CN115580649B - Intelligent information pushing method based on user network behaviors - Google Patents
Intelligent information pushing method based on user network behaviors Download PDFInfo
- Publication number
- CN115580649B CN115580649B CN202211054533.9A CN202211054533A CN115580649B CN 115580649 B CN115580649 B CN 115580649B CN 202211054533 A CN202211054533 A CN 202211054533A CN 115580649 B CN115580649 B CN 115580649B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- network
- basic
- browsing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000006399 behavior Effects 0.000 title abstract description 29
- 238000005070 sampling Methods 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 39
- 238000012790 confirmation Methods 0.000 claims description 8
- 230000002427 irreversible effect Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 238000007789 sealing Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000429 assembly Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent information pushing method based on user network behaviors, and relates to the technical field of network information service. The invention comprises the following steps: classifying the network information; sampling from different classifications of the network information according to the classification result of the network information to obtain initial sample information; pushing the initial sample information to a user; obtaining information type preference of the user according to the network behavior of the user browsing the sample information; selecting personalized information in the network information according to the information type preference of the user; pushing personalized information to a user; and updating the information type preference of the user according to the network behavior of the user for browsing the personalized information. According to the invention, the accuracy of information pushing to the user is improved by analyzing the network behavior of the user.
Description
Technical Field
The invention belongs to the technical field of network information service, and particularly relates to an intelligent information pushing method based on user network behaviors.
Background
With the tremendous growth in the amount and variety of internet information, the information content of internet information has come within the far-reaching computer. The existing information pushing algorithm is used for analyzing and extracting hot spot information according to the existing big data of the user and pushing the hot spot information, and the information requirement behind the network behavior of the user is not considered.
Moreover, as the accuracy of information needs is required to be higher and higher, the requirement of users on the pushing precision of the internet information is also higher and higher.
Disclosure of Invention
The invention aims to provide an intelligent information pushing method based on user network behaviors, which improves the accuracy of information pushing to users by analyzing the network behaviors of the users.
In order to solve the technical problems, the invention is realized by the following technical scheme:
The invention provides an intelligent information pushing method based on user network behaviors, which comprises the following steps:
Classifying the network information;
sampling from different classifications of the network information according to the classification result of the network information to obtain initial sample information;
pushing the initial sample information to a user;
Obtaining information type preference of the user according to the network behavior of the user browsing the sample information;
Selecting personalized information from the network information according to the information type preference of the user;
Pushing the personalized information to the user;
And updating the information type preference of the user according to the network behavior of the user browsing the personalized information.
In one embodiment of the present invention, the step of sampling initial sample information from different classifications of the network information according to the classification result of the network information includes,
Obtaining the number of information pieces in each type of network information, the browsing time consumption of each piece of network information and the browsing quantity of each piece of network information according to the classification result of the network information;
Selecting a network information type with the number of information reaching a set threshold as a basic information type;
Selecting the network information with the browsing quantity reaching a set threshold value in the basic information category as a basic information item;
Ordering each piece of network information in the basic information items according to the browsing time-consuming length of each piece of network information;
and pushing the initial sample information formed by the basic information items to the user, wherein the network information with shorter browsing time consumption length in the basic information items is pushed relatively preferentially.
In one embodiment of the present invention, the step of pushing the basic information item to the user to compose the initial sample information includes,
Acquiring the number of basic information items in each basic information category;
Selecting the basic information items in each basic information category as basic information pushing units according to the quantity of the basic information items contained in each basic information category in multiple times;
Pushing the basic information items in the basic information pushing unit generated by the same wave number;
and pushing the basic information items in the basic information pushing unit of the next wave when the basic information items in the basic information pushing unit of the previous wave are completely pushed.
In one embodiment of the present invention, the step of sampling initial sample information from different classifications of the network information according to the classification result of the network information further comprises,
Selecting the network information types with the number of information pieces not reaching a set threshold as extension information types;
And if the user continues to request to browse the network data after the pushing of the basic information item is completed, selecting the network information with the browsing quantity reaching a set threshold value in the expansion information category as an expansion information item, and adding the expansion information item to the initial sample information for pushing.
In one embodiment of the present invention, the step of selecting the network information category for which the number of pieces of information does not reach the set threshold as the extension information category includes,
Acquiring content similarity between the basic information category and other information categories;
marking other information types with content similarity larger than a set threshold value as extension information types;
and acquiring the proportion of the different types of the expansion information types when the information is pushed to the user according to the proportion of the content similarity between the different types of the expansion information types and the basic information types.
In one embodiment of the present invention, the step of obtaining the ratio between the different kinds of the extension information categories when pushing information to the user according to the ratio of the content similarity between the different kinds of the extension information categories and the base information category includes,
Acquiring the comparison proportion of the quantity of the basic information items between the basic information categories according to the quantity of the basic information items in each basic information category;
Acquiring the weight of the basic information category according to the comparison proportion of the quantity of the basic information items among the basic information categories;
Obtaining the similarity between each extension information category and each basic information category;
Accumulating the similarity between each expansion information type and each basic information type and the product of the weight of the corresponding basic information type to obtain the push coefficient of each expansion information type;
And obtaining the proportion among the different types of the expansion information types when the information is pushed to the user according to the relative ratio of the push coefficients of each expansion information type.
In one embodiment of the present invention, the step of obtaining the information category preference of the user according to the network behavior of the user browsing the sample information includes,
Acquiring the browsing amount of each piece of network information in real time;
If the browsing amount of the network information reaches a set threshold value, acquiring the information browsing amount of the user browsing the piece of the network information in real time;
if the information browsing amount of the user in unit time reaches a set threshold value, acquiring hardware information, a network address and corresponding network behavior data of an information access terminal of the user in real time;
judging whether the corresponding user is an abnormal user or not according to the network behavior data corresponding to the same piece of hardware information;
If not, continuing to provide the network push service;
If yes, judging whether the user is blocked or not according to the network address of the information access terminal of the abnormal user.
In one embodiment of the present invention, the step of determining whether the corresponding user is an abnormal user according to the network behavior data corresponding to the same hardware information includes,
Marking the information access terminal with the information browsing amount reaching a set threshold value in unit time as a suspicious information access terminal;
Sending a control instruction to the suspicious information access terminal, so that the suspicious information access terminal extracts and uploads the digital abstract of the network behavior data cached by the suspicious information access terminal when the information browsing amount reaches a set threshold time period;
If the digital abstracts uploaded by the suspicious information access terminals of the network information, the browsing amount of which reaches a set threshold value in the browsing unit time, have the same value, the corresponding suspicious information access terminals are extracted to be marked as abnormal information access terminals;
The user corresponding to the abnormal information access terminal is an abnormal user.
In one embodiment of the present invention, the step of determining whether the user blocking should be corresponding to the network address of the information access terminal of the abnormal user includes,
Acquiring a fuzzy geographic address of the information access terminal of the abnormal user according to the network address of the information access terminal of the abnormal user;
Acquiring a clustering center of the fuzzy geographic address of the information access terminal of the abnormal user;
acquiring a range covered by a fuzzy geographic address of an information access terminal of the abnormal user;
marking the abnormal users with overlapping coverage ranges of the fuzzy geographic addresses of the information access terminals and the clustering center as blacklist users;
And sealing and banning the blacklist user.
In one embodiment of the present invention, the step of obtaining the information category preference of the user according to the network behavior of the user browsing the sample information further comprises,
Extracting the irreversible digital abstract together with the hardware information and the secret random information of the blacklist user to be used as an encrypted public network blacklist identity;
Disclosing the encrypted public network blacklist identity;
When an external blacklist user to be confirmed is received to confirm a request, acquiring hardware information of the blacklist user to be confirmed;
extracting an irreversible digital abstract as a confirmation return value together with the hardware information and the secret random information of the blacklist user to be confirmed;
And determining that the request end compares the confirmation return value with the disclosed encrypted public network blacklist identity by the blacklist user to be confirmed, and judging whether the request end is the blacklist user.
According to the invention, through analyzing the network behaviors of the user, the accuracy of information pushing of the user is improved while the information requirement of the user is met.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating steps of an intelligent information push method based on user network behavior according to an embodiment of the present invention;
FIG. 2 is a flowchart showing a step S2 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the step S25 according to an embodiment of the present invention;
FIG. 4 is a second step flow chart of the step S2 according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating the step S26 according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating the step S263 according to an embodiment of the present invention;
FIG. 7 is a flowchart showing a step S4 according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating the step S44 according to an embodiment of the present invention;
FIG. 9 is a flowchart illustrating the step S46 according to an embodiment of the present invention;
fig. 10 is a second step flow chart of the step S4 according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
From the point of information analysis, a complex software system (Complex Software System, abbreviated as CSS) which is often widely used at present has certain errors in the process of analyzing data, namely, the information needs to be different from the information meeting requirements, and the information provided by the system is also different from the information used by a user. This deviation results from the gap between the algorithm of the system itself and the autonomous consciousness of the individual. It is therefore necessary to improve the accuracy of the information push method.
Referring to fig. 1, the invention provides an intelligent information pushing method based on user network behaviors. In the implementation process, the step S1 may be executed to classify the network information first, the step S2 may be executed to sample the initial sample information from different classifications of the network information according to the classification result of the network information, and the step S3 may be executed to push the initial sample information to the user. Step S4 may be performed next to obtain information category preferences of the user according to the network behavior of the user browsing the sample information, and step S5 may be performed next to select personalized information in the network information according to the information category preferences of the user. Step S6 may be performed to push the personalized information to the user, and finally step S7 may be performed to update the information category preference of the user according to the network behavior of the user browsing the personalized information. In the implementation process, the network behavior of the user is analyzed to obtain the information type preference of the user, personalized information is pushed to the user according to the information type preference, and the pushed personalized information is updated according to the updated user information preference, so that the technical effect of improving the information pushing accuracy of the user is achieved.
Referring to fig. 2, in order to obtain initial sample information, step S21 may be performed first to obtain the number of pieces of information in each type of network information, the browsing time of each piece of network information, and the browsing amount of each piece of network information according to the classification result of the network information in step S2. Step S22 may be performed to select a network information category for which the number of pieces of information reaches a set threshold as the basic information category. Step S23 may be performed to select network information whose browsing amount reaches a set threshold value in the basic information category as the basic information item. Step S24 may be performed next to sort each piece of network information in the basic information items according to the browsing time-consuming length of each piece of network information. Finally, step S25 may be executed to push the basic information items to the user by composing the initial sample information, where the network information with shorter browsing time consumption in the basic information items is pushed relatively preferentially. By the method, the typical representative information in the network information is selected to push the initial sample information, so that accuracy of acquiring information type preference of the user is improved.
Referring to fig. 3, in order to avoid that the sampling evaluation is insufficient due to insufficient time of the user' S initial use of the internet, thereby affecting the accuracy of the subsequent personalized information, step S25 may be performed first to obtain the number of basic information items in each basic information category in step S251. Next, step S252 may be performed to multi-wave-select the basic information items in each basic information category according to the number of basic information items that it contains as the basic information pushing unit. Step S253 may be performed next to push the basic information items in the basic information push unit generated at the same wave number. And finally, the step S254 can be executed, and when the basic information items in the basic information pushing unit of the previous wave are all pushed, the basic information items in the basic information pushing unit of the next wave are pushed. By the method, the situation that sampling evaluation is insufficient due to insufficient time of the user for the first time in using the Internet is avoided, and the acquisition accuracy of information type preference of the user is improved.
Referring to fig. 4, when the user uses the network for the first time and there is enough time, in order to improve the accuracy of obtaining the information category preference of the user, especially the information category preference of the public hobbies, step S26 may be further performed to select the network information category whose number of information pieces does not reach the set threshold as the extension information category in the above step S2. If the user continues to request to browse the network data after completing the pushing of the basic information item, step S27 may be executed to select the network information with the browsing amount reaching the set threshold value in the extension information category as the extension information item, and add the extension information item to the initial sample information for pushing. By adding the extension information types into the initial sample information, the acquisition accuracy of the information type preference of the user is improved.
Referring to fig. 5, in order to further improve the accuracy of obtaining the information category preference of the user, step S261 may be first performed to obtain the content similarity between the basic information category and the other information categories in step S26. The parsing may be performed to mark other information categories having content similarity greater than a set threshold as extension information categories in step S262. Finally, step S263 may be executed to obtain the ratio between the types of the extension information of different types when pushing the information to the user according to the ratio of the content similarity between the types of the extension information of different types and the types of the base information. The acquisition accuracy of the information category preference of the user is further improved by marking other information categories with content similarity larger than the set threshold value as extension information categories.
Referring to fig. 6, in order to determine the push status of each extension information, the accuracy of obtaining the information category preference of the user is never improved, step S2631 may be first performed in step S263, and the ratio of the number of basic information items between basic information categories may be obtained according to the number of basic information items in each basic information category. Step S2632 may be performed to acquire the weight of the basic information category according to the ratio of the number of basic information items between basic information categories. Step S2633 may be performed next to acquire a similarity between each extension information category and each base information category. Step S2634 may be performed to accumulate the product of the similarity between each extension information category and each basic information category and the weight of the corresponding basic information category, to obtain the push coefficient of each extension information category. Finally, step S263 may be executed to obtain the ratio between the types of the extension information of different types when pushing the information to the user according to the relative ratio of the pushing coefficients of each type of extension information. The accuracy of acquiring the information category preference of the user is further improved by acquiring the push coefficient of each extension information category.
Referring to fig. 7, in order to avoid the distortion caused by the network water force pushing the network information, step S41 may be first performed to obtain the browsing amount of each piece of network information in real time in step S4. If the browsing amount of the network information reaches the set threshold, step S42 may be performed to obtain the information browsing amount of the user browsing the piece of network information in real time. If the browsing amount of the user in the unit time reaches the set threshold, step S43 may be executed to acquire the hardware information, the network address and the corresponding network behavior data of the information access terminal of the user in real time. Step S44 may be performed to determine whether the corresponding user is an abnormal user according to the network behavior data corresponding to the same hardware information. If not, step S45 may be performed to continue providing the network push service. If so, step S46 may be executed to determine whether the corresponding user is blocked according to the network address of the information access terminal of the abnormal user. By judging abnormal users and further judging whether to block, distortion caused by network water armies to network information pushing is avoided, and therefore the technical effect of improving network information pushing precision is achieved.
Referring to fig. 8, in order to implement the determination of the abnormal user, in the above step S44, step S441 may be first performed to mark the information access terminal, where the information browsing amount in the unit time reaches the set threshold, as the suspicious information access terminal. Step S442 may be executed to send a control instruction to the suspicious information access end, so that the suspicious information access end extracts and uploads the digital abstract of the network behavior data cached by itself when the information browsing amount reaches the set threshold period. If the digital abstracts uploaded by the suspicious information access terminals of the network information with the browsing amount reaching the set threshold value in the browsing unit time have the same value, step S443 can be executed to extract the corresponding suspicious information access terminal as the abnormal information access terminal. Step S444 may be performed next, where the user corresponding to the abnormal information access terminal is an abnormal user. Through the mode, the judgment of the abnormal user is realized.
Referring to fig. 9, in order to accurately determine which abnormal users should be blocked, step S46 may be performed first to obtain the fuzzy geographic address of the information access terminal of the abnormal user according to the network address of the information access terminal of the abnormal user, and step S462 may be performed to obtain the clustering center of the fuzzy geographic address of the information access terminal of the abnormal user. Step S463 may be performed next to acquire a range covered by the fuzzy geographic address of the information access terminal of the abnormal user, and step S46 may be performed next to mark the abnormal user whose range covered by the fuzzy geographic address of the information access terminal overlaps with the cluster center as a blacklisted user. Finally, step S46 may be executed to block the blacklist user. By analyzing the geographic address of the information access terminal, the abnormal users are accurately judged to be forbidden, and distortion caused by pushing of network information by a network water army is further avoided.
Referring to fig. 10, in order to disclose the blacklist user while protecting the basic privacy, step S47 may be further performed to extract the irreversible digital digest as the encrypted public network blacklist identity together with the secret random information of the blacklist user in step S4, and step S48 may be performed to disclose the encrypted public network blacklist identity. Step S49 may be performed next to acquire hardware information of the blacklist user to be confirmed when receiving the external blacklist user determination request to be confirmed, and step S410 may be performed next to extract the irreversible digital digest as a confirmation return value together with the secret random information. Step S411 may be executed, where the blacklist user to be confirmed is sent out, and the request end determines whether the blacklist user is determined by comparing the confirmation return value with the blacklist identity of the public encrypted public network. The hardware information of the blacklist user is encrypted, the privacy of the blacklist user is protected while the hardware information is disclosed, and when an external third party needs to confirm whether the blacklist user is the blacklist user or not, confirmation can be completed by acquiring a confirmation return value, the hardware information is disclosed under the condition that the basic privacy of the blacklist user is protected, and the distortion and the diffusion of push information caused by the blacklist user are avoided.
In summary, the network behavior of the user is analyzed to obtain the information type preference of the user, and then the personalized information is selected from the network information according to the information type preference of the user, so that the generated personalized information is pushed to the user, and the accuracy of information pushing to the user is improved while the information requirement of the user is met.
The above description of illustrated embodiments of the invention, including what is described in the abstract, is not intended to be exhaustive or to limit the invention to the precise forms disclosed herein. Although specific embodiments of, and examples for, the invention are described herein for illustrative purposes only, various equivalent modifications are possible within the spirit and scope of the present invention, as those skilled in the relevant art will recognize and appreciate. As noted, these modifications can be made to the present invention in light of the foregoing description of illustrated embodiments of the present invention and are to be included within the spirit and scope of the present invention.
The systems and methods have been described herein in general terms as being helpful in understanding the details of the present invention. Furthermore, various specific details have been set forth in order to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that an embodiment of the invention can be practiced without one or more of the specific details, or with other apparatus, systems, assemblies, methods, components, materials, parts, and/or the like. In other instances, well-known structures, materials, and/or operations are not specifically shown or described in detail to avoid obscuring aspects of embodiments of the invention.
Thus, although the invention has been described herein with reference to particular embodiments thereof, a latitude of modification, various changes and substitutions are intended in the foregoing disclosures, and it will be appreciated that in some instances some features of the invention will be employed without a corresponding use of other features without departing from the scope and spirit of the invention as set forth. Therefore, many modifications may be made to adapt a particular situation or material to the essential scope and spirit of the present invention. It is intended that the invention not be limited to the particular terms used in following claims and/or to the particular embodiment disclosed as the best mode contemplated for carrying out this invention, but that the invention will include any and all embodiments and equivalents falling within the scope of the appended claims. Accordingly, the scope of the invention should be determined only by the following claims.
Claims (6)
1. An intelligent information pushing method based on user network behavior is characterized by comprising the steps of,
Classifying the network information;
sampling from different classifications of the network information according to the classification result of the network information to obtain initial sample information;
pushing the initial sample information to a user;
Obtaining information type preference of the user according to the network behavior of the user browsing the sample information;
Selecting personalized information from the network information according to the information type preference of the user;
Pushing the personalized information to the user;
updating the information type preference of the user according to the network behavior of the user browsing the personalized information;
The step of sampling initial sample information from different classifications of the network information according to the classification result of the network information comprises,
Obtaining the number of information pieces in each type of network information, the browsing time consumption of each piece of network information and the browsing quantity of each piece of network information according to the classification result of the network information;
Selecting a network information type with the number of information reaching a set threshold as a basic information type;
Selecting the network information with the browsing quantity reaching a set threshold value in the basic information category as a basic information item;
Ordering each piece of network information in the basic information items according to the browsing time-consuming length of each piece of network information;
Pushing the basic information items to form the initial sample information to the user, wherein the network information with shorter browsing time consumption length in the basic information items is pushed relatively preferentially;
The step of sampling initial sample information from different classifications of the network information according to the classification result of the network information further comprises,
Selecting the network information types with the number of information pieces not reaching a set threshold as extension information types;
If the user continues to request to browse network data after the pushing of the basic information item is completed, selecting the network information with the browsing quantity reaching a set threshold value in the expansion information category as an expansion information item, and adding the expansion information item to the initial sample information for pushing;
The step of selecting the network information type of which the number of information pieces does not reach the set threshold value as the extension information type includes,
Acquiring content similarity between the basic information category and other information categories;
marking other information types with content similarity larger than a set threshold value as extension information types;
According to the proportion of the content similarity between the different kinds of the expansion information types and the basic information types, obtaining the proportion between the different kinds of the expansion information types when information is pushed to a user;
The step of obtaining the ratio between the different kinds of the expanded information categories when pushing information to the user according to the ratio of the content similarity between the different kinds of the expanded information categories and the basic information categories, comprises,
Acquiring the comparison proportion of the quantity of the basic information items between the basic information categories according to the quantity of the basic information items in each basic information category;
Acquiring the weight of the basic information category according to the comparison proportion of the quantity of the basic information items among the basic information categories;
Obtaining the similarity between each extension information category and each basic information category;
Accumulating the similarity between each expansion information type and each basic information type and the product of the weight of the corresponding basic information type to obtain the push coefficient of each expansion information type;
And obtaining the proportion among the different types of the expansion information types when the information is pushed to the user according to the relative ratio of the push coefficients of each expansion information type.
2. The method of claim 1, wherein said pushing said base information item to said user comprising said initial sample information comprises,
Acquiring the number of basic information items in each basic information category;
Selecting the basic information items in each basic information category as basic information pushing units according to the quantity of the basic information items contained in each basic information category in multiple times;
Pushing the basic information items in the basic information pushing unit generated by the same wave number;
and pushing the basic information items in the basic information pushing unit of the next wave when the basic information items in the basic information pushing unit of the previous wave are completely pushed.
3. The method of claim 1, wherein the step of deriving information category preferences of the user based on network behavior of the user browsing the sample information comprises,
Acquiring the browsing amount of each piece of network information in real time;
If the browsing amount of the network information reaches a set threshold value, acquiring the information browsing amount of the user browsing the piece of the network information in real time;
if the information browsing amount of the user in unit time reaches a set threshold value, acquiring hardware information, a network address and corresponding network behavior data of an information access terminal of the user in real time;
judging whether the corresponding user is an abnormal user or not according to the network behavior data corresponding to the same piece of hardware information;
If not, continuing to provide the network push service;
If yes, judging whether the user is blocked or not according to the network address of the information access terminal of the abnormal user.
4. The method of claim 3, wherein said step of determining whether said corresponding user is an abnormal user based on said network behavior data corresponding to the same one of said hardware information comprises,
Marking the information access terminal with the information browsing amount reaching a set threshold value in unit time as a suspicious information access terminal;
Sending a control instruction to the suspicious information access terminal, so that the suspicious information access terminal extracts and uploads the digital abstract of the network behavior data cached by the suspicious information access terminal when the information browsing amount reaches a set threshold time period;
If the digital abstracts uploaded by the suspicious information access terminals of the network information, the browsing amount of which reaches a set threshold value in the browsing unit time, have the same value, the corresponding suspicious information access terminals are extracted to be marked as abnormal information access terminals;
The user corresponding to the abnormal information access terminal is an abnormal user.
5. The method of claim 3, wherein said step of determining whether said user-blocked should be corresponded to based on the network address of the information access terminal of said abnormal user comprises,
Acquiring a fuzzy geographic address of the information access terminal of the abnormal user according to the network address of the information access terminal of the abnormal user;
Acquiring a clustering center of the fuzzy geographic address of the information access terminal of the abnormal user;
acquiring a range covered by a fuzzy geographic address of an information access terminal of the abnormal user;
marking the abnormal users with overlapping coverage ranges of the fuzzy geographic addresses of the information access terminals and the clustering center as blacklist users;
And sealing and banning the blacklist user.
6. The method of claim 5, wherein the step of deriving information category preferences of the user based on network behavior of the user browsing the sample information further comprises,
Extracting the irreversible digital abstract together with the hardware information and the secret random information of the blacklist user to be used as an encrypted public network blacklist identity;
Disclosing the encrypted public network blacklist identity;
When an external blacklist user to be confirmed is received to confirm a request, acquiring hardware information of the blacklist user to be confirmed;
extracting an irreversible digital abstract as a confirmation return value together with the hardware information and the secret random information of the blacklist user to be confirmed;
And determining that the request end compares the confirmation return value with the disclosed encrypted public network blacklist identity by the blacklist user to be confirmed, and judging whether the request end is the blacklist user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211054533.9A CN115580649B (en) | 2022-08-31 | 2022-08-31 | Intelligent information pushing method based on user network behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211054533.9A CN115580649B (en) | 2022-08-31 | 2022-08-31 | Intelligent information pushing method based on user network behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115580649A CN115580649A (en) | 2023-01-06 |
| CN115580649B true CN115580649B (en) | 2024-05-03 |
Family
ID=84579114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211054533.9A Active CN115580649B (en) | 2022-08-31 | 2022-08-31 | Intelligent information pushing method based on user network behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115580649B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017071251A1 (en) * | 2015-10-28 | 2017-05-04 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN107341225A (en) * | 2017-06-30 | 2017-11-10 | 沈思远 | Information intelligent pushes and discrimination method, device and system |
| CN110717106A (en) * | 2019-10-14 | 2020-01-21 | 支付宝(杭州)信息技术有限公司 | Information pushing method and device |
| WO2022068659A1 (en) * | 2020-09-30 | 2022-04-07 | 深圳前海微众银行股份有限公司 | Information pushing method and apparatus and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11985101B2 (en) * | 2019-01-18 | 2024-05-14 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method, apparatus, electronic message server and computer program for processing a plurality of electronic messages |
-
2022
- 2022-08-31 CN CN202211054533.9A patent/CN115580649B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017071251A1 (en) * | 2015-10-28 | 2017-05-04 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN107341225A (en) * | 2017-06-30 | 2017-11-10 | 沈思远 | Information intelligent pushes and discrimination method, device and system |
| CN110717106A (en) * | 2019-10-14 | 2020-01-21 | 支付宝(杭州)信息技术有限公司 | Information pushing method and device |
| WO2022068659A1 (en) * | 2020-09-30 | 2022-04-07 | 深圳前海微众银行股份有限公司 | Information pushing method and apparatus and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| A Deep Reinforcement Learning Approach to Proactive Content Pushing and Recommendation for Mobile Users(Article);Liu, D等;《IEEE》;20191231;全文 * |
| 网络域名用户异常访问行为信息精准识别仿真;穆荣;;计算机仿真;20180715(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115580649A (en) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103117903B (en) | Surfing flow method for detecting abnormality and device | |
| CN108154425B (en) | Offline merchant recommendation method combining social network and location | |
| US9122731B2 (en) | Displaying search results | |
| RU2516762C2 (en) | Providing user with customised information based on trend identification | |
| US7558805B2 (en) | Searching content on web pages | |
| US7970750B2 (en) | Category searching | |
| US7225180B2 (en) | Filtering search results | |
| CN110321479B (en) | Privacy protection mobile service recommendation method, client and recommendation system | |
| CN113672937B (en) | Block chain link point | |
| US7424518B2 (en) | Information-presenting apparatus, information-presenting method, information-processing apparatus, information-processing method and program-storing medium | |
| CN107529093B (en) | Method and system for detecting playing amount of video file | |
| CN109583228B (en) | Privacy information management method, device and system | |
| CN112261429A (en) | Live broadcast application system, method, equipment and storage medium of cardless intelligent terminal | |
| CN103442267A (en) | User behavior information collection method and television | |
| KR100354207B1 (en) | Method and apparatus for protecting contents of porno on internet | |
| KR20070094264A (en) | Method for targeting web advertisement clickers based on click pattern by using a collaborative filtering system with neural networks and system thereof | |
| CN115580649B (en) | Intelligent information pushing method based on user network behaviors | |
| CN108596647B (en) | Advertisement putting method and device and electronic equipment | |
| CN116610040A (en) | Intelligent household appliance control method, system and device based on Internet of things | |
| CN111950657B (en) | DPI clustering and user expansion method | |
| KR101483189B1 (en) | Method and system for providing personalized advertisement by using integrated information | |
| KR20070094056A (en) | Method for targeting web advertisement clickers based on click pattern by using a collaborative filtering system and system thereof | |
| KR102458373B1 (en) | Management system with responsive customer classification | |
| CN112039994B (en) | Internet-based remote monitoring method, device and server | |
| CN112055075B (en) | Internet product monitoring method, device, server and readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |