CN108805594B - Information pushing method and device - Google Patents

Information pushing method and device Download PDF

Info

Publication number
CN108805594B
CN108805594B CN201710286678.4A CN201710286678A CN108805594B CN 108805594 B CN108805594 B CN 108805594B CN 201710286678 A CN201710286678 A CN 201710286678A CN 108805594 B CN108805594 B CN 108805594B
Authority
CN
China
Prior art keywords
target
category
user
access data
determining
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
Application number
CN201710286678.4A
Other languages
Chinese (zh)
Other versions
CN108805594A (en
Inventor
肖明昭
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.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke 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 Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201710286678.4A priority Critical patent/CN108805594B/en
Publication of CN108805594A publication Critical patent/CN108805594A/en
Application granted granted Critical
Publication of CN108805594B publication Critical patent/CN108805594B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G06Q30/0256—User search
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses an information pushing method and device. One embodiment of the method comprises: extracting order data and access data of a target user in a first preset time period and a preset website; analyzing the extracted data, respectively determining the types of products ordered by the target user and the types of products displayed on the accessed page, and determining the target type in the types of products displayed on the page accessed by the target user based on the respectively determined types; extracting a characteristic vector from the access data corresponding to the target class in the extracted access data, and inputting the characteristic vector into a pre-trained order placing prediction model corresponding to the target class to obtain a corresponding order placing prediction result; and in response to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, pushing preset information to be pushed matched with the target category to the target user. The embodiment realizes targeted information push.

