtain corresponding preset popularization information includes: and searching according to the user portrait data to obtain preset popularization information including at least one of a target sales counter and discount information matched with the user portrait data.
Specifically, the rental cabinet is associated with a sales cabinet, and the types of the sales cabinet are various, such as a sales cabinet selling snacks, a book cabinet selling books, a cabinet selling beverages, or a cabinet selling tissues, and the like. A target sales counter matching the user representation data may be selected from sales counters associated with the rental counter based on the user representation data. Preferential discount information matched with the user portrait data can be searched according to the user portrait data, for example, preferential discount information of a certain brand of milk powder in a mother-and-baby shop can be searched if the user portrait data comprises 80 Yuebao.
In this embodiment, preset promotion information including at least one of a target sales counter and discount information matched with the user portrait data is obtained by searching according to the user portrait data, so that accurate information recommendation and navigation guidance are performed on a user.
In one embodiment, as shown in fig. 4, the method further comprises:
and S410, acquiring the crowd portrait information of the user crowd corresponding to the preset popularization information.
And S420, adjusting the preset popularization information according to the crowd portrait information.
In particular, the user population includes a plurality of users, each corresponding to respective user representation data. The crowd portrait information can be obtained through user portrait data of a plurality of users, and the server stores the corresponding relation between preset popularization information and user crowds and the corresponding relation between the user crowds and the crowd portrait information. After the preset popularization information is determined, the corresponding user crowd can be determined according to the corresponding relation between the preset popularization information and the user crowd, and therefore the crowd portrait information of the user crowd is obtained. The crowd image information is user data for the user crowd, such as 80 th or 90 th crowd, or Buddha series, food, business, lipstick, etc. The crowd image information can reflect the overall characteristics of the crowd of the user, and the user induces the commonalities presented by the crowd, so that the preset popularization information is adjusted by utilizing the crowd image information. Illustratively, after the crowd portrayal information comprises 90, the recommended scheme may be adjusted according to the crowd portrayal information after 90.
In the embodiment, the crowd portrait information of the user crowd corresponding to the preset popularization information is obtained; and adjusting the preset popularization information according to the crowd portrait information. The accuracy of information recommendation is further improved, and more accurate guidance is provided for the user.
In one embodiment, as shown in fig. 5, the generation manner of the people portrait information includes:
and S510, acquiring user portrait data of a plurality of users in the user crowd.
S520, extracting keywords from the portrait data of each user to obtain a feature tag of each user.
S530, clustering the feature labels of the users to obtain the crowd portrait information.
The user portrait data includes behavior data, browsing data, and attribute data. In some embodiments, a variety of clustering algorithms may be employed, such as: K-Means clustering, mean shift clustering, density-based clustering, maximum Expectation (EM) clustering with Gaussian Mixture Model (GMM), agglomerative hierarchical clustering, and graph community detection clustering, among others. Specifically, for a certain user crowd, a plurality of users are arranged in the user crowd, user portrait data of each user in the user crowd is obtained, and keyword extraction is performed on the user portrait data to obtain a feature tag of each user. And clustering the feature labels by using a clustering algorithm to obtain the crowd portrait information of the user crowd.
In some embodiments, K-Means clustering may be employed, including the specific steps of: (1) first some classes/groups (i.e. certain feature tags) are selected and their respective center points are randomly initialized. The center point is the same length position as each data point vector. This requires a priori knowledge of the number of classes (i.e. the number of center points). (2) The distance of each data point to the center point is calculated, and the class to which the data point is closest to which center point is classified. (3) The center point of each class is calculated as the new center point. (4) Repeating the steps (1) to (3) until the center of each class does not change much after each iteration. It is also possible to randomly initialize the center point multiple times and then select the one that has the best run result. Each category represents people profile information of a user population.
In the embodiment, the crowd portrait information of the user crowd is obtained through the clustering algorithm, an accurate data base is provided for adjusting the preset popularization information, and the information recommended to the user is guaranteed to comprise commodities or shops interested by the user.
In one embodiment, the method further comprises: and responding to the renting instruction of the shared article, controlling the shared article to be ejected out of the renting cabinet, and simultaneously placing the commodity into the goods taking port position of the target sales cabinet.
Specifically, as shown in fig. 6, rental cabinet 620 is associated with a sales cabinet 610. When a user triggers a renting instruction of the shared article, the server receives the renting instruction, and sends an instruction of popping up the shared article to the renting cabinet to control the shared article to pop up from the renting cabinet. Meanwhile, if the user chooses to purchase the recommended interested commodity, the server sends an instruction for releasing the interested commodity of the user to a target sales counter associated with the rental cabinet, and the target sales counter releases the interested commodity of the user to the position of a goods taking port of the target sales counter. It should be noted that the rental cabinet 620 and the sales counter 610 may be structurally connected, for example, the sales counter 610 is located above or below the rental cabinet 620, and the sales counter 610 is located on the left side or the right side of the rental cabinet 620. The rental cabinet 620 and the sales cabinet 610 may be structurally separated, but both the rental cabinet 620 and the sales cabinet 610 may be remotely controlled by a server or a terminal at the same time, such as simultaneously completing the purchase of the shared goods when renting the shared goods, or completing the rental of the shared goods when purchasing the goods.
In the embodiment, the rental cabinet and the sales counter are associated, when the user rents the shared article, the shared article can be obtained from the rental cabinet, the commodity which the user is interested in can be obtained from the target sales counter, the functions of the rental cabinet are expanded, the requirements of the user on renting the shared article and shopping are met, and the operation cost of the user is reduced.
In an embodiment, as shown in fig. 7, in step S230, the searching according to the user portrait data and/or the rental cabinet identifier to obtain corresponding preset promoting information includes:
and S710, acquiring preset popularization information of the operation area where the rental cabinet is located according to the rental cabinet identifier.
S720, in the preset popularization information of the operation area, the preset popularization information corresponding to the user portrait data is determined.
Specifically, the server stores a corresponding relationship between the rental cabinet identifier and the operation area where the rental cabinet is located, and a corresponding relationship between the operation area and the preset popularization information. And determining an operation area where the rental cabinet is located according to the rental cabinet identifier, and acquiring preset popularization information such as shops, commodity offers and the like located in the operation area according to the operation area where the rental cabinet is located. Further, the server stores the corresponding relationship between the user portrait data and the preset popularization information, and the corresponding preset popularization information can be determined in the preset popularization information of the operation area according to the user portrait data.
In the embodiment, the preset promotion information of the operation area where the rental cabinet is located is obtained according to the rental cabinet identifier; and in the preset popularization information of the operation area, the preset popularization information corresponding to the user portrait data is determined, the preset popularization information near the rental cabinet is pertinently recommended to the user, and the conversion rate of the popularization information is improved.
In one embodiment, as shown in fig. 8, in step S240, the predicting the product in which the user is interested according to the user portrait data to obtain corresponding predicted popularization information includes:
and S810, inputting the user portrait data into a logistic regression model to obtain the recommendation probability of each commodity.
S820, determining the commodity with the recommendation probability meeting the preset condition as the commodity interesting the user, and obtaining the prediction popularization information corresponding to the user portrait data.
In some embodiments, the logistic regression model may adopt an LR (logistic regression) model, and the recommendation probability of each commodity is calculated by the LR model, so that all commodities are ranked according to the recommendation probability, and the commodity with the highest recommendation probability is selected as the recommended commodity. It will be appreciated that it is also possible to select several items that are top ranked. Specifically, the user image data is input to a logistic regression model, the probability of the user purchasing each commodity is performed according to the user image data through the logistic regression model, and the probability of the user purchasing each commodity is used as the recommendation probability of each commodity. The commodities can be sorted according to the recommendation probability of the commodities, and a preset number of commodities can be used as commodities which are interested by the user from high to low, so that the corresponding prediction popularization information of the user portrait data is obtained. Or a probability threshold value may be preset, and if the recommendation probability of the commodity is greater than the probability threshold value, the commodity is a commodity which the user is interested in. The commodity with the highest recommendation probability can be used for determining the commodity which is interested by the user.
In this embodiment, the user portrait data is input to a logistic regression model, so as to obtain the recommendation probability of each commodity. And determining the commodity with the recommendation probability meeting the preset condition as the commodity interested by the user to obtain the prediction popularization information corresponding to the user portrait data.
In one embodiment, the preset popularization information is compared with the predicted popularization information, and if the preset popularization information is matched with the predicted popularization information, the position information corresponding to the predicted popularization information is recommended to the user terminal. Specifically, the position information corresponding to the predicted promotion information is store position information of the commodity of interest to the user; the store position information of the product in which the user is interested is determined by the corresponding relation between the product information and the store position information.
In one embodiment, as shown in fig. 9, a generation method of the correspondence between the product information and the store location information includes:
s910, obtaining information of each commodity and shop position information of each commodity, wherein the shop position information comprises an identifier of a rental cabinet identifier.
S920, establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities.
Specifically, the user portrait data is predicted to obtain the commodity interested by the user, so that the shop or the shop selling the commodity can be determined according to the commodity information of the commodity interested by the user, and the shop position information is determined as the position information corresponding to the predicted popularization information. The correspondence relationship between the commodity information and the store position information is established in advance, and it is necessary to acquire each commodity information and store position information of each commodity. The store location information may include an identifier of the rental cabinet identification (e.g., the rental cabinet identification may be a-21, and the identifier is a, which may be used to identify the operating area in which the rental cabinet is located). And establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities. Illustratively, the predicted promotion information may include a peripheral store type and a type of a commodity sold in the store. For example, the peripheral store types are classified by brand into a "premium clothing store", ZARA, HM ", and the like, or classified by product type into a" gold jewelry store ", a" dining store ", and an" apparel store ", and the like. The kinds of products sold in stores are classified into men's clothing, tableware, umbrellas, watches, and the like. Each commodity information is associated with the rental cabinet identification clothes in advance, and therefore the preset popularization information can be obtained through the rental cabinet identification clothes. For example, if the identifiers of the rental stores located in mall A are all A, such as A-001, A-002, then the stores or items sold in mall A may be associated with the prefix A, such as A-HM, A-HM-men's clothing.
In one embodiment, the present application provides an information recommendation method, including:
and S1010, collecting user behavior data and user attribute data according to the user identification when the shared article is leased.
S1020, generating the user portrait data according to the user behavior data and the user attribute data.
And S1030, acquiring a rental cabinet identifier.
Wherein the rental cabinet is associated with a sales counter; the rental cabinet is used for providing the shared goods for the user;
and S1040, searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information.
Specifically, searching is carried out according to the user portrait data, and preset popularization information including at least one of a target sales counter and discount information matched with the user portrait data is obtained. Or
Acquiring preset popularization information of an operation area where the rental cabinet is located according to the rental cabinet identifier; and determining preset popularization information corresponding to the user portrait data in the preset popularization information of the operation area.
And S1050, acquiring the crowd portrait information of the user crowd corresponding to the preset popularization information.
And S1060, adjusting the preset popularization information according to the crowd portrait information.
And S1070, predicting the commodity interested by the user according to the user portrait data to obtain corresponding prediction popularization information.
Specifically, the user portrait data is input into a logistic regression model to obtain the recommendation probability of each commodity; and determining the commodity with the recommendation probability meeting the preset condition as the commodity interested by the user, and obtaining the prediction popularization information corresponding to the user portrait data.
And S1080, if the adjusted preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to the user terminal.
The position information corresponding to the prediction popularization information is shop position information of the commodity which the user is interested in; the store position information of the product in which the user is interested is determined by the corresponding relation between the product information and the store position information.
Further, a generation method of the correspondence between the product information and the store position information includes: acquiring information of each commodity and shop position information of each commodity, wherein the shop position information comprises an identifier of a rental cabinet identifier; and establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the above-mentioned flowcharts may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or the stages is not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a part of the steps or the stages in other steps.
In one embodiment, as shown in fig. 10, there is provided an information recommendation apparatus including: portrait data acquisition module 1010, lease cabinet identification acquisition module 1020, preset information search module 1030, promotion information prediction module 1040 and position information recommendation module 1050, wherein:
a portrait data acquisition module 1010, configured to acquire user portrait data according to the user identifier when the shared item is rented.
A rental cabinet identifier obtaining module 1020 for obtaining a rental cabinet identifier; the rental cabinet is used for providing the shared goods for the user.
And the preset information searching module 1030 is configured to search according to the user portrait data and/or the rental cabinet identifier to obtain corresponding preset popularization information.
And the promotion information prediction module 1040 is configured to predict the commodity of interest to the user according to the user portrait data, so as to obtain corresponding prediction promotion information.
And a location information recommending module 1050, configured to recommend location information corresponding to the predicted popularization information to the user terminal if the preset popularization information matches the predicted popularization information.
In one embodiment, the representation data obtaining module 1010 is further configured to collect user behavior data and user attribute data according to the user identifier; and generating the user portrait data according to the user behavior data and the user attribute data.
In an embodiment, the preset information searching module 1030 is further configured to search according to the user portrait data to obtain preset popularization information including at least one of a target sales counter and discount information matched with the user portrait data.
In one embodiment, the device further comprises a crowd information acquisition module and a promotion information adjustment module; wherein:
and the crowd information acquisition module is used for acquiring the crowd portrait information of the user crowd corresponding to the preset popularization information.
And the popularization information adjusting module is used for adjusting the preset popularization information according to the crowd portrait information.
In one embodiment, the apparatus further comprises a crowd information generation module for obtaining user representation data for a plurality of users within the crowd of users; extracting keywords from the portrait data of each user to obtain a feature tag of each user; and clustering the feature labels of the users to obtain the crowd portrait information.
In one embodiment, the apparatus further comprises a lease sale module for controlling the shared article to be ejected from the lease cabinet and simultaneously placing the commodity into the goods taking port of the target sale cabinet in response to a lease instruction of the shared article.
In an embodiment, the preset information searching module 1030 is further configured to obtain preset popularization information of an operation area where the rental cabinet is located according to the rental cabinet identifier; and determining preset popularization information corresponding to the user portrait data in the preset popularization information of the operation area.
In one embodiment, the promotion information prediction module 1040 is further configured to input the user portrait data to a logistic regression model to obtain a recommendation probability of each commodity; and determining the commodity with the recommendation probability meeting the preset condition as the commodity interested by the user, and obtaining the prediction popularization information corresponding to the user portrait data.
In one embodiment, the position information corresponding to the predicted promotion information is shop position information of a commodity which is interested by the user; the store position information of the product in which the user is interested is determined by the corresponding relation between the product information and the store position information.
In one embodiment, the device further comprises a corresponding relation generating module, configured to obtain information of each commodity and store location information of each commodity, where the store location information includes an identifier of a rental cabinet identifier; and establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities.
For specific limitations of the information recommendation device, reference may be made to the above limitations of the information recommendation method, which are not described herein again. The modules in the information recommendation device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an information recommendation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is provided, comprising a memory in which a computer program is stored and a processor, the processor executing the method steps of any of the above embodiments when the computer program is executed.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, realizes the method steps of any of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (13)

1. An information recommendation method, characterized in that the method comprises:
when the shared article is rented, user portrait data is obtained according to the user identification;
acquiring a rental cabinet identifier; the rental cabinet is used for providing the shared goods for the user;
searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information;
predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction popularization information;
and if the preset popularization information is matched with the prediction popularization information, recommending the position information corresponding to the prediction popularization information to a user terminal.
2. The method of claim 1, wherein said retrieving user representation data based on a user identification comprises:
collecting user behavior data and user attribute data according to the user identification;
and generating the user portrait data according to the user behavior data and the user attribute data.
3. The method of claim 2, wherein the rental cabinet is associated with a sales cabinet; the method comprises the following steps of searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information, and comprises the following steps:
and searching according to the user portrait data to obtain preset popularization information including at least one of a target sales counter and discount information matched with the user portrait data.
4. The method of claim 3, further comprising:
acquiring crowd portrait information of user crowds corresponding to the preset popularization information;
and adjusting the preset popularization information according to the crowd portrait information.
5. The method of claim 4, wherein the manner of generating the people profile information comprises:
acquiring user portrait data of a plurality of users in the user crowd;
extracting keywords from the portrait data of each user to obtain a feature tag of each user;
and clustering the feature labels of the users to obtain the crowd portrait information.
6. The method of claim 3, further comprising:
and responding to the renting instruction of the shared article, controlling the shared article to be ejected out of the renting cabinet, and simultaneously placing the commodity into the goods taking port position of the target sales cabinet.
7. The method of any one of claims 1 to 6, wherein the searching according to the user portrait data and/or the rental cabinet identifier to obtain corresponding preset promotional information comprises:
acquiring preset popularization information of an operation area where the rental cabinet is located according to the rental cabinet identifier;
and determining preset popularization information corresponding to the user portrait data in the preset popularization information of the operation area.
8. The method of claim 7, wherein the predicting the user-interested commodity according to the user portrait data to obtain corresponding predicted promotion information comprises:
inputting the user portrait data into a logistic regression model to obtain the recommendation probability of each commodity;
and determining the commodity with the recommendation probability meeting the preset condition as the commodity interested by the user, and obtaining the prediction popularization information corresponding to the user portrait data.
9. The method according to claim 8, wherein the location information corresponding to the predicted promotion information is store location information of a product of interest to the user; the store position information of the product in which the user is interested is determined by the corresponding relation between the product information and the store position information.
10. The method according to claim 9, wherein a manner of generating the correspondence relationship between the product information and the store location information includes:
acquiring information of each commodity and shop position information of each commodity, wherein the shop position information comprises an identifier of a rental cabinet identifier;
and establishing a corresponding relation between the commodity information and the store position information according to the identifier of the rental cabinet identifier, the commodity information and the store position information of the commodities.
11. An information recommendation apparatus, characterized in that the apparatus comprises:
the portrait data acquisition module is used for acquiring user portrait data according to the user identification when the shared article is rented;
the rental cabinet identification acquisition module is used for acquiring the rental cabinet identification; the rental cabinet is used for providing the shared goods for the user;
the preset information searching module is used for searching according to the user portrait data and/or the rental cabinet identification to obtain corresponding preset popularization information;
the promotion information prediction module is used for predicting the commodity which is interested by the user according to the user portrait data to obtain corresponding prediction promotion information;
and the position information recommending module is used for recommending the position information corresponding to the prediction popularization information to the user terminal if the preset popularization information is matched with the prediction popularization information.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 10 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 10.
CN202110417980.5A 2021-04-19 2021-04-19 Information recommendation method, device, computer equipment and storage medium Active CN113313545B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110417980.5A CN113313545B (en) 2021-04-19 2021-04-19 Information recommendation method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110417980.5A CN113313545B (en) 2021-04-19 2021-04-19 Information recommendation method, device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113313545A true CN113313545A (en) 2021-08-27
CN113313545B CN113313545B (en) 2024-04-23

Family

ID=77372302

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110417980.5A Active CN113313545B (en) 2021-04-19 2021-04-19 Information recommendation method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113313545B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013003817A (en) * 2011-06-16 2013-01-07 V-Sync Co Ltd Environment understanding type control system by face recognition
CN103295067A (en) * 2013-04-10 2013-09-11 南京邮电大学 Vending machine managing system based on Internet of Things
CN105824912A (en) * 2016-03-15 2016-08-03 平安科技（深圳）有限公司 Personalized recommending method and device based on user portrait
CN107247759A (en) * 2017-05-31 2017-10-13 深圳正品创想科技有限公司 A kind of Method of Commodity Recommendation and device
CN107423442A (en) * 2017-08-07 2017-12-01 火烈鸟网络(广州)股份有限公司 Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis
CN108446943A (en) * 2018-01-30 2018-08-24 深圳市阿西莫夫科技有限公司 Sales counter Method of Commodity Recommendation, device, computer equipment and storage medium
CN108776676A (en) * 2018-02-02 2018-11-09 腾讯科技（深圳）有限公司 Information recommendation method, device, computer-readable medium and electronic equipment
CN109147174A (en) * 2018-09-05 2019-01-04 深圳正品创想科技有限公司 A kind of self-service method, server and self-service cabinet
CN109658207A (en) * 2019-01-15 2019-04-19 深圳友朋智能商业科技有限公司 Method of Commodity Recommendation, system and the device of automatic vending machine
CN111028003A (en) * 2019-11-27 2020-04-17 湖南士多仔信息科技有限公司 Advertisement pushing system and method based on vending machine network
CN111260447A (en) * 2020-02-11 2020-06-09 深圳前海达闼云端智能科技有限公司 Commodity recommendation method and device for vending robot
CN111611488A (en) * 2020-05-21 2020-09-01 腾讯科技（深圳）有限公司 Information recommendation method and device based on artificial intelligence and electronic equipment
CN111652648A (en) * 2020-06-03 2020-09-11 陈包容 Method for intelligently generating personalized combined promotion scheme and system with same
CN111754292A (en) * 2020-05-07 2020-10-09 深圳市奥芯博电子科技有限公司 Control method and system for shared charging cabinet and computer readable storage medium

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013003817A (en) * 2011-06-16 2013-01-07 V-Sync Co Ltd Environment understanding type control system by face recognition
CN103295067A (en) * 2013-04-10 2013-09-11 南京邮电大学 Vending machine managing system based on Internet of Things
CN105824912A (en) * 2016-03-15 2016-08-03 平安科技（深圳）有限公司 Personalized recommending method and device based on user portrait
CN107247759A (en) * 2017-05-31 2017-10-13 深圳正品创想科技有限公司 A kind of Method of Commodity Recommendation and device
CN107423442A (en) * 2017-08-07 2017-12-01 火烈鸟网络(广州)股份有限公司 Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis
CN108446943A (en) * 2018-01-30 2018-08-24 深圳市阿西莫夫科技有限公司 Sales counter Method of Commodity Recommendation, device, computer equipment and storage medium
CN108776676A (en) * 2018-02-02 2018-11-09 腾讯科技（深圳）有限公司 Information recommendation method, device, computer-readable medium and electronic equipment
CN109147174A (en) * 2018-09-05 2019-01-04 深圳正品创想科技有限公司 A kind of self-service method, server and self-service cabinet
CN109658207A (en) * 2019-01-15 2019-04-19 深圳友朋智能商业科技有限公司 Method of Commodity Recommendation, system and the device of automatic vending machine
CN111028003A (en) * 2019-11-27 2020-04-17 湖南士多仔信息科技有限公司 Advertisement pushing system and method based on vending machine network
CN111260447A (en) * 2020-02-11 2020-06-09 深圳前海达闼云端智能科技有限公司 Commodity recommendation method and device for vending robot
CN111754292A (en) * 2020-05-07 2020-10-09 深圳市奥芯博电子科技有限公司 Control method and system for shared charging cabinet and computer readable storage medium
CN111611488A (en) * 2020-05-21 2020-09-01 腾讯科技（深圳）有限公司 Information recommendation method and device based on artificial intelligence and electronic equipment
CN111652648A (en) * 2020-06-03 2020-09-11 陈包容 Method for intelligently generating personalized combined promotion scheme and system with same

Also Published As

Publication number Publication date
CN113313545B (en) 2024-04-23

Similar Documents

Publication Publication Date Title
Reinartz et al. The impact of digital transformation on the retailing value chain
Lu et al. A video-based automated recommender (VAR) system for garments
CN108876526B (en) Commodity recommendation method and device and computer-readable storage medium
CN109165992A (en) A kind of intelligent shopping guide method, apparatus, system and computer storage medium
Chen et al. Real-time smartphone sensing and recommendations towards context-awareness shopping
CN110415065A (en) User data collection system and information-pushing method
JP2002288482A (en) Fashion information server device and fashion information managing method
JP2013512501A (en) System, apparatus and method for using context information
KR20200045668A (en) Method, apparatus and computer program for style recommendation
US20090037292A1 (en) Intelligent shopping search system
JP5260785B1 (en) Attribute information optimizing device, attribute information optimizing program, attribute information optimizing method, recommendation target selecting device, recommendation target selecting program, and recommendation target selecting method
CN106547365A (en) The method and apparatus of commercial product recommending
US20180253752A1 (en) Mobile application for advertising local deals and promotions, inventory management, mobile ordering, coupon vending, marketing and analytical tools for small businesses
Tahir et al. E-commerce platform based on Machine Learning Recommendation System
JP6945518B2 (en) Information processing equipment, information processing methods and information processing programs
Kaur et al. Joint modelling of cyber activities and physical context to improve prediction of visitor behaviors
Uncles Understanding retail customers
Lomas et al. A systematic literature review of artificial intelligence in fashion retail B2C
JP6679704B1 (en) Information processing apparatus, information processing method, and information processing program
CN113313545B (en) Information recommendation method, device, computer equipment and storage medium
CN110781399A (en) Cross-platform information pushing method and device
JP2020095608A (en) Device, method, and program for processing information
KR101694943B1 (en) Goods Recommending System, Method and Readable Recoding Medium Using Purchasing Information
CN113313546A (en) Information recommendation method and device, computer equipment and storage medium
CN114596138A (en) Information 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
GR01 Patent grant