Page pushing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a page pushing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: after a target user logs in a push application, determining at least one historical page accessed by the target user in a target historical time period; determining a plurality of similar users of the target user in the target historical period, and taking at least one historical page accessed by each similar user in the target historical period and at least one historical page accessed by the target user as pages to be screened; for each to-be-screened page, according to the behavior similarity between each similar user and the target user, determining the degree of interest of the target user to the to-be-screened page, according to the degree of interest of each to-be-screened page, determining a target page, and storing page data of the target page as hotspot data in a local cache; after the page access request of the target user is received, the target hotspot data is determined from the local cache to perform page pushing, so that the pushing effect is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a page push method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of Internet technology, the rapid expansion of business models and the growing user needs, the amount of data and user access to Web (network) applications has increased dramatically, and traditional database access methods can no longer meet access needs.

[0003] In the related art, a unified cache strategy is adopted to store and reuse previously requested push data to reduce the pressure on the database. However, the cache strategy of the related art usually focuses on the hot data of the entire push system and cannot provide personalized page push, resulting in poor page push effect. Summary of the invention

[0004] Based on this, it is necessary to provide a page push method, device, computer equipment, computer-readable storage medium and computer program product that can provide personalized page push and improve the page push effect in response to the above technical problems.

[0005] In a first aspect, the present application provides a page push method, comprising:

[0006] After the target user logs in to the push application, determining at least one historical page visited by the target user within a target historical period;

[0007] Determine a plurality of similar users who have similar page preferences as the target user during the target historical period, and use at least one historical page visited by each similar user during the target historical period and at least one historical page visited by the target user during the target historical period as pages to be screened;

[0008] For each page to be filtered, determine the interest level of the target user in the page to be filtered according to the behavior similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered according to the interest level corresponding to each page to be filtered, and store the page data of the target page as hotspot data in the local cache;

[0009] After receiving the page access request of the target user, target hotspot data is determined based on at least one hotspot data in the local cache, and page push is performed based on the target hotspot data.

[0010] In a second aspect, the present application also provides a page pushing device, including:

[0011] A page determination module, used to determine at least one historical page visited by the target user within a target historical period after the target user logs in to the push application;

[0012] A user determination module is used to determine a plurality of similar users who have similar page preferences as the target user within the target historical period, and to use at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be screened;

[0013] A page screening module, for each page to be screened, determining the interest level of the target user in the page to be screened according to the behavior similarity between each similar user and the target user, and screening out a target page from at least one page to be screened according to the interest level corresponding to each page to be screened, and storing the page data of the target page as hotspot data in a local cache;

[0014] The page push module is used to determine target hotspot data based on at least one hotspot data in the local cache after receiving a page access request from the target user, and push the page based on the target hotspot data.

[0015] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0016] After the target user logs in to the push application, determining at least one historical page visited by the target user within a target historical period;

[0017] Determine a plurality of similar users who have similar page preferences as the target user during the target historical period, and use at least one historical page visited by each similar user during the target historical period and at least one historical page visited by the target user during the target historical period as pages to be screened;

[0018] For each page to be filtered, determine the interest level of the target user in the page to be filtered according to the behavior similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered according to the interest level corresponding to each page to be filtered, and store the page data of the target page as hotspot data in the local cache;

[0019] After receiving the page access request of the target user, target hotspot data is determined based on at least one hotspot data in the local cache, and page push is performed based on the target hotspot data.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0021] After the target user logs in to the push application, determining at least one historical page visited by the target user within a target historical period;

[0022] Determine a plurality of similar users who have similar page preferences as the target user during the target historical period, and use at least one historical page visited by each similar user during the target historical period and at least one historical page visited by the target user during the target historical period as pages to be screened;

[0023] For each page to be filtered, determine the interest level of the target user in the page to be filtered according to the behavior similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered according to the interest level corresponding to each page to be filtered, and store the page data of the target page as hotspot data in the local cache;

[0024] After receiving the page access request of the target user, target hotspot data is determined based on at least one hotspot data in the local cache, and page push is performed based on the target hotspot data.

[0025] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0026] After the target user logs in to the push application, determining at least one historical page visited by the target user within a target historical period;

[0027] Determine a plurality of similar users who have similar page preferences as the target user during the target historical period, and use at least one historical page visited by each similar user during the target historical period and at least one historical page visited by the target user during the target historical period as pages to be screened;

[0028] For each page to be filtered, determine the interest level of the target user in the page to be filtered according to the behavior similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered according to the interest level corresponding to each page to be filtered, and store the page data of the target page as hotspot data in the local cache;

[0029] After receiving the page access request of the target user, target hotspot data is determined based on at least one hotspot data in the local cache, and page push is performed based on the target hotspot data.

[0030] The above-mentioned page push method, device, computer equipment, computer-readable storage medium and computer program product, after the target user logs in to the push application, determine at least one historical page visited by the target user within the target historical period; determine multiple similar users with similar page preferences as the target user within the target historical period, and use at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be filtered; for each page to be filtered, determine the target user's interest in the page to be filtered based on the behavioral similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered based on the interest corresponding to each page to be filtered, and store the page data of the target page as hot data in the local cache. That is, after filtering out the page of interest to the target user, it is stored in the local cache in advance, so that after receiving the page access request of the target user, there is no need to spend a lot of time waiting for data to be loaded, reducing access delay. Based on at least one hot spot data in the local cache, the target hot spot data that the target user is interested in can be quickly queried, and personalized page push can be performed in a timely and fast manner based on the target hot spot data. On the premise of improving the push speed, accurate push can be performed for the target user to improve the page push effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A diagram of an application environment of a page push method in an embodiment;

[0033] Figure 2 A schematic diagram of a flow chart of a page push method in one embodiment;

[0034] Figure 3 A schematic diagram of a sliding window determination step in one embodiment;

[0035] Figure 4 This is a schematic diagram of the interaction between various units when pushing a page in an embodiment;

[0036] Figure 5 A schematic diagram of a page push step in an embodiment;

[0037] Figure 6 It is a structural block diagram of a page pushing device in one embodiment;

[0038] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] Before introducing the embodiments of the present application, the following terms are explained:

[0041] Memcached: It is a memory-based key-value storage system. It is a high-performance distributed memory cache system used to store small blocks of arbitrary data (such as strings and objects). It is mainly used to accelerate the database access speed of Web applications by caching data, reduce the load on the database, and improve data retrieval efficiency.

[0042] Pearson Correlation Coefficient: It is widely used to measure the correlation between two variables, and its value is between -1 and 1.

[0043] Sliding window: A method widely used in data stream processing, real-time analysis, and cache management. It tracks and processes recent data items by maintaining a fixed-size window on the data set.

[0044] The page push method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0045] In some embodiments, after the target user logs in to the push application, the terminal 102 obtains at least one historical page visited by the target user within the target historical period and sent by the server 104; the terminal 102 determines multiple similar users who have similar page preferences as the target user within the target historical period, and uses at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be filtered; for each page to be filtered, the target user's interest in the page to be filtered is determined based on the behavioral similarity between each similar user and the target user, and based on the corresponding interest level of each page to be filtered, the target page is filtered out from at least one page to be filtered, and the page data of the target page is stored as hot spot data in the local cache; after receiving the page access request from the target user, the terminal 102 determines the target hot spot data based on at least one hot spot data in the local cache, and pushes the page based on the target hot spot data.

[0046] The local cache in the terminal 102 may be a Memcached cache. A push system is deployed on the server 104, which may be understood as a push server. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0047] In an exemplary embodiment, Figure 2 As shown, a page push method is provided, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, including the following steps S202 to S208. Among them:

[0048] Step S202: after the target user logs in to the push application, determine at least one historical page visited by the target user within a target historical period.

[0049] Among them, the push application refers to an application that can push content, and the history page is a push page in the push application.

[0050] Exemplarily, the terminal obtains historical user behavior data of the target user in the target historical period from the server, and the historical user behavior data is browsing data after the target user logs in to the push application. The terminal parses the historical user behavior data to determine at least one historical page visited by the target user in the target historical period.

[0051] Step S204, determine multiple similar users who have similar page preferences as the target user within the target historical period, and use at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be filtered.

[0052] Among them, similar users refer to users who have similar web page behaviors as the target user in the target historical period, which can be understood as other users with similar page preferences.

[0053] Optionally, the terminal obtains login data about the push application in the target historical period from the server, obtains other users who have logged into the push application in the target historical period from the login data, and obtains historical user behavior data of each other user from the login data.

[0054] The terminal determines multiple similar users from multiple other users based on the historical user behavior data of the target user and the historical user behavior data of each other user. The terminal uses at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be screened.

[0055] Exemplarily, the terminal determines the behavior similarity between the target user and other users based on the historical user behavior data of the target user and the historical user behavior data of each other user through similarity calculation (such as the Pearson correlation coefficient), and determines multiple similar users based on the corresponding behavior similarities of each other user.

[0056] In some other embodiments, after determining multiple similar users who have similar page preferences as the target user in the target historical period, the method further includes: using the multiple similar users who have similar page preferences as the target user in the target historical period as pages to be filtered. Then, continue to perform the following steps S206-208.

[0057] Step S206, for each page to be filtered, determine the target user's interest in the page to be filtered based on the behavioral similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered based on the interest level corresponding to each page to be filtered, and store the page data of the target page as hot data in the local cache.

[0058] Among them, the higher the behavior similarity between the target user and the similar user, the more similar the page preferences of the two users are.

[0059] Exemplarily, for each page to be filtered, the terminal determines the target user's interest in the page to be filtered according to the behavior similarity between the target user and each similar user, and the historical user behavior data of each similar user.

[0060] The terminal sorts the pages from high to low according to the interest level, and selects a preset number of top-ranked pages to be screened as target pages. The terminal obtains the page data of the target page returned by the server, uses the page data of the target page as hot data, and stores the hot data in a local cache in correspondence with the page ID of the target page and the target user ID.

[0061] Step S208, after receiving the page access request of the target user, determine the target hotspot data based on at least one hotspot data in the local cache, and push the page based on the target hotspot data.

[0062] Exemplarily, in response to a page access operation, one or more hotspot data are randomly selected from at least one hotspot data corresponding to a target user in a local cache as target hotspot data, and a page is pushed based on the target hotspot data.

[0063] In the above page push method, after the target user logs in to the push application, at least one historical page visited by the target user in the target historical period is determined; multiple similar users with similar page preferences as the target user in the target historical period are determined, and at least one historical page visited by each similar user in the target historical period and at least one historical page visited by the target user in the target historical period are used as pages to be filtered; for each page to be filtered, the degree of interest of the target user in the page to be filtered is determined according to the behavioral similarity between each similar user and the target user, and the target page is filtered out from at least one page to be filtered according to the degree of interest corresponding to each page to be filtered, and the page data of the target page is stored as hot data in the local cache. That is, after filtering out the page of interest to the target user, it is stored in the local cache in advance, so that after receiving the page access request of the target user, it is not necessary to spend a lot of time waiting for data to be loaded, which reduces the access delay. Based on at least one hot data in the local cache, the target hot data of interest to the target user can be quickly queried, and timely and fast personalized page push is performed based on the target hot data, and accurate push is performed for the target user on the premise of improving the push speed to improve the page push effect.

[0064] In some embodiments, the target historical time period determination step includes: counting the total historical time period of the target user logging into the push application at the current moment, and obtaining the total historical user behavior data of the target user within the total historical time period, and obtaining the total historical system load data about the push system within the total historical time period; based on the total historical user behavior data and the total historical system load data, determining the sliding window corresponding to the target user; sliding the sliding window at least once in the total historical time period, and taking the time period corresponding to the last slide as the target historical time period.

[0065] The total historical period is the total login time of the target user, which can be the period from the first login time to the latest login time; or it can be a period selected by the user without specific limitation. The total historical period is greater than or equal to the target historical period.

[0066] The total historical system load data reflects the load situation in the push system during the total historical period, and detects its performance problems. The total historical system load data at least includes CPU (Central Processing Unit) usage, memory usage, and disk I / O (input / output).

[0067] The total historical user behavior data reflects the historical access situation of a certain user within the total historical period. The total historical user behavior data at least includes the page access frequency and the user's stay time.

[0068] In this embodiment, by using the total historical user behavior data and the total historical system load data in the total historical period, the sliding window can determine the most appropriate duration closest to the current moment from the page interaction level and the load level to ensure the effectiveness and timeliness of subsequent caching. In other words, the sliding window intelligently updates the cached hotspot data to ensure that the latest or most interesting data is pushed to the user, thereby ensuring the timeliness of page push and improving user experience.

[0069] In some embodiments, Figure 3 FIG. 1 is a schematic diagram of a sliding window determination step in an embodiment. Based on the total historical user behavior data and the total historical system load data, a sliding window corresponding to a target user is determined, including:

[0070] Step S302, based on the total historical user behavior data, determine the target user's target page access frequency and target page dwell time, and determine the sliding window size according to the target page access frequency, target page dwell time and the total historical system load data.

[0071] Exemplarily, the target page access frequency and target page dwelling time of the target user in the total historical period are obtained from the total historical user behavior data. For example, the sum of the page access frequencies of each historical page visited by the target user in the total historical period is superimposed as the target page access frequency of the target user in the total historical period. Alternatively, the maximum page access frequency is selected from the page access frequencies of at least one historical page visited by the target user to be used as the target page access frequency. For example, the sum of the page dwelling time of each historical page visited by the target user in the total historical period is superimposed as the page dwelling time of the target user in the total historical period. Alternatively, the longest page dwelling time is selected from the page dwelling time of at least one historical page visited by the target user to be used as the target page dwelling time.

[0072] Exemplarily, the terminal obtains one of the CPU usage, memory usage, and disk I / O usage from the total historical system load data. The target page access frequency and the target page stay time in the total historical period are integrated with the obtained usage rate to determine the sliding window size. For example, the obtained usage rate, the target page access frequency, and the target page stay time are superimposed to obtain the sliding window size.

[0073] Step S304, obtaining the current processing capacity of the push system at the current moment, and determining the adjustment factor corresponding to the current moment based on the current system load data and the total historical system load data of the push system.

[0074] The processing capacity of the push system is related to the load. The greater the load, the smaller the processing capacity. The adjustment factor is used to adjust the ratio between the current processing capacity and the maximum processing capacity. The load refers to the load of the push system, which is represented by at least one of the CPU usage, memory usage, and disk I / O usage mentioned above. The current system load data is the system load data of the push system at the current moment.

[0075] For example, the adjustment factor is calculated using the following formula (1): :

[0076] (1)

[0077] Where e is the exponential operation, S is the target page access frequency in the total historical system load data, is the target page access frequency in the current system load data. S is the target page stay time in the historical system load total data. The duration of the target page in the current system load data.

[0078] Step S306: Determine the sliding step size based on the maximum processing capacity, current processing capacity and adjustment factor of the push system.

[0079] Exemplarily, the terminal calculates the current processing capacity and maximum processing capacity and the adjustment factor The product of is taken as the sliding step length L. For example, referring to formula (2):

[0080] (2)

[0081] It should be noted that the sliding step size L is set according to the processing capacity and real-time requirements of the push system. It determines the frequency of sliding window updates. It is necessary to ensure that data processing does not exceed the push system load and that the push system can respond to data changes in a timely manner. A smaller L means more frequent updates, which may lead to a higher push system load. Therefore, the sliding step size L should be inversely proportional to the load of the push system.

[0082] Step S308: Determine the sliding window based on the sliding window size and the sliding step size.

[0083] In this embodiment, the current sliding window is adjusted adaptively according to the load of the push system to ensure that when the hot data is determined by the currently determined sliding window, there will be no significant impact on the load of the push system, thereby ensuring the reliability of page push. That is, the sliding window can be used to intelligently update cache data to ensure that the latest or most interesting data is pushed to the user. At the same time, the cache efficiency is improved, the optimal use of the cache space is guaranteed, and system resources are used more efficiently.

[0084] In some embodiments, the sliding window size is determined based on the target page access frequency, the target page dwell time and the total historical system load data, including: weighting the target page access frequency, the target page dwell time and the total historical system load data according to their respective corresponding weights to obtain the sliding window size.

[0085] Exemplarily, one usage rate is selected from the three usage rates of CPU usage rate, memory usage rate, and disk I / O usage rate in the total historical system load data. And according to the weights corresponding to the target page access frequency, the target page stay time, and the selected usage rate, the target page access frequency, the target page stay time, and the selected usage rate are weighted to determine the sliding window size.

[0086] For example, the following formula (3) is used to determine the sliding window size: :

[0087] (3)

[0088] in, , and is the weight coefficient, which is used to adjust the impact of different factors on the window size. is the target page visit frequency in the total historical period; t is the target user's stay time in the total historical period, This is historical load data.

[0089] It should be noted that the sliding window size determines the amount of data captured to adequately represent user behavior. The larger the window, the more data is included in the processing.

[0090] In this embodiment, by taking weighted sum of the target page access frequency, the target page dwell time and the total historical system load data, the three indicators of page access frequency, dwell time and load can be integrated to obtain a more accurate sliding window size.

[0091] In some embodiments, determining multiple similar users who have similar page preferences as the target user within a target historical period includes: determining multiple other users who logged into the push application within the target historical period; for each other user, calculating the behavioral similarity between the other user and the target user based on the historical user behavior data of the other user and the historical user behavior data of the target user; sorting the multiple behavioral similarities from high to low, and taking the other users corresponding to a preset number of top-ranked behavioral similarities as similar users of the target user.

[0092] Exemplarily, for each other user and each page to be filtered, based on the historical user behavior data of other users, the sub-historical user behavior data of other users for the page to be filtered is obtained to determine the page access frequency of the other users to the page to be filtered; based on the sub-historical user behavior data of the target user for the page to be filtered, the page access frequency of the target user to the page to be filtered is determined.

[0093] For each other user and each to-be-screened page, the behavior similarity between the other user and the target user is obtained by calculating the Pearson correlation coefficient function based on the page access frequency of the other user accessing the to-be-screened page and the page access frequency of the target user accessing the to-be-screened page.

[0094] Alternatively, for each other user and each page to be filtered, the length of time the other user stays on the page to be filtered is determined based on the sub-historical user behavior data of the other user for the page to be filtered; and the length of time the target user stays on the page to be filtered is determined based on the sub-historical user behavior data of the target user for the page to be filtered.

[0095] For each other user and each page to be filtered, the behavior similarity between the other user and the target user is calculated through the Pearson correlation coefficient function according to the page dwell time of the other user visiting the page to be filtered and the page dwell time of the target user visiting the page to be filtered.

[0096] For example: For each other user v, refer to the following formula (4) to determine the behavior similarity between the other user v and the target user u: :

[0097] (4)

[0098] Where n is the number of pages to be filtered. is the page access frequency of target user u to the filtered page i in the target historical period. is the average page access frequency of the target user u in the target historical period, that is, the average of the sum of the page access frequencies of the target user u visiting each page to be filtered. is the page access frequency or page dwelling time of the target user v on the filtered page i during the target historical period. The average page access frequency of the target user v in the target historical period, that is, the average of the sum of the page access frequencies of the target user v visiting each page to be filtered.

[0099] Of course, the page access frequency can also be replaced by the page dwell time in the above formula (3) for calculation.

[0100] In this embodiment, by using the historical user behavior data of other users and the historical user behavior data of the target user, it is possible to more accurately evaluate whether the other users are users with similar page preferences to the target user.

[0101] In some embodiments, the target user's interest level in the page to be filtered is determined based on the behavioral similarity between each similar user and the target user, including: for each similar user, obtaining sub-historical user behavior data about the page to be filtered from the historical user behavior data of the similar user, and determining the sub-interest level corresponding to the similar user based on the behavioral similarity between the similar user and the target user, and the sub-historical user behavior data; and fusing the sub-interest levels corresponding to each similar user to determine the target user's interest level in the page to be filtered.

[0102] Exemplarily, for each similar user, the terminal obtains the page access frequency from the sub-historical user behavior data of the similar user for the page to be filtered, and determines the sub-interest level corresponding to the similar user based on the behavioral similarity between the similar user and the target user and the obtained page access frequency. After fusing the sub-interest levels corresponding to each similar user and normalizing them, the interest level of the target user for the page to be filtered is obtained.

[0103] Alternatively, for each similar user, the terminal obtains the page dwell time from the sub-historical user behavior data of the similar user for the page to be screened, and determines the sub-interest level corresponding to the similar user based on the behavior similarity between the similar user and the target user and the obtained page dwell time. After fusing the sub-interest levels corresponding to each similar user and normalizing them, the interest level of the target user for the page to be screened is obtained.

[0104] The following example is used to illustrate. See formula (5) for details. It is used to calculate the interest level of the target user u in the page P to be filtered. :

[0105] (5)

[0106] in, A collection of users similar to the target user. is the behavior similarity between the target user u and similar user v.

[0107] In this embodiment, the sub-historical user behavior data of similar users and the behavior similarity between similar users and the target user are used to accurately predict the target user's interest in the corresponding page to be filtered, so that the target page can be filtered out and stored in the local cache in time, thereby improving the page loading efficiency.

[0108] In a specific embodiment, Figure 4 FIG. 1 is a schematic diagram showing the interaction between various units when a page is pushed in an embodiment. Figure 4 The terminal includes a user behavior detection unit, a system load detection unit, a data processing center, a cache strategy adjustment unit, a data pre-fetching unit and a local cache. Figure 5 As shown in FIG. 1 , a schematic diagram of a page push step in an embodiment is shown in FIG. Figure 4 and Figure 5 The page push process provided by the embodiment of the present application is described as follows:

[0109] Step 1: Determine the sliding window corresponding to the target user.

[0110] Specifically, after the target user logs in to the push application at the current moment, the user behavior detection unit obtains the total historical user behavior data of the target user in the target historical period and sends it to the data processing center; and the system load detection unit obtains the total historical system load data of the push system in the total historical period and sends it to the data processing center. The data processing center determines the sliding window corresponding to the target user based on the total historical user behavior data of the target user and the total historical system load data of the push system.

[0111] Exemplarily, the total historical user behavior data and the total historical system load data of the target user can be obtained from the server, or can be obtained by the user behavior detection unit and the system load detection unit respectively. For example, the user behavior detection unit is configured with JavaScript (a scripting language), thereby enabling the query of page access frequency and the query of user stay time. Use the browser to record the pages and timestamps visited by each user, use Ajax technology (a web development technology used to create interactive web applications) to trigger the sending of data to the server regularly or when the user leaves the page, and integrate web analysis tools to automatically query the number of page visits and provide a detailed analysis report, thereby realizing page access frequency query. In order to realize the user stay time query, set a timer when the page is loaded, check the user's activities regularly, add event detectors for interactive elements on the page (such as buttons, links, forms, etc.), capture the moment when the user leaves the page by listening to the event, and calculate the stay time.

[0112] The system load detection unit collects performance data of user devices and monitors the operation status of Web applications (push applications) through the API (application programming interface) provided by the browser, and uses the chart library on the front end to visualize the performance data.

[0113] Exemplarily, the data processing center pre-processes the total historical user behavior data and the total historical system load data.

[0114] Next, the cache strategy adjustment unit determines a sliding window based on the pre-processed historical user behavior total data and the historical system load total data, and determines a sliding window corresponding to the target user.

[0115] For example, based on the total historical user behavior data, the target page visit frequency and the target page dwell time of the target user are determined, and the target page visit frequency, the target page dwell time and the historical system load total data are weighted according to their corresponding weights to obtain the sliding window size; the current processing capacity of the push system at the current moment is obtained, and based on the current system load data of the push system and the historical system load total data, the corresponding adjustment factor at the current moment is determined; based on the maximum processing capacity of the push system, the current processing capacity and the adjustment factor, the sliding step size is determined; based on the sliding window size and the sliding step size, the sliding window is determined.

[0116] Step 2: The cache strategy adjustment unit initializes the sliding window.

[0117] Step 3: The cache strategy adjustment unit slides the total historical period in sequence according to the sliding window to determine the target historical period.

[0118] Specifically, the sliding window is slid at least once in the total historical period, and the period corresponding to the last sliding is used as the target historical period.

[0119] Step 4: The data pre-fetching unit analyzes the target page that the target user is interested in based on the historical user behavior data of similar users of the target user and the historical user behavior data of the target user.

[0120] Specifically, multiple other users who logged into the push application within the target historical period are determined; for each other user, the behavior similarity between the other user and the target user is calculated based on the historical user behavior data of the other user and the historical user behavior data of the target user; multiple behavior similarities are sorted from high to low, and the other users corresponding to the preset number of behavior similarities ranked at the top are all used as similar users of the target user. At least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period are all used as pages to be screened.

[0121] For each page to be filtered and each similar user, the sub-historical user behavior data about the page to be filtered is obtained from the historical user behavior data of the similar user, and the sub-interest level corresponding to the similar user is determined based on the behavioral similarity between the similar user and the target user, as well as the sub-historical user behavior data; the sub-interest levels corresponding to each similar user are integrated to determine the interest level of the target user in the page to be filtered. According to the interest levels corresponding to each page to be filtered, the target page is filtered out from at least one page to be filtered.

[0122] Step 5: The local cache uses the page data of the target page as hot data and loads the hot data for caching. After receiving the page access request from the target user, the target hot data is determined based on at least one hot data in the local cache, and the page is pushed based on the target hot data.

[0123] In this embodiment, after the target user logs in to the push application, at least one historical page visited by the target user in the target historical period is determined; multiple similar users with similar page preferences as the target user in the target historical period are determined, and at least one historical page visited by each similar user in the target historical period and at least one historical page visited by the target user in the target historical period are used as pages to be filtered; for each page to be filtered, the degree of interest of the target user in the page to be filtered is determined according to the behavioral similarity between each similar user and the target user, and the target page is filtered out from at least one page to be filtered according to the degree of interest corresponding to each page to be filtered, and the page data of the target page is stored as hot data in the local cache. That is, after filtering out the page of interest to the target user, it is stored in the local cache in advance, so that after receiving the page access request of the target user, it is not necessary to spend a lot of time waiting for data to be loaded, which reduces the access delay. Based on at least one hot data in the local cache, the target hot data of interest to the target user can be quickly queried, and timely and fast personalized page push is performed based on the target hot data. On the premise of improving the push speed, accurate push is performed for the target user to improve the page push effect, thereby significantly improving the user experience.

[0124] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0125] Based on the same inventive concept, the embodiment of the present application also provides a page push device for implementing the page push method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more page push device embodiments provided below can refer to the limitations of the page push method above, and will not be repeated here.

[0126] In an exemplary embodiment, Figure 6 As shown, a page push device 600 is provided, comprising: a page determination module 602, a user determination module 604, a page screening module 606 and a page push module 608, wherein:

[0127] The page determination module 602 is used to determine at least one historical page visited by the target user within a target historical period after the target user logs in to the push application;

[0128] The user determination module 604 is used to determine multiple similar users who have similar page preferences as the target user in the target historical period, and use at least one historical page visited by each similar user in the target historical period and at least one historical page visited by the target user in the target historical period as pages to be filtered;

[0129] The page screening module 606 is used to determine, for each page to be screened, the interest level of the target user in the page to be screened according to the behavior similarity between each similar user and the target user, and screen out the target page from at least one page to be screened according to the interest level corresponding to each page to be screened, and store the page data of the target page as hot data in the local cache;

[0130] The page push module 608 is used to determine target hotspot data based on at least one hotspot data in the local cache after receiving a page access request from a target user, and push the page based on the target hotspot data.

[0131] In some embodiments, the device also includes a time period determination module, which is used to count the total historical time period of the target user logging into the push application at the current moment, and obtain the total historical user behavior data of the target user within the total historical time period, and obtain the total historical system load data about the push system within the total historical time period; based on the total historical user behavior data and the total historical system load data, determine the sliding window corresponding to the target user; slide the sliding window at least once in the total historical time period, and use the time period corresponding to the last slide as the target historical time period.

[0132] In some embodiments, a time period determination module is used to determine the target user's target page access frequency and target page dwell time based on the total historical user behavior data, and determine the sliding window size based on the target page access frequency, target page dwell time and the total historical system load data; obtain the current processing capacity of the push system at the current moment, and determine the adjustment factor corresponding to the current moment based on the current system load data of the push system and the total historical system load data; determine the sliding step size based on the maximum processing capacity of the push system, the current processing capacity and the adjustment factor; determine the sliding window based on the sliding window size and the sliding step size.

[0133] In some embodiments, the time period determination module is used to weight the target page access frequency, the target page dwell time and the historical system load total data according to their respective corresponding weights to obtain the sliding window size.

[0134] In some embodiments, the user determination module 604 is used to determine multiple other users who have logged into the push application within the target historical period; for each other user, based on the historical user behavior data of the other user and the historical user behavior data of the target user, calculate the behavior similarity between the other user and the target user; sort the multiple behavior similarities from high to low, and use the other users corresponding to a preset number of top-ranked behavior similarities as similar users of the target user.

[0135] In some embodiments, the page filtering module 606 is used to obtain, for each similar user, sub-historical user behavior data about the page to be filtered from the historical user behavior data of the similar user, and determine the sub-interest level corresponding to the similar user based on the behavioral similarity between the similar user and the target user, as well as the sub-historical user behavior data; and determine the target user's interest level in the page to be filtered by integrating the sub-interest levels corresponding to each similar user.

[0136] Each module in the above-mentioned page push device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0137] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a page push method is implemented.

[0138] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0143] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0145] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A page push method, characterized in that: The method comprises: After the target user logs in to the push application, determining at least one historical page visited by the target user within a target historical period; Determine a plurality of similar users who have similar page preferences as the target user during the target historical period, and use at least one historical page visited by each similar user during the target historical period and at least one historical page visited by the target user during the target historical period as pages to be screened; For each page to be filtered, determine the interest level of the target user in the page to be filtered according to the behavior similarity between each similar user and the target user, and filter out the target page from at least one page to be filtered according to the interest level corresponding to each page to be filtered, and store the page data of the target page as hotspot data in the local cache; After receiving the page access request of the target user, target hotspot data is determined based on at least one hotspot data in the local cache, and page push is performed based on the target hotspot data.

2. The method according to claim 1, characterized in that: The target historical period determination step includes: At the current moment, count the total historical time period during which the target user logs in to the push application, obtain the total historical user behavior data of the target user in the total historical time period, and obtain the total historical system load data about the push system in the total historical time period; Determine a sliding window corresponding to the target user based on the historical user behavior total data and the historical system load total data; The sliding window is used to slide at least once in the total historical period, and the period corresponding to the last slide is used as the target historical period.

3. The method according to claim 2, characterized in that The determining the sliding window corresponding to the target user based on the historical user behavior total data and the historical system load total data includes: Based on the total historical user behavior data, determine the target page access frequency and target page dwell time of the target user, and determine the sliding window size according to the target page access frequency, the target page dwell time and the total historical system load data; Acquire the current processing capacity of the push system at the current moment, and determine the adjustment factor corresponding to the current moment based on the current system load data of the push system and the total historical system load data; Determining a sliding step size based on the maximum processing capacity of the push system, the current processing capacity and the adjustment factor; The sliding window is determined based on the sliding window size and the sliding step size.

4. The method according to claim 3, characterized in that The determining of the sliding window size according to the target page access frequency, the target page stay time and the total historical system load data includes: The target page access frequency, the target page dwell time and the historical system load total data are weighted according to their respective corresponding weights to obtain the sliding window size.

5. The method according to claim 1, characterized in that The determining of a plurality of similar users having similar page preferences as the target user within the target historical period includes: Determining a plurality of other users who logged into the push application during the target historical period; For each other user, based on the historical user behavior data of the other user and the historical user behavior data of the target user, calculate the behavior similarity between the other user and the target user; The multiple behavior similarities are sorted from high to low, and other users corresponding to a preset number of top-ranked behavior similarities are all regarded as similar users of the target user.

6. The method according to claim 1, characterized in that Determining the interest of the target user in the to-be-screened page according to the behavior similarity between each similar user and the target user includes: For each similar user, sub-historical user behavior data about the to-be-screened page is obtained from the historical user behavior data of the similar user, and a sub-interest level corresponding to the similar user is determined according to the behavior similarity between the similar user and the target user and the sub-historical user behavior data; The sub-interest levels corresponding to the similar users are integrated to determine the interest level of the target user in the page to be filtered.

7. A page pushing device, characterized in that: The device comprises: A page determination module, used to determine at least one historical page visited by the target user within a target historical period after the target user logs in to the push application; A user determination module is used to determine a plurality of similar users who have similar page preferences as the target user within the target historical period, and to use at least one historical page visited by each similar user within the target historical period and at least one historical page visited by the target user within the target historical period as pages to be screened; A page screening module, for each page to be screened, determining the interest level of the target user in the page to be screened according to the behavior similarity between each similar user and the target user, and screening out a target page from at least one page to be screened according to the interest level corresponding to each page to be screened, and storing the page data of the target page as hotspot data in a local cache; The page push module is used to determine target hotspot data based on at least one hotspot data in the local cache after receiving a page access request from the target user, and push the page based on the target hotspot data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images