CN108846091B - Information recommendation method, device and equipment - Google Patents
Information recommendation method, device and equipment Download PDFInfo
- Publication number
- CN108846091B CN108846091B CN201810608509.2A CN201810608509A CN108846091B CN 108846091 B CN108846091 B CN 108846091B CN 201810608509 A CN201810608509 A CN 201810608509A CN 108846091 B CN108846091 B CN 108846091B
- Authority
- CN
- China
- Prior art keywords
- information
- preset
- information content
- condition
- content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses an information recommendation method, device and equipment, wherein the method comprises the following steps: detecting whether information content opened by a user on terminal equipment meets a preset visualization condition or not; if the opened information content is detected to meet the preset visualization condition, detecting whether the information content meets the preset effective reading condition; if the information content is detected to meet the preset effective reading condition, extracting the information key information from the information content, and acquiring the reading behavior characteristics of the user on the information content; and acquiring target information matched with the user according to the information key information and the reading behavior characteristics for pushing. Therefore, when the information content meets the visualization condition and the effective reading condition, the target information is obtained for personalized recommendation according to the information key information and the reading behavior characteristics of the current information content, so that the accuracy of reading records is ensured, and the accuracy of personalized recommendation is improved.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an information recommendation method, device and equipment.
Background
With the development of internet technology, personalized recommendation is also becoming a hot topic.
In the related art, the personalized recommendation system generally recommends according to the reading record of the user, for example, when the user reads shopping information for many times through a news client, the news client can recommend other shopping information to the user according to the reading record of the user. However, in practical applications, when a user reads, the user may be disturbed by other things and temporarily leave, or the content of the information is covered by other applications, so that the accuracy of reading records cannot be ensured, and the information recommended according to such reading records also often cannot meet the user's expectations, and the accuracy is low.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present invention is to provide an information recommendation method, so as to achieve personalized recommendation by obtaining target information according to information key information and reading behavior characteristics of current information content when the information content meets visualization conditions and effective reading conditions, thereby ensuring accuracy of reading records and improving accuracy of personalized recommendation.
The second objective of the present invention is to provide an information recommendation apparatus.
A third object of the present invention is to provide a terminal device.
A fourth object of the invention is to propose a non-transitory computer-readable storage medium.
To achieve the above object, a first aspect of the present invention provides an information recommendation method, including:
detecting whether information content opened by a user on terminal equipment meets a preset visualization condition;
if the opened information content is detected to meet the preset visualization condition, detecting whether the information content meets the preset effective reading condition;
if the information content is detected to meet a preset effective reading condition, extracting information key information from the information content, and acquiring the reading behavior characteristics of the user on the information content;
and acquiring target information matched with the user according to the information key information and the reading behavior characteristics for pushing.
In addition, the information recommendation method according to the above embodiment of the present invention may further have the following additional technical features:
optionally, the detecting whether the information content opened by the user on the terminal device meets a preset visualization condition includes: detecting whether the information content opened by the user on the terminal equipment is in a minimized state; if the information content is detected to be in the minimized state, the preset visualization condition is not met; if the information content is not detected to be in the minimized state, detecting whether the covered area of the visual interface of the information content is smaller than a preset threshold value; if the covered area of the visual interface of the information content is smaller than a preset threshold value, the condition that a preset visual condition is met is obtained; and if the covered area of the visual interface of the information content is detected to be larger than or equal to a preset threshold value, the situation that the preset visual condition is not met is known.
Optionally, the detecting whether the information content meets a preset effective reading condition includes: detecting whether the mouse moves on the visual interface of the information content within a preset first time; if the mouse is detected to move on the visual interface of the information content within the first time, the information content is acquired to meet a preset effective reading condition; if the fact that the mouse stays on the visual interface of the information content continuously within the first time is detected, the fact that the information content does not meet preset effective reading conditions is obtained.
Optionally, the detecting whether the information content meets a preset effective reading condition includes: detecting whether the rolling distance of the scroll bar of the information content in a preset second time exceeds a preset distance threshold; if the rolling distance of the scroll bar in the second time is detected to be larger than a preset distance threshold, the information content is known to meet a preset effective reading condition; and if the rolling distance of the scroll bar in the second time is detected to be smaller than or equal to a preset distance threshold, the information content is acquired not to meet a preset effective reading condition.
Optionally, the extracting information key information from the information content includes: acquiring an information title of the information content; analyzing the text content of the information content by using a preset information base matched with the information title, and extracting information keywords; and generating information key information according to the information title and the information key words.
Optionally, the obtaining, according to the information key information and the reading behavior feature, target information matched with the user for pushing includes: inquiring a preset push strategy to obtain the information quantity corresponding to the reading behavior characteristic; searching candidate information related to the information key information, and sequentially acquiring target information matched with the information quantity according to the sorting heat of the candidate information and pushing the target information to the user.
To achieve the above object, a second aspect of the present invention provides an information recommendation apparatus, comprising:
the first detection module is used for detecting whether the information content opened on the terminal equipment by the user meets the preset visualization condition;
the second detection module is used for detecting whether the information content meets a preset effective reading condition or not if the opened information content meets a preset visual condition;
the acquisition module is used for extracting information key information from the information content and acquiring the reading behavior characteristics of the user on the information content if the information content is detected to meet the preset effective reading condition;
and the pushing module is used for acquiring target information matched with the user according to the information key information and the reading behavior characteristics and pushing the target information.
In addition, the information recommendation device according to the above embodiment of the present invention may further have the following additional technical features:
optionally, the first detection module is specifically configured to: detecting whether the information content opened by the user on the terminal equipment is in a minimized state; if the information content is detected to be in the minimized state, the situation that the preset visualization condition is not met is known; if the information content is not detected to be in the minimized state, detecting whether the covered area of the visual interface of the information content is smaller than a preset threshold value; if the covered area of the visual interface of the information content is smaller than a preset threshold value, the condition that a preset visual condition is met is obtained; and if the covered area of the visual interface of the information content is detected to be larger than or equal to a preset threshold value, the situation that the preset visual condition is not met is known.
Optionally, the second detection module is specifically configured to: detecting whether the mouse moves on the visual interface of the information content within a preset first time; if the mouse is detected to move on the visual interface of the information content within the first time, the information content is acquired to meet a preset effective reading condition; if the fact that the mouse stays on the visual interface of the information content continuously within the first time is detected, the fact that the information content does not meet preset effective reading conditions is obtained.
Optionally, the second detection module is specifically configured to: detecting whether the rolling distance of the scroll bar of the information content in a preset second time exceeds a preset distance threshold or not; if the rolling distance of the scroll bar in the second time is detected to be larger than a preset distance threshold, the information content is known to meet a preset effective reading condition; and if the rolling distance of the scroll bar in the second time is detected to be smaller than or equal to a preset distance threshold, the information content is acquired not to meet a preset effective reading condition.
Optionally, the obtaining module is specifically configured to: acquiring an information title of the information content; analyzing the text content of the information content by using a preset information base matched with the information title, and extracting information keywords; and generating information key information according to the information title and the information key words.
Optionally, the pushing module is specifically configured to: inquiring a preset push strategy to obtain the information quantity corresponding to the reading behavior characteristic; and searching candidate information related to the information key information, and acquiring target information matched with the information quantity in sequence according to the sorting heat of the candidate information and pushing the target information to the user.
To achieve the above object, a third embodiment of the present invention provides a terminal device, including a processor and a memory; the processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the information recommendation method according to the embodiment of the first aspect.
To achieve the above object, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program is executed by a processor to implement the information recommendation method according to the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
whether information content opened by a user on terminal equipment meets a preset visualization condition is detected, whether the information content meets a preset effective reading condition is detected when the opened information content meets the preset visualization condition is detected, information key information is extracted from the information content when the information content meets the preset effective reading condition is detected, the reading behavior characteristics of the user on the information content are obtained, and target information matched with the user is obtained according to the information key information and the reading behavior characteristics and pushed. Therefore, when the information content meets the visualization condition and the effective reading condition, the target information is acquired according to the information key information and the reading behavior characteristic of the current information content for personalized recommendation, so that the accuracy of reading records is ensured, and the accuracy of personalized recommendation is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flowchart illustrating an information recommendation method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating another information recommendation method according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an overlay of a visual interface for information content according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating another information content visualization interface overlay according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present invention;
fig. 6 shows a block diagram of an exemplary terminal device suitable for use in implementing embodiments of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The information recommendation method, apparatus and device according to the embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of an information recommendation method according to an embodiment of the present invention, as shown in fig. 1, the information recommendation method includes:
In the embodiment of the invention, the execution main body is terminal equipment. The terminal device can be a smart phone, a tablet computer, a personal digital assistant, a wearable device, a computer and the like which can perform data processing. When a user opens the information content on the terminal equipment for reading, whether the opened information content meets the preset visualization condition can be detected. The preset visualization condition may be in various forms, for example, the preset visualization condition may be set to an information content window state, whether a screen is lighted, or not, and the preset visualization condition may be set by a user according to a need.
In an embodiment of the present invention, it may be detected whether the information content opened by the user on the terminal device is in a minimized state, and if the information content is detected to be in the minimized state, it is known that the preset visualization condition is not satisfied; if the information content is not in the minimized state, the preset visualization condition is met.
As a possible implementation manner, whether the client window corresponding to the information content is in a minimized state or not can be determined through an IsIconic function, and when the function return value is zero, it is determined that the client window corresponding to the information content is not in the minimized state, so that the visualization condition is met; and when the return value is not zero, determining that the client window corresponding to the information content is in a minimized state and does not meet the visualization condition.
It should be noted that, when the information content does not satisfy the preset visualization condition, it is determined that the current information content is not read, and step 102 is not executed.
It should be noted that, whether the information content opened by the user on the terminal device meets the preset visualization condition may be detected according to a certain frequency, or the detection may be performed in real time, which is not limited herein.
In an embodiment of the invention, whether the mouse moves on the visual interface of the information content within a preset first time can be detected through a related Web front-end behavior detection technology, and if the mouse moves on the visual interface of the information content within the first time, the information content is known to meet a preset effective reading condition; if the mouse is detected to stay on the visual interface of the information content continuously within the first time, the information content is acquired not to meet the preset effective reading condition.
For example, the first time is set to 30 seconds, the position coordinate of a mouse cursor can be obtained through a GetCursorPos function, the rectangular range of a visual interface window of information content can be obtained through a GetWindowRect function, whether the mouse is in the visual interface of the information content can be further judged according to the position coordinate and the rectangular range, when the mouse is in the visual interface of the information content, whether the mouse moves or not is detected through an onmouseove event in a JAVA description language (JavaScript), when the onmouseove event is triggered in 30 seconds, the mouse is known to move in the visual interface of the information content in the first time, and the information content is known to meet a preset effective reading condition; when detecting that the onmousecover event is not triggered within 30 seconds, knowing that the mouse continuously stays on the visual interface of the information content within the first time, knowing that the information content does not meet the preset effective reading condition.
In an embodiment of the present invention, it may be detected through a related Web front-end behavior detection technology whether a rolling distance of a scroll bar of information content in a preset second time exceeds a preset distance threshold, and if it is detected that the rolling distance of the scroll bar in the second time is greater than the preset distance threshold, it is known that the information content meets a preset effective reading condition; if the scroll distance of the scroll bar in the second time is detected to be smaller than or equal to the preset distance threshold, the information content is acquired not to meet the preset effective reading condition.
For example, the second time is set to 20 seconds, the preset distance threshold is 5 centimeters, the vertical height of the scroll bar can be obtained according to a $ (document) scrollTop () function, the vertical height of the scroll bar is obtained in real time within 20 seconds, the scroll distance of the scroll bar within the second time is further obtained through a related algorithm, the scroll distance is further compared with the preset threshold of 5 centimeters, and when the scroll distance is greater than 5 centimeters, the information content is known to meet the preset effective reading condition; when the rolling distance is less than or equal to 5 cm, the information content is not satisfied with the preset effective reading condition.
It should be noted that, in practical application, a horizontally-set scroll bar may also exist, and the horizontally-set scroll bar may be detected through a $ (document) and scrollLeft () function, where the detection process is similar to the above example, and is not described here again.
It should be noted that the first time, the second time, and the distance threshold may be determined according to a large number of experiments, or may be set by the user according to actual needs, which is not limited herein. The above-mentioned manner for detecting whether the information content satisfies the predetermined valid reading condition is only exemplary, and the detection can be performed by only one manner, or can be performed by combining multiple manners, which is not limited herein.
In this embodiment, the information key information can be extracted from the information content, for example, as follows:
optionally, the information title and the text content may be directly obtained from the information content, and then the information keyword is extracted from the text content according to a topic model (topic-model), a term frequency-inverse text frequency index (TF-IDF for short), and the information key information is further generated according to the information title and the information keyword.
The information key information may be an information title, an information keyword, an information category, and the like, which is not limited herein.
In this embodiment, the reading behavior characteristics of the user on the information content may also be obtained, which is exemplified as follows:
as a possible implementation mode, information such as a client user identification code, a password, a browsed webpage, a staying time and the like can be recorded through data (cookies) stored on a user local terminal, and then the information recorded in the cookies is called through related functions and analyzed, so that the reading behavior characteristics of the user on the information content are obtained.
The reading behavior characteristics include, but are not limited to, reading time, reading times, reading progress, user preferences, and the like.
And step 104, acquiring target information matched with the user according to the information key information and the reading behavior characteristics for pushing.
In an embodiment of the present invention, the pushing time may be determined according to the reading behavior characteristics, and information related to the key information of the information is searched as target information, so that the target information is pushed at the corresponding pushing time.
In an embodiment of the present invention, a preset push policy may be further queried to obtain an information quantity corresponding to the reading behavior feature, so as to search candidate information related to the information key information, and sequentially obtain target information matching the information quantity according to the ranking heat of the candidate information, and push the target information to the user.
In the embodiment of the invention, the accuracy of reading records can be improved by detecting whether the information content opened by the user meets the visual condition and the effective reading condition, the problem that the reading records are inaccurate due to the temporary leaving of the user or the covering of the information content, so that the deviation of the personalized recommended content occurs is solved, and the operation amount of a server side can be reduced because the information content which does not meet the condition does not participate in the personalized recommendation. Therefore, more accurate metadata can be provided for the recommendation system by ensuring the accuracy of the reading record, so that the personalized recommendation content according to the reading record is more in line with the user expectation, and the personalized recommendation accuracy is improved.
In summary, in the information recommendation method according to the embodiment of the present invention, whether the information content opened by the user on the terminal device meets the preset visualization condition is detected, and when it is detected that the opened information content meets the preset visualization condition, whether the information content meets the preset effective reading condition is detected, further, when it is detected that the information content meets the preset effective reading condition, the information key information is extracted from the information content, the reading behavior characteristic of the information content by the user is obtained, and further, the target information matched with the user is obtained according to the information key information and the reading behavior characteristic for pushing. Therefore, when the information content meets the visualization condition and the effective reading condition, the target information is acquired according to the information key information and the reading behavior characteristic of the current information content for personalized recommendation, so that the accuracy of reading records is ensured, and the accuracy of personalized recommendation is improved.
Fig. 2 is a schematic flowchart of another information recommendation method according to an embodiment of the present invention, and as shown in fig. 2, the information recommendation method includes:
As a possible implementation manner, whether the client window corresponding to the information content is in a minimized state or not can be determined through the IsIconic function, and when the function return value is zero, it is determined that the client window corresponding to the information content is not in the minimized state; and when the return value is not zero, determining that the client window corresponding to the information content is in a minimized state.
In step 203, if it is detected that the covered area of the visual interface of the information content is smaller than the preset threshold, it is known that the preset visualization condition is satisfied.
As a possible implementation manner, the covered area of the visual interface of the information content can be detected through a related client environment detection technology, so that the covered area is matched with a preset threshold value, and when the covered area of the visual interface of the information content is detected to be smaller than the preset threshold value, the condition that the preset visualization condition is met is obtained; and when the area covered on the visual interface of the information content is detected to be larger than or equal to a preset threshold value, the situation that the preset visual condition is not met is known.
For example, the preset threshold is one fourth of the area of the visual interface of the information content, and after detecting that the information content is not in the minimized state, as shown in fig. 3, if it is detected that the area covered by the visual interface of the information content is one half of the total area, the covered area is matched with the preset threshold, and it is known that the preset visualization condition is not satisfied; as shown in fig. 4, if it is detected that the covered area of the visual interface of the information content is one eighth of the total area, the covered area is matched with a preset threshold value, and it is known that the preset visualization condition is satisfied. Therefore, after the information content is detected not to be in the minimized state, whether the information content meets the visualization condition or not is judged according to the covered area of the visual interface of the information content, and the detection result is more accurate.
The preset threshold value can be determined according to a large amount of experimental data, and can also be set by a user according to actual needs.
It should be noted that, when the information content does not satisfy the preset visualization condition, it is determined that the current information content is not read, and step 204 is not executed.
It should be noted that, whether the information content opened by the user on the terminal device meets the preset visualization condition may be detected according to a certain frequency, or the detection may be performed in real time, which is not limited herein.
It should be noted that the explanation of step 102 on whether the detected information content satisfies the predetermined valid reading condition is also applicable to step 204, and is not repeated here.
In step 205, if it is detected that the information content satisfies the preset effective reading condition, the information title of the information content is obtained.
In this embodiment, if it is detected that the information content meets the preset effective reading condition, the key information of the information and the reading behavior characteristics of the user on the information content are obtained.
Optionally, an information base may be set in advance in a local terminal device or a cloud server, the text content and the information title of the information content are stored in the information base, after the information title of the information content is obtained, the information title is matched with the information base, after matching is successful, the corresponding text content is directly analyzed in the information base, the information keyword is extracted through a keyword extraction algorithm, and information key information is further generated according to the information title and the information keyword. Therefore, the calculation amount for acquiring the text content is reduced, and the processing efficiency is improved.
The information key information may be an information title, an information keyword, an information category, and the like, which is not limited herein. The explanation of the foregoing embodiment for obtaining the reading behavior characteristics of the user on the information content is also applicable to this embodiment, and is not repeated here.
For example, when the preset push strategy is to determine the number of pushed information according to the reading behavior characteristics and recommend information with high heat to the user, the push strategy is obtained through query, the number of the obtained information is calculated to be 10 according to the reading behavior characteristics through a correlation algorithm, the key information of the information is further searched through a search engine to obtain related candidate information, the heat of the candidate information is further obtained through the correlation algorithm and is ranked according to the heat from high to low, and the first 10 candidate information in the heat ranking is selected as target information to be pushed to the user.
It should be noted that, according to different application scenarios, different push strategies may be adopted to push information to a user, the number of pushed information may be determined according to reading behavior characteristics, the number of pushed information may also be directly set, target information may be obtained according to popularity, and target information may also be obtained according to similarity, which is not limited herein.
Therefore, when the information content meets the visualization condition and the effective reading condition, the target information is acquired according to the information key information and the reading behavior characteristic of the current information content for personalized recommendation, so that the accuracy of reading records is ensured, and the accuracy of personalized recommendation is improved.
In order to explain the present invention more clearly, the following detailed description is made with reference to specific application scenarios.
For example, a user browses through information using a news client, the news client window is maximized and a piece of sports information is opened while the user is chatting with QQ.
The client detects the environmental information of the current user, knows that the client is in a maximized state, and the client is covered by one third of a QQ chat interface, so that the condition that the current client does not meet the visualization condition is judged.
And then, the client side continues to detect the environmental information of the user according to a certain frequency. When the user clicks the client, the client covers the QQ chat interface, and the client detects the following information: the client is in a maximized state and is not covered by any software, so that the condition that the current client meets the visualization condition is judged, and the client sends the information meeting the visualization condition to the Web front end.
Further, the Web front end receives information that the client meets the visualization condition, and starts to detect the mouse and scroll bar states of the user, and the following information is obtained by detection before the user temporarily leaves the computer: the mouse does not move within five seconds, and the scroll bar does not have a scroll behavior, so that the information content is judged not to meet the effective reading condition.
Further, the Web front-end will continue to detect mouse and scroll bar states at a certain frequency. When the user returns to the computer desktop to continue reading the information content, the Web front end detects that the mouse moves within five seconds, and the rolling distance of the scroll bar exceeds five centimeters, so that the information content is judged to meet the effective reading condition.
Further, the information whose information content meets the effective reading condition is transmitted to the server, wherein the information content also comprises an information title, reading time, reading progress and the like. And the server side makes more accurate recommendation according to the received information. Therefore, the accuracy of reading records is guaranteed, and the accuracy of personalized recommendation is improved.
In order to implement the foregoing embodiment, the present invention further provides an information recommendation apparatus, and fig. 5 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present invention, as shown in fig. 5, the information recommendation apparatus includes: the system comprises a first detection module 100, a second detection module 200, an acquisition module 300 and a pushing module 400.
The first detection module 100 is configured to detect whether information content opened by a user on a terminal device meets a preset visualization condition.
The second detecting module 200 is configured to detect whether the information content meets a preset effective reading condition if it is detected that the opened information content meets a preset visualization condition.
The obtaining module 300 is configured to extract the information key information from the information content and obtain the reading behavior characteristics of the information content by the user if it is detected that the information content meets the preset effective reading condition.
The pushing module 400 is configured to obtain target information matched with the user according to the information key information and the reading behavior characteristics for pushing.
Further, the first detection module 100 is specifically configured to: detecting whether the information content opened by a user on the terminal equipment is in a minimized state; if the information content is detected to be in the minimized state, the situation that the preset visualization condition is not met is known; if the information content is not detected to be in the minimized state, detecting whether the covered area of the visual interface of the information content is smaller than a preset threshold value; if the covered area of the visual interface of the information content is smaller than a preset threshold value, the condition that a preset visual condition is met is obtained; if the covered area of the visual interface of the information content is detected to be larger than or equal to the preset threshold value, the condition that the preset visual condition is not met is obtained.
Further, the second detection module 200 is specifically configured to: detecting whether the mouse moves on a visual interface of the information content within a preset first time; if the mouse is detected to move on the visual interface of the information content within the first time, the information content is acquired to meet the preset effective reading condition; if the mouse is detected to stay on the visual interface of the information content continuously within the first time, the information content is acquired not to meet the preset effective reading condition.
Further, the second detection module 200 is specifically configured to: detecting whether the rolling distance of the scroll bar of the information content in a preset second time exceeds a preset distance threshold or not; if the scroll bar is detected to have a scroll distance greater than a preset distance threshold in the second time, the information content is known to meet a preset effective reading condition; if the scroll distance of the scroll bar in the second time is detected to be smaller than or equal to the preset distance threshold, the information content is acquired not to meet the preset effective reading condition.
Further, the obtaining module 300 is specifically configured to: acquiring an information title of the information content; analyzing the text content of the information content by using a preset information base matched with the information title, and extracting information keywords; generating key information according to the information title and the information keyword.
Further, the pushing module 400 is specifically configured to: inquiring a preset push strategy to obtain the information quantity corresponding to the reading behavior characteristic; candidate information related to the information key information is searched, and target information matched with the information quantity is obtained in sequence according to the sorting heat of the candidate information and pushed to the user.
It should be noted that the explanation of the information recommendation method in the foregoing embodiment is also applicable to the information recommendation apparatus in this embodiment, and is not repeated here.
The information recommendation device provided by the embodiment of the invention detects whether the information content opened by a user on the terminal equipment meets the preset visualization condition or not, further detects whether the information content meets the preset effective reading condition or not when the opened information content meets the preset visualization condition, further extracts the information key information from the information content when the information content meets the preset effective reading condition, acquires the reading behavior characteristics of the user on the information content, and further acquires the target information matched with the user according to the information key information and the reading behavior characteristics for pushing. Therefore, when the information content meets the visualization condition and the effective reading condition, the target information is acquired according to the information key information and the reading behavior characteristic of the current information content for personalized recommendation, so that the accuracy of reading records is ensured, and the accuracy of personalized recommendation is improved.
In order to implement the above embodiments, the present invention further provides a terminal device, which includes a processor and a memory; the processor reads the executable program code stored in the memory to run the program corresponding to the executable program code, so as to implement the information recommendation method according to any of the foregoing embodiments.
In order to implement the above embodiments, the present invention further provides a computer program product, which when executed by an instruction processor in the computer program product implements the information recommendation method according to any of the foregoing embodiments.
In order to achieve the above embodiments, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program is executed by a processor to implement the information recommendation method according to any of the above embodiments.
Fig. 6 shows a block diagram of an exemplary terminal device suitable for use in implementing embodiments of the present invention. The terminal device 12 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 6, terminal device 12 is in the form of a general purpose computing device. The components of terminal device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Terminal device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by terminal device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the embodiments described herein.
Terminal device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer system/server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the computer system/server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Furthermore, the terminal device 12 can also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network (e.g., the Internet) via the Network adapter 20. As shown, the network adapter 20 communicates with the other modules of the terminal device 12 over the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with terminal device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (12)
1. An information recommendation method, comprising:
detecting whether information content opened by a user on terminal equipment meets a preset visualization condition;
if the opened information content is detected to meet a preset visualization condition, detecting whether the information content meets a preset effective reading condition;
if the information content is detected to meet a preset effective reading condition, extracting information key information from the information content, and acquiring the reading behavior characteristics of the user on the information content;
acquiring target information matched with the user according to the information key information and the reading behavior characteristics and pushing the target information;
the detecting whether the information content opened by the user on the terminal device meets the preset visualization condition includes:
detecting whether the information content opened by the user on the terminal equipment is in a minimized state;
if the information content is detected to be in the minimized state, the situation that the preset visualization condition is not met is known;
if the information content is not detected to be in the minimized state, detecting whether the covered area of the visual interface of the information content is smaller than a preset threshold value;
if the covered area of the visual interface of the information content is smaller than a preset threshold value, the condition that a preset visual condition is met is obtained;
and if the covered area of the visual interface of the information content is detected to be larger than or equal to a preset threshold value, the situation that the preset visual condition is not met is known.
2. The method of claim 1, wherein said detecting whether the information content satisfies a predetermined valid reading condition comprises:
detecting whether the mouse moves on the visual interface of the information content within a preset first time;
if the mouse is detected to move on the visual interface of the information content within the first time, the information content is acquired to meet a preset effective reading condition;
if the fact that the mouse stays on the visual interface of the information content continuously within the first time is detected, the fact that the information content does not meet preset effective reading conditions is obtained.
3. The method of claim 1, wherein said detecting whether the information content satisfies a predetermined valid reading condition comprises:
detecting whether the rolling distance of the scroll bar of the information content in a preset second time exceeds a preset distance threshold;
if the rolling distance of the scroll bar in the second time is detected to be larger than a preset distance threshold, the information content is known to meet a preset effective reading condition;
and if the rolling distance of the scroll bar in the second time is detected to be smaller than or equal to a preset distance threshold, the information content is acquired not to meet a preset effective reading condition.
4. The method of claim 1, wherein said extracting information key information from said information content comprises:
acquiring an information title of the information content;
analyzing the text content of the information content by using a preset information base matched with the information title, and extracting information keywords;
and generating information key information according to the information title and the information key words.
5. The method of claim 1, wherein the obtaining target information matched with the user according to the information key information and the reading behavior characteristics for pushing comprises:
inquiring a preset push strategy to obtain the information quantity corresponding to the reading behavior characteristic;
searching candidate information related to the information key information, and sequentially acquiring target information matched with the information quantity according to the sorting heat of the candidate information and pushing the target information to the user.
6. An information recommendation apparatus, comprising:
the first detection module is used for detecting whether the information content opened on the terminal equipment by the user meets the preset visualization condition;
the second detection module is used for detecting whether the information content meets a preset effective reading condition or not if the opened information content meets a preset visual condition;
the acquisition module is used for extracting information key information from the information content and acquiring the reading behavior characteristics of the user on the information content if the information content is detected to meet the preset effective reading condition;
the pushing module is used for acquiring target information matched with the user according to the information key information and the reading behavior characteristics and pushing the target information;
the first detection module is specifically configured to:
detecting whether the information content opened by the user on the terminal equipment is in a minimized state;
if the information content is detected to be in the minimized state, the situation that the preset visualization condition is not met is known;
if the information content is not detected to be in the minimized state, detecting whether the covered area of the visual interface of the information content is smaller than a preset threshold value;
if the covered area of the visual interface of the information content is smaller than a preset threshold value, the condition that a preset visual condition is met is obtained;
and if the covered area of the visual interface of the information content is detected to be larger than or equal to a preset threshold value, the situation that the preset visual condition is not met is known.
7. The apparatus of claim 6, wherein the second detection module is specifically configured to:
detecting whether the mouse moves on the visual interface of the information content within a preset first time;
if the mouse is detected to move on the visual interface of the information content within the first time, the information content is acquired to meet a preset effective reading condition;
if the fact that the mouse stays on the visual interface of the information content continuously within the first time is detected, the fact that the information content does not meet preset effective reading conditions is obtained.
8. The apparatus of claim 6, wherein the second detection module is specifically configured to:
detecting whether the rolling distance of the scroll bar of the information content in a preset second time exceeds a preset distance threshold;
if the rolling distance of the scroll bar in the second time is detected to be larger than a preset distance threshold, the information content is known to meet a preset effective reading condition;
and if the rolling distance of the scroll bar in the second time is detected to be smaller than or equal to a preset distance threshold, the information content is acquired not to meet a preset effective reading condition.
9. The apparatus of claim 6, wherein the acquisition module is specifically configured to:
acquiring an information title of the information content;
analyzing the text content of the information content by using a preset information base matched with the information title, and extracting information keywords;
and generating information key information according to the information title and the information key words.
10. The apparatus of claim 6, wherein the push module is specifically configured to:
inquiring a preset push strategy to obtain the information quantity corresponding to the reading behavior characteristic;
and searching candidate information related to the information key information, and acquiring target information matched with the information quantity in sequence according to the sorting heat of the candidate information and pushing the target information to the user.
11. A terminal device comprising a processor and a memory;
wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, for implementing the information recommendation method according to any one of claims 1 to 5.
12. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the information recommendation method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810608509.2A CN108846091B (en) | 2018-06-13 | 2018-06-13 | Information recommendation method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810608509.2A CN108846091B (en) | 2018-06-13 | 2018-06-13 | Information recommendation method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108846091A CN108846091A (en) | 2018-11-20 |
| CN108846091B true CN108846091B (en) | 2022-05-31 |
Family
ID=64201945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810608509.2A Active CN108846091B (en) | 2018-06-13 | 2018-06-13 | Information recommendation method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108846091B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492163B (en) * | 2018-11-26 | 2021-12-10 | 北京字节跳动网络技术有限公司 | List display recording method and device, terminal equipment and storage medium |
| CN111488540B (en) * | 2019-01-29 | 2024-04-02 | 百度在线网络技术（北京）有限公司 | Information shielding monitoring method, device, equipment and computer readable medium |
| CN109977311A (en) * | 2019-03-26 | 2019-07-05 | 北京博瑞彤芸文化传播股份有限公司 | A kind of intelligent analysis method of sharing information |
| CN110457604A (en) * | 2019-07-03 | 2019-11-15 | 平安科技（深圳）有限公司 | Recommended method and relevant device based on artificial intelligence |
| CN110502112B (en) * | 2019-08-14 | 2023-11-14 | 北京金山安全软件有限公司 | Intelligent recommendation method, intelligent recommendation device, electronic equipment and storage medium |
| CN110598110B (en) * | 2019-09-16 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Service pushing method and device |
| CN111625712B (en) * | 2020-04-27 | 2023-06-30 | 北京三快在线科技有限公司 | User browsing behavior reporting method and device, readable storage medium and electronic equipment |
| CN114817730B (en) * | 2022-05-06 | 2023-06-20 | 成都坐联智城科技有限公司 | Information activity information recommendation system and method under big data situation |
| CN116304128B (en) * | 2023-03-01 | 2023-12-15 | 微众梦想科技(北京)有限公司 | Multimedia information recommendation system based on big data |
| CN116484091A (en) * | 2023-03-10 | 2023-07-25 | 湖北天勤伟业企业管理有限公司 | Card information program interaction method and device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314423A (en) * | 2010-06-29 | 2012-01-11 | 百度在线网络技术（北京）有限公司 | Method and device for detecting heat degree of subset in open type interactive platform |
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
| CN103186866A (en) * | 2011-12-29 | 2013-07-03 | 阿里巴巴集团控股有限公司 | Method and system for counting advertisement showing times |
| CN105224529A (en) * | 2014-05-28 | 2016-01-06 | 济南政和科技有限公司 | A kind of personalized recommendation method based on user browsing behavior and device |
| CN105224654A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of Web browsing mode changing method and electronic equipment |
| CN105844498A (en) * | 2016-04-22 | 2016-08-10 | 无锡牵手信息技术有限公司 | Business popularization system based on Internet |
| CN106528704A (en) * | 2016-10-26 | 2017-03-22 | 网易传媒科技（北京）有限公司 | Method and device for determining interest degree of user in tag |
| US9720978B1 (en) * | 2014-09-30 | 2017-08-01 | Amazon Technologies, Inc. | Fingerprint-based literary works recommendation system |
| CN107180088A (en) * | 2017-05-10 | 2017-09-19 | 广西师范学院 | News based on Fuzzy C-Means Cluster Algorithm recommends method |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
-
2018
- 2018-06-13 CN CN201810608509.2A patent/CN108846091B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314423A (en) * | 2010-06-29 | 2012-01-11 | 百度在线网络技术（北京）有限公司 | Method and device for detecting heat degree of subset in open type interactive platform |
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN103186866A (en) * | 2011-12-29 | 2013-07-03 | 阿里巴巴集团控股有限公司 | Method and system for counting advertisement showing times |
| CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
| CN105224529A (en) * | 2014-05-28 | 2016-01-06 | 济南政和科技有限公司 | A kind of personalized recommendation method based on user browsing behavior and device |
| US9720978B1 (en) * | 2014-09-30 | 2017-08-01 | Amazon Technologies, Inc. | Fingerprint-based literary works recommendation system |
| CN105224654A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of Web browsing mode changing method and electronic equipment |
| CN105844498A (en) * | 2016-04-22 | 2016-08-10 | 无锡牵手信息技术有限公司 | Business popularization system based on Internet |
| CN106528704A (en) * | 2016-10-26 | 2017-03-22 | 网易传媒科技（北京）有限公司 | Method and device for determining interest degree of user in tag |
| CN107180088A (en) * | 2017-05-10 | 2017-09-19 | 广西师范学院 | News based on Fuzzy C-Means Cluster Algorithm recommends method |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108846091A (en) | 2018-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846091B (en) | Information recommendation method, device and equipment | |
| US20190340194A1 (en) | Associating still images and videos | |
| CN107609152B (en) | Method and apparatus for expanding query expressions | |
| US9436707B2 (en) | Content-based image ranking | |
| Williams et al. | Detecting good abandonment in mobile search | |
| JP5947131B2 (en) | Search input method and system by region selection method | |
| US8326091B1 (en) | Ranking of images and image labels | |
| US8868569B2 (en) | Methods for detecting and removing duplicates in video search results | |
| US10592571B1 (en) | Query modification based on non-textual resource context | |
| US20100125568A1 (en) | Dynamic feature weighting | |
| CN109918555B (en) | Method, apparatus, device and medium for providing search suggestions | |
| US10210181B2 (en) | Searching and annotating within images | |
| CN103136228A (en) | Image search method and image search device | |
| US9805120B2 (en) | Query selection and results merging | |
| CN107911448B (en) | Content pushing method and device | |
| US20120036144A1 (en) | Information and recommendation device, method, and program | |
| CN111310011B (en) | Information pushing method and device, electronic equipment and storage medium | |
| WO2017143930A1 (en) | Method of sorting search results, and device for same | |
| US8290925B1 (en) | Locating product references in content pages | |
| JP2019522852A (en) | System and method for providing contextual information | |
| CN104899306A (en) | Information processing method, information display method and information display device | |
| US10212240B2 (en) | Method for tracking content and electronic device using the same | |
| US9223854B2 (en) | Document relevance determining method and computer program | |
| CN113407818A (en) | Automatic information retrieval | |
| KR101955920B1 (en) | Search method and apparatus using property language |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191126 Address after: 519030 Room 105-53811, No. 6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Applicant after: Zhuhai Seal Interest Technology Co., Ltd. Address before: 519070, No. 10, main building, No. six, science Road, Harbour Road, Tang Wan Town, Guangdong, Zhuhai, 601F Applicant before: Zhuhai Juntian Electronic Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |