CN112445980B - Information pushing method and device and storage medium - Google Patents
Information pushing method and device and storage medium Download PDFInfo
- Publication number
- CN112445980B CN112445980B CN201910818564.9A CN201910818564A CN112445980B CN 112445980 B CN112445980 B CN 112445980B CN 201910818564 A CN201910818564 A CN 201910818564A CN 112445980 B CN112445980 B CN 112445980B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- user set
- function value
- added
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
Abstract
The invention discloses an information pushing method, which comprises the steps of calculating a second community function value between a first user label to be added and each user label in a first user set; determining whether to add the first user to be added to the first user set or not based on the second community function value and a first community function value between user tags of the first user set, and determining whether the first user set completes user adding processing or not; when the first user set is determined not to be added to the first user set and the first user set is determined to finish adding processing, pushing information corresponding to the labels of the first user set to the users contained in the first user set. The invention also discloses an information pushing device and a storage medium. Therefore, the information corresponding to the label of the user can be pushed for the user, and the information pushing is more accurate.
Description
Technical Field
The present invention relates to the field of multimedia technologies, and in particular, to an information pushing method, an information pushing device, and a storage medium.
Background
With the development of information technology and the internet, people gradually move from the times of lacking information to the times of information overload, and then, how to find information of interest from a large amount of information follows. Therefore, various information recommendation methods have been developed to help users discover new content of interest to them.
Currently, a method for determining a set of users with similar interests is to calculate distance similarity and acquaintance based on a geographical location where the users check in and common friends, so as to obtain a set of users with similar interests. In the method, the geographic position information of the user needs permission of the user, and obviously, the situation that the user is not permitted frequently occurs, so that the determination of a similar user set is deviated, and the accurate pushing of the information is influenced.
Disclosure of Invention
In view of the above, embodiments of the present invention are intended to provide an information pushing method, an information pushing apparatus, and a storage medium, which are used to solve the above problems in the prior art.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
the embodiment of the invention provides an information pushing method, which comprises the following steps:
calculating a second community function value between the first to-be-added user label and each user label in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
determining whether to add the first user to be added to the first user set and determining whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set;
when the first user to be added is determined not to be added to the first user set and the first user set is determined to finish adding processing, pushing information corresponding to the labels of the first user set to the users contained in the first user set.
In the foregoing solution, the determining whether to add the first user to be added to the first user set and determining whether to complete user addition processing for the first user set based on the second community function value and the first community function value between the user tags of the first user set includes:
when the second community function value is larger than the first community function value, adding the first user to be added to the first user set, and continuing to perform user adding processing of the first user set; alternatively, the first and second liquid crystal display panels may be,
when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
In the foregoing solution, the calculating a second community function value between the first to-be-added user tag and each user tag in the first user set includes:
determining external edge density according to the cosine similarity between the first to-be-added user label and part of user labels in the first user set;
determining internal edge density according to cosine similarity among user labels in the first user set;
and obtaining the second community function value according to the internal edge density and the external edge density.
In the above scheme, the method further comprises:
determining label information of a user according to a browsing record of the user; alternatively, the first and second electrodes may be,
the label information of the user is directly obtained by acquiring the information input by the user.
In the above scheme, the method further comprises:
analyzing information to be pushed, and determining the type of the information to be pushed;
and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
The embodiment of the invention provides a device for pushing information, which comprises: the device comprises a calculation module, a judgment module and a pushing module; wherein the content of the first and second substances,
the calculation module is used for calculating a second community function value between the first to-be-added user label and each user label in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
the judging module is configured to determine whether to add the first user to be added to the first user set based on the second community function value and a first community function value between user tags of the first user set, and determine whether to complete user addition processing for the first user set;
the pushing module is configured to, when it is determined that the first user to be added is not added to the first user set and it is determined that the first user set completes the addition processing, push information corresponding to the tag of the first user set to the users included in the first user set.
In the foregoing solution, the determining module is specifically configured to, when the second community function value is greater than the first community function value, add the first user to be added to the first user set, and continue the user adding process of the first user set; or when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
In the foregoing scheme, the calculating module is specifically configured to determine the external edge density according to the cosine similarity between the first to-be-added user tag and part of the user tags in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; and obtaining the second community function value according to the internal edge density and the external edge density.
In the above scheme, the apparatus further includes an obtaining module, configured to determine tag information of the user according to a browsing record of the user; or, the label information of the user is directly obtained by acquiring the information input by the user.
In the above scheme, the device further includes an analysis module, configured to analyze the information to be pushed, and determine a type of the information to be pushed; and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
The embodiment of the present invention further provides a storage medium, on which an executable program is stored, and the executable program implements the steps in the above technical solution when executed by a processor.
The embodiment of the present invention further provides an information pushing apparatus, which includes a memory, a processor, and an executable program stored on the memory and capable of being executed by the processor, and is characterized in that the processor executes the steps in the above technical solution when executing the executable program.
According to the information pushing method, the information pushing device and the information pushing storage medium, whether the expansion process of the first user set is finished or not can be determined by calculating the community function value between the user tag to be added and the first user set tag and the community function value between the users of the first user set and then comparing the community function values. Further, after the first user set is expanded, information corresponding to the tags of the first user set is pushed to the first user set. Furthermore, labels corresponding to the self content are marked for the information to be pushed, and then the information to be pushed is pushed to the user set similar to the labels of the self content, so that the pushed information is more in line with the requirements of users, and the information pushing is more accurate.
Drawings
Fig. 1 is a schematic view illustrating an implementation flow of an information push method according to an embodiment of the present invention;
FIG. 2 is a first diagram illustrating a scenario of determining a user set according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a second scenario of determining a user set according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a third scenario of determining a user set according to an embodiment of the present invention;
FIG. 5 is a first schematic diagram illustrating a structure of an information pushing apparatus according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a second exemplary embodiment of an information pushing apparatus;
fig. 7 is a schematic diagram of a hardware structure of an information pushing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The first embodiment,
In the embodiment of the present invention, a schematic diagram of an implementation flow of an information pushing method is shown in fig. 1, and includes the following steps:
step 101: calculating a second community function value between the first to-be-added user label and each user label in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
step 102: determining whether to add the first user to be added to the first user set and determining whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set;
step 103: when the first user to be added is determined not to be added to the first user set and the first user set is determined to finish adding processing, pushing information corresponding to the labels of the first user set to the users contained in the first user set.
In step 101 in the embodiment of the present invention, the first user set is a basic set, and includes at least two users, where tags of at least some users in the first user set are the same, and the at least some users are related to friends. The first set of users may pre-select users. For example, several users of a department are determined as a first set of users.
Further, before determining the first set of users, the method further includes: determining label information of a user according to the browsing record of the user; or, the label information of the user is directly obtained by acquiring the information input by the user. Specifically, when the user logs in the application process to browse various information, the browsing record of the user is saved. Here, the application processes include hundredth, netbook, migu reading, arcade art, and the like. And then, according to the browsing record of the user, obtaining the classification of the reading content of the user through analysis, and sequencing the classification of the reading content from high to low according to the browsing frequency of the user. And then, according to the classification of the reading content, attaching a corresponding label to the user. Then, it may be determined that the user likes the encyclopedia and the temporal content, and encyclopedia and temporal labels may be sequentially attached to the user according to the browsing frequency. Here, the number of the user tags is not limited, and the number of the user tags is at least one.
Further, when the user logs in the application process, an information registration page is pushed, and the user directly inputs the classification information of the read content to obtain the label information of the user. For example, when the user logs in the migu for reading for the first time, the registration interface is directly pushed, and the user defines the label by himself.
Further, calculating a second community function value between the first to-be-added user label and each user label in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
wherein, the calculating a second community function value between the first to-be-added user tag and each user tag in the first user set includes: determining external edge density according to the cosine similarity between the first to-be-added user label and part of user labels in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; and obtaining the second community function value according to the internal edge density and the external edge density.
Specifically, the calculation formula of the community function value is as follows:
wherein s represents a label of the user set; f(s) represents a community function value; />
Representing an internal edge density of the collection;/>
indicating the outer edge density. Here, the internal edge density is used to indicate that the cosine similarity of the user tags in the user set is greater than a preset value, that is, the users are in a friend relationship, and the internal edge density between the users having a friend relationship among the users in the user set is defined as 2; the external edge density is used for representing that the cosine similarity of at least one user label in the user set and labels of users outside the user set is larger than a preset value, and the external edge density between the users in the user set and the users with friend relationships of the users outside the user set is defined as 1. Here, the preset value of the label cosine similarity is an empirical value, for example, set to 60%, 65%, or the like.
In step 102, it is determined whether to add the first user to be added to the first user set and whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set.
Specifically, when the second community function value is greater than the first community function value, the first user to be added is added to the first user set, and the user addition processing of the first user set is continued; or when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
Specifically, the first community function value is a preset empirical value. Next, calculating a second community function value between a label of a first user X to be added and each user label in the first user set, comparing the second community function value with an initial first community function value, adding the first user X to be added to the first user set when the second community function value is larger than the initial first community function value, and taking the second community function value as a new first community function value. And then, recalculating a second community function value between a newly appeared label of a first user Y to be added and each user label in the first user set containing the first user X, further comparing the community function values, and adding the first user Y to be added to the first user set when the new second community function value is larger than the first community function value. Thus, the users with similar labels are added to the first user set in a plurality of loops. Further, when the second community function value is smaller than or equal to the first community function value, the expansion process of the first user set is stopped.
In step 103, when it is determined that the first user to be added is not added to the first user set and it is determined that the first user set completes the adding process, pushing information corresponding to the tags of the first user set to the users included in the first user set.
Here, the tags of the users in the first set of users that completed the adding are similar. For example, the user's label is classical literature, fashion, science and technology, and the like. Analyzing the information to be pushed, and determining the type of the information to be pushed; and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed. Then, the users of the first user set who finish the adding process push the same information as the labels thereof.
The information pushing method in the embodiment realizes accurate pushing of information. Specifically, the community function value between the first to-be-added user tag and each user tag in the first user set is calculated, and then the community function value is compared with the community function value between each user tag in the first user set, so that the user set of the to-be-pushed information is finally determined. And meanwhile, analyzing the information to be pushed, and attaching a label corresponding to the content of the information to be pushed to the information to be pushed. Then, when the information to be pushed is pushed to the user set, the pushed information can be more suitable for the users in the user set.
Example II,
The information pushing process is described in detail below with reference to an example.
Here, tag information of the user is determined according to the browsing history of the user; or, the label information of the user is directly obtained by acquiring the information input by the user. For example, a user's browsing history is saved when the user logs in to migu for reading. Then, according to the browsing records of the user, the classification of the reading content of the user is obtained through analysis, and the classification of the reading content is sequenced from high to low according to the browsing frequency of the user. And labeling the user according to the classification of the reading content.
In addition, when the user logs in the Migu for reading for the first time, the information registration page is pushed, and the classification information of the reading content is directly input by the user to obtain the label information of the user.
Further, the first set of users is predetermined. For example, 8 users in a certain department are determined as the first set of users. The labels of at least some users in the first user set are the same, and the at least some users are friend relationships. As shown in fig. 2, there are 8 users a to H in the first set of users. At this point, the users of the first set of users have similar labels.
Further, the calculating a second community function value between the first to-be-added user tag and each user tag in the first user set includes: determining external edge density according to the cosine similarity between the first to-be-added user label and part of user labels in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; and obtaining the second community function value according to the internal edge density and the external edge density.
The internal edge density is used for indicating that the cosine similarity of the user labels in the user set is greater than a preset value, namely the users are in friend relationship, and the internal edge density between the users with friend relationship in the users in the user set is defined as 2; the external edge density is used for representing that the cosine similarity of at least one user label in the user set and the labels of the users outside the user set is larger than a preset value, and the external edge density between the users in the user set and the users with friend relationships between the users outside the user set is defined as 1.
For example, a tag vector is established for each user. Wherein, the label vectors of the user A and the user B are respectively
And &>
As shown in fig. 3, the connection between user a and user B belongs to the inner edge density, and similarly, the connection between user C and user F belongs to the inner edge density. I.e. the connection between two users in the first set belongs to the inner edge density. Similarly, the connection between user K and user D belongs to the outer edge density. Then, calculating the label cosine similarity of the user a and the user B by using a cosine similarity formula, specifically:
wherein | a | | and | B | | | represent the moduli of the user a and user B label vectors, respectively. Next, when δ is greater than 60%, the users a and B in the first user set are determined to be friendships, and the internal edge density of the users a and B is 2. And calculating the cosine similarity of the labels of the first user C to be added and the user A in the first user set by adopting the same method, and determining that the external edge density of the user K and the user D is 1 when the delta is greater than 60%.
Further, when the user K has similar labels to the user D in the first user set, calculating a community function value of the label of the user K and each user label in the first user set as follows:
wherein s is 2 RepresentThe sum of the label of the user K and each user label in the first user set; f(s) 2 ) A community function value representing a label of a user K and each user label in the first user set; />
Representing an internal edge density of the first set of users; />
An outer edge density representing the first set of users.
Then, F(s) is calculated using the above formula 2 ) Then, F(s) is added 2 ) And F(s) 1 ) Making a comparison when F(s) 2 ) Greater than F(s) 1 ) Then user K is added to the first set of users, as shown in fig. 4. Wherein, F(s) 1 ) The initial value of (2) is a set empirical value. F(s) is added after one user to be added is added to the first user set 2 ) And when the second community function value is larger than the first community function value, adding the user to be added to the first user set. And when the second community function value is smaller than or equal to the first community function value, stopping the adding processing process of the first user set.
Further, when it is determined that the first user to be added is not added to the first user set and it is determined that the first user set completes the adding process, information corresponding to the tags of the first user set is pushed to the users included in the first user set. For example, after it is determined that the user tag of the first user set is technology, pushing technology-class information to the users of the second user set.
In addition, the information to be pushed is analyzed, and the type of the information to be pushed is determined. And then, according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed. Here, a convolutional neural network text classification algorithm may be employed to improve the accuracy of information classification. The specific process is as follows:
firstly, the text content is converted into an input format required by the convolutional layer to obtain an input vector n × k × chann, wherein n represents the number of text words, k represents the dimension, and channel is 1.
Then, after passing through an input layer, carrying out convolution operation m multiplied by k multiplied by depth on an input vector, wherein m represents the number of words in the text processed each time; depth denotes the depth of filtration. And respectively convolving different m to extract more features so as to obtain the feature representation of the whole text.
Further, feature vectors representing the text are obtained after convolution pooling, probability vectors representing different categories are obtained through processing, and information classification is completed.
In this embodiment, a user set with similar labels is determined by comparing the community function values. Meanwhile, the information to be pushed is analyzed, and a label corresponding to the information to be pushed is determined. Furthermore, information similar to the label of the user is pushed to the users of the user set, and the accuracy of information pushing can be improved.
Example III,
In order to implement the information push method, an embodiment of the present invention further provides an information push apparatus, where a schematic structural diagram of the apparatus is shown in fig. 5, and the apparatus includes: a calculation module 51, a judgment module 52 and a push module 53; wherein the content of the first and second substances,
the calculating module 51 is configured to calculate a second community function value between the first to-be-added user tag and each user tag in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels.
The determining module 52 is configured to determine whether to add the first user to be added to the first user set based on the second community function value and a first community function value between user tags of the first user set, and determine whether to complete user addition processing for the first user set.
Here, the determining module 52 is specifically configured to, when the second community function value is greater than the first community function value, add the first user to be added to the first user set and continue the user adding process of the first user set; or when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
The pushing module 53 is configured to, when it is determined that the first user to be added is not added to the first user set and it is determined that the first user set completes the adding process, push information corresponding to the tag of the first user set to the users included in the first user set.
Here, the calculating module 51 is specifically configured to determine the external edge density according to the cosine similarity between the first to-be-added user tag and part of the user tags in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; and obtaining the second community function value according to the internal edge density and the external edge density. Here, the preset value of the tag cosine similarity is an empirical value.
Here, the calculation formula of the community function value is:
wherein s represents the sum of the user tags; f(s) represents a community function value; />
Representing an internal edge density of the collection; />
Indicating the outer edge density. The internal edge density is used for indicating that the cosine similarity of the user labels in the user set is greater than a preset value, namely that friends exist among users, and the users in the user set have friendsThe internal edge density between households is defined as 2; the external edge density is used for representing that the cosine similarity between at least one user label in the user set and the label of the user outside the user set is greater than a preset value, and the external edge density between the user in the user set and the user with friend relationship outside the user set is defined as 1.
The apparatus further includes an obtaining module 54, configured to determine tag information of the user according to the browsing record of the user; or, the label information of the user is directly obtained by acquiring the information input by the user. Specifically, when the user logs in the application process to browse various information, the browsing record of the user is saved. And then, according to the browsing record of the user, obtaining the classification of the reading content of the user through analysis, and sequencing the classification of the reading content from high to low according to the browsing frequency of the user. And then labeling the user according to the classification of the reading content.
Further, when the user logs in the application process, an information registration page is pushed, and the user directly inputs the classification information of the read content to obtain the label information of the user.
The device further comprises an analysis module 55, configured to analyze the information to be pushed, and determine the type of the information to be pushed; and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
Further, the structural composition of the information pushing apparatus in fig. 5 is also applied to the structural composition shown in fig. 6, and specifically includes: the device comprises a calculation module 51, a judgment module 52, a push module 53, an acquisition module 54 and an analysis module 55.
In addition, the specific implementation process of this embodiment has been explained in detail in the foregoing technical solutions, and is not described herein again.
In practical applications, the calculating module 51, the judging module 52, the pushing module 53, the obtaining module 54, and the analyzing module 55 may be implemented by a Central Processing Unit (CPU), a microprocessor Unit (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like located in the terminal device.
It should be noted that: in the information pushing apparatus provided in the above embodiment, only the division of the program modules is exemplified when information is pushed, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the apparatus may be divided into different program modules to complete all or part of the processing described above. In addition, the information push apparatus and the information push method provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments and are not described herein again.
In order to implement the foregoing method, another information pushing apparatus is further provided in an embodiment of the present invention, where the apparatus includes a memory, a processor, and an executable program that is stored in the memory and can be executed by the processor, and when the processor executes the executable program, the following operations are performed:
calculating a second community function value between the first to-be-added user label and each user label in the first user set; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
determining whether to add the first user to be added to the first user set and determining whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set;
when the first user to be added is determined not to be added to the first user set and the first user set is determined to finish adding processing, pushing information corresponding to the labels of the first user set to the users contained in the first user set.
The processor is further configured to, when running the executable program, perform the following:
when the second community function value is larger than the first community function value, adding the first user to be added to the first user set, and continuing to perform user adding processing of the first user set; alternatively, the first and second electrodes may be,
when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
The processor is further configured to, when running the executable program, perform the following:
determining external edge density according to the cosine similarity between the first to-be-added user label and part of user labels in the first user set;
determining internal edge density according to cosine similarity among user labels in the first user set;
and obtaining the second community function value according to the internal edge density and the external edge density.
The processor is further configured to, when running the executable program, perform the following:
determining label information of a user according to a browsing record of the user; alternatively, the first and second electrodes may be,
the label information of the user is directly obtained by acquiring the information input by the user.
The processor is further configured to, when running the executable program, perform the following:
analyzing information to be pushed, and determining the type of the information to be pushed;
and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
The following takes as an example that the information pushing apparatus is implemented as a server or a terminal for pushing information, and further describes a hardware structure of the information pushing apparatus.
Fig. 7 is a schematic diagram of a hardware structure of an information pushing apparatus according to an embodiment of the present invention, where the information pushing apparatus 700 shown in fig. 7 includes: at least one processor 701, memory 702, user interface 703, and at least one network interface 704. The various components in the information pushing device 700 are coupled together by a bus system 705. It is understood that the bus system 705 is used to enable connected communication between these components. The bus system 705 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various busses are labeled in figure 7 as the bus system 705.
The user interface 703 may include, among other things, a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touch pad, or a touch screen.
It will be appreciated that the memory 702 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory.
The memory 702 in the embodiments of the present invention is used for storing various types of data to support the operation of the information pushing apparatus 700. Examples of such data include: any computer program for operating on the information pushing device 700, such as the executable program 7021, can be included in the executable program 7021 to implement the method of the embodiment of the present invention.
The method disclosed in the above embodiments of the present invention may be applied to the processor 701, or implemented by the processor 701. The processor 701 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by integrated logic circuits of hardware or instructions in the form of software in the processor 701. The processor 701 described above may be a general purpose processor, a DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 901 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the memory 702, and the processor 701 reads the information in the memory 702 and performs the steps of the method in combination with its hardware.
In an exemplary embodiment, an embodiment of the present invention further provides a storage medium having an executable program stored thereon, which when executed by a processor performs the foregoing method.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or executable program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of an executable program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and executable program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by executable program instructions. These executable program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor with reference to a programmable data processing apparatus to produce a machine, such that the instructions, which execute via the computer or processor with reference to the programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These executable program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These executable program instructions may also be loaded onto a computer or reference programmable data processing apparatus to cause a series of operational steps to be performed on the computer or reference programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or reference programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. An information pushing method, characterized in that the method comprises:
determining the external edge density according to the cosine similarity between the first to-be-added user label and at least one user label in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; obtaining a second community function value according to the internal edge density and the external edge density; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
determining whether to add the first user to be added to the first user set and determining whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set;
when the first user to be added is determined not to be added to the first user set and the first user set is determined to finish adding processing, pushing information corresponding to the labels of the first user set to the users contained in the first user set.
2. The method of claim 1, wherein the determining whether to add the first to-be-added user to the first user set and determining whether the first user set completes user adding processing based on the second community function value and a first community function value between user tags of the first user set comprises:
when the second community function value is larger than the first community function value, adding the first user to be added to the first user set, and continuing to perform user adding processing of the first user set; alternatively, the first and second electrodes may be,
when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
3. The method of claim 1, further comprising:
determining label information of a user according to a browsing record of the user; alternatively, the first and second electrodes may be,
the label information of the user is directly obtained by acquiring the information input by the user.
4. The method of claim 1, further comprising:
analyzing information to be pushed, and determining the type of the information to be pushed;
and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
5. An information pushing apparatus, characterized in that the apparatus comprises: the device comprises a calculation module, a judgment module and a pushing module; wherein the content of the first and second substances,
the calculation module determines the external edge density according to the cosine similarity between the first to-be-added user tag and at least one user tag in the first user set; determining internal edge density according to cosine similarity among user labels in the first user set; obtaining a second community function value according to the internal edge density and the external edge density; the first user to be added is a user out of the first user set; the community function value is used for representing the similarity degree between the user labels;
the judging module is configured to determine whether to add the first user to be added to the first user set based on the second community function value and a first community function value between user tags of the first user set, and determine whether to complete user addition processing for the first user set;
the pushing module is configured to push information corresponding to the tag of the first user set to the users included in the first user set when it is determined that the first user set is not added to the first user set and it is determined that the adding process of the first user set is completed.
6. The apparatus according to claim 5, wherein the determining module is specifically configured to add the first user to be added to the first user set and continue the user adding process of the first user set when the second community function value is greater than the first community function value; or when the second community function value is smaller than or equal to the first community function value, the first user to be added is not added to the first user set, and the first user set is determined to finish adding processing.
7. The apparatus according to claim 5, further comprising an obtaining module, configured to determine tag information of the user according to a browsing record of the user; or, the label information of the user is directly obtained by acquiring the information input by the user.
8. The apparatus according to claim 5, further comprising an analysis module, configured to analyze the information to be pushed, and determine a type of the information to be pushed; and according to the type of the information to be pushed, marking a label corresponding to the type of the information to be pushed for the information to be pushed.
9. A storage medium having stored thereon an executable program, the executable program when executed by a processor implementing the steps of the method of any one of claims 1 to 4.
10. An information pushing apparatus comprising a memory, a processor and an executable program stored on the memory and capable of being executed by the processor, wherein the steps of the method of any one of claims 1 to 4 are performed when the executable program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818564.9A CN112445980B (en) | 2019-08-30 | 2019-08-30 | Information pushing method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818564.9A CN112445980B (en) | 2019-08-30 | 2019-08-30 | Information pushing method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112445980A CN112445980A (en) | 2021-03-05 |
| CN112445980B true CN112445980B (en) | 2023-04-07 |
Family
ID=74733799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910818564.9A Active CN112445980B (en) | 2019-08-30 | 2019-08-30 | Information pushing method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112445980B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016201963A1 (en) * | 2015-06-19 | 2016-12-22 | 赤子城网络技术（北京）有限公司 | Application pushing method and device |
| CN107341173A (en) * | 2017-05-16 | 2017-11-10 | 阿里巴巴集团控股有限公司 | A kind of information processing method and device |
| CN108810089A (en) * | 2018-05-04 | 2018-11-13 | 微梦创科网络科技（中国）有限公司 | A kind of information-pushing method, device and storage medium |
-
2019
- 2019-08-30 CN CN201910818564.9A patent/CN112445980B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016201963A1 (en) * | 2015-06-19 | 2016-12-22 | 赤子城网络技术（北京）有限公司 | Application pushing method and device |
| CN107341173A (en) * | 2017-05-16 | 2017-11-10 | 阿里巴巴集团控股有限公司 | A kind of information processing method and device |
| CN108810089A (en) * | 2018-05-04 | 2018-11-13 | 微梦创科网络科技（中国）有限公司 | A kind of information-pushing method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112445980A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106919625B (en) | Internet user attribute identification method and device | |
| CN110705214A (en) | Automatic coding method and device | |
| CN109213932B (en) | Information pushing method and device | |
| CN104081380A (en) | Identifying and ranking solutions from multiple data sources | |
| CN112148843B (en) | Text processing method and device, terminal equipment and storage medium | |
| CN111125376B (en) | Knowledge graph generation method and device, data processing equipment and storage medium | |
| CN110888866B (en) | Data expansion method and device, data processing equipment and storage medium | |
| CN113032580B (en) | Associated file recommendation method and system and electronic equipment | |
| CN112102031A (en) | Recommendation method, recommendation device and terminal equipment | |
| CN113052079B (en) | Regional passenger flow statistical method, system, equipment and medium based on face clustering | |
| CN110751515A (en) | Decision-making method and device based on user consumption behaviors, electronic equipment and storage medium | |
| CN111148045B (en) | User behavior cycle extraction method and device | |
| CN110134721B (en) | Data statistics method and device based on bitmap and electronic equipment | |
| CN115525838A (en) | Health knowledge recommendation method and system based on big data user portrait | |
| CN111782946A (en) | Book friend recommendation method, calculation device and computer storage medium | |
| CN111310065A (en) | Social contact recommendation method and device, server and storage medium | |
| CN112445980B (en) | Information pushing method and device and storage medium | |
| CN113434762A (en) | Association pushing method, device and equipment based on user information and storage medium | |
| CN108830298B (en) | Method and device for determining user feature tag | |
| CN114491134B (en) | Trademark registration success rate analysis method and system | |
| CN111104550A (en) | Video recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN114449443A (en) | Information pushing method and device, storage medium and electronic equipment | |
| CN112348638B (en) | Activity document recommending method and device, electronic equipment and storage medium | |
| CN116384473B (en) | Calculation graph improvement and information pushing method and device | |
| Ogiela et al. | Predictive intelligence in secure data processing, management, and forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |