CN113918736A - Information pushing method, device, equipment and storage medium - Google Patents

Information pushing method, device, equipment and storage medium Download PDF

Info

Publication number
CN113918736A
CN113918736A CN202111284949.5A CN202111284949A CN113918736A CN 113918736 A CN113918736 A CN 113918736A CN 202111284949 A CN202111284949 A CN 202111284949A CN 113918736 A CN113918736 A CN 113918736A
Authority
CN
China
Prior art keywords
information
media information
media
base
attenuation
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
Application number
CN202111284949.5A
Other languages
Chinese (zh)
Other versions
CN113918736B (en
Inventor
佟德超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yancheng Tianyanchawei Technology Co ltd
Original Assignee
Yancheng Jindi Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yancheng Jindi Technology Co Ltd filed Critical Yancheng Jindi Technology Co Ltd
Priority to CN202111284949.5A priority Critical patent/CN113918736B/en
Publication of CN113918736A publication Critical patent/CN113918736A/en
Application granted granted Critical
Publication of CN113918736B publication Critical patent/CN113918736B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/435—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/45—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Information Transfer Between Computers (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present disclosure relates to an information pushing method, apparatus, device, and medium, the method comprising: the method comprises the steps of obtaining first media information with the highest score in an initial information base on the basis of a first mapping relation among a plurality of types of information, the plurality of first media information and the plurality of score information by obtaining the first media information with the highest score in the initial information base and corresponding target type information, determining the plurality of first media information corresponding to the target type information in the initial information base, attenuating the score information of the first media information according to a first attenuation proportion to obtain an attenuation information base, obtaining the first media information with the highest score in the attenuation information base, and pushing the media information to a user terminal, wherein the pushed media information at least comprises the obtained first media information. The method and the device are used for realizing richer media information pushed to the user and reducing content homogenization.

Description

Information pushing method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of data transmission, and in particular, to an information pushing method, apparatus, device, and storage medium.
Background
In the prior art, content which is interesting to a user is presented to the user in an information stream mode through a feed stream, a certain amount of personalized information which is interesting to the user is recalled and pushed to the user based on refreshing operation of the user in an app, and the user sequentially browses the corresponding personalized information on the app according to a pushing sequence. However, the preference of the user is fixed, homogeneous information is more in the personalized information recalled according to the preference of the user, and thus information push can cause that the information content presented in the feed stream is not rich enough, so that the user is easy to get tired of the content in the app and bad user experience is brought.
Disclosure of Invention
The present disclosure aims to provide an information push method, an information push device, an information push apparatus, and a storage medium, so as to solve the technical problems of insufficient enrichment and content homogenization of the information push content.
According to a first aspect of the embodiments of the present disclosure, there is provided an information pushing method, including:
acquiring first media information with the highest score in an initial information base, wherein the initial information base comprises a plurality of types of information, a plurality of first media information and a first mapping relation among a plurality of score information;
based on the first mapping relation, acquiring first media information with the highest grade in the initial information base and corresponding target category information;
determining a plurality of first media information corresponding to the target category information in the initial information base, and attenuating the scoring information of the first media information according to a first attenuation proportion to obtain an attenuation information base;
acquiring first media information with the highest grade in the attenuation information base;
and pushing media information to the user terminal, wherein the pushed media information at least comprises the acquired first media information.
Optionally, the pushing media information to the user terminal, where the pushed media information at least includes the acquired first media information, includes:
under the condition that the obtained first media information does not reach a first specified quantity, the attenuation information base is used as the initial information base again, and the steps from obtaining the target category information corresponding to the first media information with the highest score in the initial information base based on the mapping relation to obtaining the first media information with the highest score in the attenuation information base are repeatedly executed until the obtained first media information reaches the first specified quantity;
under the condition that the obtained first media information reaches the first specified quantity, sequencing the obtained first media information based on the grading information in the attenuation information base to obtain the pushing sequence;
and pushing the acquired first media information to the user terminal according to the pushing sequence.
Optionally, the pushing media information to the user terminal, where the pushed media information at least includes the acquired first media information, includes:
acquiring a heat degree information base based on the current time, wherein the heat degree information base comprises a second mapping relation between a plurality of second media information and a plurality of heat degree scores;
acquiring one or more second media information in the popularity information base;
ordering the acquired first media information and the one or more second media information according to a preset ordering rule based on the heat degree scores and the score information in the attenuation information base to obtain the pushing sequence;
and pushing the acquired first media information and the one or more second media information to the user terminal according to the pushing sequence.
Optionally, the ranking the acquired first media information and the one or more second media information according to a preset ranking rule based on the heat score and the score information in the attenuation information base to obtain the push sequence includes:
ranking the acquired first media information based on scoring information in the attenuation information base;
and arranging the one or more second media information between first target information and second target information to obtain the pushing sequence, wherein the first target information is the first media information with the highest score in the initial information base, and the second target information is the first media information with the highest score in the attenuation information base.
Optionally, the pushing media information to the user terminal, where the pushed media information at least includes the acquired first media information, includes:
acquiring a heat degree information base based on the current time, wherein the heat degree information base comprises mapping relations between a plurality of second media information and a plurality of heat degree scores;
acquiring one or more second media information as hot information based on the hot information base;
selecting a first preset number of pieces of first media information from the acquired first media information according to a preset extraction ratio, and selecting a second preset number of pieces of second media information from the hot information, wherein the sum of the first preset number and the second preset number is a second specified number;
sorting the first media information of the first preset quantity and the second media information of the second preset quantity based on the grading information and the heat grading in the attenuation information base to obtain the pushing sequence;
and pushing the first media information with the first preset quantity and the second media information with the second preset quantity to the user terminal according to the pushing sequence.
Optionally, the method further comprises:
and if the target scoring information smaller than a first preset scoring threshold exists in the attenuation information base, deleting the target scoring information, and the first media information and the category information corresponding to the target scoring information.
Optionally, the method further comprises:
attenuating the scoring information in the attenuation information base based on a second attenuation proportion under the condition that a preset condition is reached;
and if the target scoring information smaller than a second preset scoring threshold exists in the attenuation information base, deleting the target scoring information, and the first media information and the category information corresponding to the target scoring information.
Optionally, before the obtaining the first media information with the highest score in the initial information base, the method further includes:
acquiring a plurality of pieces of first media information according to the user portrait, wherein the first media information comprises a plurality of pieces of quantity information and identification information corresponding to a plurality of pieces of dimension information;
obtaining scoring information corresponding to the plurality of first media information based on the plurality of quantity information corresponding to the plurality of dimension information;
and obtaining the initial information base based on the identification information and the grading information corresponding to the first media information.
Optionally, the obtaining the scoring information corresponding to the first media information based on the plurality of pieces of quantity information corresponding to the plurality of pieces of dimension information includes:
acquiring a plurality of feature weights corresponding to the plurality of dimensional information;
and calculating the quantity information corresponding to the dimensions according to a preset algorithm based on the characteristic weights to obtain the grading information.
According to a second aspect of the embodiments of the present disclosure, there is provided an information pushing apparatus including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire first media information with the highest score in an initial information base, and the initial information base comprises a plurality of first category information, a plurality of first media information and a first mapping relation among the plurality of score information;
the second obtaining module is used for obtaining the first media information with the highest grade and the corresponding target category information in the initial information base based on the first mapping relation;
a third obtaining module, configured to determine, in the initial information base, a plurality of pieces of first media information corresponding to the target category information, and attenuate score information of each of the plurality of pieces of first media information according to a first attenuation ratio to obtain an attenuation information base;
the fourth acquisition module is used for acquiring the first media information with the highest grade in the attenuation information base;
and the pushing module is used for pushing the media information to the user terminal, and the pushed media information at least comprises the acquired first media information.
According to a third aspect of embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the information pushing method according to any one of the first aspects of the present disclosure.
According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the information pushing method of any one of the first aspect of the present disclosure.
According to the technical scheme, the first media information with the highest score in the initial information base is obtained, wherein the initial information base comprises a plurality of types of information, a first mapping relation among the plurality of first media information and the plurality of score information, the first media information with the highest score and the corresponding target type information in the initial information base are obtained based on the first mapping relation, the plurality of first media information corresponding to the target type information are determined in the initial information base, the score information of the first media information is attenuated according to a first attenuation proportion, an attenuation information base is obtained, the first media information with the highest score in the attenuation information base is obtained, the media information is pushed to the user terminal, and the pushed media information at least comprises the obtained first media information. Therefore, the media information is sequenced through the grading information, and the probability of continuously selecting the same type of media information for pushing is reduced through the type information and the attenuation proportion when the information is pushed, so that the media information of different types in the information stream pushed to the user is increased, the diversity and the non-repeatability of the media information of the user side are improved, and the content homogenization of the pushed information can be avoided.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a flowchart illustrating an information pushing method according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating a method for acquiring an initial information base according to an exemplary embodiment.
Fig. 3 is a flowchart illustrating another information pushing method according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating a further information pushing method according to an exemplary embodiment.
Fig. 5 is a control diagram of an information pushing apparatus according to an exemplary embodiment.
Fig. 6 is a block diagram of an electronic device in accordance with an example embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
In order to solve the technical problem that the content homogeneity of the information pushed to the user is severe and the user is tired in the prior art, an embodiment of the present disclosure provides an information pushing method, and fig. 1 is a schematic flow diagram of an information pushing method according to an exemplary embodiment. It is understood that the method can be applied to a server to form an information push platform. As shown in fig. 1, the information push method includes the following steps:
s11, the first media information with the highest score in the initial information base is obtained, and the initial information base comprises a plurality of category information, a plurality of first media information and a plurality of first mapping relations among the score information.
S12, based on the first mapping relation, the first media information with the highest score and the corresponding target category information in the initial information base are obtained.
And S13, determining a plurality of first media information corresponding to the target category information in the initial information base, and attenuating the scoring information of the first media information according to a first attenuation proportion to obtain an attenuation information base.
And S14, acquiring the first media information with the highest grade in the attenuation information base.
S15, media information is pushed to the user terminal, and the pushed media information at least comprises the acquired first media information.
For example, in step S11, it is understood that the first media information in this embodiment may be picture information, video information, text information, and the like, and the server serves as an information pushing platform, and may schedule a general information base of the pushing platform based on media information uploaded by different users or media information uploaded by a server operator, so as to be browsed by a user corresponding to the server. In order to facilitate pushing of media information, the server needs to classify the media information in the initial information base, for example, the media information is classified into movie-type media information, animation-type media information, game-type media information, food-type media information, and the like according to content presented in the media information, which is not limited in this embodiment. Meanwhile, in order to distinguish the degree of goodness of the content presented in each piece of media information, the media information may be scored according to the content of the media information, for example, the media information may be scored according to the number of praise or collection in the media information.
Optionally, referring to fig. 2, fig. 2 is a schematic flowchart of a method for acquiring an initial information base according to an exemplary embodiment, where the step S11 may further include:
and S111, acquiring a plurality of pieces of first media information according to the user portrait, wherein the first media information comprises a plurality of pieces of quantity information and identification information corresponding to the plurality of pieces of dimension information.
And S112, obtaining scoring information corresponding to the first media information based on the quantity information corresponding to the dimension information.
S113, obtaining an initial information base based on the identification information and the grading information corresponding to the first media information.
For example, in step S111, in this embodiment, the server platform has a large number of pieces of media information, the content tags of the pieces of media information are obtained by classifying the content presented in the pieces of media information, the personal preference of the user is determined by obtaining the user portrait of the user corresponding to the user terminal, and the corresponding content tags are searched on the server platform according to the personal preference of the user, so as to obtain a plurality of pieces of first media information corresponding to the personal preference of the user. It can be understood that, in order to characterize the heat of the media information to the user and facilitate the user to discriminate, the data of different dimensions in the media information are usually counted, and the counted quantity information is displayed to the user. It can be understood that the identification information in the media information is used to indicate an identity category of the media information and to identify an affiliation of the media information, and for example, the media information may be classified according to a company associated with the media information, which is not limited in this embodiment.
In step S112, summing the quantity information corresponding to the obtained dimension information to obtain the rating information corresponding to each first media information, for example, taking the dimension information as an example, the quantity information corresponding to the obtained dimension information is the number of comment information pieces, the number of praise and the number of forwarding, and summing the quantity information to obtain the rating information corresponding to the first media information.
Optionally, the step S112 may further include:
and acquiring a plurality of feature weights corresponding to the dimension information.
And calculating a plurality of quantity information corresponding to the plurality of dimension information according to a preset algorithm based on the plurality of characteristic weights to obtain scoring information.
It can be understood that, when the media information is evaluated, in order to make the evaluation information of the representation more accurate, a weight needs to be set for the quantity information corresponding to the different dimension information, for example, the contribution degree of the praise quantity to the evaluation can be set to be weak, so that the quantity information corresponding to the praise dimension occupies a smaller proportion, the contribution degree of the forwarding dimension to the evaluation can be set to be stronger, and thus the quantity information corresponding to the forwarding dimension occupies a larger proportion.
For example, after determining the influence degree of the plurality of pieces of quantity information on the rating information according to the feature weight corresponding to the dimension information, the quantity information corresponding to the plurality of pieces of dimension information is multiplied by the corresponding feature weight, and the obtained quantities are added to obtain the rating information corresponding to the media information. For example, the number of praise corresponding to the acquired media information is 65798, the number of comment information pieces is 18457, the forwarding number is 6547, and the feature weights of three dimensions of praise, comment and forwarding are 0.45%, 0.1% and 0.6%, respectively, then the score information corresponding to the media information is 95% after the weighted sum calculation.
In step S113, after obtaining the rating information corresponding to each piece of media information through the above steps, a corresponding mapping relationship may be established according to the identification information and the rating information corresponding to the piece of media information, so as to form an initial information base, for example, category information may be set as a company associated with the piece of media information, and a first mapping relationship may be established according to the following initial information base table, where the initial information base table is:
Figure BDA0003332664400000091
it is understood that, in step S12, according to the first mapping relationship among the category information, the media information, and the rating information in the initial information base, the first media information and the category information corresponding to the highest rating information, and other media information under the affiliated category information are determined, and the corresponding category information is taken as the target category information, for example, in the above-mentioned initial information base table, if the query rating information determines 97-bit highest rating, the corresponding first media information is media information 5, and the corresponding target category information is company B.
For example, in step S13, it is understood that after the first media information that can be pushed to the user terminal is acquired through the above steps, the server needs to further filter other media information, so as to implement continuous pushing for the user. Generally, most of the scoring information of the media information in the same category is similar, which results in that most of the media information with high scoring belongs to the same category, and if the first media information is obtained by the method for obtaining the media information corresponding to the highest scoring information, a plurality of media information pushed to the user belong to the same category, which results in that the media information received by the user has high repeatability. Therefore, after the first media information and the target category information corresponding to the highest-score information are acquired through the above steps, in order to avoid selecting other media information under the same category for multiple times, meanwhile, in order to avoid the first media information corresponding to the highest score in the initial information base obtained through the above steps from being selected again, it is necessary to set a first attenuation ratio for the score information corresponding to the plurality of media information under the target category information, thereby obtaining the attenuation information base corresponding to the latest grading information, for example, the first attenuation ratio can be set to be 0-0.8, wherein 0 is the attenuation ratio corresponding to the first media information with the highest score in the initial information base, and 0.8 is the attenuation ratio corresponding to other media information except the first media information in the target category information, and the following attenuation information base table is obtained by taking the initial information base table as an example:
Figure BDA0003332664400000101
Figure BDA0003332664400000111
it is to be understood that, in step S14, the highest-scoring media information in the decay information base is determined as the second first media information, for example, the decay information base table as described above, and the highest-scoring media information at this time is determined as the second first media information, i.e., the media information 2.
For example, in step S15, after the two pieces of first media information are obtained through the above steps, that is, the first media information corresponding to the highest scoring information in the initial information base and the first media information corresponding to the highest scoring information in the attenuation information base, and the obtained first media information is pushed to the user terminal, for example, the order of pushing to the user terminal may be to determine the scoring information corresponding to the two pieces of first media information first, and compare the two pieces of scoring information, and push the two pieces of scoring information to the user terminal as the pushing order. It can be understood that, in this embodiment, for a single piece of displayed media information, for example, video information, the push sequence at this time may be a transmission sequence sent by the server to the user terminal, for example, taking the initial information base table and the attenuation information base table as an example, if the first media information corresponding to the initial information base is media information 5, the first media information corresponding to the attenuation information base is media information 2, the score value corresponding to the media information 5 is 97, and the score value corresponding to the media information 2 is 96, the server sequentially sends the media information 5 and the media information 3 to the user terminal, and the user terminal browses the media information 5 first and then browses the media information 3 based on a sliding operation. Optionally, for media information that can be displayed in multiple ways in the same user interface, such as picture information, article information, and the like, the pushing sequence at this time is a typesetting sequence on the user display page, taking the pushing sequence as an example, the display sequence is the media information 5 arranged at the most prominent position, and the media information 3 arranged at the secondary prominent position, which is not limited in this embodiment.
Optionally, the step S15 may further include:
and under the condition that the acquired first media information does not reach the first specified quantity, the attenuation information base is used as the initial information base again, and the steps from acquiring the target category information corresponding to the first media information with the highest score in the initial information base to acquiring the first media information with the highest score in the attenuation information base based on the mapping relation are repeatedly executed until the acquired first media information reaches the first specified quantity.
And under the condition that the obtained first media information reaches a first specified number, sequencing the obtained first media information based on the grading information in the attenuation information base to obtain a pushing sequence.
And pushing the acquired first media information to the user terminal according to the pushing sequence.
It can be understood that, when the server pushes information to the user terminal, the server generally pushes the information in the form of a feed stream, and the feed stream provides a certain amount of media information to the user based on one-time refresh behavior of the user, so that the server generally contains a plurality of media information when preparing to push information for the user terminal, and therefore, after two first media information are obtained through the above steps S11-S14, the obtained amount of the first media information is compared with a preset first specified amount, and when the amount of the first media information fails to reach the first specified amount, the attenuation information base is taken as a new initial information base to repeat the above steps S11-S14 until the obtained amount of the first media information reaches the preset first specified amount. For example, when the first designated number is 10, the above steps of S11-S14 need to be repeated 5 times to obtain 10 different-scoring first media information.
Illustratively, after a plurality of first media information of a first specified number are acquired through the above steps, according to the rating information corresponding to the first media information extraction, a pushing sequence for pushing the media information to the user terminal is determined according to the height sequence of the rating information, and the corresponding media information is pushed to the user terminal according to the pushing sequence.
Optionally, the step S15 may further include:
and S151, acquiring a heat degree information base based on the current time, wherein the heat degree information base comprises a second mapping relation between a plurality of second media information and a plurality of heat degree scores.
S152 acquires one or more second media information in the hotness information base.
S153 ranks the acquired first media information and one or more second media information according to a preset ranking rule based on the rating information in the heat rating and attenuation information base, so as to obtain a push order.
S154, sequencing the acquired first media information according to the pushing sequence and pushing one or more second media information to the user terminal.
Referring to fig. 3, fig. 3 is a flowchart illustrating another information pushing method according to an exemplary embodiment, it may be understood that, in step S151, to further enrich media information pushed to a user terminal, so as to enrich types covered by the media information in a feed stream, a server may obtain, according to a current time, a plurality of pieces of hotness information with highest hotness in the server at that time as a plurality of pieces of second media information, for example, the hotness score at that time may be evaluated according to an accumulated click volume of each piece of media information in the server at the current time, the higher the accumulated click volume of the user is, the higher the hotness score is, and a second mapping relationship between each piece of hotness information and the hotness score is established according to the hotness score corresponding to the second media information. It is worth mentioning that, in addition to the click amount, the popularity score may be calculated based on other dimensions, such as the number of comment information pieces, the number of likes and the number of forwards, or may be collectively evaluated based on the click amount, the number of comment information pieces, the number of likes and the number of forwards.
It is to be understood that, in step S152, one or more pieces of second media information with the highest scores in the popularity information base are determined according to the second mapping relationship, and for example, when the number of pieces of second media information in the popularity information base needs to be extracted is 10, 10 pieces of second media information with the top scores of 10 are obtained according to the second mapping relationship.
It is understood that, in step S153, after the plurality of first media information are acquired through the above steps S11 to S12, and after the one or more second media information are acquired through the above steps S151 to S152, at this time, the media information that needs to be pushed to the user in the server has been filtered, and the acquired plurality of first media information and the acquired second media information need to be sorted, so that the server can complete pushing of the media information.
Optionally, the step S153 may further include:
the acquired first media information is sorted based on the scoring information in the decay information base.
One or more second media information is arranged between the first target information and the second target information to obtain a push order. The first target information is the first media information with the highest grade in the initial information base, and the second target information is the first media information with the highest grade in the attenuation information base.
For example, in step S153, according to the score information corresponding to the first media information, the plurality of first media information may be sorted in a descending order, according to the popularity score information corresponding to the second media information, the second media information (at this time, if the second media information is a plurality of second media information, the second media information is directly extracted if the second media information is a single second media information) may be sorted in a descending order, and the second media information is inserted into the sequence of the first media information in order, so that the first media information in the first media information is not adjacent to each other, thereby obtaining the push order.
Illustratively, in step S154, according to the obtained pushing sequence in the above steps, the obtained first media information and second media information are sequentially pushed to the user terminal, so that when the user browses information, the information types are richer, the repeated information is less, and the user experience is improved.
Optionally, referring to fig. 4, fig. 4 is a schematic flowchart of another information pushing method according to an exemplary embodiment, where the step S15 may further include:
s155 obtains a popularity information base based on the current time, where the popularity information base includes mapping relationships between a plurality of second media information and a plurality of popularity scores.
S156 acquires one or more second media information as hit information based on the popularity information base.
S157 selects a first preset number of first media information from the acquired first media information according to a preset extraction ratio, and selects a second preset number of second media information from the hot information, where a sum of the first preset number and the second preset number is a second designated number.
S158 ranks the first media information of the first preset number and the second media information of the second preset number based on the rating information and the popularity rating in the attenuation information base, so as to obtain a push sequence.
S159, pushing the first media information of the first preset number and the second media information of the second preset number to the user terminal according to the pushing sequence.
For example, since the first media information in the initial information base is the first media information associated with the personal preference of the user, which is obtained according to the user portrait of the user, it can be understood that, in order to enrich the content of the media information pushed to the user, other information bases can be obtained according to other filtering dimensions, and in this embodiment, the second media information with higher heat degree at the current time is obtained as the heat degree information base.
It can be understood that, for the plurality of information bases, the weight of the media information to be extracted in each information base may be set as a preset extraction ratio according to the type weight of the media information to be pushed to the user, and then the corresponding amount of the first media information and the second media information is extracted from the highest score to the lowest score according to the first preset amount and the second preset amount in the heat information base and the attenuation information base respectively according to the above extraction methods, and the plurality of first score information and the plurality of second score information are sorted according to the score information and the heat score information of the first media information and the second media information, for example, the push order may be obtained by the above random sorting method, and then the corresponding first media information and second media information are sent according to the push order, for example, the preset extraction ratio may be set to be 7: 3, if the second designated number is 10, then 7 different pieces of first media information are obtained in the attenuation information base according to the selection mode in the steps S11-S12, 3 pieces of second media information with the highest popularity scores are selected in the popularity information base, and then the 7 pieces of first media information and the 3 pieces of second media information are pushed to the user terminal according to a random sorting method. For example, for a user with less user data corresponding to less user favorite types in the user representation, when the media information in the initial information base obtained by the method cannot reach a first preset number, the first media information is supplemented by the second media information, so that the number of the pushed media information reaches a second specified number.
Optionally, the information pushing method may further include:
and if the target scoring information smaller than the first preset scoring threshold exists in the attenuation information base, deleting the target scoring information, the first media information corresponding to the target scoring information and the category information.
It can be understood that, based on each refreshing behavior of the user, the media information in the initial information base is filled once, and after multiple information pushing and score information attenuation, the score information is not selected by the server when reaching a certain value, and in order to save storage space, when the target score information reaches a threshold value, the target score information and the corresponding media information are deleted from the server.
Optionally, the method further comprises:
attenuating the scoring information in the attenuation information base based on the second attenuation proportion under the condition that the preset condition is reached;
and if the target scoring information smaller than the second preset scoring threshold exists in the attenuation information base, deleting the target scoring information, the first media information corresponding to the target scoring information and the category information.
For example, in order to ensure freshness of the media information pushed by the server and prevent the media information from being outdated and causing boredom to the user, in the embodiment, by setting a preset condition, when the preset condition is reached, the scoring information in the decay information base is decayed according to the second decay proportion. Illustratively, the preset condition is a time condition, when the initial information base is established, a timer is set for the media information stored in the initial information base, when the time reaches a certain threshold, the score information corresponding to the media information is attenuated according to a second attenuation proportion, when the score information in the attenuation information base is smaller than a second preset score threshold, the media information and the score information under the corresponding category information are deleted from the attenuation information base, illustratively, the second attenuation value is 90%, the time threshold is set to be 24h, and the second preset score threshold is set to be 30, so that the media information in the initial information base can be moved out of the attenuation information base after 30 days have elapsed.
Fig. 5 is a block diagram of an information pushing device according to an example embodiment. Referring to fig. 5, the information pushing apparatus 100 includes a first obtaining module 110, a second obtaining module 120, a third obtaining module 130, a fourth obtaining module 140 and a pushing module 150.
The first obtaining module 110 is configured to obtain first media information with the highest score in an initial information base as first target information, where the initial information base includes a plurality of first category information, a plurality of first media information, and a first mapping relationship between the plurality of score information.
The second obtaining module 120 is configured to obtain, based on the first mapping relationship, the first media information with the highest score and the corresponding target category information in the initial information base.
The third obtaining module 130 is configured to determine, in the initial information base, a plurality of pieces of first media information corresponding to the target category information, and attenuate score information of each of the plurality of pieces of first media information according to a first attenuation ratio to obtain an attenuation information base.
The fourth obtaining module 140 is configured to obtain the first media information with the highest score in the attenuation information base.
The pushing module 150 is configured to push media information to the user terminal, where the pushed media information at least includes the acquired first media information.
Optionally, the information pushing apparatus 100 further includes:
and the fifth acquisition module is used for acquiring a plurality of pieces of first media information according to the user portrait, wherein the first media information comprises a plurality of pieces of quantity information and identification information corresponding to the plurality of pieces of dimension information.
The sixth obtaining module is configured to obtain scoring information corresponding to the plurality of first media information based on the plurality of quantity information corresponding to the plurality of dimension information.
And the seventh obtaining module is used for obtaining the initial information base based on the identification information and the grading information corresponding to the first media information.
Optionally, the sixth obtaining module is configured to:
acquiring a plurality of feature weights corresponding to a plurality of dimension information;
and calculating a plurality of quantity information corresponding to the plurality of dimensions according to a preset algorithm based on the plurality of characteristic weights to obtain scoring information.
Optionally, the pushing module 150 includes:
and the execution submodule is used for taking the attenuation information base as the initial information base again under the condition that the obtained first media information does not reach the first specified quantity, and repeatedly executing the steps from obtaining the target category information corresponding to the first media information with the highest score in the initial information base to obtaining the first media information with the highest score in the attenuation information base on the basis of the mapping relation until the obtained first media information reaches the first specified quantity.
And the first sequencing submodule is used for sequencing the acquired first media information based on the grading information in the attenuation information base under the condition that the acquired first media information reaches the first specified quantity to obtain a pushing sequence.
And the first pushing submodule is used for pushing the acquired first media information to the user terminal according to the pushing sequence.
Optionally, the pushing module 150 further includes:
and the first obtaining submodule is used for obtaining a heat degree information base based on the current time, wherein the heat degree information base comprises a plurality of second media information and a plurality of second mapping relations between heat degree scores.
And the second acquisition sub-module is used for acquiring one or more second media information in the heat information base.
And the second sorting submodule is used for sorting the acquired first media information and one or more second media information according to a preset sorting rule based on the heat degree score and the score information in the attenuation information base to obtain a pushing sequence.
And the second pushing submodule is used for pushing the acquired first media information and one or more second media information to the user terminal according to the pushing sequence.
Optionally, the second sorting sub-module is configured to:
the acquired first media information is sorted based on the scoring information in the decay information base.
And arranging one or more second media information between first target information and second target information to obtain a push sequence, wherein the first target information is the first media information with the highest score in the initial information base, and the second target information is the first media information with the highest score in the attenuation information base.
Optionally, the pushing module 150 further includes:
and the third obtaining submodule is used for obtaining a heat degree information base based on the current time, wherein the heat degree information base comprises a plurality of second media information and a plurality of mapping relations between heat degree scores.
And the fourth obtaining sub-module is used for obtaining one or more second media information as hot information based on the hot information base.
And the extraction submodule is used for selecting a first preset number of pieces of first media information from the acquired first media information according to a preset extraction ratio and selecting a second preset number of pieces of second media information from the hot information, and the sum of the first preset number and the second preset number is a second specified number.
And the third sorting submodule is used for sorting the first media information with the first preset quantity and the second media information with the second preset quantity based on the grading information in the attenuation information base and the heat degree grading to obtain a pushing sequence.
And the second pushing submodule is used for pushing the first media information with the first preset quantity and the second media information with the second preset quantity to the user terminal according to the pushing sequence.
Optionally, the information pushing apparatus 100 may further include:
and the first deleting module is used for deleting the target scoring information and the first media information and the category information corresponding to the target scoring information if the target scoring information smaller than the first preset scoring threshold exists in the attenuation information base.
Optionally, the information pushing apparatus 100 may further include:
and the judging module is used for attenuating the grading information in the attenuation information base based on the second attenuation proportion under the condition that the preset condition is reached.
And the second deleting module is used for deleting the target scoring information and the first media information and the category information corresponding to the target scoring information if the target scoring information smaller than the second preset scoring threshold exists in the attenuation information base.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 6 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, the electronic device 1900 may be provided as a server. Referring to fig. 6, an electronic device 1900 includes a processor 1922, which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processor 1922 may be configured to execute the computer program to perform the information push method described above.
Additionally, electronic device 1900 may also include a power component 1926 and a communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 1900. In addition, the electronic device 1900 may also include an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, stored in memory 1932TM，Mac OS XTM，UnixTM，LinuxTMAnd so on.
In another exemplary embodiment, a computer readable storage medium including program instructions, which when executed by a processor, implement the steps of the information pushing method described above, is also provided. For example, the non-transitory computer readable storage medium may be the memory 1932 that includes program instructions executable by the processor 1922 of the electronic device 1900 to perform the information pushing method described above.
In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable apparatus, the computer program having code portions for performing the information pushing method described above when executed by the programmable apparatus.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.

Claims (12)

1. An information pushing method, comprising:
acquiring first media information with the highest score in an initial information base, wherein the initial information base comprises a plurality of types of information, a plurality of first media information and a first mapping relation among a plurality of score information;
based on the first mapping relation, acquiring first media information with the highest grade in the initial information base and corresponding target category information;
determining a plurality of first media information corresponding to the target category information in the initial information base, and attenuating the scoring information of the first media information according to a first attenuation proportion to obtain an attenuation information base;
acquiring first media information with the highest grade in the attenuation information base;
and pushing media information to the user terminal, wherein the pushed media information at least comprises the acquired first media information.
2. The method of claim 1, wherein the pushing media information to the user terminal, the pushed media information including at least the first media information that has been acquired, comprises:
under the condition that the obtained first media information does not reach a first specified quantity, the attenuation information base is used as the initial information base again, and the steps from obtaining the target category information corresponding to the first media information with the highest score in the initial information base based on the mapping relation to obtaining the first media information with the highest score in the attenuation information base are repeatedly executed until the obtained first media information reaches the first specified quantity;
under the condition that the obtained first media information reaches the first specified quantity, sequencing the obtained first media information based on the grading information in the attenuation information base to obtain the pushing sequence;
and pushing the acquired first media information to the user terminal according to the pushing sequence.
3. The push method according to claim 1, wherein the pushing media information to the user terminal, the pushed media information including at least the acquired first media information, comprises:
acquiring a heat degree information base based on the current time, wherein the heat degree information base comprises a second mapping relation between a plurality of second media information and a plurality of heat degree scores;
acquiring one or more second media information in the popularity information base;
ordering the acquired first media information and the one or more second media information according to a preset ordering rule based on the heat degree scores and the score information in the attenuation information base to obtain the pushing sequence;
and pushing the acquired first media information and the one or more second media information to the user terminal according to the pushing sequence.
4. The push method according to claim 3, wherein ranking the obtained first media information and the one or more second media information according to a preset ranking rule based on the heat score and the score information in the attenuation information base to obtain the push order comprises:
ranking the acquired first media information based on scoring information in the attenuation information base;
and arranging the one or more second media information between first target information and second target information to obtain the pushing sequence, wherein the first target information is the first media information with the highest score in the initial information base, and the second target information is the first media information with the highest score in the attenuation information base.
5. The push method according to claim 1, wherein the pushing media information to the user terminal, the pushed media information including at least the acquired first media information, comprises:
acquiring a heat degree information base based on the current time, wherein the heat degree information base comprises mapping relations between a plurality of second media information and a plurality of heat degree scores;
acquiring one or more second media information as hot information based on the hot information base;
extracting a first preset number of pieces of first media information from the acquired first media information according to a preset extraction ratio, and extracting a second preset number of pieces of second media information from the hot information, wherein the sum of the first preset number and the second preset number is a second specified number;
sorting the first media information of the first preset quantity and the second media information of the second preset quantity based on the grading information and the heat grading in the attenuation information base to obtain the pushing sequence;
and pushing the first media information with the first preset quantity and the second media information with the second preset quantity to the user terminal according to the pushing sequence.
6. The push method of claim 2, further comprising:
and if the target scoring information smaller than a first preset scoring threshold exists in the attenuation information base, deleting the target scoring information, and the first media information and the category information corresponding to the target scoring information.
7. The push method of claim 1, further comprising:
attenuating the scoring information in the attenuation information base based on a second attenuation proportion under the condition that a preset condition is reached;
and if the target scoring information smaller than a second preset scoring threshold exists in the attenuation information base, deleting the target scoring information, and the first media information and the category information corresponding to the target scoring information.
8. The push method according to claim 1, wherein before the obtaining the first media information with the highest score in the initial information base, the method further comprises:
acquiring a plurality of pieces of first media information according to the user portrait, wherein the first media information comprises a plurality of pieces of quantity information and identification information corresponding to a plurality of pieces of dimension information;
obtaining scoring information corresponding to the plurality of first media information based on the plurality of quantity information corresponding to the plurality of dimension information;
and obtaining the initial information base based on the identification information and the grading information corresponding to the first media information.
9. The push method according to claim 8, wherein the obtaining the score information corresponding to the first media information based on the quantity information corresponding to the dimension information comprises:
acquiring a plurality of feature weights corresponding to the plurality of dimensional information;
and calculating the quantity information corresponding to the dimensions according to a preset algorithm based on the characteristic weights to obtain the grading information.
10. An information pushing apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first media information with the highest score in an initial information base, and the initial information base comprises a plurality of first category information, a plurality of first media information and a first mapping relation among the plurality of score information;
the second obtaining module is used for obtaining target category information corresponding to the first media information with the highest grade in the initial information base based on the first mapping relation;
a third obtaining module, configured to determine, in the initial information base, a plurality of pieces of first media information corresponding to the target category information, and attenuate score information of each of the plurality of pieces of first media information according to a first attenuation ratio to obtain an attenuation information base;
the fourth acquisition module is used for acquiring the first media information with the highest grade in the attenuation information base;
and the pushing module is used for pushing the media information to the user terminal, and the pushed media information at least comprises the acquired first media information.
11. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.
12. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 9.
CN202111284949.5A 2021-11-01 2021-11-01 Information pushing method, device, equipment and storage medium Active CN113918736B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111284949.5A CN113918736B (en) 2021-11-01 2021-11-01 Information pushing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111284949.5A CN113918736B (en) 2021-11-01 2021-11-01 Information pushing method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113918736A true CN113918736A (en) 2022-01-11
CN113918736B CN113918736B (en) 2024-09-13

Family

ID=79244888

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111284949.5A Active CN113918736B (en) 2021-11-01 2021-11-01 Information pushing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113918736B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114780842A (en) * 2022-04-20 2022-07-22 北京字跳网络技术有限公司 Data processing method, device, equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104090912A (en) * 2014-06-10 2014-10-08 腾讯科技（深圳）有限公司 Information pushing method and device
US20150294011A1 (en) * 2014-04-14 2015-10-15 Baidu Online Network Technology (Beijing) Co., Ltd Method and apparatus for providing recommended information
CN105260379A (en) * 2015-09-08 2016-01-20 百度在线网络技术（北京）有限公司 Information push method and device
CN109857923A (en) * 2019-02-01 2019-06-07 夏鲁宏 A kind of news intelligent recommendation method and system based on area media
CN111400603A (en) * 2020-03-20 2020-07-10 腾讯科技（深圳）有限公司 Information pushing method, device and equipment and computer readable storage medium
KR102227552B1 (en) * 2020-06-08 2021-03-15 주식회사 그로우키친 System for providing context awareness algorithm based restaurant sorting personalized service using review category
CN113177160A (en) * 2021-05-25 2021-07-27 上海众源网络有限公司 Pushed document generation method and device, electronic equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150294011A1 (en) * 2014-04-14 2015-10-15 Baidu Online Network Technology (Beijing) Co., Ltd Method and apparatus for providing recommended information
CN104090912A (en) * 2014-06-10 2014-10-08 腾讯科技（深圳）有限公司 Information pushing method and device
CN105260379A (en) * 2015-09-08 2016-01-20 百度在线网络技术（北京）有限公司 Information push method and device
CN109857923A (en) * 2019-02-01 2019-06-07 夏鲁宏 A kind of news intelligent recommendation method and system based on area media
CN111400603A (en) * 2020-03-20 2020-07-10 腾讯科技（深圳）有限公司 Information pushing method, device and equipment and computer readable storage medium
KR102227552B1 (en) * 2020-06-08 2021-03-15 주식회사 그로우키친 System for providing context awareness algorithm based restaurant sorting personalized service using review category
CN113177160A (en) * 2021-05-25 2021-07-27 上海众源网络有限公司 Pushed document generation method and device, electronic equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张瑞典;: "基于信任关系和时间衰减效应的协同过滤推荐算法", 东莞理工学院学报, no. 03, 22 June 2020 (2020-06-22) *
黄成;: "基于用户动机的微博客信息流个性化推荐模型构建", 情报杂志, no. 11, 18 November 2013 (2013-11-18) *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114780842A (en) * 2022-04-20 2022-07-22 北京字跳网络技术有限公司 Data processing method, device, equipment and storage medium
CN114780842B (en) * 2022-04-20 2022-12-13 北京字跳网络技术有限公司 Data processing method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN113918736B (en) 2024-09-13

Similar Documents

Publication Publication Date Title
CN106528813B (en) A kind of multimedia recommendation method and device
CN107273489B (en) Content delivery method, electronic equipment and computer storage medium
KR101792587B1 (en) Method and apparatus of predicting preference rating for contents, and method and apparatus for selecting sample contents
CN106686063A (en) Information recommendation method and apparatus, and electronic device
US9978093B2 (en) Method and system for pushing mobile application
CN103886090B (en) Content recommendation method and device based on user preferences
CN108763519A (en) The recommendation method, apparatus and readable storage medium storing program for executing of reading
CN104504149A (en) Application recommendation method and device
CN107835520B (en) Wifi hotspot connection method and device and storage medium
RU2010117390A (en) SYSTEMS, APPARATUS AND METHODS FOR MAKING RECOMMENDATIONS
CN109241451B (en) Content combination recommendation method and device and readable storage medium
CN106446186A (en) Associative word searching method and device and terminal
CN112423134B (en) Video content recommendation method and device, computer equipment and storage medium
CN113918736A (en) Information pushing method, device, equipment and storage medium
CN106777201B (en) Method and device for sorting recommended data on search result page
CN111241400A (en) Information searching method and device
CN105589873B (en) Data searching method, terminal and server
CN117708418A (en) Application recommendation method, device, computer equipment and storage medium
CN116628338A (en) Mobile terminal product recommendation method, system, computer and readable storage medium
JP7392271B2 (en) Item presentation method, item presentation program, and item presentation device
CN109474832B (en) Information searching and sorting method, intelligent terminal and storage medium
CN104636366B (en) Method and device for acquiring search result queue
US20170017999A1 (en) Information processing device, information processing method, and information processing program
CN113434775B (en) Method and device for determining search content
CN112148941B (en) Information prompting method, device and terminal equipment

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
TA01 Transfer of patent application right

Effective date of registration: 20230801

Address after: 224008 Rooms 404-405 and 504, Building B-17-1, Big data Industrial Park, Kecheng Street, Yannan High tech Zone, Yancheng, Jiangsu Province

Applicant after: Yancheng Tianyanchawei Technology Co.,Ltd.

Address before: 224008 room 501-503, building b-17-1, Xuehai road big data Industrial Park, Kecheng street, Yannan high tech Zone, Yancheng City, Jiangsu Province (CNK)

Applicant before: Yancheng Jindi Technology Co.,Ltd.

GR01 Patent grant
GR01 Patent grant