Description

Information pushing method and device
Technical Field
The application relates to the technical field of computers, in particular to the technical field of internet, and particularly relates to an information pushing method and device.
Background
Information push, also called "network broadcast", is a technology for reducing information overload by pushing information required by users on the internet through a certain technical standard or protocol. The information push technology can reduce the time spent by the user in searching on the network by actively pushing information to the user. Taking e-commerce platform as an example, it is usually necessary to push some product information to users to help users browse more quickly and richly.
However, the existing information pushing method usually directly and manually selects information to be pushed and users to be pushed, and then directly pushes the information to be pushed to each selected user, so that the problem of lack of pertinence in information pushing exists.
Disclosure of Invention
An object of the embodiments of the present application is to provide an improved information pushing method and apparatus, so as to solve the technical problems mentioned in the above background section.
In a first aspect, an embodiment of the present application provides an information pushing method, where the method includes: extracting order data and access data of a target user in a first preset time period and a preset website; analyzing the order data and the access data, respectively determining the types of products ordered by the target user and the types of products displayed on the accessed page, and determining the target type in the types of products displayed on the page accessed by the target user based on the respectively determined types; extracting a feature vector from the access data corresponding to the target category in the extracted access data, and inputting the feature vector into a pre-trained order-placing prediction model corresponding to the target category to obtain an order-placing prediction result corresponding to the target category, wherein the order-placing prediction model is used for representing the corresponding relation between the feature vector and the order-placing prediction result; and in response to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, pushing preset information to be pushed matched with the target category to the target user.
In some embodiments, determining a target category of categories of products presented on the page visited by the target user based on the respectively determined categories comprises: respectively extracting the determined product type identification of the order placed by the target user and the product type identification of the product displayed on the accessed page; determining the extracted item identification of the ordered product as a first item identification to generate a first item identification list, and determining the extracted item identification of the product displayed on the accessed page as a second item identification to generate a second item identification list; for each second item identification in the second item identification list, in response to determining that each first item identification in the first item identification list is not matched with the second item identification, determining the second item identification as a target item identification, and determining the item indicated by the target item identification as a target item.
In some embodiments, the feature vector includes a number of searches for products of the target category, a number of visits to the target page, and at least one of: the method comprises the following steps of average access time of an accessed target page, browsing time of an evaluation area of the accessed target page, the number of the accessed target pages, times of adding shopping carts, times of inquiring customer service, average discount value of products displayed on the target page and average good rating of exhibits displayed on the target page, wherein the target page is a page for displaying the products of a target category.
In some embodiments, before extracting the order data and the access data of the target user at the preset website within the first preset time period, the method further comprises: extracting access data of a plurality of users in a first preset time period and a preset website; for each user in the plurality of users, analyzing the extracted access data corresponding to the user, and determining the search times and the access times of the user on products of various categories; determining the demand degree of the user for products of various categories based on the determined search times and access times; if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user; the method comprises the following steps of: for each category, determining the product of the search times of the user on the products of the category and a preset second numerical value; and determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category.
In some embodiments, after determining the user as the target user if there is a demand greater than a preset first value in the determined demands, the method further includes: extracting the class identification of each class; for each user determined as a target user, in response to determining that the user is the target user, sorting the category identifications of the categories according to the sequence from large to small of the demand degree of the user for the products of the categories to generate a category identification list corresponding to the user; and storing the generated item identification list.
In some embodiments, before extracting the order data and the visit data of the target user at the preset website within the first preset time period, the method further comprises a step of training an order placing prediction model, comprising: determining the access data of the user in a second preset time period and on a preset website as historical access data; determining historical access data meeting a first preset condition in the historical access data as first historical access data, and determining historical access data meeting a second preset condition in the historical access data as second historical access data, wherein the first historical data has an order-placing mark, and the second historical data has an order-not-placing mark; extracting a first feature vector from the first historical access data and extracting a second feature vector from the second historical access data; and respectively taking the first feature vector and the second feature vector as input and taking the placed order identifier and the placed order identifier as output by using a machine learning method, and training to obtain a placed order prediction model.
In a second aspect, an embodiment of the present application provides an information pushing apparatus, where the apparatus includes: the first extraction unit is configured to extract order data and access data of a target user in a first preset time period and a preset website; the analysis unit is configured to analyze the order data and the access data, respectively determine the types of products ordered by the target user and the types of products displayed on the accessed page, and determine a target type in the types of products displayed on the page accessed by the target user based on the respectively determined types; the input unit is configured to extract a feature vector from the access data corresponding to the target category in the extracted access data, input the feature vector to a pre-trained ordering prediction model corresponding to the target category, and obtain an ordering prediction result corresponding to the target category, wherein the ordering prediction model is used for representing the corresponding relation between the feature vector and the ordering prediction result; and the pushing unit is configured to respond to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, and push preset information to be pushed, which is matched with the target category, to the target user.
In some embodiments, the parsing unit comprises: the extraction module is configured to respectively extract the determined product type identification of the order placed by the target user and the product type identification of the product displayed on the accessed page; the generation module is configured to determine the extracted item identification of the ordered product as a first item identification to generate a first item identification list, and determine the extracted item identification of the product displayed on the accessed page as a second item identification to generate a second item identification list; and the determining module is configured to, for each second category identifier in the second category identifier list, determine, in response to determining that each first category identifier in the first category identifier list is not matched with the second category identifier, the second category identifier as a target category identifier, and determine, as the target category, the category indicated by the target category identifier.
In some embodiments, the feature vector includes a number of searches for products of the target category, a number of visits to the target page, and at least one of: the method comprises the following steps of average access time of an accessed target page, browsing time of an evaluation area of the accessed target page, the number of the accessed target pages, times of adding shopping carts, times of inquiring customer service, average discount value of products displayed on the target page and average good rating of exhibits displayed on the target page, wherein the target page is a page for displaying the products of a target category.
In some embodiments, the apparatus further comprises: the second extraction unit is configured to extract access data of a plurality of users in a first preset time period and a preset website; the first determining unit is configured to analyze the extracted access data corresponding to the user for each user in the plurality of users, and determine the search times and the access times of the user on products of various categories; determining the demand degree of the user for products of various categories based on the determined search times and access times; if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user; the method comprises the following steps of: for each category, determining the product of the search times of the user on the products of the category and a preset second numerical value; and determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category.
In some embodiments, the apparatus further comprises: the third extraction unit is used for extracting the category identification of each category; the sorting unit is configured to, for each user determined as a target user, in response to determining that the user is the target user, sort the item identifiers of the various items according to the descending order of the demand degree of the user for the products of the various items so as to generate an item identifier list corresponding to the user; and the storage unit is configured to store the generated item identification list.
In some embodiments, the apparatus further comprises: the second determining unit is configured to determine the access data of the user in the preset website in a second preset time period as historical access data; the third determining unit is configured to determine historical access data meeting a first preset condition in the historical access data as first historical access data, and determine historical access data meeting a second preset condition in the historical access data as second historical access data, wherein the first historical data has an order-placing identifier, and the second historical data has an order-not-placing identifier; a fourth extraction unit configured to extract the first feature vector from the first historical access data and extract the second feature vector from the second historical access data; and the training unit is configured to use a machine learning method to train the first feature vector and the second feature vector as input and the placed order mark as output to obtain a placed order prediction model.
In a third aspect, an embodiment of the present application provides a server, including: one or more processors; a storage device, configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method according to any embodiment of the information push method.
According to the information pushing method and device provided by the embodiment of the application, the extracted order data and the access data are analyzed so as to determine the target category in the categories of products displayed on the page accessed by the target user, then the characteristic vector is extracted from the access data corresponding to the target category so as to determine the ordering prediction result based on the characteristic vector and the ordering prediction model which is trained in advance and corresponds to the target category, and finally the preset information to be pushed matched with the target category is pushed to the target user in response to the ordering prediction result being larger than the preset value. Therefore, the target category can be selected based on the analysis of the ordering situation and the access situation of the target user, and whether the information is pushed or not and the information to be pushed are determined based on the ordering prediction result of the target user on the product of the target category, so that the targeted information pushing is realized.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of an information push method according to the present application;
FIG. 3 is a schematic diagram of an application scenario of an information push method according to the present application;
FIG. 4 is a flow diagram of yet another embodiment of an information push method according to the present application;
FIG. 5 is a schematic diagram of an embodiment of an information pushing device according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which the information push method or the information push apparatus of the present application can be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a shopping application, a web browser application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server that provides various services, such as a data analysis server that analyzes behavior data (e.g., order placing data, access data, etc.) of the terminal apparatuses 101, 102, 103 in a certain website. The data analysis server may extract a plurality of data, analyze the extracted data, and perform other processing, obtain a corresponding processing result (e.g., an order placing prediction result for indicating whether a user places an order for a certain type of product), determine whether to push information to a certain user, and determine information to be pushed to the user.
It should be noted that the information pushing method provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the information pushing apparatus is generally disposed in the server 105.
It should be noted that the server 105 may be a single server, or may be composed of a plurality of servers or a plurality of server clusters.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of an information push method according to the present application is shown. The information pushing method comprises the following steps:
step 201, extracting order data and access data of a target user in a first preset time period and a preset website.
An electronic device (for example, the server 105 shown in fig. 1) on which the information push method operates may extract order data and access data of a target user at a preset website (for example, on the same day, or within 24 hours, or within 48 hours, etc.) within a first preset time period from another server (not shown in fig. 1) for storing operation data of the preset website (for example, a certain electronic commerce website) through a wired connection manner or a wireless connection manner. In addition, the operation data of the preset website can be stored in the local of the electronic device. At this time, the electronic device may directly obtain the order data and the access data from a local area. The target user may be a user in a preset user list or a preset user set, or may be a user that satisfies certain conditions (for example, the number of visits to the preset website is greater than a certain specified value, and the number of searches in the preset website is greater than a certain specified value). It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.
It should be noted that the order data may be data related to the order of the target user in the preset website. For example, the order data may include, but is not limited to, order creation time, product information of the product recorded in the order (e.g., name of the product, type identifier, model number, price, rating, discount value, etc.), order status (e.g., shipped, waiting for delivery), and the like. The item identifier may be a character string composed of various characters, and may be used to indicate the item (e.g., electronic type, case type, cosmetic type, etc.) of the product.
It should be further noted that the access data may be various data generated and stored when the target user performs page access, browsing, and the like, where each page accessed may display a product, and the extracted access data may include product information (for example, a name, a category identifier, a model, a price, a rating, a discount value, and the like of the product displayed on each page). In addition, the access data may further include information related to the operation of the target user on the page, and for example, may include, but is not limited to, information such as a web address of the accessed page, a search term sent before the page is accessed, a search time, an identification of a product category indicated by the search term, an access time and a stop access time at each page, an access time and a stop access time at a rating area of the accessed page, the number of pages accessed, a customer service inquiry time, contents of customer service inquiry, and the like.
Generally, a user may access each web page of the preset website by using a web browser installed on a client (e.g., the terminal devices 101, 102, 103 shown in fig. 1). In this embodiment, the web page may include a web page in html format, xhtml format, asp format, php format, jsp format, shtml format, nsp format, xml format, or other future developed format (as long as the web page file in this format can be opened and browsed by a browser or the contents of pictures, texts, etc. contained in the web page file).
Step 202, analyzing the order data and the access data, respectively determining the types of the products ordered by the target user and the types of the products displayed on the accessed page, and determining the target type in the types of the products displayed on the page accessed by the target user based on the respectively determined types.
In this embodiment, the order data may include a category identifier of each product ordered by the target user, and the access data may include a category identifier of a product displayed on each webpage accessed by the target user. The electronic device may first analyze the order data and the access data to determine the type of the product ordered by the target user and the type of the product displayed on the accessed page, respectively. Then, the electronic device may determine a target category of categories of products displayed on the page accessed by the target user based on the respectively determined categories. As an example, the electronic device may determine, as the target item, an item that is accessed more than a preset number of times (e.g., 6 times, 10 times, etc.) among the items of the product displayed on the page accessed by the target user. As another example, the electronic device may determine, as the target item, an item of a product that is not placed by the target user among the items of the products displayed on the page visited by the target user. As another example, the electronic device may further determine, as the target item, an item that is included in the product displayed on the page visited by the target user and visited by the target user more than a preset number of times and is not placed by the target user.
And 203, extracting a characteristic vector from the access data corresponding to the target class in the extracted access data, and inputting the characteristic vector into a pre-trained order-placing prediction model corresponding to the target class to obtain an order-placing prediction result corresponding to the target class.
In this embodiment, the electronic device may first analyze the extracted access data, and determine that the category of the displayed product in the page accessed by the target user is the page of the target category; and then, extracting the data generated and stored in the process that the target user accesses and browses the determined page, and determining the data as the access data corresponding to the target category. The electronic device may then extract feature vectors from the determined access data corresponding to the target category. Here, the feature vector may include various information for characterizing an access operation of the target user, or may include various information for characterizing content of a page accessed by the target user. By way of example, the information may include the total time length of the target user accessing each page, the average price of the product displayed in each page accessed, the average sales volume, and the like.
In this embodiment, the electronic device may store a plurality of pre-trained ordering prediction models, and each stored ordering prediction model corresponds to one category. After extracting the feature vector, the electronic device may input the feature vector to a pre-trained ordering prediction model corresponding to the target category to obtain an ordering prediction result corresponding to the target category. Here, the obtained ordering prediction result may be used to indicate a prediction of whether the target user orders the product of the target category, and the ordering prediction result may be a numerical value. It should be noted that the downward single prediction model may be used to characterize the correspondence between the feature vector and the downward single prediction result. As an example, the ordering prediction model may be a correspondence table that is prepared in advance by a technician based on statistics of a large number of feature vectors and ordering prediction results and stores correspondence of a plurality of feature vectors and ordering prediction results; or a calculation formula which is preset and stored in the electronic device by a technician based on statistics of a large amount of data and is used for performing numerical calculation on one or more numerical values in the feature vector to obtain a calculation result for representing the ordering prediction result, for example, the calculation formula may be a formula for multiplying the total time for accessing each page in the feature vector by the average sales amount, and the obtained product may be used for representing the ordering prediction result.
In some optional implementations of this embodiment, the electronic device may train the downward order prediction model in advance according to the following steps:
first, the electronic device may extract access data of the user within a second preset time period (e.g., within 30 days before the current date, within 60 days before the current date, etc.), and determine the extracted access data as historical access data.
Then, the electronic device may determine, as the first historical access data, historical access data that satisfies a first preset condition among the historical access data, and may determine, as the second historical access data, historical access data that satisfies a second preset condition among the historical access data. Here, the first preset condition may be a condition that: the categories which are generated and stored when the user accesses the page within a preset time (for example, within 3 days) before ordering are the same as the categories of the products ordered by the user. The second preset condition may be as follows: the corresponding category is a category which is not ordered by the user for the products of the same category within the preset time after the user accesses a certain page, and is generated and stored by the user accessing the page showing the products of the same category within the preset time. It should be noted that the first history data may have a placed order flag, and the second history data may have an un-placed order flag. Here, as an example, when the order placing prediction model corresponding to the electronic product is trained, the electronic device may determine, as the first historical access data, historical access data generated and stored when the user accesses a page of the electronic product within the first 3 days of the order placing product, and may determine, as the second historical access data, historical access data generated and stored when the user accesses the page of the electronic product within 3 days after accessing the page of the electronic product without placing an order for the electronic product within the 3 days.
Then, the electronic device extracts a first feature vector from the first historical access data, and extracts a second feature vector from the second historical access data. Here, the basic method for extracting the first feature vector and the second feature vector is substantially the same as the method for extracting the feature vector from the determined access data corresponding to the target category, which is described above, and thus, the description thereof is omitted.
Finally, the electronic device may use a machine learning method to train the order placing prediction model by using the first feature vector and the second feature vector as inputs and using the placed-order flag and the un-placed-order flag as outputs. Specifically, the electronic device may use a Naive Bayesian Model (NBM) or a Support Vector Machine (SVM) for classification, and the like, and use the first feature Vector as an input of the Model, the placed-order identifier as a corresponding Model output, and use the second feature Vector as a Model input, the not-placed-order identifier as a corresponding Model output, and train the Model by using a Machine learning method to obtain a placed-order prediction Model. It should be noted that each category may correspond to a pre-trained order placement prediction model, and the training methods of the order placement prediction models corresponding to each category are the same. For each class, a first feature vector and a second feature quantity of the ordering prediction model corresponding to the class are respectively extracted from first historical access data corresponding to the class and second historical access data corresponding to the class.
And step 204, in response to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, pushing preset information to be pushed, which is matched with the target category, to the target user.
In this embodiment, in response to determining that the obtained ordering prediction result is not less than a preset value (e.g., 0.5 or 1), the electronic device may push preset information to be pushed, which matches the target category, to the target user. The information to be pushed may be information (for example, summary information, pictures, links, etc.) of one or more products of the target category.
With continuing reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the information push method according to the present embodiment. In the application scenario of fig. 3, the target user uses the terminal device 301 to perform an access operation and a placing operation on a page in a preset website. First, the server 302 extracts order data 303 and access data 304 of a target user at a first preset website within a first preset time period. Then, the server 302 parses the order data 303 and the access data 304, and determines the category of the product ordered by the target user and the category of the product displayed on the accessed page, respectively, thereby determining the target category 305. Then, the server 302 extracts a feature vector 306 from the visit data corresponding to the target category 305 among the extracted visit data 304, inputs the feature vector 306 to a pre-trained ordering prediction model corresponding to the target category 305, and obtains an ordering prediction result 307. Finally, in response to determining that the ordering prediction result 307 is not smaller than the preset value, extracting preset information to be pushed 308 matched with the target category 305, and pushing the information to be pushed 308 to the terminal device 301 used by the target user.
The method provided by the above embodiment of the application analyzes the extracted order data and the access data to determine a target category in categories of products displayed on a page accessed by a target user, extracts a feature vector from the access data corresponding to the target category to determine an order-placing prediction result based on the feature vector and a pre-trained order-placing prediction model corresponding to the target category, and pushes preset information to be pushed, which is matched with the target category, to the target user in response to the order-placing prediction result being greater than a preset value. Therefore, the target category can be selected based on the analysis of the ordering situation and the access situation of the target user, and whether the information is pushed or not and the information to be pushed are determined based on the ordering prediction result of the target user on the product of the target category, so that the targeted information pushing is realized.
With further reference to fig. 4, a flow 400 of yet another embodiment of an information push method is shown. The process 400 of the information pushing method includes the following steps:
step 401, extracting access data of a plurality of users in a first preset time period and a preset website.
In this embodiment, an electronic device (for example, the server 105 shown in fig. 1) on which the information push method operates may extract access data of a plurality of users at a preset website within a first preset time period (for example, the current day).
Step 402, analyzing the extracted access data corresponding to the user for each user in the plurality of users, and determining the search times and the access times of the user on products of various categories; determining the demand degree of the user for products of various categories based on the determined search times and access times; and if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user.
In this embodiment, for each of the plurality of users, the electronic device performs the following steps:
in the first step, the extracted access data corresponding to the user may be analyzed to determine the number of searches and accesses of the user to the products of each category. The number of times of access by the user to the products of each category may be the number of times of access by the user to a page on which the products of each category are displayed. For example, the number of visits to a page showing an electronic product is 6, and the number of visits to a page showing a clothing product is 8. In practice, the access data may include information related to the user's access operation to the page, and may include, but is not limited to, the web address of the accessed page, the search term entered before accessing the page, the search time, the category identification of the product indicated by the search term, the access time and stop access time at each page, the access time and stop access time at the evaluation area of the accessed page, the number of pages accessed, the customer service inquiry time, the customer service inquiry content, and the like. The electronic equipment can perform statistics and calculation on the access data to determine the search times and the access times of the user on the products of various categories.
In the second step, the demand degree of the user for each product category can be determined based on the determined search times and visit times. The number of times, the desirability may be a numerical value for characterizing the degree of interest or desirability of the product by the user. The method comprises the following steps of: firstly, for each category, determining the product of the search times of the user for the products of the category and a preset second numerical value (for example, 5); and then determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category. As an example, if the number of searches for the product whose category is electronic is 2, the number of visits is 6, and the second value is 5, the demand level of the user for the product whose category is electronic is 16.
And thirdly, comparing the determined demand degree with a preset first value (for example, 6), and if the demand degree greater than the first value exists in the determined demand degree, determining the user as the target user.
In some optional implementation manners of this embodiment, after the electronic device performs the operation of determining the target user, the electronic device may first extract the category identifier of each category; then, for each user determined as a target user, in response to determining that the user is the target user, the electronic device may sort the item identifiers of the respective items in order from the highest demand level to the lowest demand level of the user for the products of the respective items to generate an item identifier list corresponding to the user; finally, the electronic device may store the generated item identification list.
Step 403, extracting order data and access data of the target user in a first preset time period and a preset website.
In this embodiment, the electronic device may extract order data and access data of the target user in a preset website within the first preset time period.
Step 404, analyzing the order data and the access data, respectively determining the types of the products ordered by the target user and the types of the products displayed on the accessed page, and determining the target type in the types of the products displayed on the page accessed by the target user based on the respectively determined types.
In this embodiment, the order data may include a category identifier of each product ordered by the target user, and the access data may include a category identifier of a product displayed on each webpage accessed by the target user. The electronic device may first analyze the order data and the access data to determine the type of the product ordered by the target user and the type of the product displayed on the accessed page, respectively. Then, the electronic device may determine the target category according to the following steps: first, the determined item identifier of the product placed by the target user and the item identifier of the product displayed on the accessed page may be extracted respectively. Thereafter, the extracted item identification of the ordered product may be determined as a first item identification to generate a first item identification list, and the extracted item identification of the product presented on the accessed page may be determined as a second item identification to generate a second item identification list. Finally, for each second category identifier in the second category identifier list, the electronic device may match the second category identifier with each first category identifier in the first category identifier list. In response to determining that each first category identifier in the first category identifier list does not match the second category identifier, the second category identifier may be determined as a target category identifier, and the category indicated by the target category identifier may be determined as a target category.
And 405, extracting a feature vector from the access data corresponding to the target class in the extracted access data, and inputting the feature vector into a pre-trained order-placing prediction model corresponding to the target class to obtain an order-placing prediction result corresponding to the target class.
In this embodiment, the electronic device may first analyze the extracted access data, and determine that the category of the displayed product in the page accessed by the target user is the page of the target category; then, the determined page may be used as a target page, data generated and stored in the process of accessing the target page by the target user is extracted, and the data is determined as access data corresponding to the target category. The electronic device may then extract feature vectors from the determined access data corresponding to the target category. The feature vector may include a number of searches for products of the target category, a number of visits to a target page, and at least one of: the average visit duration of the visited target pages, the browsing duration of the evaluation areas of the visited target pages, the number of the visited target pages, the times of adding shopping carts, the times of inquiring customer service, the average discount value of products displayed on the target pages and the average good rating of exhibits displayed on the target pages.
In this embodiment, the electronic device may store a plurality of pre-trained ordering prediction models, and each stored ordering prediction model corresponds to one category. After extracting the feature vector, the electronic device may input the feature vector to a pre-trained ordering prediction model corresponding to the target category to obtain an ordering prediction result corresponding to the target category.
And step 406, in response to determining that the obtained ordering prediction result is not less than the preset value, pushing preset information to be pushed, which is matched with the target category, to the target user.
In this embodiment, in response to determining that the obtained ordering prediction result is not less than a preset value, the electronic device may push preset information to be pushed, which is matched with the target category, to the target user.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the information pushing method in the present embodiment highlights the step of determining the target user. Therefore, the scheme described in the embodiment can determine the target user based on the analysis of the access data without manual selection or determination, so that the labor cost is reduced while the targeted information push is realized.
With further reference to fig. 5, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an information pushing apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied in various electronic devices.
As shown in fig. 5, the information pushing apparatus 500 according to the present embodiment includes: a first extraction unit 501, configured to extract order data and access data of a target user in a first preset time period and a preset website; an analyzing unit 502 configured to analyze the order data and the access data, determine a category of a product ordered by the target user and a category of a product displayed on the accessed page, and determine a target category of the categories of the products displayed on the page accessed by the target user based on the determined categories; an input unit 503 configured to extract a feature vector from the visit data corresponding to the target category in the extracted visit data, and input the feature vector to a pre-trained ordering prediction model corresponding to the target category, so as to obtain an ordering prediction result corresponding to the target category, wherein the ordering prediction model is used for representing a correspondence relationship between the feature vector and the ordering prediction result; the pushing unit 504 is configured to, in response to determining that the obtained ordering prediction result is not smaller than a preset value, push preset information to be pushed, which is matched with the target category, to the target user.
In this embodiment, the first extracting unit 501 may extract order data and access data of the target user at the preset website within a first preset time period.
In this embodiment, the analyzing unit 502 may first analyze the order data and the access data to determine the type of the product ordered by the target user and the type of the product displayed on the accessed page, respectively. Then, a target category among categories of products presented on the page accessed by the target user may be determined based on the respectively determined categories.
In some optional implementations of this embodiment, the parsing unit 502 may further include an extracting module, a generating module, and a determining module (not shown in the figure). The extracting module may be configured to extract the determined category identifier of the product ordered by the target user and the category identifier of the product displayed on the accessed page, respectively. The generation module may be configured to determine the item identifier of the extracted ordered product as a first item identifier to generate a first item identifier list, and determine the item identifier of the extracted product displayed on the accessed page as a second item identifier to generate a second item identifier list. The determining module may be configured to, for each second category identifier in the second category identifier list, in response to determining that each first category identifier in the first category identifier list does not match the second category identifier, determine the second category identifier as a target category identifier, and determine a category indicated by the target category identifier as a target category.
In this embodiment, the input unit 503 may first analyze the extracted access data, and determine that the category of the displayed product in the page accessed by the target user is the page of the target category; and then, extracting the data generated and stored in the process that the target user accesses and browses the determined page, and determining the data as the access data corresponding to the target category. Feature vectors may then be extracted from the determined visit data corresponding to the target category. After extracting the feature vector, the feature vector may be input to a pre-trained ordering prediction model corresponding to the target category to obtain an ordering prediction result corresponding to the target category.
In some optional implementations of the embodiment, the feature vector includes a number of times that the product of the target category can be searched, a number of times that the target page is visited, and at least one of: the average visit duration of the visited target pages, the browsing duration of the evaluation areas of the visited target pages, the number of the visited target pages, the times of adding shopping carts, the times of inquiring customer service, the average discount value of products displayed on the target pages and the average good rating of exhibits displayed on the target pages.
In this embodiment, the pushing unit 504 may push preset information to be pushed, which matches the target category, to the target user in response to determining that the obtained ordering prediction result is not smaller than a preset value. The information to be pushed may be information (for example, summary information, pictures, links, etc.) of one or more products of the target category.
In some optional implementations of the present embodiment, the information pushing apparatus 500 may further include a second extraction unit and a first determination unit (not shown in the figure). The second extraction unit may be configured to extract access data of a plurality of users in a first preset time period at a preset website. The first determining unit may be configured to, for each of the plurality of users, parse the extracted access data corresponding to the user, and determine the number of searches and the number of accesses of the user to the products of each category; determining the demand degree of the user for products of various categories based on the determined search times and access times; if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user; the method comprises the following steps of: for each category, determining the product of the search times of the user on the products of the category and a preset second numerical value; and determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category.
In some optional implementations of the present embodiment, the information pushing apparatus 500 may further include a third extracting unit, a sorting unit, and a storing unit (not shown in the figure). The third extracting unit may be configured to extract the category identifier of each category. The sorting unit may be configured to, for each user determined as a target user, in response to determining that the user is the target user, sort the item identifiers of the respective items in an order from a high demand degree of the user for the products of the respective items to generate an item identifier list corresponding to the user. The storage unit may be configured to store the generated item identification list.
In some optional implementations of the present embodiment, the information pushing apparatus 500 may further include a second determining unit and a third determining unit (not shown in the figure). The second determining unit may be configured to determine, as the historical access data, the access data of the user at the preset website within a second preset time period. The third determining unit may be configured to determine, as first historical access data, historical access data that satisfies a first preset condition in the historical access data, and determine, as second historical access data, historical access data that satisfies a second preset condition in the historical access data, where the first historical data has an order-placed flag, and the second historical data has an order-not-placed flag; a fourth extraction unit configured to extract a first feature vector from the first historical access data and extract a second feature vector from the second historical access data; and a training unit configured to train the order placing prediction model by using a machine learning method and using the first feature vector and the second feature vector as input and the order placing mark and the order not placing mark as output.
In the apparatus provided by the above embodiment of the present application, the order data and the access data extracted by the first extracting unit 501 are analyzed by the analyzing unit 502, so as to determine a target category in categories of products displayed on a page visited by a target user, then the input unit 503 extracts a feature vector from the access data corresponding to the target category, so as to determine an order placement prediction result based on the feature vector and a pre-trained order placement prediction model corresponding to the target category, and finally the pushing unit 504, in response to the order placement prediction result being greater than a preset value, pushes preset information to be pushed matching with the target category to the target user. Therefore, the target category can be selected based on the analysis of the ordering situation and the access situation of the target user, and whether the information is pushed or not and the information to be pushed are determined based on the ordering prediction result of the target user on the product of the target category, so that the targeted information pushing is realized.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first extraction unit, an analysis unit, an input unit, and a push unit. Here, the names of the units do not constitute a limitation to the units themselves in some cases, and for example, the extraction unit may also be described as a "unit that extracts order data and access data of the target user at a preset website within a first preset time period".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: extracting order data and access data of a target user in a first preset time period and a preset website; analyzing the extracted data, respectively determining the types of products ordered by the target user and the types of products displayed on the accessed page, and determining the target type in the types of products displayed on the page accessed by the target user based on the respectively determined types; extracting a characteristic vector from the access data corresponding to the target class in the extracted access data, and inputting the characteristic vector into a pre-trained order placing prediction model corresponding to the target class to obtain a corresponding order placing prediction result; and in response to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, pushing preset information to be pushed matched with the target category to the target user.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims (12)

1. An information pushing method, characterized in that the method comprises:
extracting order data and access data of a target user in a first preset time period and a preset website;
analyzing the order data and the access data, respectively determining the types of products ordered by the target user and the types of products displayed on the accessed page, and determining a target type in the types of products displayed on the page accessed by the target user based on the respectively determined types;
extracting a feature vector from the access data corresponding to the target class in the extracted access data, and inputting the feature vector into a pre-trained order-placing prediction model corresponding to the target class to obtain an order-placing prediction result corresponding to the target class, wherein the order-placing prediction model is used for representing the corresponding relation between the feature vector and the order-placing prediction result;
in response to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, pushing preset information to be pushed matched with the target category to the target user;
the determining a target category of categories of products shown on the page visited by the target user based on the respectively determined categories comprises:
respectively extracting the determined product type identification of the order placed by the target user and the product type identification of the product displayed on the accessed page;
determining the extracted item identification of the ordered product as a first item identification to generate a first item identification list, and determining the extracted item identification of the product displayed on the accessed page as a second item identification to generate a second item identification list;
for each second category identification in the second category identification list, in response to determining that each first category identification in the first category identification list is not matched with the second category identification, determining the second category identification as a target category identification, and determining a category indicated by the target category identification as a target category.
2. The information push method according to claim 1, wherein the feature vector includes a number of searches for the product of the target category, a number of visits to a target page, and at least one of: the method comprises the following steps of average access time length of an accessed target page, browsing time length of a rating area of the accessed target page, the number of the accessed target pages, times of adding shopping carts, times of inquiring customer service, average discount value of products displayed on the target page and average good rating of exhibits displayed on the target page, wherein the target page is used for displaying the products of the target category.
3. The information pushing method according to claim 1, wherein before the extracting order data and access data of the target user at a preset website within a first preset time period, the method further comprises:
extracting access data of a plurality of users in a first preset time period and a preset website;
for each user in the plurality of users, analyzing the extracted access data corresponding to the user, and determining the search times and the access times of the user on products of various categories; determining the demand degree of the user for products of various categories based on the determined search times and access times; if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user;
the method comprises the following steps of: for each category, determining the product of the search times of the user on the products of the category and a preset second numerical value; and determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category.
4. The information push method according to claim 3, wherein after determining the user as the target user if there is a demand degree greater than a preset first value in the determined demand degrees, the method further comprises:
extracting the class identification of each class;
for each user determined as a target user, in response to determining that the user is the target user, sorting the category identifications of the categories according to the sequence from large to small of the demand degree of the user for the products of the categories to generate a category identification list corresponding to the user;
and storing the generated item identification list.
5. The information pushing method according to claim 1, wherein before the extracting order data and visit data of the target user at a preset website within a first preset time period, the method further comprises a step of training an order placement prediction model, comprising:
determining the access data of the user in a second preset time period and on a preset website as historical access data;
determining historical access data meeting a first preset condition in the historical access data as first historical access data, and determining historical access data meeting a second preset condition in the historical access data as second historical access data, wherein the first historical access data is provided with an order-placed identifier, and the second historical access data is provided with an order-not-placed identifier;
extracting a first feature vector from the first historical access data and extracting a second feature vector from the second historical access data;
and training to obtain an order placing prediction model by using a machine learning method and taking the first feature vector and the second feature vector as input and the placed order mark and the un-placed order mark as output respectively.
6. An information pushing apparatus, characterized in that the apparatus comprises:
the first extraction unit is configured to extract order data and access data of a target user in a first preset time period and a preset website;
the analysis unit is configured to analyze the order data and the access data, respectively determine the types of products ordered by the target user and the types of products displayed on the accessed page, and determine a target type in the types of products displayed on the page accessed by the target user based on the respectively determined types;
the input unit is configured to extract a feature vector from the access data corresponding to the target category in the extracted access data, input the feature vector to a pre-trained ordering prediction model corresponding to the target category, and obtain an ordering prediction result corresponding to the target category, wherein the ordering prediction model is used for representing the corresponding relation between the feature vector and the ordering prediction result;
the pushing unit is configured to respond to the fact that the obtained ordering prediction result is not smaller than a preset numerical value, and push preset information to be pushed, which is matched with the target category, to the target user;
the analysis unit includes:
the extraction module is configured to respectively extract the determined product type identification of the order placed by the target user and the product type identification of the product displayed on the accessed page;
the generation module is configured to determine the extracted item identification of the ordered product as a first item identification to generate a first item identification list, and determine the extracted item identification of the product displayed on the accessed page as a second item identification to generate a second item identification list;
and the determining module is configured to, for each second category identifier in the second category identifier list, determine, in response to determining that each first category identifier in the first category identifier list does not match the second category identifier, the second category identifier as a target category identifier, and determine, as the target category, the category indicated by the target category identifier.
7. The information pushing device according to claim 6, wherein the feature vector includes a number of searches for the product of the target category, a number of visits to a target page, and at least one of: the method comprises the following steps of average access time length of an accessed target page, browsing time length of a rating area of the accessed target page, the number of the accessed target pages, times of adding shopping carts, times of inquiring customer service, average discount value of products displayed on the target page and average good rating of exhibits displayed on the target page, wherein the target page is used for displaying the products of the target category.
8. The information push device according to claim 6, wherein the device further comprises:
the second extraction unit is configured to extract access data of a plurality of users in a first preset time period and a preset website;
the first determining unit is configured to analyze the extracted access data corresponding to the user for each user in the plurality of users, and determine the search times and the access times of the user on products of various categories; determining the demand degree of the user for products of various categories based on the determined search times and access times; if the determined demand degree has a demand degree larger than a preset first numerical value, determining the user as a target user; the method comprises the following steps of: for each category, determining the product of the search times of the user on the products of the category and a preset second numerical value; and determining the sum of the determined product and the number of times of access of the user to the products of the category as the demand degree of the user to the products of the category.
9. The information pushing apparatus according to claim 8, further comprising:
the third extraction unit is used for extracting the category identification of each category;
the sorting unit is configured to, for each user determined as a target user, in response to determining that the user is the target user, sort the item identifiers of the various items according to the descending order of the demand degree of the user for the products of the various items so as to generate an item identifier list corresponding to the user;
and the storage unit is configured to store the generated item identification list.
10. The information push device according to claim 6, wherein the device further comprises:
the second determining unit is configured to determine the access data of the user in the preset website in a second preset time period as historical access data;
a third determining unit, configured to determine, as first historical access data, historical access data that satisfies a first preset condition in the historical access data, and determine, as second historical access data, historical access data that satisfies a second preset condition in the historical access data, where the first historical access data has an identifier that an order has been placed, and the second historical access data has an identifier that an order has not been placed;
a fourth extraction unit, configured to extract a first feature vector from the first historical access data, and extract a second feature vector from the second historical access data;
and the training unit is configured to use a machine learning method to train the first feature vector and the second feature vector as input and the placed-order mark and the un-placed-order mark as output to obtain a placed-order prediction model.
11. A server, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
CN201710286678.4A 2017-04-27 2017-04-27 Information pushing method and device Active CN108805594B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710286678.4A CN108805594B (en) 2017-04-27 2017-04-27 Information pushing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710286678.4A CN108805594B (en) 2017-04-27 2017-04-27 Information pushing method and device

Publications (2)

Publication Number Publication Date
CN108805594A CN108805594A (en) 2018-11-13
CN108805594B true CN108805594B (en) 2022-04-12

Family

ID=64070178

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710286678.4A Active CN108805594B (en) 2017-04-27 2017-04-27 Information pushing method and device

Country Status (1)

Country Link
CN (1) CN108805594B (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111242713A (en) * 2018-11-29 2020-06-05 北京京东尚科信息技术有限公司 Information pushing method and device
CN117349546A (en) * 2019-01-31 2024-01-05 北京沃东天骏信息技术有限公司 Method, device and system for generating information
CN109903126B (en) * 2019-02-01 2021-07-30 北京字节跳动网络技术有限公司 Processing method and device for comment list in comment area and related equipment thereof
CN111598597A (en) * 2019-02-21 2020-08-28 北京京东尚科信息技术有限公司 Method and apparatus for transmitting information
CN109993583B (en) * 2019-04-02 2021-07-27 深圳市腾讯信息技术有限公司 Information pushing method and device, storage medium and electronic device
US10902298B2 (en) 2019-04-29 2021-01-26 Alibaba Group Holding Limited Pushing items to users based on a reinforcement learning model
CN110263245B (en) * 2019-04-29 2020-08-21 阿里巴巴集团控股有限公司 Method and device for pushing object to user based on reinforcement learning model
CN110266805A (en) * 2019-06-28 2019-09-20 京东数字科技控股有限公司 Information-pushing method, device, electronic equipment and readable medium
CN110675217A (en) * 2019-09-05 2020-01-10 广州亚美信息科技有限公司 Personalized background image generation method and device
CN110910180B (en) * 2019-12-02 2021-02-26 北京嘀嘀无限科技发展有限公司 Information pushing method and device, electronic equipment and storage medium
CN112950304B (en) * 2019-12-11 2024-06-18 北京沃东天骏信息技术有限公司 Information pushing method, device, equipment and storage medium
CN113469767A (en) * 2020-03-31 2021-10-01 珠海优特智厨科技有限公司 Order information processing method, device, equipment and computer readable storage medium
CN112330059B (en) * 2020-11-24 2023-05-30 北京沃东天骏信息技术有限公司 Method, apparatus, electronic device, and medium for generating predictive score
CN113763112A (en) * 2021-02-25 2021-12-07 北京沃东天骏信息技术有限公司 Information pushing method and device
CN113191797A (en) * 2021-04-20 2021-07-30 北京异乡旅行网络科技有限公司 Broadcast promotion method, device and storage medium suitable for peripheral supermarket

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103581270B (en) * 2012-08-08 2015-12-16 腾讯科技（深圳）有限公司 User's recommend method and system
CN105528374A (en) * 2014-10-21 2016-04-27 苏宁云商集团股份有限公司 A commodity recommendation method in electronic commerce and a system using the same
CN106296242A (en) * 2015-05-22 2017-01-04 苏宁云商集团股份有限公司 A kind of generation method of commercial product recommending list in ecommerce and the system of generation
CN106339393B (en) * 2015-07-09 2020-08-11 阿里巴巴集团控股有限公司 Information pushing method and device
CN105224623B (en) * 2015-09-22 2019-06-18 北京百度网讯科技有限公司 The training method and device of data model
CN106202516A (en) * 2016-07-24 2016-12-07 广东聚联电子商务股份有限公司 A kind of e-commerce platform merchandise display method according to timing node

Also Published As

Publication number Publication date
CN108805594A (en) 2018-11-13

Similar Documents

Publication Publication Date Title
CN108805594B (en) Information pushing method and device
US11252245B2 (en) Information pushing method and device
CN109145280B (en) Information pushing method and device
CN109522483B (en) Method and device for pushing information
WO2018192491A1 (en) Information pushing method and device
CN107577807B (en) Method and device for pushing information
CN105573966B (en) Adaptive modification of content presented in a spreadsheet
CN111125574B (en) Method and device for generating information
CN109388548B (en) Method and apparatus for generating information
WO2017035970A1 (en) Information pushing method and apparatus
CN107679217B (en) Associated content extraction method and device based on data mining
CN110413872B (en) Method and device for displaying information
CN106897905B (en) Method and device for pushing information and electronic equipment
CN106919711B (en) Method and device for labeling information based on artificial intelligence
CN107517251B (en) Information pushing method and device
US10599760B2 (en) Intelligent form creation
CN107908662B (en) Method and device for realizing search system
CN105488205A (en) Page generation method and page generation apparatus
US8819537B2 (en) Information generation device, information generation method, information generation program, and recording medium
CN110473042B (en) Method and device for acquiring information
CN108804448A (en) The method and apparatus for generating information to be pushed
CN112749323A (en) Method and device for constructing user portrait
CN109981712B (en) Method and device for pushing information
KR102575415B1 (en) Method and apparatus for providing information on advertisements available for reservation during the marketer's workload period
CN108959289B (en) Website category acquisition method and device

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