CN107423355B - Information recommendation method and device, electronic equipment - Google Patents

Information recommendation method and device, electronic equipment Download PDF

Info

Publication number
CN107423355B
CN107423355B CN201710395439.2A CN201710395439A CN107423355B CN 107423355 B CN107423355 B CN 107423355B CN 201710395439 A CN201710395439 A CN 201710395439A CN 107423355 B CN107423355 B CN 107423355B
Authority
CN
China
Prior art keywords
information
recommendation result
recommendation
undisplayed
behavior data
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
CN201710395439.2A
Other languages
Chinese (zh)
Other versions
CN107423355A (en
Inventor
张轩皓
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 Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online 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 Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN201710395439.2A priority Critical patent/CN107423355B/en
Publication of CN107423355A publication Critical patent/CN107423355A/en
Application granted granted Critical
Publication of CN107423355B publication Critical patent/CN107423355B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The purpose of the present invention is to provide a kind of information recommendation method and devices, electronic equipment, this method comprises: obtaining the first recommendation results corresponding with user's request, according to the size of display screen, show the partial information in first recommendation results；The behavioral data of information execution has been displayed in first recommendation results in acquisition user in real time, and the behavioral data is sent to server；The second recommendation results to match with the behavioral data for receiving the server feedback, update in first recommendation results according to second recommendation results and do not show information.Information recommendation method and device in through the invention is it is contemplated that user adjusts recommendation results according to the Real-time Feedback of user dynamic during user browses recommendation results to the Real-time Feedback of recommendation results.

Description

Information recommendation method and device and electronic equipment
Technical Field
The invention relates to the technical field of internet, in particular to an information recommendation method and device and electronic equipment.
Background
With the rapid development of internet technology, information provided by the internet to users is increased explosively, the information requirements of users are increasing day by day, and how to enable users to timely and accurately acquire required information from massive information of the internet becomes a problem which needs to be solved urgently in the internet technology development process.
The internet personalized information recommendation technology is a technology capable of recommending required information to a user in a personalized manner, and can collect and analyze information requirements, interests and hobbies, use habits, access histories and the like of the user, and screen and sort information on the internet according to an analysis result, so that the user is guided to browse and retrieve the information or the information is actively pushed to the user.
The inventor finds in research that the recommendation result generated by the existing information recommendation technology according to the user request is fixed, the real-time feedback of the user to the recommendation result is not considered, and the recommendation result cannot be dynamically adjusted according to the real-time feedback of the user in the process of browsing the recommendation result by the user.
Disclosure of Invention
In view of the above, the present invention provides an information recommendation method and apparatus, and an electronic device to solve the above problems.
In a first aspect, an embodiment of the present invention provides an information recommendation method, including: acquiring a first recommendation result corresponding to a user request, and displaying part of information in the first recommendation result according to the size of a display screen; acquiring behavior data executed by a user on the displayed information in the first recommendation result in real time, and sending the behavior data to a server; and receiving a second recommendation result matched with the behavior data and fed back by the server, and updating undisplayed information in the first recommendation result according to the second recommendation result.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the updating, according to the second recommendation result, the undisplayed information in the first recommendation result includes: detecting whether the information in the second recommendation result is overlapped with the displayed information in the first recommendation result; if the second recommendation result exists, removing information which is overlapped with the displayed information in the first recommendation result from the second recommendation result to obtain an updated second recommendation result; and replacing the undisplayed information in the first recommendation result by the updated second recommendation result.
With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where before receiving the second recommendation result, the method further includes: and sending indication information to the server, wherein the indication information is used for representing the displayed information in the first recommendation result.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where before receiving the second recommendation result, the method further includes: and sending the quantity control information to the server by taking the quantity of all information in the first recommendation result or the quantity of undisplayed information in the first recommendation result as quantity control information.
With reference to the second or third possible implementation manner of the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the updating, according to the second recommendation result, the undisplayed information in the first recommendation result includes: and replacing the undisplayed information in the first recommendation result with the second recommendation result.
With reference to the foregoing implementation manner of the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the updating, according to the second recommendation result, the undisplayed information in the first recommendation result includes: detecting the speed of the user for browsing the first recommendation result; and if the speed is less than or equal to a preset speed threshold, updating the undisplayed information in the first recommendation result according to the second recommendation result.
In a second aspect, an embodiment of the present invention provides an information recommendation method, including: receiving behavior data which is sent by a client and executed by a user on the displayed information in the first recommendation result; and determining a second recommendation result matched with the behavior data, and sending the second recommendation result to the client, wherein the second recommendation result is used for updating undisplayed information in the first recommendation result.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where before the determining a second recommendation that matches the behavior data, the method further includes: obtaining undisplayed information in the first recommendation result; the determining a second recommendation that matches the behavioral data includes: screening out information matched with the behavior data from the obtained undisplayed information, and taking the information obtained by screening out as a second recommendation result; or respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
With reference to the second aspect, an embodiment of the present invention provides a second possible implementation manner of the second aspect, where the determining a second recommendation matching the behavior data includes: screening out a plurality of pieces of information matched with the behavior data in a local database or a remote database; and sequencing the plurality of pieces of information according to the matching degree of the plurality of pieces of information and the behavior data, and taking the sequenced plurality of pieces of information as a second recommendation result.
With reference to the second aspect or the second possible implementation manner of the second aspect, an embodiment of the present invention provides a third possible implementation manner of the second aspect, where before sending the second recommendation result to the client, the method further includes: receiving indication information sent by the client, wherein the indication information is used for representing displayed information in the first recommendation result; the sending the second recommendation result to the client includes: and in the second recommendation result, removing information superposed with the displayed information in the first recommendation result according to the indication information, and sending the residual information in the second recommendation result to the client.
With reference to the second possible implementation manner of the second aspect, an embodiment of the present invention provides a fourth possible implementation manner of the second aspect, where before sending the second recommendation result to the client, the method further includes: receiving quantity control information sent by the client, wherein the quantity control information comprises the quantity of all information in the first recommendation result or the quantity of undisplayed information in the first recommendation result; the sending the second recommendation result to the client includes: and screening partial information with the top rank from the second recommendation result according to the quantity control information, and sending the screened partial information to the client.
In a third aspect, an embodiment of the present invention provides an information recommendation method, including: the method comprises the steps that a client side obtains a first recommendation result corresponding to a user request, and partial information in the first recommendation result is displayed according to the size of a display screen; the client acquires behavior data executed by the user on the displayed information in the first recommendation result in real time and sends the behavior data to a server; the server receives the behavior data, determines a second recommendation result matched with the behavior data, and sends the second recommendation result to the client; and the client receives the second recommendation result and updates the undisplayed information in the first recommendation result according to the second recommendation result.
In a fourth aspect, an embodiment of the present invention provides an information recommendation apparatus, including: the information display module is used for acquiring a first recommendation result corresponding to a user request and displaying part of information in the first recommendation result according to the size of a display screen; the behavior acquisition module is used for acquiring behavior data executed by the user on the displayed information in the first recommendation result in real time and sending the behavior data to the server; and the information updating module is used for receiving a second recommendation result which is fed back by the server and matched with the behavior data, and updating the undisplayed information in the first recommendation result according to the second recommendation result.
In a fifth aspect, an embodiment of the present invention provides an information recommendation apparatus, including: the data receiving module is used for receiving behavior data which is sent by the client and executed by the user on the displayed information in the first recommendation result; and the information recommendation module is used for determining a second recommendation result matched with the behavior data and sending the second recommendation result to the client, wherein the second recommendation result is used for updating undisplayed information in the first recommendation result.
In a sixth aspect, an embodiment of the present invention provides an information recommendation system, including a client and a server; the client is used for acquiring a first recommendation result corresponding to a user request, displaying part of information in the first recommendation result according to the size of a display screen, acquiring behavior data executed by a user on the displayed information in the first recommendation result in real time, sending the behavior data to the server, receiving a second recommendation result which is fed back by the server and matched with the behavior data, and updating undisplayed information in the first recommendation result according to the second recommendation result; the server is used for receiving the behavior data, determining the second recommendation result and sending the second recommendation result to the client.
In a seventh aspect, an embodiment of the present invention provides an electronic device, which includes a first memory, a first processor, and a computer program stored in the first memory and executable on the first processor, where the first processor implements the steps of the method according to the first aspect when executing the computer program.
In an eighth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method according to the first aspect.
In a ninth aspect, an embodiment of the present invention provides an electronic device, which includes a second memory, a second processor, and a computer program stored in the second memory and executable on the second processor, where the second processor implements the steps of the method according to the second aspect when executing the computer program.
In a tenth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method according to the second aspect.
According to the information recommendation method and device, the real-time feedback of the user on the recommendation result can be considered, the recommendation result can be dynamically adjusted according to the real-time feedback of the user in the information browsing process, the recommendation result can better meet the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of an information recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of an information recommendation method according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a module composition of an information recommendation apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a module composition of another information recommendation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
In consideration of the fact that the existing information recommendation technology does not consider real-time feedback of a user on a recommendation result, and cannot dynamically adjust the recommendation result according to the real-time feedback of the user in the process of browsing the recommendation result by the user, the invention provides an information recommendation method, an information recommendation device and electronic equipment.
Fig. 1 is a schematic flow chart of an information recommendation method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step S102, the client side obtains a first recommendation result corresponding to the user request, and partial information in the first recommendation result is displayed according to the size of the display screen.
The client is a terminal device such as a smart phone, a computer, a tablet computer, a vehicle-mounted computer, and a smart television capable of accessing the internet, an application program for executing the method in the embodiment is built in the client, and when a user opens the application program or performs operations such as searching and clicking in the application program, the application program generates a user request.
The client sends the user request to the server, the server searches in the database according to the user request to obtain a first recommendation result corresponding to the user request, and sends the first recommendation result to the client, wherein the user request carries a user ID and can also carry search keywords of the user, and the first recommendation result comprises a plurality of pieces of information, and the plurality of pieces of information at least correspond to the user request and can also be matched with interests, habits, access histories and the like of the user.
In a specific embodiment, when a user opens an application program in a client, the client sends a user request to a server, the user request carries a user ID, after receiving the user request, the server obtains a plurality of pieces of information matched with interests, habits and access histories of the user in a database according to the user ID, and sends the plurality of pieces of information as a first recommendation result to the client.
The client side is provided with a display screen, partial information in the first recommendation result is displayed by the client side according to the size of the display screen so that a user can browse the information, and the display screen is limited in size, so that when the number of pieces of information contained in the first recommendation result is large, the partial information in the first recommendation result is displayed by the display screen, and the rest information which is not displayed is displayed after the user performs screen sliding or scrolling operation.
And step S104, the client acquires behavior data executed by the user on the displayed information in the first recommendation result in real time and sends the behavior data to the server.
After the client displays part of the information in the first recommendation result, the user can initiate actions such as clicking, adding a shopping cart, adding a collection, placing an order, paying and the like on the displayed information in the first recommendation result in a touch screen, mouse or keyboard mode. In the process that the user browses the first recommendation result, the client acquires behavior data executed by the user on the displayed information in the first recommendation result in real time and sends the acquired behavior data to the server, wherein the behavior data correspond to behaviors initiated by the user and comprise click data, shopping cart adding data, collection adding data, order placing data, payment data and the like.
Preferably, the client acquires the behavior data of the user in real time, and periodically sends the behavior data to the server at intervals of a predetermined time, for example, the behavior data is sent to the server once every 0.5 second, so that the server performs subsequent processing according to the behavior data.
In one embodiment, the server sending the first recommendation result to the client and the server receiving the behavior data are the same server, and in another embodiment, the server sending the first recommendation result to the client and the server receiving the behavior data are different servers. In this embodiment, since the server needs to perform subsequent processing after receiving the behavior data, it is preferable that the server that sends the first recommendation result to the client and the server that receives the behavior data are different servers, the former may be referred to as a basic recommendation server, and the latter may be referred to as a dynamic recommendation server, and the following description will proceed with the embodiment taking an example in which the two servers are different servers.
And step S106, the server receives the behavior data sent by the client, determines a second recommendation result matched with the behavior data, and sends the second recommendation result to the client.
And after receiving behavior data, sent by the client, of the user on the displayed information in the first recommendation result, the dynamic recommendation server determines a second recommendation result matched with the behavior data.
In some scenarios, the first recommendation result is very comprehensive and includes all information matching with the user request, which is acquired by the basic recommendation server in the remote database or the local database according to the access history, hobbies and usage habits of the user, in this case, the dynamic recommendation server may acquire undisplayed information in the first recommendation result, such as undisplayed information in the first recommendation result sent by the receiving client, before determining the second recommendation result, and determine the second recommendation result in the undisplayed information in the first recommendation result in the following manner (a11) or manner (a 12).
(a11) The dynamic recommendation server screens out information matched with the behavior data from the acquired undisplayed information, and the information obtained through screening is used as a second recommendation result; (a12) and the dynamic recommendation server respectively calculates the matching degree of each piece of information in the undisplayed information and the behavior data, reorders each piece of information in the undisplayed information according to the matching degree, and takes the sorted undisplayed information as a second recommendation result.
In a specific embodiment, the (a11) may be: the dynamic recommendation server analyzes behavior data executed by the user on the displayed information in the first recommendation result to obtain positive feedback data and negative feedback data of the user on the displayed information in the first recommendation result, the positive feedback data represent certain information preferred by the user, the negative feedback data represent that the user is not interested in the certain information, and the dynamic recommendation server determines the information preference of the user according to the positive feedback data and the negative feedback data. And after acquiring the undisplayed information, the dynamic recommendation server determines the information preferred by the user in the undisplayed information according to the information preference of the user, screens the information preferred by the user as the information matched with the behavior data, and takes the screened information as a second recommendation result.
In a specific embodiment, the (a12) may be: the dynamic recommendation server analyzes behavior data executed by the user on the displayed information in the first recommendation result to obtain positive feedback data and negative feedback data of the user on the displayed information in the first recommendation result, the positive feedback data represent certain information preferred by the user, the negative feedback data represent that the user is not interested in the certain information, and the dynamic recommendation server determines the information preference of the user according to the positive feedback data and the negative feedback data. After the dynamic recommendation server obtains the undisplayed information, determining the information preferred by the user and the information not preferred by the user in the undisplayed information according to the information preference of the user, improving the weight corresponding to the information preferred by the user, reducing the weight corresponding to the information not preferred by the user, then calculating the score of each piece of information in the undisplayed information after the weight adjustment according to a weight score calculation formula, wherein the score is the matching degree, sequencing each piece of information in the undisplayed information according to the sequence of the scores of each piece of information from high to low, and taking the sequenced undisplayed information as a second recommendation result. In the weight fraction calculation formula, the weight is positively correlated with the fraction.
If the dynamic recommendation server cannot obtain the undisplayed information in the first recommendation result, the dynamic recommendation server may obtain all information in the first recommendation result before determining the second recommendation result, for example, obtain all information in the first recommendation result from the basic recommendation server, and then determine the second recommendation result from all information in the first recommendation result according to the following manner (b11) or manner (b 12).
(b11) The dynamic recommendation server screens out information matched with the behavior data from all the acquired information, and the information obtained by screening is used as a second recommendation result; (b12) and the dynamic recommendation server respectively calculates the matching degree of each piece of information in the acquired all pieces of information with the behavior data, reorders all pieces of information in the all pieces of information according to the matching degree, and takes the ordered all pieces of information as a second recommendation result.
The specific processes of the mode (b11) and the mode (b12) can refer to the mode (a11) and the mode (a12), and are not described in detail here. It can be understood that the manner (a11), the manner (a12), (b11) and the manner (b12) are four parallel schemes, and the dynamic recommendation server selects to execute. Since the manner (a11), the manner (a12), the manner (b11) and the manner (b12) are all used for determining the second recommendation result in the first recommendation result, the four manners are all applicable to the situation that the first recommendation result is relatively comprehensive.
When the first recommendation result contains less information and the information is incomplete, the dynamic recommendation server can screen out the information which is currently preferred by the user as a second recommendation result in the local database or the remote database according to the behavior data executed by the user on the displayed information in the first recommendation result. In this case, the dynamic recommendation server determines that the second recommendation result specifically is: and the dynamic recommendation server screens out a plurality of pieces of information matched with the behavior data in a local database or a remote database, sorts the plurality of pieces of information according to the matching degree of the plurality of pieces of information and the behavior data, and takes the sorted plurality of pieces of information as a second recommendation result.
For example, the behavior data includes payment behavior data, the dynamic recommendation server searches a plurality of products having the same attribute, class and label as the product in a remote database or a local database according to the attribute, class and label of the product paid by the user, searches products having an association relationship with the product according to a collaborative filtering principle, such as products purchased at the same time or products used at the same time, calculates the matching degree of the product information of the plurality of searched products with the behavior data, sorts the plurality of product information according to the sequence of the matching degree from high to low, and takes the sorted plurality of product information as a second recommendation result.
In this step, the plurality of pieces of information in the second recommendation result are sorted in the order of the matching degree with the behavior data from high to low, so that the higher the information matching with the behavior data is, the higher the information sorting is, the readability of the second recommendation result can be improved.
In order to improve the content diversity of the second recommendation result, the second recommendation result may further include information that is frequently browsed by social friends of the user in the application program, information that a large number of popular users browse at present, information that is relatively popular among people and the like.
And step S108, the client receives the second recommendation result, and updates the undisplayed information in the first recommendation result according to the second recommendation result.
And the client receives a second recommendation result matched with the behavior data and fed back by the server, and updates the undisplayed information in the first recommendation result according to the second recommendation result. Updating the undisplayed information in the first recommendation result according to the second recommendation result, specifically, replacing the undisplayed information in the first recommendation result with the second recommendation result. And if the client detects the screen sliding operation of the user, displaying part of the updated undisplayed information according to the size of the display screen.
In this embodiment, steps S104 to S108 are repeatedly executed for multiple times until the user exits from the first recommendation result and the sub-page included in the first recommendation result, so that it is ensured that the first recommendation result is updated in real time according to the behavior feedback of the user in the process of browsing and operating the first recommendation result by the user.
According to the information recommendation method, the real-time feedback of the user on the recommendation result can be considered, the recommendation result can be dynamically adjusted according to the real-time feedback of the user in the information browsing process, the recommendation result can better meet the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
In this embodiment, the undisplayed information in the first recommendation result is updated by using the second recommendation result, so that the updating action is unknown to the user, the information that the user has not seen is updated under the condition that the user does not know, and the browsing experience of the user can be further improved.
According to the foregoing, in this embodiment, two servers may be provided, where the basic recommendation server is configured to provide a first recommendation result, and the dynamic recommendation server is configured to provide a second recommendation result, and a mechanism in which the two servers separately operate is adopted, so that the performance requirements of the servers can be ensured, and the accuracy of the first recommendation result and the accuracy of the second recommendation result can be ensured.
Considering that when the speed of browsing the first recommendation result by the user is too fast, that is, the speed of sliding or turning the page of the user is too fast, the client does not timely update the undisplayed information in the first recommendation result according to the second recommendation result, in this embodiment, the updating of the undisplayed information in the first recommendation result by the client specifically includes detecting the speed of browsing the first recommendation result by the user, and if the speed is less than or equal to a preset speed threshold, updating the undisplayed information in the first recommendation result according to the second recommendation result.
And if the speed of the user for browsing the first recommendation result is greater than the preset speed threshold value, not updating the undisplayed information in the first recommendation result. Specifically, the client detects the speed of the user for browsing the first recommendation result, namely detects the speed of screen sliding or page turning of the user, and takes the speed as the speed of the user for browsing the first recommendation result.
In order to avoid the user from browsing the repeated information, the embodiment of the present invention provides any one of the following two ways to solve the problem.
(c11) The client updates the undisplayed information in the first recommendation result according to the second recommendation result in the following mode: detecting whether the information in the second recommendation result is overlapped with the displayed information in the first recommendation result; and if the second recommendation result exists, removing the information which is overlapped with the displayed information in the first recommendation result from the second recommendation result to obtain an updated second recommendation result, and replacing the undisplayed information in the first recommendation result by using the updated second recommendation result. The client can detect whether the information in the second recommendation result is overlapped with the displayed information in the first recommendation result according to the identifier of each piece of information.
(c12) And the client sends indication information to the dynamic recommendation server before receiving a second recommendation result fed back by the dynamic recommendation server, wherein the indication information is used for representing displayed information in the first recommendation result. The indication information may be the displayed information in the first recommendation result, and may also be an identifier of the displayed information. Correspondingly, when the dynamic recommendation server executes the method in this embodiment, before sending the second recommendation result to the client, the method further includes: receiving indication information sent by the client, and sending a second recommendation result to the client by the dynamic recommendation server, wherein the second recommendation result is specifically: and in the second recommendation result, removing information superposed with the displayed information in the first recommendation result according to the indication information, and sending the residual information in the second recommendation result to the client. And the dynamic recommendation server determines the displayed information in the first recommendation result according to the indication information, and removes the information overlapped with the displayed information in the first recommendation result from the second recommendation result.
In this embodiment, when determining the second recommendation result, if the second recommendation result is determined in the undisplayed information of the first recommendation result, the dynamic recommendation server does not need to perform information deduplication in the above manner (c11) or (c 12); if the second recommendation result is determined in all the information of the first recommendation result, or the second recommendation result is determined in the local database or the remote database, the information duplication removal needs to be performed in the above-mentioned manner (c11) or (c 12).
In order to facilitate the client to update the undisplayed information in the first recommendation result, in this embodiment, the client and the dynamic recommendation server may perform information deduplication in the manner (c12) described above, or the dynamic recommendation server determines the second recommendation result in the undisplayed information in the first recommendation result, in this case, when the client updates the undisplayed information in the first recommendation result according to the second recommendation result, the undisplayed information in the first recommendation result may be directly replaced with the second recommendation result.
In view of the fact that when the dynamic recommendation server determines the second recommendation result in the local database or the remote database, the number of information included in the determined second recommendation result may be too large, in this embodiment, before the client receives the second recommendation result, the client further sends the number control information to the server, with the number of all information in the first recommendation result or the number of undisplayed information in the first recommendation result as the number control information. Correspondingly, before sending the second recommendation result to the client, the dynamic recommendation server also receives quantity control information sent by the client, and sends the second recommendation result to the client, specifically: and screening partial information with the top rank from the second recommendation result according to the quantity control information, and sending the screened partial information to the client. The ranking refers to ranking of the matching degree of the plurality of pieces of information in the second recommendation result and the behavior data from high to low.
The dynamic recommendation server screens out part of information with the top ranking from the second recommendation result according to the quantity control information, and may screen out information with the top ranking one by one and the same number as the number of information pieces indicated by the quantity control information from the first information in the second recommendation result.
In this embodiment, the client sends the quantity control information to the dynamic recommendation server, and the dynamic recommendation server screens part of information in the second recommendation result according to the quantity control information and sends the part of information to the client, so that the quantity of information received by the client is appropriate, thereby avoiding the excessive quantity of information displayed by the client and meeting the requirement of the current scene on the quantity of information displayed.
In this embodiment, when the dynamic recommendation server determines the second recommendation result in the local database or the remote database, the dynamic recommendation server preferably performs information deduplication according to the above-mentioned method (c12), and then performs information quantity screening according to the above-mentioned method after deduplication, in which case, when the client updates the first recommendation result, the client may directly replace the undisplayed information in the first recommendation result with the second recommendation result. Of course, the client may also directly replace the information not shown in the first recommendation result with the second recommendation result in other cases, for example, after the dynamic server controls the number of pieces of information of the second recommendation result only according to the quantity control information, which is not listed here.
It can be understood that, the above three schemes of client information deduplication, server information deduplication and server information quantity control are provided, in the specific implementation, the scheme of client information deduplication and the scheme of server information deduplication are alternatively executed, the scheme of client information deduplication may be combined with the scheme of server information quantity control, the scheme of server information deduplication may be combined with the scheme of server information quantity control, and the combined scheme is also within the scope of this embodiment. And will not be described in detail herein.
Fig. 2 is a schematic view of an application scenario of a method provided by an embodiment of the present invention, as shown in fig. 2, when a client is a smart phone of a user, and the user opens an application program on the smart phone to select takeout, the smart phone obtains a first recommendation result from a basic recommendation server, and displays part of information according to the size of a display screen, in the process that the user browses the first recommendation result, the client collects behavior data and sends the behavior data to a dynamic recommendation server, the dynamic recommendation server determines first information matched with the behavior data in the first recommendation result obtained in advance according to the behavior data, determines second information to be recommended in a local database, integrates the first information and the second information as a second recommendation result, and sends the second recommendation result to the client, and the client selects information that is not displayed in the first recommendation result in the second recommendation result, the undisplayed information in the first recommendation result is updated by the undisplayed information, so that the information which meets the current requirements of the user is provided for the user in one browsing scene, and the takeout experience of the user is improved. The second information to be recommended comprises a type of information which is never browsed by the user so as to assist in mining points of interest of the user.
In summary, the information recommendation method provided by the embodiment of the invention has the following advantages:
(1) the real-time performance is higher. The client can quickly collect the behavior data of the user to adjust the recommendation result according to the behavior data.
(2) The recommendation result is more accurate. The dynamic recommendation server utilizes the behavior data fed back by the user in real time at present, and can ensure that the recommendation result is closer to the user requirement.
(3) More diversification is recommended. According to behavior data fed back by the user, the dynamic recommendation server dynamically adjusts the recommendation strategy to meet the preference of the user in real time, and meanwhile, information that some users have not browsed or are relatively cold or relatively hot before can be added to the second recommendation result, so that the diversity of the recommendation result is enriched.
(4) Better user experience. And presenting a recommendation result to the user according to the behavior data fed back by the user in real time, really realizing the real-time interaction between the user and the dynamic recommendation server and enabling the user to experience the intelligence of a recommendation strategy.
Corresponding to the information recommendation method, an embodiment of the present invention provides an information recommendation apparatus, where the apparatus is configured to execute a method executed by the client, and fig. 3 is a schematic diagram of module composition of the apparatus provided in the embodiment of the present invention, and as shown in fig. 3, the apparatus includes:
the information display module 21 is configured to obtain a first recommendation result corresponding to the user request, and display part of information in the first recommendation result according to the size of the display screen;
the behavior acquisition module 22 is used for acquiring behavior data executed by the user on the displayed information in the first recommendation result in real time and sending the behavior data to the server;
and the information updating module 23 is configured to receive a second recommendation result matched with the behavior data and fed back by the server, and update the undisplayed information in the first recommendation result according to the second recommendation result.
The information updating module 23 is specifically configured to replace the undisplayed information in the first recommendation result with the second recommendation result.
Considering that when the speed of the user browsing the first recommendation result is too fast, that is, the speed of the user sliding or turning the page is too fast, the client does not timely update the undisplayed information in the first recommendation result according to the second recommendation result, in this embodiment, the information updating module 23 includes: the speed detection unit is used for detecting the speed of the user for browsing the first recommendation result; and the first updating unit is used for updating the undisplayed information in the first recommendation result according to the second recommendation result if the speed is less than or equal to the preset speed threshold.
To avoid the user browsing duplicate information, in one embodiment, the information update module 23 includes: the information detection unit is used for detecting whether the information in the second recommendation result is overlapped with the displayed information in the first recommendation result or not; the information removing unit is used for removing information which is overlapped with the displayed information in the first recommendation result from the second recommendation result if the information is overlapped, so as to obtain an updated second recommendation result; and the second updating unit is used for replacing the undisplayed information in the first recommendation result by the updated second recommendation result.
In order to avoid the user browsing the repeated information, in another embodiment, the client further includes: and the first sending module is used for sending indication information to the server before receiving the second recommendation result, wherein the indication information is used for representing the displayed information in the first recommendation result.
In a scenario where the requirement on the amount of information presented by the client is strict, the client in this embodiment further includes: and the second sending module is used for sending the quantity control information to the server by taking the quantity of all information in the first recommendation result or the quantity of undisplayed information in the first recommendation result as the quantity control information before receiving the second recommendation result.
According to the embodiment of the invention, the behavior data executed by the user on the displayed information in the first recommendation result can be collected, and the undisplayed information in the first recommendation result is updated by using the second recommendation result matched with the behavior data, so that the recommendation result can be dynamically adjusted according to the real-time feedback of the user in the information browsing process by considering the real-time feedback of the user on the recommendation result, the recommendation result is more in line with the requirement of the user in the current browsing scene, and the browsing experience of the user is improved.
Corresponding to the information recommendation method, an embodiment of the present invention further provides another information recommendation apparatus, where the apparatus is configured to execute the method executed by the dynamic recommendation server, and fig. 4 is a schematic diagram of module compositions of the apparatus provided in the embodiment of the present invention, and as shown in fig. 4, the apparatus includes:
the data receiving module 31 is configured to receive behavior data sent by the client, where the behavior data is executed by the user on the displayed information in the first recommendation result, where the first recommendation result corresponds to the user request and is displayed on the display screen according to the size of the display screen of the client;
and the information recommending module 32 is configured to determine a second recommending result matched with the behavior data, and send the second recommending result to the client, where the second recommending result is used to update the undisplayed information in the first recommending result.
When the information covered by the first recommendation result is relatively comprehensive, the server in this embodiment may determine a second recommendation result in the undisplayed information of the first recommendation result, in this case, the server in this embodiment further includes a first obtaining module, configured to obtain the undisplayed information in the first recommendation result before determining the second recommendation result that matches the behavior data, and correspondingly, the information recommendation module 32 is specifically configured to, in the obtained undisplayed information, screen out the information that matches the behavior data, and take the screened information as the second recommendation result; or respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
In this case, the server in this embodiment further includes a second obtaining module, configured to obtain all information in the first recommendation result before determining the second recommendation result that matches the behavior data, and correspondingly, the information recommending module 32 is specifically configured to, among all the obtained information, screen out information that matches the behavior data, and use the screened information as the second recommendation result; or respectively calculating the matching degree of each piece of information in all the pieces of information and the behavior data, reordering each piece of information in all the pieces of information according to the matching degree, and taking all the ordered information as a second recommendation result.
When the information covered by the first recommendation result is not complete, the server in this embodiment may determine the second recommendation result in the local database or the remote database, in which case, the information recommendation module 32 is specifically configured to screen out a plurality of pieces of information matched with the behavior data in the local database or the remote database; and sequencing the plurality of pieces of information according to the matching degree of the plurality of pieces of information and the behavior data, and taking the sequenced plurality of pieces of information as a second recommendation result.
In order to avoid that the user browses repeated information, the server in this embodiment further includes a first receiving module, configured to receive indication information sent by the client before sending the second recommendation result to the client, where the indication information is used to represent displayed information in the first recommendation result; correspondingly, the information recommending module 32 is specifically configured to, in the second recommendation result, remove information that overlaps with the displayed information in the first recommendation result according to the indication information, and send remaining information in the second recommendation result to the client.
In a scenario where the requirement on the amount of information presented by the client is strict, the server in this embodiment further includes a second receiving module, configured to receive amount control information sent by the client before sending the second recommendation result to the client, where the amount control information includes an amount of all information in the first recommendation result or an amount of undisplayed information in the first recommendation result; correspondingly, the information recommending module 32 is specifically configured to, according to the quantity control information, screen out partial information with the top rank from the second recommending result, and send the screened partial information to the client.
According to the embodiment of the invention, the second recommendation result can be generated according to the behavior data of the user, the behavior data is the behavior data executed by the user on the displayed information in the first recommendation result in the process of browsing the first recommendation result, and the second recommendation result is used for updating the undisplayed information in the first recommendation result.
Corresponding to the information recommendation method, the embodiment of the invention provides an information recommendation system, which comprises the client and the server (namely, a dynamic recommendation server), and based on the content, the information recommendation system can consider the real-time feedback of the user on the recommendation result, and dynamically adjust the recommendation result according to the real-time feedback of the user in the information browsing process, so that the recommendation result is more in line with the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
In view of the specific implementation manner of the method in this embodiment, an electronic device is further provided in this embodiment of the present invention, fig. 5 is a schematic structural diagram of an electronic device provided in this embodiment of the present invention, and as shown in fig. 5, the client includes a display screen 41, a first memory 42, a first processor 43, and a computer program stored in the first memory 42 and capable of being executed on the first processor 43, where the display screen 41 is capable of being touched by a user to browse information, and the first processor 43 implements the steps of the information recommendation method executed by the client when executing the computer program.
Based on the above content, the electronic device can consider the real-time feedback of the user on the recommendation result, and dynamically adjust the recommendation result according to the real-time feedback of the user in the information browsing process, so that the recommendation result better meets the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
In view of the specific implementation manner of the method in this embodiment, an embodiment of the present invention further provides another electronic device, fig. 6 is a schematic structural diagram of another electronic device provided in the embodiment of the present invention, as shown in fig. 6, the server includes a second memory 51, a second processor 52, and a computer program stored in the second memory 51 and capable of running on the second processor 52, and when the second processor 52 executes the computer program, the steps of the information recommendation method executed by the server are implemented.
Based on the above content, the electronic device can consider the real-time feedback of the user on the recommendation result, and dynamically adjust the recommendation result according to the real-time feedback of the user in the information browsing process, so that the recommendation result better meets the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
Further, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the information recommendation method executed by the client.
Specifically, the storage medium can be a general storage medium, such as a usb disk, a mobile magnetic disk, a hard disk, an optical disk, and the like, and when a computer program on the storage medium is executed, the steps of the information recommendation method executed by the client can be executed, and the recommendation result can be dynamically adjusted according to the real-time feedback of the user in the information browsing process in consideration of the real-time feedback of the user on the recommendation result, so that the recommendation result better meets the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
Further, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the information recommendation method executed by the server. The server here refers to the dynamic recommendation server described above.
Specifically, the storage medium can be a general storage medium, such as a usb disk, a mobile magnetic disk, a hard disk, an optical disk, and the like, and when a computer program on the storage medium is executed, the steps of the information recommendation method executed by the server can be executed, and the recommendation result can be dynamically adjusted according to the real-time feedback of the user in the information browsing process in consideration of the real-time feedback of the user on the recommendation result, so that the recommendation result better meets the requirements of the user in the current browsing scene, and the browsing experience of the user is improved.
The apparatus provided by the embodiment of the present invention may be specific hardware on the device, or software or firmware installed on the device, etc. The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the foregoing systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided by the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (14)

1. An information recommendation method, comprising:
acquiring a first recommendation result corresponding to a user request, and displaying part of information in the first recommendation result according to the size of a display screen;
acquiring behavior data executed by a user on the displayed information in the first recommendation result in real time, and sending the behavior data to a server;
receiving a second recommendation result matched with the behavior data and fed back by the server, and updating undisplayed information in the first recommendation result according to the second recommendation result;
the server obtains a second recommendation result matched with the behavior data through the following method:
obtaining undisplayed information in the first recommendation result;
screening out information matched with the behavior data from the obtained undisplayed information, and taking the information obtained by screening out as a second recommendation result; or,
and respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
2. The method of claim 1, wherein updating the undisplayed information in the first recommendation according to the second recommendation comprises:
detecting whether the information in the second recommendation result is overlapped with the displayed information in the first recommendation result;
if the second recommendation result exists, removing information which is overlapped with the displayed information in the first recommendation result from the second recommendation result to obtain an updated second recommendation result;
and replacing the undisplayed information in the first recommendation result by the updated second recommendation result.
3. The method of claim 1, further comprising, prior to receiving the second recommendation:
and sending indication information to the server, wherein the indication information is used for representing the displayed information in the first recommendation result.
4. The method of claim 1, further comprising, prior to receiving the second recommendation:
and sending the quantity control information to the server by taking the quantity of all information in the first recommendation result or the quantity of undisplayed information in the first recommendation result as quantity control information.
5. The method of claim 3 or 4, wherein the updating the undisplayed information in the first recommendation according to the second recommendation comprises:
and replacing the undisplayed information in the first recommendation result with the second recommendation result.
6. The method of any one of claims 1 to 4, wherein the updating the undisplayed information in the first recommendation according to the second recommendation comprises:
detecting the speed of the user for browsing the first recommendation result;
and if the speed is less than or equal to a preset speed threshold, updating the undisplayed information in the first recommendation result according to the second recommendation result.
7. An information recommendation method, comprising:
receiving behavior data which is sent by a client and executed by a user on the displayed information in the first recommendation result;
determining a second recommendation result matched with the behavior data, and sending the second recommendation result to the client, wherein the second recommendation result is used for updating undisplayed information in the first recommendation result;
before the determining the second recommendation matching the behavior data, further comprising: obtaining undisplayed information in the first recommendation result;
the determining a second recommendation that matches the behavioral data includes:
screening out information matched with the behavior data from the obtained undisplayed information, and taking the information obtained by screening out as a second recommendation result; or,
and respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
8. The method of claim 7, wherein determining the second recommendation that matches the behavior data comprises:
screening out a plurality of pieces of information matched with the behavior data in a local database or a remote database;
and sequencing the plurality of pieces of information according to the matching degree of the plurality of pieces of information and the behavior data, and taking the sequenced plurality of pieces of information as a second recommendation result.
9. The method according to claim 7 or 8, wherein before the sending the second recommendation result to the client, further comprising: receiving indication information sent by the client, wherein the indication information is used for representing displayed information in the first recommendation result;
the sending the second recommendation result to the client includes:
and in the second recommendation result, removing information superposed with the displayed information in the first recommendation result according to the indication information, and sending the residual information in the second recommendation result to the client.
10. The method of claim 8, wherein before sending the second recommendation to the client, further comprising: receiving quantity control information sent by the client, wherein the quantity control information comprises the quantity of all information in the first recommendation result or the quantity of undisplayed information in the first recommendation result;
the sending the second recommendation result to the client includes:
and screening partial information with the top rank from the second recommendation result according to the quantity control information, and sending the screened partial information to the client.
11. An information recommendation apparatus, comprising:
the information display module is used for acquiring a first recommendation result corresponding to a user request and displaying part of information in the first recommendation result according to the size of a display screen;
the behavior acquisition module is used for acquiring behavior data executed by the user on the displayed information in the first recommendation result in real time and sending the behavior data to the server;
the information updating module is used for receiving a second recommendation result matched with the behavior data and fed back by the server and updating undisplayed information in the first recommendation result according to the second recommendation result; the server obtains a second recommendation result matched with the behavior data through the following method:
obtaining undisplayed information in the first recommendation result;
screening out information matched with the behavior data from the obtained undisplayed information, and taking the information obtained by screening out as a second recommendation result; or,
and respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
12. An information recommendation apparatus, comprising:
the data receiving module is used for receiving behavior data which is sent by the client and executed by the user on the displayed information in the first recommendation result;
the information recommendation module is used for determining a second recommendation result matched with the behavior data and sending the second recommendation result to the client, wherein the second recommendation result is used for updating undisplayed information in the first recommendation result;
the information recommending module is further used for acquiring undisplayed information in the first recommending result before the second recommending result matched with the behavior data is determined;
the information recommendation module is specifically configured to determine a second recommendation result matched with the behavior data by using the following method: screening out information matched with the behavior data from the obtained undisplayed information, and taking the information obtained by screening out as a second recommendation result; or respectively calculating the matching degree of each piece of information in the undisplayed information and the behavior data, reordering each piece of information in the undisplayed information according to the matching degree, and taking the ordered undisplayed information as a second recommendation result.
13. An electronic device comprising a first memory, a first processor and a computer program stored on the first memory and executable on the first processor, wherein the steps of the method of any of the preceding claims 1 to 6 are performed when the computer program is executed by the first processor.
14. An electronic device comprising a second memory, a second processor and a computer program stored on the second memory and executable on the second processor, wherein the steps of the method of any of the preceding claims 7 to 10 are implemented when the computer program is executed by the second processor.
CN201710395439.2A 2017-05-26 2017-05-26 Information recommendation method and device, electronic equipment Active CN107423355B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710395439.2A CN107423355B (en) 2017-05-26 2017-05-26 Information recommendation method and device, electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710395439.2A CN107423355B (en) 2017-05-26 2017-05-26 Information recommendation method and device, electronic equipment

Publications (2)

Publication Number Publication Date
CN107423355A CN107423355A (en) 2017-12-01
CN107423355B true CN107423355B (en) 2019-03-15

Family

ID=60429148

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710395439.2A Active CN107423355B (en) 2017-05-26 2017-05-26 Information recommendation method and device, electronic equipment

Country Status (1)

Country Link
CN (1) CN107423355B (en)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108460082B (en) * 2018-01-12 2021-05-25 北京三快在线科技有限公司 Recommendation method and device and electronic equipment
CN108156522A (en) * 2018-02-06 2018-06-12 南京创维信息技术研究院有限公司 Homepage content method for pushing, device and computer readable storage medium
CN108228907B (en) * 2018-02-08 2021-04-23 北京三快在线科技有限公司 Information recommending method and device, electronic equipment and storage medium
CN108762880B (en) * 2018-06-19 2021-07-02 北京金山安全软件有限公司 Method and device for determining display position of recommended content
CN110020194B (en) * 2018-08-09 2021-10-08 南京尚网网络科技有限公司 Resource recommendation method, device and medium
CN111241381A (en) * 2018-11-28 2020-06-05 北京奇虎科技有限公司 Information recommendation method and device, electronic equipment and computer-readable storage medium
CN109582872B (en) * 2018-12-04 2021-11-16 北京羽扇智信息科技有限公司 Information pushing method and device, electronic equipment and storage medium
CN109615428A (en) * 2018-12-10 2019-04-12 拉扎斯网络科技（上海）有限公司 Merchant recommendation method, device, system and server
CN109558544B (en) * 2018-12-12 2021-04-27 拉扎斯网络科技（上海）有限公司 Sorting method and device, server and storage medium
CN109657142B (en) * 2018-12-13 2021-04-23 拉扎斯网络科技（上海）有限公司 Information processing method, information processing device, electronic equipment and computer readable storage medium
CN112016985B (en) * 2019-05-31 2023-10-27 京东方科技集团股份有限公司 User identity recognition method and device, electronic equipment and storage medium
CN111191132B (en) * 2019-12-31 2023-10-27 支付宝(杭州)信息技术有限公司 Information recommendation method and device and electronic equipment
CN113395304A (en) * 2020-03-12 2021-09-14 阿里巴巴集团控股有限公司 Information pushing method and system, client, storage medium and computing terminal
CN111737579B (en) * 2020-06-28 2024-06-25 北京达佳互联信息技术有限公司 Object recommendation method and device, electronic equipment and storage medium
CN112989240A (en) * 2021-02-10 2021-06-18 北京三快在线科技有限公司 Object display method and device, electronic equipment and readable storage medium
CN112597293B (en) * 2021-03-02 2021-05-18 南昌鑫轩科技有限公司 Data screening method and data screening system for achievement transfer transformation
CN115080835A (en) * 2021-03-10 2022-09-20 阿里巴巴新加坡控股有限公司 Information recommendation method and device, user side and equipment
CN113010809A (en) * 2021-03-11 2021-06-22 北京三快在线科技有限公司 Information recommendation method and device
CN116932866B (en) * 2022-03-30 2024-07-23 腾讯科技（深圳）有限公司 Content recommendation method, content recommendation device, storage medium, electronic equipment and product
CN117435818B (en) * 2023-12-20 2024-04-02 深圳市唯博易科技有限公司 Processing method and system of PDA machine based on personalized recommendation application

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103714084A (en) * 2012-10-08 2014-04-09 腾讯科技（深圳）有限公司 Method and device for recommending information
CN106708874A (en) * 2015-11-16 2017-05-24 百度在线网络技术（北京）有限公司 Method and device for adjusting arrangement of searching categories in searching page

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9495460B2 (en) * 2009-05-27 2016-11-15 Microsoft Technology Licensing, Llc Merging search results
CN102930022B (en) * 2012-10-31 2015-11-25 中国运载火箭技术研究院 User oriented information search engine system and method
CN103678518B (en) * 2013-11-28 2017-02-15 北京邮电大学 Method and device for adjusting recommendation lists
CN105843885A (en) * 2016-03-21 2016-08-10 乐视网信息技术（北京）股份有限公司 Information recommendation method and apparatus applied to mobile terminal

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103714084A (en) * 2012-10-08 2014-04-09 腾讯科技（深圳）有限公司 Method and device for recommending information
CN106708874A (en) * 2015-11-16 2017-05-24 百度在线网络技术（北京）有限公司 Method and device for adjusting arrangement of searching categories in searching page

Also Published As

Publication number Publication date
CN107423355A (en) 2017-12-01

Similar Documents

Publication Publication Date Title
CN107423355B (en) Information recommendation method and device, electronic equipment
CN105808685B (en) Promotion information pushing method and device
CN102073699B (en) For improving the method for Search Results, device and equipment based on user behavior
US20170083965A1 (en) Item Recommendation Method and Apparatus
US10210237B2 (en) Information processing system, similar category identification method, program, and computer readable information storage medium
CN110413870B (en) Commodity recommendation method and device and server
CN103019550B (en) The real-time exhibiting method of content association and system
CN106878405B (en) Method and device for adjusting push items
US9268858B1 (en) Previewing content based on detected customer activities
US9177341B2 (en) Determining search relevance from user feedback
CN103488465B (en) Functional configuration recommends method and system
US9065827B1 (en) Browser-based provisioning of quality metadata
CN110163703B (en) Classification model establishing method, file pushing method and server
EP2981942A2 (en) Content presentation based on social recommendations
CN105930527B (en) Searching method and device
US11748365B2 (en) Multi-dimensional search
US20130110803A1 (en) Search driven user interface for navigating content and usage analytics
US20160098416A1 (en) Auto complete search box based on the user's context to reduce user's input
US8898297B1 (en) Device attribute-customized metadata for browser users
CN115408092A (en) Privacy notification information display method and electronic equipment
CN117216396A (en) Intelligent recommendation method, device, equipment and storage medium based on big data analysis
US8903817B1 (en) Determining search relevance from user feedback
CN113392329A (en) Content recommendation method and device, electronic equipment and storage medium
JP6414192B2 (en) Information processing apparatus, information processing method, and information processing program
CN111177564A (en) Product recommendation method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant