CN114116822A - Information push method, terminal and storage medium - Google Patents
Information push method, terminal and storage medium Download PDFInfo
- Publication number
- CN114116822A CN114116822A CN202111430897.8A CN202111430897A CN114116822A CN 114116822 A CN114116822 A CN 114116822A CN 202111430897 A CN202111430897 A CN 202111430897A CN 114116822 A CN114116822 A CN 114116822A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- reading
- target user
- user
- 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.)
- Pending
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to an information pushing method, a terminal and a storage medium. The method comprises the following steps: determining the type of a target user to which the target user belongs based on the reading behavior data of the target user; determining a target push strategy corresponding to the type of a target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style; and pushing information to the target user based on the target pushing strategy. According to the embodiment of the invention, the information is more personalized to be pushed to the user, so that the pushed information is more in line with the user requirement, the click through rate of the pushed information is improved, the use experience of the user on the application program is improved, and the retention rate of the user is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an information pushing method, a terminal, and a storage medium.
Background
During the use of the application by the user, the application may push information to the user, such as advertisements, offer profiles, feature profiles, and the like.
However, the number of users using the same application program is large, and each user has different requirements for pushing information. If the information is pushed to each user according to the same rule, the click through rate of the pushed information is influenced, interference is caused to some users, the application program using experience of the users is reduced, and even the users are lost.
Disclosure of Invention
In order to solve the technical problems that the personalized degree of information push is low, the click through rate of the pushed information is low, and the user retention rate is reduced, the invention provides an information push method, a terminal and a storage medium.
In a first aspect, the present invention provides an information pushing method, including:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
In a second aspect, the present invention provides a terminal, comprising:
a processor and a memory to store executable instructions that cause the processor to:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
In a third aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program causes the processor to implement the information pushing method described in the first aspect.
According to the information pushing method, the terminal and the storage medium, the type of the target user to which the target user belongs can be determined according to the reading behavior data of the target user in the information pushing process, the target pushing strategy corresponding to the type of the target user is determined from a plurality of preset pushing strategies, and then information is pushed to the target user according to the target pushing strategy, so that the information is pushed to the user more individually, the pushed information is made to be more in fit with the user requirements, the click through rate of the pushed information is improved, the use experience of the user on an application program is improved, and further the user retention rate is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present invention will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
Fig. 1 is a flowchart of an information pushing method according to an embodiment of the present invention;
fig. 2 is a flowchart of another information pushing method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and the embodiments of the present invention are illustrative only and are not intended to limit the scope of the present invention.
It should be understood that the various steps recited in the method embodiments of the present invention may be performed in a different order and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the invention is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present invention are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in the present invention are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that reference to "one or more" unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present invention are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Many existing reading applications (i.e., applications that provide online book reading) provide functionality for pushing information to users, such as advertisements, profiles of new online functions, profile of offers, and so forth. At present, the rule for pushing information to a user by a reading application program is mainly to determine the pushing frequency of the information according to the type of a book read by the user, and then push the information to all users reading the book type according to the pushing frequency. However, the degree of demand for push information is different for each user. The push frequency determined according to the scheme not only influences the click through rate of the push information, but also causes interference to some users, reduces the use experience of the users, and even causes user loss.
Based on the above situation, embodiments of the present invention provide an information push method, a terminal, and a storage medium, so as to implement dividing user types according to reading behavior data of a user, matching a suitable target push policy for the user type from a plurality of preset push policies, and then pushing information to the user according to the target push policy, thereby improving personalization degree of information push, and thus improving click through rate and user retention rate of information.
The information pushing method provided by the embodiment of the invention is mainly suitable for scenes that various application programs push information to users. For example, it may be applied to reading-class applications to push advertisements, offer profiles, etc. to users; the method can also be applied to E-commerce application programs for pushing commodity information, store information and the like to users; but also to search-class applications that push search results to the user, and so on. In the embodiment of the present invention, information pushing of the reading application is taken as an example for description.
The information pushing method provided by the embodiment of the invention can be executed by an information pushing device, the device can be realized by software and/or hardware, and the device can be integrated in electronic equipment capable of providing certain computing capability. The electronic device may include, but is not limited to, a device such as a laptop computer, a desktop computer, a server or server cluster, or the like.
Fig. 1 shows a flowchart of an information pushing method provided by an embodiment of the present invention. Referring to fig. 1, the information push method specifically includes:
s110, determining the type of the target user to which the target user belongs based on the reading behavior data of the target user.
The target user refers to a user to be pushed. The reading behavior data refers to behavior data in the process that the user uses the application program to read the related content. For example, the reading behavior data may be various behavior data in the process that the target user reads a book through the reading application program. The behavior data may be, for example, an interactive behavior for pushing information, a reading behavior for a book, an interactive behavior for a function provided by an application, or the like. The target user type refers to a user type to which the target user belongs. The user types are different user categories divided according to different requirements of users on various push information.
Specifically, in consideration of different requirements of each user for different pieces of push information, in the embodiment of the present invention, multiple user types are preset, and different user types correspond to different information push requirements. In addition, considering that the behavior data of the user can reflect the degree of the requirement of the user on different push information, the embodiment of the invention defines the division basis of each user type by the reading behavior data authorized by the user. Therefore, after the reading behavior data of the target user is obtained, the electronic equipment can compare and analyze the reading behavior data and the division basis corresponding to each user type, so as to determine which user type the target user belongs to, namely determine the target user type the target user belongs to.
In some embodiments, the push information is an advertisement, the application program is a reading-type application program, and the data items of the reading behavior data may include activation duration, advertisement push-free permission, reading duration, reading quantity, online frequency, and interaction data.
In the above embodiment, the activation duration refers to a duration for the user to register and activate the reading application. The advertisement push-free permission refers to the permission not to push the advertisement. The reading duration refers to the duration of reading books by a user, and can be the average daily reading duration, namely the ratio of the cumulative daily reading duration to the reading days with reading records in the statistical period; it may also be the total reading accumulated time length, that is, the total of the cumulative reading time lengths of the days in the statistical period when the user reads the book. The reading number refers to the total number of books which are read by the user and exceed a certain chapter number, and is used for representing the reading quality of the user. The online frequency is a rating of the user logging in the reading application program, and is used for reflecting the activity of the user, and may include, for example, a date of last logging in the reading application program, a number of days of logging in the reading application program in a statistical period, and the like. The interactive data refers to data generated by a user performing interactive operation in the process of using the reading application program. The interactive data may include at least one of a right acquisition number, an advertisement closing number, a function triggering number, a resource acquisition number, and a resource extraction number. The number of times of acquiring the permission refers to the number of times of executing, by the user, acquiring the advertisement push-free permission, for example, the number of times of clicking a control for opening the advertisement push-free permission. The function triggering times refer to times of triggering the chapter/book downloading function, the book listening function, and the like provided in the reading application program by the user. The resource acquisition times refer to the times that the user triggers the related control to acquire the resource. The resources may be, for example, virtual articles such as coins, chapters, books, and the like. The resource withdrawal count refers to the number of operations for converting a virtual item into an actual currency withdrawal.
It should be noted that, each data item of the reading behavior data is only a statistical index, and a specific statistical behavior of the reading behavior data may be determined according to a control setting of an application program, which is not limited in the embodiment of the present invention.
On the basis of the data items of the reading behavior data, the user types in the embodiment of the present invention may include a new user type, a resource preference type, a permission preference type, a function preference type, an advertisement preference type, and an advertisement blocking type. The new user type refers to a user type that newly registers and activates an application. The resource preference type refers to a user type that the user prefers to acquire virtual transaction currencies such as gold coins, books and the like. The permission preference type refers to a user type that the user prefers to acquire the advertisement push-free permission. The function preference type refers to a user type that a user prefers to acquire and use some unique functions provided by an application. The advertisement preference type refers to a type of user that the user does not exclude any pushed advertisements. The advertisement blocking type refers to a type of user that the user dislikes/dislikes the pushed advertisement.
Based on the above embodiments, the statistical behavior corresponding to each data item in the reading behavior data is embodied, and the user type division basis shown in table 1 can be obtained:
TABLE 1 subscriber types and their basis for division
On the basis of the above embodiments, S110 may be implemented as: and acquiring reading behavior data of the target user, and splitting each data item in the reading behavior data according to the statistical data item corresponding to each user type in the table 1. Then, according to preset rules of user classification (such as the matching number of data items, the matching degree of numerical values of the data items and the like), the score of the reading behavior data of the target user close to each user type is calculated. And finally, classifying the target user into the closest user type according to the score corresponding to each user type of the branch office, namely determining the target user type.
In some embodiments, S110 may be implemented as: weighting each data item in the reading behavior data to obtain a behavior data value; and determining the target user type from the user types based on the behavior data value and the behavior data value range corresponding to each user type.
Wherein, the behavior data value refers to the calculated score of each data item of the target user. The behavior data value range is a numerical range formed by the upper limit and the lower limit of the behavior data value corresponding to the user type, and is used for defining each user type.
Specifically, for each user type, the electronic device performs weighted calculation on values of data items in the reading behavior data of the target user corresponding to the user type to obtain a behavior data value of the target user corresponding to the user type. The electronic device then compares the behavior data value to a range of behavior data values for the user type. If the behavior data value falls within the behavior data value range, determining that the target user is assigned to the user type. If the behavior data value does not fall within the behavior data value range, it is determined that the target user does not belong to the user type. According to the above process, the type of the target user to which the target user belongs can be determined. Therefore, the importance degree of each data item in the user type can be flexibly adjusted through setting the weight, so that the user type to which the target user belongs is adjusted, and further, the preset pushing strategy for pushing information to the target user is adjusted through subsequent steps. In addition, the target user type can be quantitatively determined through simple calculation, and the fineness and the accuracy of user type division are improved.
In some embodiments, when the preset instruction is detected, the step of determining the target user type to which the target user belongs based on the reading behavior data of the target user is executed again to update the target user type of the target user.
The preset instruction is an instruction generated when a preset event is triggered, and may be, for example, an instruction generated when a timer arrives, an instruction issued upstream, or an instruction generated by an operation and maintenance worker performing a certain triggering operation. The preset instruction is used for triggering execution of user type updating.
Specifically, in the process of reading a book by using a reading application program, the target user may have a change in the degree of demand for pushing information. Therefore, in order to further improve the accuracy of the pushed information and ensure the click through rate and the user retention rate of the pushed information, the type of the target user to which the target user belongs needs to be updated in the embodiment of the present invention. In specific implementation, when the electronic device detects the preset instruction, the electronic device re-executes S110 to re-determine the type of the target user.
S120, determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies.
The preset push strategy is a preset push information strategy. Illustratively, the preset push policy includes at least one of an information type, an information push frequency, an information display position, and an information display style. The information type here refers to the kind of push information. In an example, the information type may be classified into a hot blood type advertisement, a speech type advertisement, a science popularization type advertisement, and the like according to the content of the information. In another example, the information type can be further divided into a comprehensive advertisement, a resource preference advertisement, a permission preference advertisement and a function preference advertisement according to feedback content after viewing the information. The resource preference type advertisement refers to the advertisement type of feedback resources (gold coins, books and the like) after being viewed. The permission preference type advertisement refers to an advertisement type which feeds back the advertisement without push permission after being checked. The function preference type advertisement refers to an advertisement type for feeding back some functions of the free use application program after viewing. The comprehensive advertisement refers to an advertisement type that the feedback content after being viewed contains at least one of resources, authorities and functions. The information display position refers to a position where push information is displayed, and is also called an advertisement space. The information display style refers to a style of information display, such as a small button style, a large button style, a dynamic floating style, and the like. The electronic device/operation and maintenance personnel can generate different preset push strategies by adjusting at least one of the information type, the information push frequency, the information display position and the information display style.
Specifically, a plurality of preset push policies are preset in the electronic device, and each preset push policy corresponds to one user type, that is, a mapping relationship between the user type and the preset push policy is maintained in the electronic device. Then, after determining the type of the target user, the electronic device may query the mapping relationship, so as to obtain a target push policy adapted to the target user.
For the embodiment shown in table 1, the preset push policy corresponding to each user type may be generated by adjusting at least one of the information type, the information push frequency, the information display position, and the information display style, as shown in table 2.
In table 2, the information push frequencies are expressed by the 1 st to 5 th gears, the 1 st gear corresponds to the lowest information push frequency, the 5 th gear corresponds to the highest information push frequency, and the 3 rd gear is the average information push frequency.
S130, pushing information to the target user based on the target pushing strategy.
Specifically, the electronic device pushes information to the target user according to the target pushing strategy. For example, the electronic device pushes information belonging to a target information type in the target push policy to a target user according to a target information push frequency in the target push policy, and instructs the client to display the pushed information in an information display style at an information display position in the target push policy.
According to the information pushing method of each embodiment, in the information pushing process, the target user type to which the target user belongs can be determined according to the reading behavior data of the target user, the target pushing strategy corresponding to the target user type is determined from a plurality of preset pushing strategies, and then information is pushed to the target user according to the target pushing strategy, so that information is pushed to the user more individually, the pushed information is made to be more in line with the user requirements, the click through rate of the pushed information is improved, the use experience of the user on the application program is improved, and further the user retention rate is improved.
In some embodiments, S110 may be implemented as: and if the target user is determined to belong to at least two candidate user types based on the reading behavior data of the target user, determining the type of the target user based on the information push frequency corresponding to each candidate user type.
The candidate user type refers to a user type to which the target user belongs, which is determined preliminarily. The information push frequency is the frequency at which information is pushed to the user.
Specifically, according to the above description, the purpose of dividing the user type in the embodiment of the present invention is to more personally and finely push appropriate information to the user, that is, to determine a target push policy. And when the candidate user types to which the target user belongs are determined according to the user classification process and the number of the candidate user types is greater than or equal to 2, indicating that the target user can belong to at least two user types simultaneously. Then, when the preset push policies corresponding to the candidate user types are inconsistent, an information push error is easily caused.
In one case, in order to avoid an information pushing error and improve the exposure rate and the click through rate of the pushed information on the basis that the pushing strategy includes the information pushing frequency, the electronic device may compare the information pushing frequencies corresponding to the candidate user types, determine the highest information pushing frequency from the information pushing frequencies, and determine the candidate user type corresponding to the highest information pushing frequency as the target user type.
In another case, to avoid information push errors and balance the user retention rate and the click through rate of the pushed information, the electronic device may select a median or a mode of the information push frequency corresponding to each candidate user type, and determine the candidate user type corresponding to the selected information push frequency as the target user type.
In another case, to avoid an information push error, the electronic device may further randomly determine one candidate user type from the candidate user types as the target user type.
Fig. 2 is a flowchart illustrating another information pushing method according to an embodiment of the present invention. On the basis of the above embodiments, the information push method adds a related step of dynamically adjusting the information push frequency. As shown in fig. 2, the information push method specifically includes:
s210, determining the type of the target user to which the target user belongs based on the reading behavior data of the target user.
S220, determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies.
And S230, adjusting the target information push frequency in the target push strategy based on the reading event information.
The reading event information is related information reflecting a certain reading event, and may be, for example, occurrence time of the reading event (i.e., a reading period), related information of a subject of the reading event (i.e., a target user), related information of an object of the reading event (i.e., a reading chapter currently being read), and the like. Illustratively, the reading event information contains at least one of an attrition probability, a reading chapter attribute, and a reading period of the target user. The churn probability here refers to the probability that a user may churn in a certain future period. The reading chapter attribute refers to chapter information of the reading chapter, which reflects popularity or importance of the reading chapter (i.e., chapter content heat), attribute of chapter content (length, content type), and the like.
Specifically, the determined target push policy is a preset push policy corresponding to a type of a target user, and in order to further improve the personalization degree of information push, the target information push frequency in the target push policy may be adjusted according to a situation and a reading situation of a single user after the target push policy is determined, so as to determine the information push frequency more suitable for the target user. In specific implementation, the electronic device acquires reading event information corresponding to a target user, and then dynamically adjusts the target information pushing frequency according to at least one of the loss probability of the target user, the reading chapter attribute and the reading time period in the reading event information.
The adjustment of the target information pushing frequency can be realized by adjusting the number of information display positions, for example, by increasing or decreasing the number of advertisement slots in table 2; the method can also be realized by adjusting the information display density/frequency at certain information display positions, for example, adjusting the target information pushing frequency by prolonging or shortening the inter-cut page interval of the inter-cut page advertisement, adjusting the target information pushing frequency by increasing or decreasing the number of times of reading page welfare popup windows, the display number of times of inter-cut screen advertisements and the like, adjusting the target information pushing frequency by advancing or delaying the start chapter marks of the advertisements displayed by the advertisement positions such as inter-cut pages, reading prompt pages, bottom banner controls and the like, and adjusting the target information pushing frequency by increasing or decreasing the number of advertisements in full-screen advertisements of inter-cut pages, advertisement styles and the like; the target information pushing frequency can be adjusted through other indexes influencing advertisement clicking, for example, the delayed sliding time of page turning delay, the effective probability of a wrong point area, the number of times of advertisement mistaken clicking, the probability of sliding mistaken touching, the interval duration of sliding mistaken touching, the number of times of effective clicking of sliding mistaken touching and the like.
It should be further noted that, in addition to dynamically adjusting the target information pushing frequency, the electronic device may also dynamically adjust the content information type in the target pushing policy according to the book type read by the target user. That is, after determining that the target information type is an integrated advertisement, a resource preference advertisement, a rights preference advertisement or a function preference advertisement, further determining that the content information type divided according to the content of the information is a hot blood advertisement or a speech advertisement according to the book type in the target information type, and determining the target information type + the content information type as the information type to be pushed to the target user. Thus, the personalization degree of the pushed information can be further improved.
In some embodiments, in the case that the reading event information is the attrition probability, S230 may be implemented as:
s231, determining the loss probability of the target user based on the historical behavior data of the target user.
The historical behavior data refers to behavior data authorized by a target user and obtained before the current moment. Illustratively, the historical behavior data includes historical chapter dwell time, historical content interaction data, and historical login frequency for the target user. The historical chapter dwell time here refers to the dwell time of the target user reading the chapter during the historical period of time prior to the current time. The historical content interaction data refers to interaction data of the target user on the reading chapter in a historical time period, and may be, for example, the historical praise number, the historical comment number, the historical sharing number, and the like. The historical login frequency refers to the frequency with which the target user logs in to the application program within a historical period of time, and may be characterized by a login interval, for example.
Specifically, the electronic device obtains historical behavior data authorized by a target user within a historical time period. The historical behavior data is then analyzed to determine the attrition probability of the target user.
In an example, behavior data of a plurality of users and churn data of corresponding users may be obtained in advance, and the behavior data and the churn data corresponding to the behavior data may be used as training data to train a machine learning model, so as to obtain a model capable of predicting churn probability according to the behavior data of the users. And then, inputting the historical behavior data into the trained model, and outputting the loss probability of the target user through model operation.
In another example, each item of historical behavior data may be analyzed to obtain the attrition probability of the target user. For example, the longer the historical chapter stays, the greater the churn probability of the target user, indicating that the target user is likely to no longer use the application to read the book; the more the historical content interaction data is, the more frequent the interaction of the target user on the reading section is, and the smaller the loss probability of the target user is; the lower the historical login frequency, the longer the login interval, which means that the frequency of using the application program by the user is lower and lower, the greater the churn probability of the target user. The electronic device can perform weighting processing on the value of each data item according to the preset weight of each item, and the obtained result is the loss probability of the target user.
S232, target information pushing frequency in the target pushing strategy is adjusted based on the loss probability.
Specifically, if the churn probability of the target user is high, the electronic device reduces the target information push frequency to reduce information push to the target user, and reduces interference of the push information to the user, so that the user can reserve the target information. If the loss probability of the target user is smaller, the electronic equipment improves the target information pushing frequency so as to increase the information pushing for the target user, and the exposure rate and the click through rate of the pushed information are improved more on the basis of ensuring the retention of the user.
Illustratively, S232 may be implemented as: if the loss probability is greater than the first probability threshold, reducing the target information pushing frequency; and if the loss probability is smaller than a second probability threshold, increasing the target information pushing frequency.
The first probability threshold and the second probability threshold are preset probability critical values. The first probability threshold is greater than or equal to the second probability threshold.
Specifically, the attrition probability of the target user is compared with a first probability threshold and a second probability threshold, respectively, in the electronic device. If the churn probability is higher than the first probability threshold, it indicates that the target user is likely to churn, and the target information push frequency is decreased. If the churn probability is lower than the second probability threshold, it indicates that the target user has a low possibility of future churn, and the target information push frequency can be increased.
According to the embodiment of the churn probability, the corresponding target information push frequency can be dynamically adjusted according to the churn probability of a single user, so that the retention rate of the user is further improved.
In other embodiments, in the case that the reading event information is the reading chapter attribute, S230 may be implemented as:
and S233, determining the chapter content popularity of the reading chapter based on the chapter information of the reading chapter.
The chapter information comprises at least one of chapter loss rate, chapter reading duration, chapter reading number, chapter downloading amount, chapter interaction data and chapter importance identification. The chapter churn rate is used for representing the user condition of churn of the reading chapters, and can be represented by the ratio of the number of users corresponding to the reading chapters to the number of users corresponding to the book in the historical time period. The chapter reading duration is the average time used by each user to read the chapter in the historical time period. The reading number of chapters refers to the number of users corresponding to the reading chapters. The chapter interaction data refers to data of interaction operations such as clicking, praise, commenting and sharing on the reading chapter by each user. The chapter importance mark is identification information representing the importance of reading chapters in the book, and may be obtained by, for example, an expert/operation and maintenance person labeling the importance of each chapter in advance.
Specifically, the electronic equipment acquires chapter information of reading chapters and determines the content popularity of the chapters according to the chapter information. For example, the electronic device obtains a chapter churn rate of a reading chapter, and determines that the chapter churn rate is high, which indicates that many users churn at the reading chapter, so that it can be determined that the chapter content of the reading chapter is low in popularity. The electronic equipment obtains the reading time of the chapters and sections, judges that the reading time of the chapters and sections is short, and indicates that the reading chapters can be quickly read by a user, so that the content popularity of the chapters and sections can be determined to be high. The electronic device obtains the mark that the reading number of the chapters of the reading chapters is large (or the downloading amount of the chapters is large, or the interaction data of the chapters is large, or the importance mark of the chapters is important), and the popularity of the reading chapters is high or important, so that the content popularity of the reading chapters can be determined to be high.
In addition, the electronic device can determine the chapter content heat of the reading chapter according to values of at least two items of chapter loss rate, chapter reading time, chapter reading number, chapter downloading amount, chapter interaction data and chapter importance identification. For example, the smaller the chapter run-off rate, the shorter the chapter reading duration, the greater the number of chapter readers, the greater the chapter download amount, the greater the chapter interaction data, and the more the chapter importance identifier is biased toward the important identifier, the greater the chapter content popularity.
And S234, adjusting the target information pushing frequency based on the chapter content heat of the reading chapter corresponding to the target user.
Specifically, if the content of reading chapters is hot, the electronic device increases the target information pushing frequency to increase information pushing for the target user, and on the basis of ensuring user retention, the exposure rate and click through rate of the pushed information are increased more. If the content of reading chapters is low in popularity, the electronic equipment reduces the target information pushing frequency so as to reduce information pushing on a target user and reduce interference of pushing information on the user, and the user is expected to keep the information.
Illustratively, S234 may be implemented as: if the content heat of the chapters is larger than a first heat threshold, increasing the target information pushing frequency; and if the chapter content heat is smaller than a second heat threshold, reducing the target information pushing frequency.
The first heat threshold and the second heat threshold are both preset critical values of the heat of the chapter content. The first heat threshold is greater than or equal to the second heat threshold.
Specifically, the chapter content heat of the reading chapters which are being read by the target user is compared with a first heat threshold and a second heat threshold respectively in the electronic device. If the chapter content popularity of the reading chapter is higher than the first popularity threshold, the reading chapter is very popular with the target user, and even if the pushed information is more displayed in the reading chapter, the target user cannot easily run away, so that the electronic device can improve the target information pushing frequency. If the content popularity of the reading section is lower than the second popularity threshold, which indicates that the attraction of the reading section to the target user is not high enough, and if the pushed information is displayed too much in the reading section, the target user is likely to run away due to the interference of the pushed information, then the electronic device may reduce the target information pushing frequency.
According to the embodiment of the chapter content popularity of the reading chapters, the target information pushing frequency of one type of users of the target user type can be dynamically adjusted according to the chapter information of the reading chapters, the effects of the same user, different reading chapters and different target information pushing frequencies are achieved, the personalization degree of information pushing is further improved, and therefore the click through rate and the user retention rate of the pushed information are further improved.
In still other embodiments, in the case that the reading event information is a reading period, S230 may be implemented as:
and S235, if the reading time interval is the idle time interval, increasing the target information pushing frequency.
Specifically, which periods are idle periods and which periods are busy periods are predefined in the electronic device. When the electronic device obtains the reading time period corresponding to the target user, the reading time period can be judged to belong to the idle time period or the busy time period according to the definition of the idle time period and the busy time period. If the reading time period belongs to the idle time period, it indicates that the target user may have time to view the push information in the reading time period, and at this time, the electronic device may increase the frequency of pushing the target information.
And S236, if the reading time interval is a busy time interval, reducing the target information pushing frequency.
Specifically, if the electronic device determines that the reading period belongs to a busy period, which indicates that the target user may not have more time to view the pushed information in the reading period, the electronic device may decrease the frequency of pushing the target information at this time. Therefore, the information can be pushed in a customized manner according to the reading time period of the target user, and the personalization degree of information pushing is further improved, so that the click through rate and the user retention rate of the pushed information are further improved.
In still other embodiments, the electronic device may dynamically adjust the target information pushing frequency according to two or three of the churn probability, reading chapter attributes, and reading period of the target user. For example, the smaller the churn probability of the target user, the higher the content heat of reading chapters and the higher the reading period is the idle period, the larger the target information push frequency can be set, that is, the target information push frequency can be increased by the electronic device, so that the pushed information amount is increased under the condition of ensuring the user retention rate, and the information click through rate is further increased. On the contrary, the larger the loss probability of the target user is, the lower the chapter content heat of reading chapters is, and the busy reading time period is, the smaller the target information push frequency can be set, that is, the target information push frequency can be reduced by the electronic device, so as to further improve the user retention rate.
And S240, pushing information to the target user based on the target pushing strategy.
The information push method of each embodiment can adjust the target information push frequency in the target push strategy based on the reading event information including at least one of the loss probability, the reading chapter attribute and the reading time period of the target user after determining the target push strategy, and further realize dynamic adjustment of the target information push frequency to determine the information push frequency more adaptive to the target user, thereby further improving the personalization degree of information push and further ensuring the click through rate and the user retention rate of the push information.
Fig. 3 shows a schematic structural diagram of a terminal according to an embodiment of the present invention. The terminal 300 in the embodiment of the present invention may be the electronic device described above. It should be further noted that the terminal 300 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments of the present invention.
The terminal 300 conventionally includes a processor 310 and a computer program product or computer readable medium in the form of a memory 320. The memory 320 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 320 has a storage space 321 for executable instructions (or program code) 3211 for performing any of the method steps in the information push method described above. For example, the storage space 321 for executable instructions may include respective executable instructions 3211 for implementing various steps in the above information push method, respectively. The executable instructions may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such computer program products are typically portable or fixed storage units. The storage unit may have a storage section or a storage space or the like arranged similarly to the memory 320 in the terminal of fig. 3. The executable instructions may be compressed, for example, in a suitable form. Typically, the storage unit comprises executable instructions for performing the steps of the information push method according to the invention, i.e. code that can be read by a processor, such as the processor 310, for example, and which, when run by the terminal, causes the terminal to perform the steps of the information push method described above.
Of course, for the sake of simplicity, only some of the components of the terminal 300 related to the present invention are shown in fig. 3, and components such as a bus, input/output interfaces, input devices, and output devices, etc. are omitted. In addition, terminal 300 may include any other suitable components depending on the particular application.
Embodiments of the present invention further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the information pushing method provided in the embodiments of the present invention.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable medium may be embodied in the terminal; or may exist separately and not be assembled into the terminal.
In an embodiment of the present invention, program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The invention discloses:
A1. an information pushing method, comprising:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
A2. The method of a1, wherein, in a case that the information push frequency is included in the target push policy, after the determining a target push policy based on the target user type, the method further comprises:
adjusting the target information pushing frequency in the target pushing strategy based on the reading event information; wherein the reading event information comprises at least one of the attrition probability, reading chapter attribute and reading time period of the target user.
A3. The method according to a2, wherein, in a case that the reading event information is the churn probability, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information includes:
determining the attrition probability of the target user based on the historical behavior data of the target user; the historical behavior data comprises the historical chapter dwell time, the historical content interaction data and the historical login frequency of the target user;
and adjusting the target information pushing frequency in the target pushing strategy based on the attrition probability.
A4. The method according to a3, wherein the adjusting a target information push frequency in the target push policy based on the churn probability comprises:
if the churn probability is greater than a first probability threshold, reducing the target information push frequency;
and if the loss probability is smaller than a second probability threshold, increasing the target information pushing frequency.
A5. The method according to a2, wherein, in a case that the reading event information is the reading chapter attribute, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information includes:
determining chapter content popularity of the reading chapters based on the chapter information of the reading chapters; the chapter information comprises at least one of chapter loss rate, chapter reading time, chapter reading number, chapter downloading amount, chapter interaction data and chapter importance identification;
and adjusting the target information pushing frequency based on the chapter content heat of the reading chapter corresponding to the target user.
A6. The method according to a5, wherein the adjusting the target information pushing frequency based on the chapter content heat of the reading chapter corresponding to the target user comprises:
if the content heat of the chapters is larger than a first heat threshold, increasing the target information pushing frequency;
and if the content heat of the chapters is smaller than a second heat threshold, reducing the target information pushing frequency.
A7. The method according to a2, wherein, in the case that the reading event information is the reading period, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information includes:
if the reading time interval is an idle time interval, increasing the target information pushing frequency;
and if the reading time interval is a busy time interval, reducing the target information pushing frequency.
A8. The method of any one of A1-A7, wherein the determining, based on reading behavior data of a target user, a type of target user to which the target user belongs comprises:
and if the target user is determined to belong to at least two candidate user types based on the reading behavior data of the target user, determining the target user type based on the information push frequency corresponding to each candidate user type.
A9. The method of a1, wherein the method further comprises:
and when a preset instruction is detected, re-executing the reading behavior data based on the target user, and determining the target user type to which the target user belongs so as to update the target user type of the target user.
A10. The method of any one of A1-A9, wherein the determining, based on reading behavior data of a target user, a type of target user to which the target user belongs comprises:
weighting each data item in the reading behavior data to obtain a behavior data value;
and determining the target user type from the user types based on the behavior data values and the corresponding behavior data value range of each user type.
A11. The method according to a10, wherein each data item of the reading behavior data comprises activation duration, advertisement push-free permission, reading duration, reading quantity, online frequency and interaction data; the interactive data comprises at least one of authority acquisition times, advertisement closing times, function triggering times, resource acquisition times and resource extraction times;
the user types comprise a new user type, a resource preference type, a permission preference type, a function preference type, an advertisement preference type and an advertisement shielding type;
the information types comprise comprehensive advertisements, resource preference advertisements, permission preference advertisements and function preference advertisements.
B12. A terminal, comprising: a processor and a memory to store executable instructions that cause the processor to:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
B13. The terminal of B12, wherein, in a case that the information push frequency is included in the target push policy, after the processor performs the determining a target push policy based on the target user type, the executable instructions further cause the processor to:
adjusting the target information pushing frequency in the target pushing strategy based on the reading event information; wherein the reading event information comprises at least one of the attrition probability, reading chapter attribute and reading time period of the target user.
B14. The terminal of B13, wherein, when the processor executes the adjusting of the target information push frequency in the target push policy based on the reading event information when the reading event information is the churn probability, the executable instructions specifically cause the processor to:
determining the attrition probability of the target user based on the historical behavior data of the target user; the historical behavior data comprises the historical chapter dwell time, the historical content interaction data and the historical login frequency of the target user;
and adjusting the target information pushing frequency in the target pushing strategy based on the attrition probability.
B15. The terminal of B14, wherein the executable instructions, when the processor executes the adjusting of the target information push frequency in the target push policy based on the churn probability, specifically cause the processor to:
if the churn probability is greater than a first probability threshold, reducing the target information push frequency;
and if the loss probability is smaller than a second probability threshold, increasing the target information pushing frequency.
B16. The terminal of B13, wherein, when the processor executes the adjusting of the target information pushing frequency in the target pushing policy based on the reading event information when the reading event information is the reading chapter attribute, the executable instructions specifically cause the processor to:
determining chapter content popularity of the reading chapters based on the chapter information of the reading chapters; the chapter information comprises at least one of chapter loss rate, chapter reading time, chapter reading number, chapter downloading amount, chapter interaction data and chapter importance identification;
and adjusting the target information pushing frequency based on the chapter content heat of the reading chapter corresponding to the target user.
B17. The terminal of B16, wherein, when the processor executes the adjusting of the target information push frequency based on the chapter content heat of the reading chapter corresponding to the target user, the executable instructions specifically cause the processor to:
if the content heat of the chapters is larger than a first heat threshold, increasing the target information pushing frequency;
and if the content heat of the chapters is smaller than a second heat threshold, reducing the target information pushing frequency.
B18. The terminal of B13, wherein, when the processor performs the adjusting of the target information pushing frequency in the target pushing policy based on the reading event information when the reading event information is the reading period, the executable instructions specifically cause the processor to:
if the reading time interval is an idle time interval, increasing the target information pushing frequency;
and if the reading time interval is a busy time interval, reducing the target information pushing frequency.
B19. The terminal of any one of B12-B18, wherein the executable instructions, when the processor executes the target user-based reading behavior data to determine a target user type to which the target user belongs, specifically cause the processor to:
and if the target user is determined to belong to at least two candidate user types based on the reading behavior data of the target user, determining the target user type based on the information push frequency corresponding to each candidate user type.
B20. The terminal of B12, wherein the executable instructions further cause the processor to:
and when a preset instruction is detected, re-executing the reading behavior data based on the target user, and determining the target user type to which the target user belongs so as to update the target user type of the target user.
B21. The terminal of any one of B12-B20, wherein the executable instructions, when the processor executes the target user-based reading behavior data to determine a target user type to which the target user belongs, specifically cause the processor to:
weighting each data item in the reading behavior data to obtain a behavior data value;
and determining the target user type from the user types based on the behavior data values and the corresponding behavior data value range of each user type.
B22. The terminal according to B21, wherein each data item of the reading behavior data includes activation duration, advertisement push-free permission, reading duration, reading number, online frequency, and interaction data; the interactive data comprises at least one of authority acquisition times, advertisement closing times, function triggering times, resource acquisition times and resource extraction times;
the user types comprise a new user type, a resource preference type, a permission preference type, a function preference type, an advertisement preference type and an advertisement shielding type;
the information types comprise comprehensive advertisements, resource preference advertisements, permission preference advertisements and function preference advertisements.
C23. A computer-readable storage medium, wherein the storage medium stores a computer program which, when executed by a processor, causes the processor to implement the information push method as described in any one of a1-a 11.
Various component embodiments of the invention may be implemented in whole or in part in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in an … … apparatus according to embodiments of the invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
The foregoing description is only exemplary of the preferred embodiments of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents is encompassed without departing from the spirit of the disclosure. For example, the above features and (but not limited to) features having similar functions disclosed in the present invention are mutually replaced to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the invention. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. An information pushing method, comprising:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
2. The method according to claim 1, wherein in a case that the information push frequency is included in the target push policy, after the determining a target push policy based on the target user type, the method further comprises:
adjusting the target information pushing frequency in the target pushing strategy based on the reading event information; wherein the reading event information comprises at least one of the attrition probability, reading chapter attribute and reading time period of the target user.
3. The method of claim 2, wherein in the case that the reading event information is the churn probability, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information comprises:
determining the attrition probability of the target user based on the historical behavior data of the target user; the historical behavior data comprises the historical chapter dwell time, the historical content interaction data and the historical login frequency of the target user;
and adjusting the target information pushing frequency in the target pushing strategy based on the attrition probability.
4. The method according to claim 2, wherein in the case that the reading event information is the reading chapter attribute, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information comprises:
determining chapter content popularity of the reading chapters based on the chapter information of the reading chapters; the chapter information comprises at least one of chapter loss rate, chapter reading time, chapter reading number, chapter downloading amount, chapter interaction data and chapter importance identification;
and adjusting the target information pushing frequency based on the chapter content heat of the reading chapter corresponding to the target user.
5. The method of claim 2, wherein in the case that the reading event information is the reading period, the adjusting the target information pushing frequency in the target pushing policy based on the reading event information comprises:
if the reading time interval is an idle time interval, increasing the target information pushing frequency;
and if the reading time interval is a busy time interval, reducing the target information pushing frequency.
6. The method of claim 1, further comprising:
and when a preset instruction is detected, re-executing the reading behavior data based on the target user, and determining the target user type to which the target user belongs so as to update the target user type of the target user.
7. The method according to any one of claims 1 to 6, wherein the determining a target user type to which the target user belongs based on the reading behavior data of the target user comprises:
weighting each data item in the reading behavior data to obtain a behavior data value;
and determining the target user type from the user types based on the behavior data values and the corresponding behavior data value range of each user type.
8. The method of claim 7, wherein each of the data items of the reading behavior data includes activation duration, advertisement push-free rights, reading duration, reading number, online frequency, and interaction data; the interactive data comprises at least one of authority acquisition times, advertisement closing times, function triggering times, resource acquisition times and resource extraction times;
the user types comprise a new user type, a resource preference type, a permission preference type, a function preference type, an advertisement preference type and an advertisement shielding type;
the information types comprise comprehensive advertisements, resource preference advertisements, permission preference advertisements and function preference advertisements.
9. A terminal comprising a processor and a memory, the memory to store executable instructions that cause the processor to:
determining the type of a target user to which the target user belongs based on reading behavior data of the target user;
determining a target push strategy corresponding to the type of the target user from a plurality of preset push strategies; the preset push strategy comprises at least one of an information type, an information push frequency, an information display position and an information display style;
and pushing information to the target user based on the target pushing strategy.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, causes the processor to implement the information pushing method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111430897.8A CN114116822A (en) | 2021-11-29 | 2021-11-29 | Information push method, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111430897.8A CN114116822A (en) | 2021-11-29 | 2021-11-29 | Information push method, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114116822A true CN114116822A (en) | 2022-03-01 |
Family
ID=80371038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111430897.8A Pending CN114116822A (en) | 2021-11-29 | 2021-11-29 | Information push method, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114116822A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115033907A (en) * | 2022-07-19 | 2022-09-09 | 北京护城河科技有限公司 | Data interaction method, system, device and storage medium |
| CN117478629A (en) * | 2023-12-20 | 2024-01-30 | 福建省捷云软件股份有限公司 | Basic community treatment information disclosure system |
| WO2024087752A1 (en) * | 2022-10-24 | 2024-05-02 | 中兴通讯股份有限公司 | User preference analysis method and apparatus |
-
2021
- 2021-11-29 CN CN202111430897.8A patent/CN114116822A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115033907A (en) * | 2022-07-19 | 2022-09-09 | 北京护城河科技有限公司 | Data interaction method, system, device and storage medium |
| WO2024087752A1 (en) * | 2022-10-24 | 2024-05-02 | 中兴通讯股份有限公司 | User preference analysis method and apparatus |
| CN117478629A (en) * | 2023-12-20 | 2024-01-30 | 福建省捷云软件股份有限公司 | Basic community treatment information disclosure system |
| CN117478629B (en) * | 2023-12-20 | 2024-04-12 | 福建省捷云软件股份有限公司 | Basic community treatment information disclosure system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114116822A (en) | Information push method, terminal and storage medium | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| CN109145210B (en) | Information recommendation method and device and storage medium | |
| Headen et al. | The duplication of viewing law and television media schedule evaluation | |
| Epure et al. | Recommending personalized news in short user sessions | |
| US20190279231A1 (en) | Analytical precursor mining for personalized recommendation | |
| US10896237B2 (en) | Reducing database stress using cognitive data caching | |
| US20180307733A1 (en) | User characteristic extraction method and apparatus, and storage medium | |
| CN110489646B (en) | User portrait construction method and terminal equipment | |
| Van Canneyt et al. | Modeling and predicting the popularity of online news based on temporal and content-related features | |
| CN111833113A (en) | Product recommendation method, device and equipment based on big data and storage medium | |
| US8688716B1 (en) | Recommending pairwise video comparisons to improve ranking | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN112104505A (en) | Application recommendation method and device, server and computer-readable storage medium | |
| Fraser et al. | Scrutable and persuasive push-notifications | |
| AU2018429394B2 (en) | Media source measurement for incorporation into a censored media corpus | |
| CN110708361B (en) | System, method and device for determining grade of digital content publishing user and server | |
| CN113159213A (en) | Service distribution method, device and equipment | |
| CN117593089A (en) | Credit card recommendation method, apparatus, device, storage medium and program product | |
| JP2023159414A (en) | Source code trading system by using ai | |
| CN113342762B (en) | Intelligent processing method and related device for shared messages of friends of merchants | |
| CN112767027B (en) | Cloud cost prediction method and system based on service perception | |
| Borges et al. | Feature-blind fairness in collaborative filtering recommender systems | |
| Piao et al. | Recommender system architecture based on mahout and a main memory database | |
| CN114676351A (en) | Method, device and equipment for determining recommended position and storage medium |
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 |