CN106878405B - Method and device for adjusting push items - Google Patents
Method and device for adjusting push items Download PDFInfo
- Publication number
- CN106878405B CN106878405B CN201710061291.9A CN201710061291A CN106878405B CN 106878405 B CN106878405 B CN 106878405B CN 201710061291 A CN201710061291 A CN 201710061291A CN 106878405 B CN106878405 B CN 106878405B
- Authority
- CN
- China
- Prior art keywords
- item
- user
- browsing
- list
- record
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method for adjusting a push project, which comprises the following steps: acquiring a first record of a user browsing item according to a user Identification (ID); the first record comprises a user browsing item list, browsing duration and an operation record; determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period; based on a preset rule, determining a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user; matching the non-target item with a preset push item list, and adjusting the weight of the matched non-target item in the push item list downwards; the weight characterizes the number of times an item in the list of pushed items is pushed to the user. The invention also discloses a device for adjusting the push items.
Description
Technical Field
The invention relates to the technical field of internet information, in particular to a method and a device for adjusting a push project.
Background
Under the environment of information explosion in the internet era, recommending information required by each user to different users from a large amount of complicated information is a very necessary business function. The recommender system may help the user find the information the user wants among a myriad of information, such as: music, news, etc.; furthermore, the recommendation system can also reduce the overload of information, and if all the information is displayed on the home page of the webpage, a user cannot read the information, and the utilization rate of the information is very low. Therefore, the recommendation system can help the user filter out low-value information; meanwhile, the internet company can be helped to improve the click rate of the portal website and the conversion rate of the content information, so that the recommendation system is extremely important for the user, the internet company and all items related to the internet field.
At present, algorithms generally applied to a recommendation system are content-based recommendation algorithms or collaborative filtering recommendation algorithms and the like, and the algorithms lack detection and judgment on user behaviors. However, in the prior art, detection and judgment of user behaviors are generally limited to use of a camera or a sensor, and sensing detection of an actual environment or detection of user behaviors is performed.
However, the recommendation system using the above algorithm or device does not further analyze and judge the user behavior, and cannot recommend a product meeting the current interest of the user to the user according to the user behavior in real time; moreover, under the condition that the user behavior is judged to be inaccurate, a phenomenon that products which are not interested by the user are frequently pushed to the user occurs, so that the user experience is poor.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide a method and an apparatus for adjusting a pushed item, which can adjust an item pushed to a user in real time, and improve the accuracy of pushing the item.
To achieve the above object, an embodiment of the present invention provides a method for adjusting a push item, including:
acquiring a first record of a user browsing item according to the user identification ID; the first record comprises a user browsing item list, browsing duration and an operation record;
determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period;
based on a preset rule, determining a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
matching the non-target item with a preset push item list, and adjusting the weight of the matched non-target item in the push item list downwards; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
In the above method, after the non-target item is matched with a preset push item list and the weight of the matched non-target item in the push item list is adjusted downward, the method further includes:
after a preset third time period, acquiring a second record of a user browsing item in the third time period; the second record comprises a list of user browsing items;
matching the non-target item with the user browsing item list, and if the matching is successful, increasing the weight of the non-target item in the pushing item list; if the match is unsuccessful, the non-target item is deleted from the push item list.
In the above method, after the weight of the matched non-target item in the push item list is adjusted downward, the method further includes:
and pushing the item to the user according to the adjusted pushing item list.
The determining non-target items by using the browsing duration and the operation records in the first record of the first browsing item browsed by the user based on the preset rule comprises the following steps:
determining a second time period according to the browsing duration, and judging whether the user operation record exceeds a preset threshold value in the second time period;
and when the operation record exceeds a set threshold value, determining that the first browsing item is a non-target item.
In the above method, the determining a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user based on the preset rule further includes:
determining a target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
when the target item is matched with a preset push item list, the weight of the matched target item in the push item list is maintained;
when the target item is not matched with the push item list, adding the target item into the push item list;
and pushing the item to the user according to the adjusted pushing item list.
The embodiment of the invention also provides a device for adjusting the push items, which comprises:
the acquisition module is used for acquiring a first record of a user browsing item according to the user ID; the first record comprises a user browsing item list, browsing duration and an operation record;
the first determining module is used for determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period;
the second determining module is used for determining a non-target item by utilizing the browsing duration and the operation record in the first record of the first browsing item browsed by the user based on a preset rule;
the adjusting module is used for matching the non-target item with a preset push item list and adjusting the weight of the matched non-target item in the push item list downwards; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
In the device, the obtaining module is further configured to obtain a second record of a user browsing item in a third time period after the third time period is preset; the second record comprises a list of user browsing items;
the adjusting module is further configured to match the non-target item with the user browsing item list, and if the matching is successful, the weight of the non-target item in the push item list is increased; if the matching is unsuccessful, deleting the non-target item from the push item list;
and the pushing module is used for pushing the items to the user according to the adjusted pushing item list.
The second determining module is specifically configured to:
determining a second time period according to the browsing duration, and judging whether the user operation record exceeds a preset threshold value in the second time period;
and when the operation record exceeds a set threshold value, determining that the first browsing item is a non-target item.
Wherein the second determining module is further configured to: and determining the target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user.
Wherein, the adjusting module is specifically configured to:
when the target item is matched with a preset push item list, the weight of the matched target item in the push item list is maintained;
and when the target item is not matched with the push item list, adding the target item into the push item list.
According to the method and the device for adjusting the pushed item, provided by the embodiment of the invention, a first record of a user browsing item is obtained according to a user identification ID; the first record comprises a user browsing item list, browsing duration and an operation record; determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period; based on a preset rule, determining a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user; matching the non-target item with a preset push item list, and adjusting the weight of the matched non-target item in the push item list downwards; the weight represents the number of times that the items in the item pushing list are pushed to the user; therefore, the items pushed to the user can be adjusted in real time according to the user behavior; moreover, after a period of time, the user behavior is rechecked, so that the probability that the user interest is consistent with the item pushing is improved, and the item pushing accuracy is improved.
Drawings
FIG. 1 is a schematic flow chart illustrating an implementation of a method for adjusting a push item according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus for adjusting push items according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating a method for adjusting a pushed project according to an embodiment of the present invention, where a user watches an animation video or a cartoon work.
Detailed Description
In order to understand the features and technical contents of the embodiments of the present invention in more detail, the following describes the implementation of the embodiments of the present invention in detail.
Fig. 1 is a schematic flow chart illustrating an implementation process of a method for adjusting a push item according to an embodiment of the present invention, as shown in fig. 1, the method for adjusting a push item according to an embodiment of the present invention includes the following steps:
step 101: acquiring a first record of a user browsing item according to the user identification ID;
here, the first record includes a user browsing item list, a browsing duration and an operation record; specifically, the first record includes a record list of all items browsed by the user, browsing duration used for browsing each item, and an operation record of the item during browsing each item;
here, the user browsing item may be an animated video and a comic work; the browsing duration can be the time length of stay of a user in browsing the animation video or the cartoon works; the operation record may be a fast forward operation during the user's viewing of the animation video or a page turn operation record during the user's viewing of the comic work.
In practical applications, the user identification ID may use an International Mobile Equipment Identity (IMEI), a Universal Unique Identifier (UUID), or an ID that can identify the user Identity and is set by the user.
Step 102: determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period;
specifically, the user browsing item list includes history records of all items watched by the user, the item browsed by the user for the first time within a preset first time period is judged, the items browsed by the user for multiple times within the first time period are identified as target items, and the weight of the target items in the recommendation list is not adjusted; the target item represents a user interest item;
the preset first time period may be set according to actual needs, and the set time period may be set as a period of the project and may be sufficient to represent a behavior habit of the user in the first time period, for example: setting the first time period to be 3 months, wherein in practical application, the period of the project is generally quarterly used as a period unit, so that the 3 months can sufficiently represent the behavior habit of the user within 3 months; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
Step 103: based on a preset rule, determining whether the first browsing item is a non-target item or not by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
determining a second time period according to the browsing duration of the first browsing item, wherein the preset rule is used for judging whether the operation times of the user in the operation record of the first browsing item in the second time period exceed a preset threshold value; when the operation times exceed a set threshold value, determining that the first browsing item is a non-target item;
specifically, the browsing duration of the item browsed for the first time in a first record of a user and an operation record during browsing are obtained, a second time period is determined according to the browsing duration, whether the operation times in the operation record of the user reach a preset threshold value or not is judged in the second time period, and if the operation times reach the preset threshold value, the item browsed for the first time by the user is determined to be a non-target item; the non-target items represent non-user items of interest;
the second time period may be set according to an actual requirement, and in an actual application, the second time period should be less than the browsing duration, for example: the browsing time of the user browsing the items is 60 seconds, the second time period can be set to 30 seconds, and whether the operation times of the user browsing the items within 30 seconds exceed a set threshold value is judged;
in practical applications, the preset threshold may be set according to items browsed by a user, for example: if the item browsed by the user is an animation video, a threshold value can be set to be 3, wherein 3 represents the number of fast forwarding times, and the preset rule is that when the user carries out fast forwarding operations for more than 3 times in the process of watching the animation video, the animation video is determined to be a non-target item.
Here, the step 103 further includes: matching the target item with a preset push item list, and maintaining the weight of the matched target item in the push item list; if the target item does not match the push item list, adding the target item to the push item list; wherein the target item characterizes a user interest item; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
Step 104: matching the non-target item with a preset push item list, and adjusting the weight of the matched non-target item in the push item list downwards;
here, the preset push item list determines a user interest item category according to information provided by a user, and an item corresponding to the interest item category is added to the push item list;
when the determined non-target item is matched with an item in a push item list, determining that the matched item is a non-user interest item, and adjusting the weight of the non-target item in the push item list; the weight represents the number of times that items in the pushed item list are pushed to the user;
in practical application, the adjusting of the weight of the non-target item may be adding an additional score reflecting user behavior to the non-target item, and adjusting the level of a corresponding value of the additional score to make the recommended total score of the non-target item decrease or increase, further, the weight of the non-target item also decreases or increases correspondingly, and finally, the number of times that the non-target item is pushed to the user is reduced or increased; for example: according to the behavior habits of the users, a recommendation algorithm is used for determining an initial item weight value for each item in a user recommendation list, the initial weight value is a fixed value which cannot be adjusted, the method for adjusting item push in the embodiment of the invention can add a weight additional value for each item in the recommendation item list, the weight additional value is taken by fast forwarding or fast page turning operation of the users during item browsing, when the number of times of fast forwarding or page turning operation of the users during item browsing is more, the weight additional value is larger, and the total weight of the final recommendation item is obtained by subtracting the weight additional value from the initial weight value; when the number of fast forwarding or fast page turning operations is more during item browsing by a user, the weight additional value is larger, the total weight value is smaller, the ranking of the item in the recommended item list is later, and the number of times that the item is recommended to the user is correspondingly reduced;
the adjusting of the weight of the non-target item can also be directly adjusting the total recommended score of the non-target item to decrease or increase, further, the weight of the non-target item correspondingly decreases or increases, and finally, the number of times that the non-target item is pushed to a user is reduced or increased; for example: according to information such as item browsing behaviors of a user line and interest characteristics provided by the user, a total weight value is determined for each item in a user recommendation list by using a recommendation algorithm, and the items in the recommendation list are ranked according to the total weight value; when the number of fast forward or page turning operations of a user during item browsing is more, the lower total weight value is larger, the rank of the item in the recommendation list is larger, and the number of times that the item is recommended to the user is correspondingly smaller;
specifically, the weight may be obtained by a recommendation algorithm, and first, input parameters are obtained, where the input parameters are various attributes and features of a user or an item in practical application, for example: the recommendation algorithm processes the input parameters, and then outputs a list after the items are sorted according to the interests and hobbies of the user, the weight of the item corresponding to the first ranked item of the list is the largest, and by analogy, the weight of the item corresponding to the first ranked item is smaller;
here, the recommendation algorithms used can be roughly classified into the following categories:
ranking the items according to the popularity of the users, for example, recommending the sports content in the ranking list to the users interested in sports, and pushing the political news to the users loving to discuss politics;
the collaborative filtering algorithm is used for analyzing the evaluation of the user on the project, the evaluation can be obtained by browsing the record and purchasing the record, and the similarity between the users is calculated according to the evaluation of the user on the project; selecting N users with the most similar similarity to the current user; recommending the items which are evaluated highest by the N users and not browsed by the current user to the current user;
extracting characteristic parameters according to the behavior of the user and the content of the user browsing item based on a content algorithm, decomposing the behavior of the user and the content of the user browsing item into sounds according to the characteristic parameters, calculating the vector distance to obtain the similarity between the user and the item, and pushing the item with high similarity to the user according to the similarity;
analyzing user behaviors to obtain characteristic parameters x influencing the user behaviors and the like degree y of the user to the items based on a model algorithm, wherein x and y are in one-to-one correspondence, and x comprises: age group, gender, region, price of the item, category of the item, etc. of the user, y comprising: purchasing records, browsing records, collecting records and the like, fitting a function by obtaining a large amount of x and y data, and calculating a coefficient corresponding to x, wherein the coefficient is a weight corresponding to a characteristic parameter, and the more the weight value is, the more important the characteristic parameter is for a user to select items;
and the hybrid algorithm is used for fusing a plurality of algorithms, and the expected purpose is achieved by adding a weight comprehensive result to the results of different algorithms or mixing different algorithms in different calculation links.
The step 104 further includes: after a preset third time period, acquiring a second record of a user browsing item in the third time period; the second record comprises a list of user browsing items; the third time period start time is after the non-target item weight is adjusted;
matching the non-target item with the user browsing item list, and if the matching is successful, increasing the weight of the non-target item in the pushing item list; if the matching is unsuccessful, deleting the non-target item from the push item list;
specifically, after the weight of the non-target item in the pushed item list is adjusted downward in step 104, rechecking the non-target item, obtaining a second record of the user in a third time period, where the second record at least includes a history record list of items browsed by the user in the third time period, matching the non-target item determined in step 103 with the user browsed item list in the second record, and if matching, determining that the non-target item is judged incorrectly in step 103, where the non-target item is a target item, raising the weight of the non-target item in the pushed item list again, and increasing the number of times that the non-target item is pushed to the user; if not, determining that the judgment of the non-target item in the step 103 is correct, and deleting the non-target item from the pushed item list, so that the item cannot be pushed to the user actively; wherein the non-target items characterize non-user interest items and the target items characterize user interest items.
Fig. 2 is a schematic diagram of a component structure of an apparatus for adjusting a push item according to an embodiment of the present invention, as shown in fig. 2, fig. 2 (a) shows the apparatus used before a third time period in a method for adjusting a push item according to an embodiment of the present invention, fig. 2 (b) shows the apparatus used after the third time period in the method for adjusting a push item according to an embodiment of the present invention, as shown in fig. 2 (a), including the following modules:
an obtaining module 201, configured to obtain a first record of a user browsing item according to a user identifier ID; the first record comprises a user browsing item list, browsing duration and an operation record;
a first determining module 202, configured to determine, within a preset first time period, a first browsing item of a user according to the user browsing item list in the first record;
the second determining module 203 is configured to determine a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user based on a preset rule;
the second determining module 203 is further specifically configured to determine a second time period according to the browsing duration, and determine whether the user operation record exceeds a preset threshold in the second time period; when the operation record exceeds a set threshold value, determining that the first browsing item is a non-target item; the method is also used for determining the target item by utilizing the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
the adjusting module 204 is configured to match the non-target item with a preset push item list, and adjust the weight of the matched non-target item in the push item list downward; the weight represents the number of times that the items in the item pushing list are pushed to the user;
the adjusting module 204 is further specifically configured to match the target item with a preset push item list, and maintain a weight of the matched target item in the push item list; adding the target item to a list of push items if the target item does not match the list of push items
And the pushing module 205 is configured to push an item to the user according to the adjusted push item list.
As shown in fig. 2 (b), in the apparatus for adjusting push items according to the embodiment of the present invention,
the obtaining module 201 is further configured to obtain a second record of a user browsing item in a preset third time period after the preset third time period; the second record comprises a list of user browsing items;
the adjusting module 204 is further configured to match the non-target item with the user browsing item list, and if the matching is successful, increase the weight of the non-target item in the push item list; if not, deleting the non-target item from the push item list;
a pushing module 205, configured to push an item to a user according to the adjusted push item list;
it should be noted that: the implementation functions of the modules can be understood by referring to the related description of the method for adjusting the push item described in fig. 1, and are not described herein again.
In practical applications, the obtaining module 201, the first determining module 202, the second determining module 203, the adjusting module 204, and the pushing module 205 may be implemented by a processor in a device for adjusting a pushed project.
The method for adjusting the push item according to the embodiment of the present invention is described in detail below by taking an item as an example of an animation video or a cartoon work, and as shown in fig. 3, the embodiment of the present invention includes the following steps:
step 301: the acquisition module acquires the history record of watching the animation video or the cartoon work by the user;
here, the acquisition module acquires the history record of the animation video or cartoon works browsed by the user through IMEI, UUID or ID set by the user; the history records comprise a record list of animation videos or cartoon works browsed by a user, the time length for browsing the animation videos or the cartoon works, and the number of fast forwarding times or page turning times in the animation videos or the cartoon works;
the fast-forward or page-turning operation record in the animation video or cartoon work browsed by the user can be obtained according to the positions of clicking and releasing the picture on the interface of the animation video or cartoon work by the user, and can also be obtained by judging the sliding distance, the sliding direction and the sliding time of the user operation according to the positions of clicking and releasing by the user; for example, when the user browses the cartoon work, the user may be determined to be performing a page turning operation by sliding up and down or sliding left and right for multiple times, and the operation is recorded, in an actual application, a sliding time interval may be set, for example: judging whether the user performs fast page turning or fast forwarding operation within 0.5 second;
further, the obtaining module may also calculate and record a duration of the user watching the animation video or the cartoon work according to the history, and calculate and record a number of times of fast page turning or fast forward of the user in the browsing process.
Step 302: determining the animation video or cartoon work watched by the user for the first time according to the history record;
the first determining module judges whether the user has the animation video or cartoon work watched for the first time within a preset first time period (preset according to requirements, such as 6 months) according to the history record, and if the user is judged to browse the animation video or cartoon work for multiple times within the first time period, the user is determined to be in the heavy-temperature animation video or cartoon work without weighting the animation video or cartoon work in a recommendation list; if the first browsed animation video or cartoon work is determined, the following step 303 is performed on the first browsed animation video or cartoon work.
Step 303: determining whether the animation video or cartoon work browsed for the first time is a user interest item;
first, the second determining module sets a corresponding threshold according to whether the user watches the animation video or the cartoon work, for example: if the cartoon is watched, setting the threshold value of the fast page turning for 5 times (the threshold value can be set according to actual needs); if the video is watched as the animation video, setting the threshold value of the fast forward times to be 3 times (the threshold value can be set according to actual needs);
secondly, the second determining module determines a second time period according to the browsing duration in the history record, for example: assuming that the time length for the user to browse the animation video or the cartoon work for the first time is 120 seconds, a second time period can be set to be 30 seconds or 60 seconds, and if the user watches the animation video, when the number of fast forward operations exceeding a set threshold value occur in the second time period, the user is determined not to be interested in the animation video; if the cartoon work is watched by the user, determining that the user is not interested in the cartoon work when the user has the rapid page turning operation times exceeding a set threshold value in the second time period; and if the operation times of the user in the second time period do not exceed the set threshold, determining that the animation video or the cartoon work browsed by the user is the item interested by the user, and not adjusting the weight of the item interested by the user in the push list.
Step 304: adjusting the weight of the non-user interest item in a push item list downwards;
the push item list can be established according to interest information provided by a user, and items meeting the interest of the user are added into the list according to the interest information provided by the user;
the weight of the non-user interest item is adjusted to enable the total recommended score of the non-user interest item to be reduced or increased, and further, the weight of the non-user interest item is correspondingly reduced or increased, and finally, the number of times that the non-user interest item is pushed to the user is reduced or increased; the adjusting of the weight of the non-target item may also be directly adjusting the total recommended score of the non-target item to decrease or increase, further, the weight of the non-target item also decreases or increases correspondingly, and finally, the number of times that the non-target item is pushed to the user is reduced or increased.
Step 305: rechecking the non-user interest items, and readjusting the pushing weight of the recommended item list according to the rechecking result;
after the weight of the push item in the push item list is adjusted, the second determining module obtains the history of the animation video or the cartoon work browsed by the user in a third time period (which may be set according to actual needs, for example, 15 days) after the preset third time period. Matching the non-user interest items of which the weights are adjusted downwards in the step 304 with the history records, determining that the user is interested in the non-user interest items if the user browses the non-user interest items again in the third time period, and adjusting the weights of the non-user interest items adjusted downwards in the step 304 upwards again by a second adjusting module to improve the pushing times of the non-user interest items to the user; and if the user does not browse the non-user interest items again within the third time period, determining that the user has no interest in the non-user interest items, and deleting the non-user interest items from the push list by the second adjusting module, so that the non-user interest items are not pushed to the user actively any more.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. A method of adjusting a pushed item, the method comprising:
acquiring a first record of a user browsing item according to the user identification ID; the first record comprises a user browsing item list, browsing duration and an operation record;
determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period;
based on a preset rule, determining a non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
matching the non-target item with a preset push item list, and adjusting the weight of the matched non-target item in the push item list downwards; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
2. The method of claim 1, wherein the matching of the non-target item with a preset list of push items, after the weight of the matched non-target item in the list of push items is adjusted downward, the method further comprises:
after a preset third time period, acquiring a second record of a user browsing item in the third time period; the second record comprises a list of user browsing items;
matching the non-target item with the user browsing item list, and if the matching is successful, increasing the weight of the non-target item in the pushing item list; if the match is unsuccessful, the non-target item is deleted from the push item list.
3. The method of claim 2, wherein after adjusting down the weight of the matching non-target item in the list of push items, the method further comprises:
and pushing the item to the user according to the adjusted pushing item list.
4. The method according to claim 1, wherein the determining, based on the preset rule, the non-target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user comprises:
determining a second time period according to the browsing duration, and judging whether the user operation record exceeds a preset threshold value in the second time period;
and when the operation record exceeds a set threshold value, determining that the first browsing item is a non-target item.
5. The method of claim 1, further comprising:
determining a target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user;
when the target item is matched with a preset push item list, the weight of the matched target item in the push item list is maintained;
when the target item is not matched with the push item list, adding the target item into the push item list;
and pushing the item to the user according to the adjusted pushing item list.
6. An apparatus for adjusting a pushed item, the apparatus comprising:
the acquisition module is used for acquiring a first record of a user browsing item according to the user ID; the first record comprises a user browsing item list, browsing duration and an operation record;
the first determining module is used for determining a first browsing item of a user according to the user browsing item list in the first record within a preset first time period;
the second determining module is used for determining a non-target item by utilizing the browsing duration and the operation record in the first record of the first browsing item browsed by the user based on a preset rule;
the adjusting module is used for matching the non-target item with a preset push item list and adjusting the weight of the matched non-target item in the push item list downwards; the weight characterizes the number of times an item in the list of pushed items is pushed to the user.
7. The apparatus of claim 6,
the acquisition module is further used for acquiring a second record of the user browsing item in a third time period after the preset third time period; the second record comprises a list of user browsing items;
the adjusting module is further configured to match the non-target item with the user browsing item list, and if the matching is successful, the weight of the non-target item in the push item list is increased; if the matching is unsuccessful, deleting the non-target item from the push item list;
and the pushing module is used for pushing the items to the user according to the adjusted pushing item list.
8. The apparatus of claim 6, wherein the second determining module is specifically configured to:
determining a second time period according to the browsing duration, and judging whether the user operation record exceeds a preset threshold value in the second time period;
and when the operation record exceeds a set threshold value, determining that the first browsing item is a non-target item.
9. The apparatus of claim 6 or 7, wherein the second determining module is further configured to: and determining the target item by using the browsing duration and the operation record in the first record of the first browsing item browsed by the user.
10. The apparatus of claim 9, wherein the adjustment module is specifically configured to:
when the target item is matched with a preset push item list, the weight of the matched target item in the push item list is maintained;
and when the target item is not matched with the push item list, adding the target item into the push item list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710061291.9A CN106878405B (en) | 2017-01-25 | 2017-01-25 | Method and device for adjusting push items |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710061291.9A CN106878405B (en) | 2017-01-25 | 2017-01-25 | Method and device for adjusting push items |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106878405A CN106878405A (en) | 2017-06-20 |
| CN106878405B true CN106878405B (en) | 2019-12-24 |
Family
ID=59158811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710061291.9A Active CN106878405B (en) | 2017-01-25 | 2017-01-25 | Method and device for adjusting push items |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106878405B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376297A (en) * | 2018-08-31 | 2019-02-22 | 中国联合网络通信集团有限公司 | User characteristic data treating method and apparatus |
| CN109698858A (en) * | 2018-11-01 | 2019-04-30 | 百度在线网络技术（北京）有限公司 | Resource supplying method, equipment and storage medium for smart machine |
| CN111327661A (en) * | 2018-12-17 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Pushing method, pushing device, server and computer readable storage medium |
| CN109658197A (en) * | 2018-12-24 | 2019-04-19 | 北交金科金融信息服务有限公司 | A kind of method for pushing and system |
| CN112565903B (en) * | 2019-09-10 | 2022-11-22 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN112714359B (en) * | 2019-10-24 | 2022-09-09 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, computer equipment and storage medium |
| CN111626767B (en) * | 2020-04-29 | 2023-09-08 | 拉扎斯网络科技（上海）有限公司 | Resource data issuing method, device and equipment |
| CN115292630A (en) * | 2022-10-09 | 2022-11-04 | 深圳市明源云客电子商务有限公司 | Data processing method, device and computer readable storage medium |
| CN117495513B (en) * | 2024-01-03 | 2024-03-29 | 深圳市智百威科技发展有限公司 | Shopping recommendation method and system based on big data and artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102685565A (en) * | 2012-05-18 | 2012-09-19 | 合一网络技术(北京)有限公司 | Click feedback type individual recommendation system |
| WO2015188349A1 (en) * | 2014-06-12 | 2015-12-17 | Hewlett-Packard Development Company, L.P. | Recommending of an item to a user |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
-
2017
- 2017-01-25 CN CN201710061291.9A patent/CN106878405B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102685565A (en) * | 2012-05-18 | 2012-09-19 | 合一网络技术(北京)有限公司 | Click feedback type individual recommendation system |
| WO2015188349A1 (en) * | 2014-06-12 | 2015-12-17 | Hewlett-Packard Development Company, L.P. | Recommending of an item to a user |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于用户行为的电子商务推荐系统的设计与研究;王义;《中国优秀硕士学位论文全文数据库 信息科技辑》;20110415 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106878405A (en) | 2017-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106878405B (en) | Method and device for adjusting push items | |
| CN106021586B (en) | Information processing method and server | |
| JP5235251B1 (en) | Information processing apparatus, information processing method, and information processing program | |
| US9075875B1 (en) | System and method for recommending television programs based on user search queries | |
| US9691096B1 (en) | Identifying item recommendations through recognized navigational patterns | |
| CN105677767B (en) | Equipment configuration recommendation method and device | |
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| CN110543598B (en) | Information recommendation method and device and terminal | |
| CN111178970B (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
| CN107562939B (en) | Vertical domain news recommendation method and device and readable storage medium | |
| US20140298364A1 (en) | Recommendations for media content based on emotion | |
| US10402479B2 (en) | Method, server, browser, and system for recommending text information | |
| CN110163703B (en) | Classification model establishing method, file pushing method and server | |
| US20100100566A1 (en) | Methods and Systems for Identifying the Fantasies of Users Based on Image Tagging | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| JP5961670B2 (en) | Learning device, learning method, and learning program | |
| CN111310046B (en) | Object recommendation method and device | |
| CN108229991B (en) | Method and device for displaying aggregation promotion information, browser and terminal equipment | |
| CN107592572B (en) | Video recommendation method, device and equipment | |
| EP3818492B1 (en) | Communication via simulated user | |
| CN112100513A (en) | Knowledge graph-based recommendation method, device, equipment and computer readable medium | |
| CN111159570B (en) | Information recommendation method and server | |
| US20170287041A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN111079016A (en) | Short video recommendation method and device and electronic equipment | |
| KR20200003577A (en) | Method for Providing of Information of Goods based on image searching and service device supporting the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |