CN114679490A - Big data based information message content intelligent pushing system and method - Google Patents
Big data based information message content intelligent pushing system and method Download PDFInfo
- Publication number
- CN114679490A CN114679490A CN202210251902.7A CN202210251902A CN114679490A CN 114679490 A CN114679490 A CN 114679490A CN 202210251902 A CN202210251902 A CN 202210251902A CN 114679490 A CN114679490 A CN 114679490A
- Authority
- CN
- China
- Prior art keywords
- subscription
- analyzed
- user
- index
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Landscapes
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses an intelligent pushing system and method for information message content based on big data, wherein the intelligent pushing system comprises a user subscription library, a subscription monitoring module, an identification analysis module and an identification acquisition module, the user subscription library is used for storing subscription content of a user, the subscription monitoring module monitors the content of the user subscription library, when the situation that the subscription content of the user is updated is monitored, the identification analysis module analyzes viewing information of the user on the subscription content and determines identification information of the subscription content according to the viewing information, the identification acquisition module acquires the identification information of the subscription content, if the identification information of the subscription content is a first identification, the updated content of the subscription content is pushed to the user, and if the identification information of the subscription content is a second identification, the updated information of the subscription content is generated and pushed to the user.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an intelligent information message content pushing system and method based on big data.
Background
With the development of network technology, more and more information is provided on the internet, and users often refer to relevant information through search engines. When a user watches some continuously uploaded contents on the network, the user needs to enter the same webpage to check whether the contents are updated or not every time, and sometimes the updating time of some contents is not accurately timed, so that the user needs to check the webpage frequently, a large amount of time is occupied for the user, and the operation is complicated.
In the prior art, there is a technology for performing update reminding on contents concerned by a user, but the update reminding is performed on the contents concerned by the user in a uniform mode, and the individual pertinence to the user is not strong.
Disclosure of Invention
The present invention provides a system and a method for pushing information message content intelligently based on big data, so as to solve the problems proposed in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent pushing system for information message contents based on big data comprises a user subscription library, a subscription monitoring module, an identification analysis module and an identification acquisition module, wherein the user subscription library is used for storing subscription contents of a user, the subscription monitoring module monitors the contents of the user subscription library, when the situation that the subscription contents of the user are updated is monitored, the identification analysis module analyzes viewing information of the subscription contents of the user to determine identification information of the subscription contents, the identification acquisition module acquires the identification information of the subscription contents, if the identification information of the subscription contents is a first identification, the updated contents of the subscription contents are pushed to the user, and if the identification information of the subscription contents is a second identification, the updated information of the subscription contents is pushed to the user.
Further, the identification analysis module includes an initial judgment index calculation module, an initial judgment index comparison module, a candidate duration analysis module, a reference duration acquisition module, an attention index calculation module and an attention index comparison module, the initial judgment index calculation module sets a certain subscription content as a subscription to be analyzed, acquires the number Uz of historical update contents of the subscription to be analyzed and the number Us of update contents watched by the subscription to be analyzed of the user, the initial judgment index V of the subscription to be analyzed is Us/Uz, the initial judgment index comparison module compares the initial judgment index of the subscription to be analyzed with an initial judgment threshold, if the initial judgment index of the subscription to be analyzed is less than or equal to the initial judgment threshold, then adds second identification information to the subscription to be analyzed, if the initial judgment index of the subscription to be analyzed is greater than the initial judgment threshold, the attention index calculation module acquires k update information of the subscription to be analyzed, which is recently watched by the user, and calculating therefrom an interest index of the subscription to be analyzed
Wherein h isiThe time spent by the user for viewing the ith update information of the analysis subscription is the closest, H is the sum of the times spent by the user for viewing the k update information of the analysis subscription is the closest, DiThe reference time length in the process of watching the ith update information to be analyzed and subscribed by a user most recently, the candidate time length analysis module obtains the stay time length of the user watching a certain page of the update information when the user watches the certain update information to be analyzed and subscribed, if the stay time length of the certain page is greater than or equal to the stay threshold, the page sliding speed when the page sliding is detected for the first time after the certain page stays is obtained, if the page sliding speed is less than the speed threshold, the stay time length is the candidate time length, the reference time length obtaining module obtains all the candidate time lengths when the user watches the certain update information to be analyzed and subscribed, sorts all the candidate time lengths of the update information according to the sequence from large to small, selects the first candidate time length as the reference time length of the update information, and the attention index comparison module compares the attention index to be analyzed and subscribed with the attention threshold, and if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, adding first identification information to the subscription to be analyzed.
Further, the intelligent push system further includes an association subscription selecting module, where the association subscription selecting module includes an association index calculating module that obtains a situation that the user views the user subscription content each time, and sets a certain subscription content as a base subscription, and the subscription contents in the user subscription library except the base subscription are candidate subscriptions, and then an association index G ═ Rs/Rz of a certain candidate subscription and the base subscription, where Rz is a number of times that the base subscription is viewed historically, and Rs is a number of times that the candidate subscription is viewed in the number of times that the base subscription is viewed historically, and the association index comparing module also views the number of times that the candidate subscription and the base subscription are viewed in the presence of a certain association index that the candidate subscription and the base subscription is greater than an association threshold, and then the candidate subscription is an association subscription that the base subscription is based subscription.
The identification analysis module further comprises a sweep index calculation module and a sweep index comparison module, wherein if the attention index of the subscription to be analyzed is smaller than an attention threshold, the sweep index calculation module acquires the watching condition of the associated subscription of the subscription to be analyzed, and calculates the sweep index b of the subscription to be analyzed, which is Qs/Qz, wherein Qz is the number of the base subscriptions to be analyzed, Qs is the number of the base subscriptions watched when each base subscription to be analyzed updates the subscription information most recently, the sweep index comparison module compares the sweep index of the subscription to be analyzed with the sweep threshold, if the sweep index of the subscription to be analyzed is greater than the sweep threshold, first identification information is added to the subscription to be analyzed, and if the sweep index of the subscription to be analyzed is smaller than or equal to the sweep threshold, second identification information is added to the subscription to be analyzed.
An intelligent pushing method for information message content based on big data comprises the following steps:
establishing a user subscription library for storing the subscription content of the user,
monitoring the content of the user subscription library, acquiring the identification information of the subscription content when the subscription content of the user is monitored to be updated, wherein the identification information of the subscription content is determined by analyzing the watching information of the subscription content of the user,
if the identification information of the subscription content is the first identification, pushing the updated content of the subscription content to the user;
and if the identification information of the subscription content is the second identification, generating and pushing the update information of the subscription content to the user.
Further, the analyzing the viewing information of the user on the subscription content to determine the identification information of the subscription content according to the viewing information comprises:
setting a certain subscription content as a subscription to be analyzed, acquiring the number Uz of historical updating content of the subscription to be analyzed and the number Us of updating content viewed by the subscription to be analyzed of a user, and then setting an initial judgment index V of the subscription to be analyzed as Us/Uz,
if the initial judgment index of the subscription to be analyzed is less than or equal to the initial judgment threshold, adding second identification information to the subscription to be analyzed,
If the initial judgment index of the subscription to be analyzed is larger than the initial judgment threshold value, acquiring k pieces of updated information which is viewed by the user recently, wherein when the user views a certain piece of updated information to be analyzed and subscribed, the stay time of the user viewing a certain page of the updated information is acquired, if the stay time of the certain page is larger than or equal to the stay threshold value, the page sliding speed when the page sliding is detected for the first time after the page is stopped is acquired, if the page sliding speed is smaller than the speed threshold value, the stay time is a candidate time, all candidate times when the user views the certain piece of updated information to be analyzed and subscribed are acquired, all the candidate times of the updated information are sequenced according to the sequence from large to small, and the first sequenced candidate time is selected as the reference time of the updated information,
calculating interest indices for subscriptions to be analyzed
Wherein h isiThe time taken for the user to most recently view the ith update information of the analysis subscription, H is the sum of the times taken for the user to most recently view the k update information of the analysis subscription, DiThe reference duration in the process of viewing the ith update message to be analyzed for the user's closest time,
And comparing the attention index of the subscription to be analyzed with an attention threshold, and if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, adding first identification information to the subscription to be analyzed.
Further, the intelligent pushing method further comprises:
acquiring the condition that the user watches the user subscription content each time, setting a certain subscription content as a base subscription, and setting the subscription contents in the user subscription library except the base subscription as candidate subscriptions,
then the association index G ═ Rs/Rz of a candidate subscription with the base subscription, where Rz is the number of historically viewed base subscriptions, Rs is the number of times that the candidate subscription was viewed among the number of historically viewed base subscriptions,
if there is a candidate subscription whose association index with the base subscription is greater than the association threshold, then the candidate subscription is the associated subscription of the base subscription.
Further, the comparing the interest index of the subscription to be analyzed with the interest threshold further includes:
if the attention index of the subscription to be analyzed is smaller than the attention threshold, acquiring the viewing condition of the associated subscription of the subscription to be analyzed,
calculating the sweep index b of the subscriptions to be analyzed as Qs/Qz, wherein Qz is the number of base subscriptions to be analyzed, Qs is the number of base subscriptions viewed when the subscription information is updated last time by each base subscription to be analyzed,
Compare the sweep index of the subscription to be analyzed to a sweep threshold,
and if the sweep index of the subscription to be analyzed is greater than the sweep threshold, adding first identification information to the subscription to be analyzed.
Further, the comparing the sweep index of the subscription to be analyzed with the sweep threshold further includes:
and if the sweep index of the subscription to be analyzed is less than or equal to the sweep threshold, adding second identification information to the subscription to be analyzed.
Compared with the prior art, the invention has the following beneficial effects: according to the method and the device, the user subscription library is established in advance, when the situation that the subscription content of the user is updated is monitored, whether the updated content of the subscription content is pushed to the user or only the updated information of the subscription content is generated and pushed to the user is judged according to the situation that the user watches the updated information of the subscription content historically, the situation that the user checks and tracks the updated content of the subscription content is omitted, different modes are pushed according to different subscription contents, and the pertinence of the user is higher.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
Fig. 1 is a schematic structural diagram of an intelligent push system for information message content based on big data according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, the present invention provides the following technical solutions: an intelligent pushing system for information message contents based on big data comprises a user subscription library, a subscription monitoring module, an identification analysis module and an identification acquisition module, wherein the user subscription library is used for storing subscription contents of users, the subscription monitoring module monitors the contents of the user subscription library, when the situation that the subscription contents of the users are updated is monitored, the identification analysis module analyzes watching information of the users on the subscription contents to determine identification information of the subscription contents, the identification acquisition module acquires the identification information of the subscription contents, if the identification information of the subscription contents is a first identification, the updated contents of the subscription contents are pushed to the users, and if the identification information of the subscription contents is a second identification, the updated information of the subscription contents is pushed to the users.
The identification analysis module comprises a preliminary judgment index calculation module, a preliminary judgment index comparison module, a candidate duration analysis module, a reference duration acquisition module, an attention index calculation module and an attention index comparison module, wherein the preliminary judgment index calculation module sets a certain subscription content as a subscription to be analyzed, acquires the number Uz of historical updating contents of the subscription to be analyzed and the number Us of updating contents watched by the subscription to be analyzed of a user, the preliminary judgment index V of the subscription to be analyzed is equal to Us/Uz, the preliminary judgment index comparison module compares the preliminary judgment index of the subscription to be analyzed with a preliminary judgment threshold, if the preliminary judgment index of the subscription to be analyzed is less than or equal to the preliminary judgment threshold, second identification information is added to the subscription to be analyzed, if the preliminary judgment index of the subscription to be analyzed is greater than the preliminary judgment threshold, the attention index calculation module acquires k pieces of updating information of the subscription to be analyzed, which is recently watched by the user, and calculating therefrom an interest index of the subscription to be analyzed
Wherein h isiThe time spent by the user for viewing the ith update information of the analysis subscription is the closest, H is the sum of the times spent by the user for viewing the k update information of the analysis subscription is the closest, DiThe reference time length in the process of watching the ith update information to be analyzed and subscribed by a user most recently, the candidate time length analysis module obtains the stay time length of the user watching a certain page of the update information when the user watches the certain update information to be analyzed and subscribed, if the stay time length of the certain page is greater than or equal to the stay threshold, the page sliding speed when the page sliding is detected for the first time after the certain page stays is obtained, if the page sliding speed is less than the speed threshold, the stay time length is the candidate time length, the reference time length obtaining module obtains all the candidate time lengths when the user watches the certain update information to be analyzed and subscribed, sorts all the candidate time lengths of the update information according to the sequence from large to small, selects the first candidate time length as the reference time length of the update information, and the attention index comparison module compares the attention index to be analyzed and subscribed with the attention threshold, and if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, adding first identification information to the subscription to be analyzed.
The intelligent push system further comprises an association subscription selecting module, wherein the association subscription selecting module comprises an association index calculating module for acquiring the condition that a user watches the user subscription content each time, a certain subscription content is set as a base subscription, the subscription contents except the base subscription in the user subscription library are candidate subscriptions, and then the association index G of a certain candidate subscription and the base subscription is Rs/Rz, wherein Rz is the number of times of historically watching the base subscription, Rs is the number of times of also watching the candidate subscription in the number of times of historically watching the base subscription, and the association index comparing module is used for comparing the association index of a certain candidate subscription and the base subscription with the association index larger than the association threshold, and then the candidate subscription is the association subscription of the base subscription.
The identification analysis module further comprises a sweep index calculation module and a sweep index comparison module, if the attention index of the subscription to be analyzed is smaller than an attention threshold, the sweep index calculation module acquires the watching condition of the associated subscription of the subscription to be analyzed, and calculates the sweep index b of the subscription to be analyzed, which is Qs/Qz, wherein Qz is the number of the base subscriptions of the subscription to be analyzed, Qs is the number of the base subscriptions watched when each base subscription to be analyzed updates subscription information last time, the sweep index comparison module compares the sweep index of the subscription to be analyzed with the sweep threshold, if the sweep index of the subscription to be analyzed is larger than the sweep threshold, first identification information is added to the subscription to be analyzed, and if the sweep index of the subscription to be analyzed is smaller than or equal to the sweep threshold, second identification information is added to the subscription to be analyzed.
An intelligent pushing method for information message content based on big data comprises the following steps:
establishing a user subscription library for storing the subscription content of the user,
monitoring the content of the user subscription library, and acquiring the identification information of the subscription content when the subscription content of the user is monitored to be updated, wherein the identification information of the subscription content is determined by analyzing the watching information of the user to the subscription content,
the analyzing the viewing information of the user on the subscription content to determine the identification information of the subscription content according to the viewing information comprises:
setting a certain subscription content as a subscription to be analyzed, acquiring a historical updated content number Uz of the subscription to be analyzed and an updated content number Us watched by a user through the subscription to be analyzed, and then setting a primary judgment index V (Us/Uz) of the subscription to be analyzed, for example, if a blog exists in a user subscription library, then Us is the space of the blog in the blog watched by the user, Uz is the total space of the blog in the blog, or actually Uz can also select the total space updated by the blog, which is stored in the user subscription library by the user, of the blog;
if the initial judgment index of the subscription to be analyzed is less than or equal to the initial judgment threshold, adding second identification information to the subscription to be analyzed, and when the initial judgment index of the subscription to be analyzed is smaller, indicating that the user does not see the updated content of the subscription to be analyzed for a long time, the updated content of the subscription to be analyzed is not interested in what,
If the initial judgment index of the subscription to be analyzed is larger than the initial judgment threshold, it means that the updated content of the subscription to be analyzed may be of great interest to the user, or may be simply passed through, swept at a glance,
acquiring k pieces of update information to be analyzed and subscribed which is recently viewed by a user, wherein when the user views a piece of update information to be analyzed and subscribed, the stay time length of a certain page of the update information viewed by the user is acquired, if the stay time length of the certain page is greater than or equal to a stay threshold, the page sliding speed when the page sliding is detected for the first time after the certain page stays is acquired, if the page sliding speed is less than a speed threshold, the stay time length is a candidate time length, all candidate time lengths when the user views the piece of update information to be analyzed and subscribed are acquired, all the candidate time lengths of the piece of update information are ranked according to a sequence from large to small, and the first ranked candidate time length is selected as the reference time length of the piece of update information,
when a user watches updated information to be analyzed and subscribed, the user does not need to carefully watch every local user, some places of the user can be carefully watched, some places of the user can be roughly watched, and the user can also directly not be carefully watched; according to the method and the device, the fact that whether contents which a user wants to see or is interested in exist in the watching process is often known by the user, the user can slowly slide the page to see down under the condition of being interested in the contents, the user can directly and quickly slide the page to find the next interested place under the condition of not being interested in the contents, the candidate duration is selected based on the finding, and under the condition that the candidate duration is longer, the user is more interested in the updated information to be analyzed and subscribed;
Calculating interest indices for subscriptions to be analyzed
Wherein h isiIs most suitable for usersH is the sum of the times spent by the user to most recently view the k update information of the analysis subscription, DiThe reference duration in the process of viewing the ith update message to be analyzed for the user most recently,
comparing the attention index of the subscription to be analyzed with an attention threshold, if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, and if the attention index of the subscription to be analyzed is larger, the user is indicated to watch the updated content carefully in the process of watching the updated content of the subscription to be analyzed, and then adding first identification information to the subscription to be analyzed;
if the attention index of the subscription to be analyzed is smaller than the attention threshold, acquiring the viewing condition of the associated subscription of the subscription to be analyzed,
calculating the sweep index b of the subscriptions to be analyzed as Qs/Qz, wherein Qz is the number of base subscriptions to be analyzed, Qs is the number of base subscriptions viewed when the subscription information is updated last time by each base subscription to be analyzed,
compare the sweep index of the subscription to be analyzed to a sweep threshold,
if the sweep index of the subscription to be analyzed is larger than the sweep threshold, if the sweep index of the subscription to be analyzed is larger, the tendency that the user is likely to be interested in the sweep index is shown, and first identification information is added to the subscription to be analyzed;
And if the sweep index of the subscription to be analyzed is less than or equal to the sweep threshold, when the sweep index of the subscription to be analyzed is smaller, the interest of the user on the subscription to be analyzed and the associated subscription is smaller, and second identification information is added to the subscription to be analyzed.
The intelligent pushing method further comprises the following steps:
acquiring the condition that the user watches the user subscription content each time, setting a certain subscription content as a base subscription, and setting the subscription contents in the user subscription library except the base subscription as candidate subscriptions,
then the association index G ═ Rs/Rz of a certain candidate subscription with the base subscription, where Rz is the number of times the base subscription was viewed historically, Rs is the number of times the candidate subscription was viewed among the number of times the base subscription was viewed historically,
if there is a candidate subscription whose association index with the base subscription is greater than the association threshold, then the candidate subscription is an associated subscription of the base subscription.
If the identification information of the subscription content is the first identification, the user pays more attention to the subscription content, so that the updated content of the subscription content is pushed to the user, and the user can watch the latest information of the subscription content conveniently;
if the identification information of the subscription content is the second identification, the watching interest of the user to the subscription content is not so large, so that only the update information of the subscription content is generated and pushed to the user to remind the user. For example, when the user pays attention to a blog, the blogger updates an article on a certain day, if the identification of the blog in the user subscription database is a first identification, the updated article is directly sent to the user, and if the identification of the blog in the user subscription database is a second identification, the information of the article updated by the blog is directly sent to the user.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. An intelligent pushing system for information message contents based on big data is characterized by comprising a user subscription library, a subscription monitoring module, an identification analysis module and an identification acquisition module, wherein the user subscription library is used for storing subscription contents of users, the subscription monitoring module monitors the contents of the user subscription library, when the situation that the subscription contents of the users are updated is monitored, the identification analysis module analyzes the watching information of the users to the subscription contents to determine the identification information of the subscription contents, the identification acquisition module acquires the identification information of the subscription contents, if the identification information of the subscription contents is a first identification, the updated contents of the subscription contents are pushed to the users, and if the identification information of the subscription contents is a second identification, the updated information of the subscription contents is generated and pushed to the users.
2. The system of claim 1, wherein the system comprises: the identification analysis module comprises a preliminary judgment index calculation module, a preliminary judgment index comparison module, a candidate duration analysis module, a reference duration acquisition module, an attention index calculation module and an attention index comparison module, wherein the preliminary judgment index calculation module sets a certain subscription as a subscription to be analyzed, acquires the number Uz of historical updating contents of the subscription to be analyzed and the number Us of updating contents observed by the subscription to be analyzed of a user, the preliminary judgment index V (Us)/Uz of the subscription to be analyzed is acquired, the preliminary judgment index comparison module compares the preliminary judgment index of the subscription to be analyzed with a preliminary judgment threshold value, if the preliminary judgment index of the subscription to be analyzed is less than or equal to the preliminary judgment threshold value, second identification information is added to the subscription to be analyzed, if the preliminary judgment index of the subscription to be analyzed is greater than the preliminary judgment threshold value, the attention index calculation module acquires k pieces of updating information which are recently observed by the user and are to be analyzed, and calculating therefrom an interest index of the subscription to be analyzed 
Wherein h isiThe time taken for the user to most recently view the ith update information of the analysis subscription, H is the sum of the times taken for the user to most recently view the k update information of the analysis subscription, DiThe reference time length in the process of watching the ith update information to be analyzed and subscribed by a user most recently, the candidate time length analysis module acquires the stay time length of the user watching a certain page of the update information when the user watches the certain update information to be analyzed and subscribed, if the stay time length of the certain page is greater than or equal to a stay threshold, the page sliding speed when the page sliding is detected for the first time after the certain page stays is acquired, if the page sliding speed is less than the speed threshold, the stay time length is a candidate time length, the reference time length acquisition module acquires all candidate time lengths when the user watches the certain update information to be analyzed and subscribed, sorts all the candidate time lengths of the update information according to the sequence from large to small, selects the first sorted candidate time length as the reference time length of the update information, and the attention index comparison module compares the attention index to be analyzed and subscribed with an attention threshold, and if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, adding first identification information to the subscription to be analyzed.
3. The system of claim 2, wherein the system comprises: the intelligent push system further comprises an association subscription selecting module, the association subscription selecting module comprises an association index calculating module and an association index comparing module, the association index calculating module acquires the condition that the user watches the user subscription content each time, a certain subscription content is set as a base subscription, the subscription contents except the base subscription in the user subscription library are candidate subscriptions, and then the association index G of a certain candidate subscription and the base subscription is Rs/Rz, wherein Rz is the number of times of historically watching the base subscription, Rs is the number of times of also watching the candidate subscription in the number of times of historically watching the base subscription, and the association index comparing module is used for judging that the association index of a certain candidate subscription and the base subscription is greater than the association threshold value when the association index of the certain candidate subscription and the base subscription is greater than the association threshold value, and then the candidate subscription is the association subscription of the base subscription.
4. The system of claim 3, wherein the system comprises: the identification analysis module further comprises a sweep index calculation module and a sweep index comparison module, if the attention index of the subscription to be analyzed is smaller than an attention threshold, the sweep index calculation module acquires the watching condition of the associated subscription of the subscription to be analyzed, and calculates the sweep index b of the subscription to be analyzed, which is Qs/Qz, wherein Qz is the number of the base subscriptions of the subscription to be analyzed, Qs is the number of the base subscriptions watched when each base subscription to be analyzed updates subscription information last time, the sweep index comparison module compares the sweep index of the subscription to be analyzed with the sweep threshold, if the sweep index of the subscription to be analyzed is larger than the sweep threshold, first identification information is added to the subscription to be analyzed, and if the sweep index of the subscription to be analyzed is smaller than or equal to the sweep threshold, second identification information is added to the subscription to be analyzed.
5. An intelligent pushing method for information message content based on big data is characterized in that: the intelligent pushing method comprises the following steps:
establishing a user subscription library for storing the subscription content of the user,
monitoring the content of the user subscription library, and acquiring the identification information of the subscription content when the subscription content of the user is monitored to be updated, wherein the identification information of the subscription content is determined by analyzing the watching information of the user to the subscription content,
if the identification information of the subscription content is the first identification, pushing the updated content of the subscription content to the user;
and if the identification information of the subscription content is the second identification, generating and pushing the update information of the subscription content to the user.
6. The method as claimed in claim 5, wherein the method comprises: the analyzing the viewing information of the user on the subscription content to determine the identification information of the subscription content according to the viewing information comprises:
setting a certain subscription content as a subscription to be analyzed, acquiring the number Uz of historical updating content of the subscription to be analyzed and the number Us of updating content viewed by the subscription to be analyzed of a user, and then setting an initial judgment index V of the subscription to be analyzed as Us/Uz,
If the initial judgment index of the subscription to be analyzed is less than or equal to the initial judgment threshold, adding second identification information to the subscription to be analyzed,
if the initial judgment index of the subscription to be analyzed is greater than the initial judgment threshold, acquiring k pieces of update information of the subscription to be analyzed, which is recently watched by a user, wherein when the user watches a certain piece of update information of the subscription to be analyzed, the stay time of the user watching a certain page of the update information is acquired, if the stay time of the certain page is greater than or equal to the stay threshold, the page sliding speed when the page sliding is detected for the first time after the page is stopped is acquired, if the page sliding speed is less than the speed threshold, the stay time is a candidate time, all candidate times when the user watches the certain piece of update information of the subscription to be analyzed are acquired, all the candidate times of the update information are sorted according to the sequence from large to small, and the first candidate time is selected as the reference time of the update information,
calculating an attention index for a subscription to be analyzed
Wherein h isiThe time spent by the user for viewing the ith update information of the analysis subscription is the closest, H is the sum of the times spent by the user for viewing the k update information of the analysis subscription is the closest, D iThe reference duration in the process of viewing the ith update message to be analyzed for the user's closest time,
and comparing the attention index of the subscription to be analyzed with an attention threshold, and if the attention index of the subscription to be analyzed is greater than or equal to the attention threshold, adding first identification information to the subscription to be analyzed.
7. The method as claimed in claim 6, wherein the method comprises: the intelligent pushing method further comprises the following steps:
acquiring the condition that a user watches the content subscribed by the user each time, setting a certain subscribed content as a base subscription, setting the subscribed contents except the base subscription in a user subscription library as candidate subscriptions,
then the association index G ═ Rs/Rz of a certain candidate subscription with the base subscription, where Rz is the number of times the base subscription was viewed historically, Rs is the number of times the candidate subscription was viewed among the number of times the base subscription was viewed historically,
if there is a candidate subscription whose association index with the base subscription is greater than the association threshold, then the candidate subscription is the associated subscription of the base subscription.
8. The method as claimed in claim 7, wherein the method comprises: the comparing the interest index of the subscription to be analyzed with the interest threshold further comprises:
If the attention index of the subscription to be analyzed is smaller than the attention threshold, acquiring the watching condition of the associated subscription of the subscription to be analyzed,
calculating the sweep index b of the subscriptions to be analyzed as Qs/Qz, wherein Qz is the number of base subscriptions to be analyzed, Qs is the number of base subscriptions viewed when the subscription information is updated last time by each base subscription to be analyzed,
compare the sweep index of the subscription to be analyzed to a sweep threshold,
and if the sweep index of the subscription to be analyzed is greater than the sweep threshold, adding first identification information to the subscription to be analyzed.
9. The intelligent pushing method for information message content based on big data as claimed in claim 8, wherein: the comparing the sweep index of the subscription to be analyzed to a sweep threshold further comprises:
and if the sweep index of the subscription to be analyzed is less than or equal to the sweep threshold, adding second identification information to the subscription to be analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251902.7A CN114679490B (en) | 2022-03-15 | 2022-03-15 | Information message content intelligent pushing system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251902.7A CN114679490B (en) | 2022-03-15 | 2022-03-15 | Information message content intelligent pushing system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114679490A true CN114679490A (en) | 2022-06-28 |
| CN114679490B CN114679490B (en) | 2024-04-26 |
Family
ID=82073600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210251902.7A Active CN114679490B (en) | 2022-03-15 | 2022-03-15 | Information message content intelligent pushing system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114679490B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7984056B1 (en) * | 2007-12-28 | 2011-07-19 | Amazon Technologies, Inc. | System for facilitating discovery and management of feeds |
| CN103036970A (en) * | 2012-12-11 | 2013-04-10 | 北京奇虎科技有限公司 | Method and system for page frame content subscription |
| CN103034716A (en) * | 2012-12-11 | 2013-04-10 | 北京奇虎科技有限公司 | Subscribing method and device for page content |
| WO2019051849A1 (en) * | 2017-09-18 | 2019-03-21 | 深圳市云中飞网络科技有限公司 | Method and device for subscribing message, computer apparatus, and computer storage medium |
| CN113364670A (en) * | 2021-06-16 | 2021-09-07 | 北京轻松筹信息技术有限公司 | Data pushing method and device and electronic equipment |
| CN113468194A (en) * | 2021-07-02 | 2021-10-01 | 广东蕾特恩科技发展有限公司 | Customer relationship management data updating system and method based on big data |
| CN113645488A (en) * | 2021-10-18 | 2021-11-12 | 南京聚通时讯科技有限公司 | Internet television video recommendation system and method based on user data |
-
2022
- 2022-03-15 CN CN202210251902.7A patent/CN114679490B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7984056B1 (en) * | 2007-12-28 | 2011-07-19 | Amazon Technologies, Inc. | System for facilitating discovery and management of feeds |
| CN103036970A (en) * | 2012-12-11 | 2013-04-10 | 北京奇虎科技有限公司 | Method and system for page frame content subscription |
| CN103034716A (en) * | 2012-12-11 | 2013-04-10 | 北京奇虎科技有限公司 | Subscribing method and device for page content |
| WO2019051849A1 (en) * | 2017-09-18 | 2019-03-21 | 深圳市云中飞网络科技有限公司 | Method and device for subscribing message, computer apparatus, and computer storage medium |
| CN113364670A (en) * | 2021-06-16 | 2021-09-07 | 北京轻松筹信息技术有限公司 | Data pushing method and device and electronic equipment |
| CN113468194A (en) * | 2021-07-02 | 2021-10-01 | 广东蕾特恩科技发展有限公司 | Customer relationship management data updating system and method based on big data |
| CN113645488A (en) * | 2021-10-18 | 2021-11-12 | 南京聚通时讯科技有限公司 | Internet television video recommendation system and method based on user data |
Non-Patent Citations (2)
| Title |
|---|
| M. THOMSON; MOZILLA; P. BEVERLOO; GOOGLE;: "Voluntary Application Server Identification for Web Push draft-thomson-webpush-vapid-02", IETF * |
| 刘世雄;张俊: "基于兴趣图谱的移动端个性化消息推送服务研究", 电脑知识与技术 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114679490B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7171620B2 (en) | System and method for managing document retention of shared documents | |
| CN110322738B (en) | Course optimization method, device and system | |
| RU2382401C2 (en) | Principles and methods of personalising news flow by analysing recentness and dynamics of information | |
| CN110704603B (en) | Method and device for discovering current hot event through information | |
| CN107888950A (en) | A kind of method and system for recommending video | |
| CN110717093B (en) | Movie recommendation system and method based on Spark | |
| CN108446351B (en) | Hotel screening method and system based on user preference of OTA platform | |
| JP2008262251A (en) | Information processor, information processing method and information processing program | |
| CN111639988B (en) | Broker recommendation method, device, electronic equipment and storage medium | |
| CN106126544B (en) | Internet content delivery method and device | |
| CN113643070A (en) | Intelligent information pushing method and system based on big data | |
| CN112417302A (en) | Big data-based information content intelligent analysis recommendation processing system | |
| KR101151176B1 (en) | The Content Recommendation Method by Using Menu Preferences | |
| JP4891638B2 (en) | How to classify target data into categories | |
| CN114679490A (en) | Big data based information message content intelligent pushing system and method | |
| CN116010700B (en) | Knowledge graph-based user portrayal method | |
| CN113127720A (en) | Hot word searching determination method and device | |
| CN113392266B (en) | Training and sorting method and device of sorting model, electronic equipment and storage medium | |
| CN110188277A (en) | A kind of recommended method and device of resource | |
| CN111191126B (en) | Keyword-based scientific and technological achievement accurate pushing method and device | |
| CN111353101A (en) | Data pushing method | |
| CN110111183A (en) | A kind of Products Show method and device | |
| CN114969545B (en) | Personalized intelligent recommendation system and method for mental health courses | |
| CN114969558B (en) | User portrait generation method and system based on user behavior habit analysis | |
| CN114661949B (en) | Client data analysis system and method under big data situation |
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: 20240320 Address after: Room 503, Building 1, Huangzhou Industrial Zone, No.1 Ruihua Road, Tianhe District, Guangzhou City, Guangdong Province, 510000 Applicant after: Guangzhou Meiqi Network Technology Co.,Ltd. Country or region after: China Address before: 362342 No. 292, Jiancai street, Shuitou Town, Nan'an City, Quanzhou City, Fujian Province Applicant before: Quanzhou Yidian Information Technology Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |