Information display frequency control method based on user behavior characteristics

Abstract

The invention discloses an information display frequency control method based on user behavior characteristics, relates to the technical field of information display control, is used for solving the problem of excessive pushing of display contents, and obtains similar potential groups by setting a group division mechanism for initial users. Selecting target information according to the information display duration of each group, extracting word frequency, screening representative vocabularies, screening a target group according to the representative vocabularies, displaying the information of the target group on a user interface, setting a display frequency, monitoring the browsing duration and the browsing amount of a user in real time, performing statistics, and screening out the target group according to a result. Generating an update ratio according to the screening quantity to enter a frequency adjustment mechanism, adjusting a display frequency by using the update ratio to obtain a precise frequency, monitoring a screening result in real time to judge whether to quit the frequency adjustment mechanism, and collecting user click search and active refresh times during quit to determine whether to quit the group division mechanism; user fatigue caused by information redundancy is avoided, and information utilization efficiency and resource allocation rationality are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information display control, more particularly, the present application relates to a method for controlling information display frequency based on user behavior characteristics. BACKGROUND

[0002] With the rapid development of Internet information services, there are more and more ways for users to obtain information through terminal devices, and information pushing and display have gradually become the key means for platforms to improve user stickiness and information dissemination efficiency. Most of the existing information display methods are based on user registration information, historical browsing records or platform recommendation algorithms.

[0003] The prior art has the following disadvantages: At present, the prior art generally adopts fixed display frequency or rough frequency adjustment strategy, which cannot be dynamically adjusted in combination with real-time behavior characteristics of users, lacks depth analysis of potential group behavior characteristics, and thus leads to over-pushing of display content, insufficient information relevance and decline of user experience. Therefore, a method for controlling information display frequency based on user behavior characteristics is proposed.

[0004] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a method for controlling information display frequency based on user behavior characteristics, which uses a dynamic control strategy combining group division mechanism, word frequency analysis and similarity screening, activity calculation based on browsing behavior and frequency adjustment mechanism to solve the problems raised in the above background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme, a method for controlling information display frequency based on user behavior characteristics, comprising the following steps: Step S1: setting a group division mechanism for an initial user to obtain multiple same-potential groups of the initial user, and selecting target information of the same-potential groups according to the information display time length of each same-potential group; Step S2: extracting the word frequency of the target information of the same-potential groups and screening to obtain representative words of the same-potential groups, screening the same-potential groups according to the representative words to obtain a target group, and displaying the information of the target group to the initial user interface; Step S3: setting a display frequency, real-time monitoring and counting the browsing time length and browsing volume of the initial user to each target group information, screening out the target groups according to the browsing time length and browsing volume, and generating an update ratio according to the number of screened-out target groups; Step S4: After generating the update rate, enter the frequency adjustment mechanism, adjust the display frequency using the update rate and obtain the accurate display frequency, and monitor the screening results of the target group in real time to determine whether to exit the frequency adjustment mechanism; Step S5: When exiting the frequency adjustment mechanism, collect the number of user clicks and the number of active refreshes to determine whether to exit the group division mechanism.

[0007] In a preferred embodiment, in step S1, the initial user is substituted into the set group division mechanism, and the initial information filled in by the initial user when registering is collected; The initial information is substituted into the preset group division mechanism to divide the initial user into a plurality of preset groups, the preset group into which the initial user is divided is marked, and a plurality of same-potential groups of the initial user are obtained. The information display time of each same-potential group is counted by the built-in clock, and the information with the longest information display time in each same-potential group is selected as the target information of the same-potential group.

[0008] In a preferred embodiment, in step S2, the number of occurrences of each word in the target information of the same-potential group is counted to obtain the number of occurrences of each word and the total number of word occurrences in the target information, and the ratio of the number of occurrences of each word to the total number of word occurrences is calculated to obtain the word frequency of each word in the target information of the same-potential group. The word frequencies of each word in the target information of the same-potential group are sorted in descending order according to the numerical value, and the word with the largest word frequency value is selected as the representative word of the same-potential group. The word frequency of the representative word of the same-potential group is called, sorted in descending order according to the numerical value of the word frequency of the representative word of the same-potential group, and the representative words of the preset comparison quantity are selected as comparison representative words according to the arrangement order, and the remaining representative words are selected as candidate representative words. The same-potential group corresponding to the comparison representative word is marked as the target group by default.

[0009] In a preferred embodiment, in step S2, each candidate representative word and each comparison representative word is vectorized, and the similarity between each candidate representative word and each comparison representative word is calculated according to the cosine similarity calculation formula. The similarity between each candidate representative word and each comparison representative word is grouped according to the number of candidate representative words to obtain each candidate representative word similarity group. The target value of each candidate representative word is obtained by averaging each candidate representative word similarity group. The target value of each candidate representative word is compared with the preset similarity threshold. If the candidate representative word target value exceeds the similarity threshold value, the same type of potential group corresponding to the current candidate representative word is screened out; If the candidate representative word target value is lower than the similarity threshold value, the same type of potential group corresponding to the current candidate representative word is marked as a target group; The information corresponding to the target group screened out is used for interface display of the initial user.

[0010] In a preferred embodiment, in step S3, the browsing time and the browsing volume of the initial user for each target group information are monitored in real time within the set display frequency; During the browsing process of the initial user within the display frequency, the single stay time of each information belonging to the current target group is recorded, and the stay time of all information under the current target group within the display frequency is accumulated to obtain the browsing time of the target group information; Each time the initial user clicks to enter any information of the current target group within the display frequency is counted as one browsing and is counted to obtain the browsing volume of the target group information.

[0011] In a preferred embodiment, in step S3, the browsing time and the browsing volume of each target group information after standardization are substituted into the geometric mean method to obtain the activity coefficient of each target group; The activity coefficient of each target group is compared with the activity threshold value; If the activity coefficient of the target group exceeds the activity threshold value, the current target group is retained; If the activity coefficient of the target group is lower than the activity threshold value, the current target group is screened out; The number of screened-out target groups is counted to obtain the total number of screened-out target groups, and the total number of screened-out target groups is multiplied by a preset adjustment coefficient to obtain an update ratio.

[0012] In a preferred embodiment, in step S4, after entering the frequency adjustment mechanism, the update ratio is multiplied by the display frequency to obtain a display frequency adjustment amount, the display frequency is subtracted by the display frequency adjustment amount to obtain a precise display frequency; After obtaining the precise display frequency, the browsing time and the browsing volume of the initial user for each target group information are monitored in real time within the precise display frequency and are counted, and the target group is screened out comprehensively according to the browsing time and the browsing volume.

[0013] In a preferred embodiment, in step S4, the number of screened-out target groups is detected, if the number of screened-out target groups is zero, an exit signal is generated and executed, and the frequency adjustment mechanism is exited; If the number of screened target groups is not zero, an update rate is generated, and the accurate display frequency is adjusted again according to the update rate to obtain an updated accurate display frequency; When the updated accurate display frequency is obtained, the initial user's browsing time length and browsing volume for the information of each target group are repeatedly monitored and counted, and the target groups are screened according to the browsing time length and the browsing volume until an exit signal is generated.

[0014] In a preferred embodiment, in step S5, when the exit frequency adjustment mechanism is adjusted, the user's search click frequency and the active refresh frequency are collected within the accurate display frequency according to the accurate display frequency. The total number of times that the initial user clicks the search box to search within the accurate display frequency is counted to obtain the user's search click frequency. The number of times that the initial user triggers information refresh through page refresh within the accurate display frequency is counted as the active refresh frequency.

[0015] In a preferred embodiment, in step S5, the user's search click frequency and the active refresh frequency are standardized and then input into a polynomial regression calculation to obtain an exit group coefficient. The exit group coefficient is compared with a preset group threshold value. If the exit group coefficient exceeds the group threshold value, the group division mechanism is exited, and an alarm signal is generated. If the exit group coefficient is lower than the group threshold value, the group division mechanism is retained.

[0016] Technical effects and advantages of the present application: The present application sets up a group division mechanism for the initial user to obtain multiple same-potential groups of the initial user, selects target information of the same-potential group according to the information display time length of the same-potential group, extracts word frequency to obtain representative words of the same-potential group, screens the same-potential group according to the representative words to obtain target groups, displays the information of the target groups to the initial user interface, sets a display frequency, monitors and counts the initial user's browsing time length and browsing volume for the information of each target group in real time, screens the target groups according to the browsing time length and the browsing volume, generates an update rate according to the number of screened target groups, enters a frequency adjustment mechanism, adjusts the display frequency using the update rate and obtains an accurate display frequency, monitors the screening result of the target groups in real time to determine whether to exit the frequency adjustment mechanism, collects the user's search click frequency and the active refresh frequency to determine whether to exit the group division mechanism when the frequency adjustment mechanism is exited, realizes the personalization and precision of information display, avoids user fatigue caused by information redundancy, and improves the utilization efficiency of information display and the rationality of information resource allocation. BRIEF DESCRIPTION OF DRAWINGS

[0017] Fig. 1 The flow chart of the implementation of the information display frequency control method based on user behavior characteristics.

[0018] Fig. 2 The step schematic diagram of the information display frequency control method based on user behavior characteristics. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0020] Embodiment 1 Please refer to Figs. 1-2 The information display frequency control method based on user behavior characteristics, and the specific operation process is as follows: Step S1: The initial user is set into the group division mechanism to obtain multiple same-potential groups of the initial user, and the target information of the same-potential group is selected according to the information display time length of the same-potential group; Step S2: The word frequency of the target information of the same-potential group is extracted and screened to obtain the representative words of the same-potential group, the target group is obtained by screening the same-potential group according to the representative words, and the target group information is displayed on the initial user interface; Step S3: Set the display frequency, and real-time monitor and count the browsing time and browsing volume of the initial user to each target group information, and screen out the target group according to the browsing time and browsing volume, and generate an update rate according to the number of screened-out target groups; Step S4: After generating the update rate, enter the frequency adjustment mechanism, adjust the display frequency using the update rate and obtain the accurate display frequency, and real-time monitor the screening result of the target group to determine whether to exit the frequency adjustment mechanism; Step S5: When exiting the frequency adjustment mechanism, collect the number of user clicks and the number of active refreshes to determine whether to exit the group division mechanism.

[0021] The specific implementation process is as follows: In step S1, the initial user is put into the set group division mechanism, and the initial information filled in by the initial user during registration is collected; The initial user refers to a user who completes first registration or first login in the system, and the behavior characteristics of the current user cannot be retrieved in the user behavior characteristic library. The specific initial user identification and judgment conditions can be set by the person skilled in the art according to the actual application requirements and user behavior characteristic collection constraints, and will not be repeated here. Further, the user behavior characteristic library refers to a database for storing behavior data generated by the user in the system. The user behavior characteristics recorded in the library include but are not limited to the user's browsing behavior characteristics, the user's interaction behavior characteristics, the user's preference behavior characteristics, and the user's access environment characteristics, etc. The specific types and collection range of behavior characteristics are not limited, and will not be repeated here. The initial information includes initial user gender, age, interest label, IP address, and registration channel information, etc. The specific number of initial information is determined by the person skilled in the art according to the information filling box set by the user when entering the registration UI interface, and will not be repeated here. Further, the interest label sets the core dimension according to the application platform type (e.g. commodity category of e-commerce platform or content field of information platform, form, etc.), and is collected through multiple selection and semantic matching. The initial information is substituted into the preset group division mechanism to divide the initial user into multiple preset groups. The preset group into which the initial user is divided is marked to obtain multiple same-potential groups of the initial user. Specifically, for example, the group division mechanism includes a classification method based on attribute characteristics, a method based on geographic labels, and a division method based on clustering algorithm, etc. For example, the classification method based on attribute characteristics divides the user into the corresponding group according to gender, age interval, etc. For example, the method based on geographic labels divides the user into the group according to the regional range or network access location of the IP address. For example, the division method based on clustering algorithm divides the initial user into multiple same-potential groups by using K-means, DBSCAN, hierarchical clustering, etc. The implementation of the specific group division mechanism is not limited, and will not be repeated here. The implementation process of the specific clustering method is well known to the person skilled in the art, and will not be repeated here. Further, the person skilled in the art can set that the multiple same-potential groups of the initial user need to meet the following conditions, for example, in static attribute matching, the coincidence degree of the initial user and the preset group in the initial information such as gender, age interval, IP address, etc. exceeds the preset coincidence degree, etc. It should be noted that the preset group is a user classification set set in the group division mechanism, and is used for potential group matching of the initial user; for the preset group, it is set through historical user behavior statistical analysis and expert experience setting, and the number of specific preset groups and the method of dividing the group boundary are not limited, which will not be repeated here; The information display time length in each similar potential group is counted by the built-in clock, and the information with the longest information display time length in each similar potential group is selected as the target information of the similar potential group. The built-in clock refers to a timing device or timing module in the system for recording the user's stay time on each information interface. It can collect the display time length of each information on the user's browsing homepage in real time with a preset time accuracy, and use the collected data for subsequent information display statistics and target information identification in the group.

[0022] In step S2, the number of occurrences of each word in the target information of the similar potential group is counted to obtain the number of occurrences of each word in the target information and the total number of word occurrences. The number of occurrences of each word is calculated by the total number of word occurrences to obtain the word frequency of each word in the target information of the similar potential group. Wherein, the word recognition in the target information is based on natural language processing technology and word segmentation algorithm, and the specific word recognition method and its implementation method are not limited here, but are selected by the skilled person according to the corpus characteristics and semantic application scene requirements, which will not be repeated here. The word frequency of each word in the target information of the similar potential group is sorted in descending order according to the numerical value, and the word with the largest word frequency value is selected as the representative word of the similar potential group. Further, the above method is used to select the representative word of each similar potential group for the target information of each similar potential group, which will not be repeated here. The word frequency of the representative word of the similar potential group is called, and the representative words are sorted in descending order according to the numerical value of the word frequency of the representative word of the similar potential group. The representative words of the preset comparison quantity are selected as the comparison representative words according to the arrangement order, and the remaining representative words are selected as the candidate representative words. The similar potential group corresponding to the comparison representative word is marked as the target group by default. It can be understood that for the similar potential group corresponding to the comparison representative word, since its representative word can best reflect the core information of the similar potential group in the target information of the similar potential group, it is marked as the target group by default, and the comparison representative word is used to analyze whether the similar potential group corresponding to the candidate representative word can be marked as the target group. It should be noted that the calculation method of the word frequency of the representative words of the same potential group has been described in the above content, and will not be repeated here. The preset comparison quantity refers to the number of words used to construct the comparison representative word set according to the application scenario or system requirement, which is preset by the system or dynamically configured by the experiment personnel according to historical sample data after sorting the representative words of the same potential group. Specifically, the preset comparison quantity can be a fixed value (for example, the first 3 or 5 words) or a dynamic value, that is, a proportion of the number of representative words is selected, for example, the first 10% or 20% of the representative words or a proportion of the total number of representative words (less than 10, take the first 3, 10 to 20, take the first 5, more than 20, take the first 8) and the like. It can also be determined based on experimental statistics, that is, by analyzing the effect of historical user data, the optimal comparison quantity is selected, and the like, which will not be repeated here. The candidate representative words and the comparison representative words are vectorized, and the similarity between each candidate representative word and each comparison representative word is calculated by substituting all candidate representative words into the cosine similarity calculation formula. Specifically, the cosine similarity calculation formula is expressed as follows: In the formula, is the similarity between the xth candidate representative word and the yth comparison representative word, is the vectorization representation of the xth candidate representative word, is the vectorization representation of the yth comparison representative word, is the vector dot product operation, is the Euclidean norm of the vector; Wherein, the experiment personnel can select Word2Vec model for vectorization processing, and the parameters are set as follows, for example, the word vector dimension is 100, the window size is 5, the minimum word frequency is 2 (to filter low-frequency meaningless words), and the training corpus is the user interaction text (such as product description, information title) selected by the platform by default, and the like, which will not be repeated here. For example, the existing comparison representative words A, B and C, and the candidate representative words D, E, F and G, then for the candidate representative word D, the AD similarity, BD similarity and CD similarity are calculated, for the candidate representative word E, the AE similarity, BE similarity and CE similarity are calculated, and the like. The similarity between each candidate representative word and each comparison representative word is calculated. The similarity between each candidate representative word and each comparison representative word is grouped according to the number of candidate representative words, and the similarity group of each candidate representative word is obtained. ​As shown in the foregoing examples, the AD similarity, the BD similarity, and the CD similarity are divided into a similar group of D candidate representative words, the AE similarity, the BE similarity, and the CE similarity are divided into a similar group of E candidate representative words, and so on, to complete the grouping operation according to the number of candidate representative words, and obtain each candidate representative word similarity group; The target value of each candidate representative word is obtained by performing mean value calculation on each candidate representative word similarity group; As shown in the foregoing examples, the AD similarity, the BD similarity, and the CD similarity are added and then subjected to ratio calculation with the number, that is, (AD similarity+BD similarity+CD similarity) / 3, to obtain the target value of the D candidate representative word, and so on to obtain the target values of the E, F, and G candidate representative words; The target value of each candidate representative word is compared with a preset similarity threshold value; If the target value of the candidate representative word exceeds the similarity threshold value, the same type of potential group corresponding to the current candidate representative word is excluded; If the target value of the candidate representative word is lower than the similarity threshold value, the same type of potential group corresponding to the current candidate representative word is marked as a target group; It should be noted that the similarity threshold value is set by the experimenters according to the number scale of the candidate representative word and the word frequency distribution of the comparison representative word, which is not described herein; It can be understood that when the target value of the candidate representative word is larger, the similarity between the candidate representative word and the comparison representative word is higher, and it is easier to produce repeated recommendation, causing information redundancy and increasing the browsing burden of the user, and therefore it is more necessary to exclude the same type of potential group corresponding to the candidate representative word. Conversely, when the target value of the candidate representative word is lower, the similarity between the candidate representative word and the comparison representative word is lower, which means that the same type of potential group corresponding to the candidate representative word can provide new and differentiated information, and it is more necessary to mark the same type of potential group corresponding to the candidate representative word as a target group for accurate information display to the initial user; The information corresponding to the target group obtained by screening is used for interface display of the initial user; Optionally, the information in each target group is summarized to generate a target group information set. For each information entry in the target group information set, the information can be sorted according to a preset display rule, for example, according to information importance or time priority. Subsequently, the sorted target group information is mapped and distributed according to the initial user interface layout requirements, for example, in the e-commerce platform scenario, it can be distributed to the home page recommendation module, the search result module, or the personalized information stream. In each display position, the display capacity or the number of information entries per page can be set to avoid interface overcrowding and other design methods, which are not described herein.

[0023] In step S3, the initial user's browsing time length and browsing volume of each target group information are monitored in real time in the set display frequency; It should be noted that the display frequency refers to the period of displaying the target group information to the user. The present experiment personnel sets the display frequency according to the historical user behavior characteristic parameters and the push capacity parameters, and monitors the browsing time length and browsing volume of each target group information in real time in the display frequency. The specific monitoring method is not limited, and will not be described here. The browsing time length of the target group information refers to the cumulative residence time of the initial user to all information contents under the same target group in the set display frequency. The acquisition logic is that the single residence time of each information belonging to the current target group is recorded during the initial user's browsing in the display frequency, and the residence time of all information under the current target group in the display frequency is accumulated to obtain the browsing time length of the target group information. It should be noted that the recording method of recording each information of the current target group is the page residence time length statistics of each information, which will not be described here. The browsing volume of the target group information refers to the cumulative access times of the initial user to the information contents under the same target group in the set display frequency. The acquisition logic is that each time the initial user clicks into any information of the current target group in the display frequency is counted as one browsing and is counted to obtain the browsing volume of the target group information. Further, the acquisition logic of the above browsing time length of the target group information and the browsing volume of the target group information can be used in the collection method of the browsing time length and the browsing volume of each target group information, which will not be described here. The browsing time length and the browsing volume of each target group information are standardized to keep the browsing time length of each target group information and the browsing volume of each target group information in the same dimension, and the numerical expression range is between 0 and 1. It should be noted that the standardization processing method includes but is not limited to the standard linear transformation based on interval scaling, the Z-Score standardization method based on statistics, or the normalization method based on nonlinear mapping function. The application method of standardization processing will not be described here. The browsing time length and the browsing volume of each target group information after standardization are substituted into the geometric mean method to obtain the active coefficient of each target group. The geometric mean method refers to a statistical method of multiplying two or more non-negative values and taking the square root, which is known to those skilled in the art. Specifically, the browsing time length standardized value and the browsing volume standardized value of the target group information are multiplied and the square root is taken to obtain the active coefficient of the current target group. It should be noted that the longer the browsing duration and the browsing volume of the target group information, the higher the attention and interest of the initial user to the current target group, the more representative and valuable the current target group information, and the more necessary it is to retain the current target group; The target group activity coefficient is compared with the activity threshold value; If the target group activity coefficient exceeds the activity threshold value, the current target group is retained; If the target group activity coefficient is lower than the activity threshold value, the current target group is screened out; It should be noted that the activity threshold value is set by the experimenters according to historical user behavior data and the number of target groups, which will not be repeated here; The total number of screened-out target groups is obtained by counting the number of screened-out target groups, and the update rate is calculated by multiplying the total number of screened-out target groups by the preset adjustment coefficient; The preset adjustment coefficient is obtained by the experimenters according to historical display data and user behavior feedback, for example, the preset adjustment coefficient is set according to platform type and user activity, and the value range of the update rate is kept between 0 and 1, which will not be repeated here; It should be noted that the larger the total number of screened-out target groups, the larger the generated update rate, so that the display frequency of the remaining target groups is adjusted more significantly to reduce the display of low-activity or redundant information.

[0024] In step S4, after entering the frequency adjustment mechanism, the update rate is multiplied by the display frequency to obtain the display frequency adjustment amount, and the display frequency is subtracted from the display frequency to obtain the accurate display frequency; Further, if the display frequency adjustment amount is consistent with the display frequency, the accurate display frequency is zero, and there is no need to display information to the remaining target groups, and the method ends; After obtaining the accurate display frequency, the browsing duration and the browsing volume of the initial user to each target group information are monitored and counted again in the accurate display frequency, and the target groups are screened out according to the browsing duration and the browsing volume; The number of screened-out target groups is detected, and if the number of screened-out target groups is zero, an exit signal is generated and executed to exit the frequency adjustment mechanism; If the number of screened-out target groups is not zero, the update rate is generated, and the accurate display frequency is adjusted again according to the update rate to obtain the updated accurate display frequency; Further, when the updated accurate display frequency is obtained, the browsing duration and the browsing volume of the initial user to each target group information are monitored and counted again, and the target groups are screened out according to the browsing duration and the browsing volume until the exit signal is generated. It can be understood that the loop operation in the frequency adjustment mechanism is actually a repetition of the operations from step S3 to step S4, the purpose of which is to update and control the display frequency so that the content of initial user interest can be captured in a short period of time. Among them, the experimenters can optionally set a bottom value in the frequency adjustment mechanism. When the precise display frequency is less than the bottom value, the frequency adjustment mechanism is forced to exit, so as to avoid the ineffective display of target group information due to too low frequency; It should be noted that the bottom value is set as the minimum effective display frequency in the frequency adjustment mechanism. Specifically, this experimenter set it as follows according to the platform type. For example, the bottom value of the e-commerce platform is to update and display the target group information once every 3 minutes to ensure that users have enough time to browse; the bottom value of the information platform is to update and display the target group information once every 2 minutes. Due to the high frequency of information updates, a higher display frequency is required. Furthermore, the forced exit logic exits the adjustment mechanism when the precise display frequency is less than the bottom value to avoid having no information to display.

[0025] In step S5, when the frequency adjustment mechanism is exited, the number of user click searches and active refreshes are collected within the precise display frequency according to the precise display frequency; It should be noted that, in actual application, the frequency adjustment mechanism may cycle multiple times to obtain the accurate display frequency updated multiple times. In this embodiment, only the accurate display frequency obtained for the first time after entering the frequency adjustment mechanism is used as an example for explanation. In fact, the collection and processing method of the accurate display frequency after multiple rounds of updates is consistent with this embodiment and will not be repeated here. The logic for obtaining the number of user clicks to search is to calculate the total number of times the initial user clicks the search box to search within the precise display frequency to obtain the number of user clicks to search; The search box is an input interaction component set up by the experimenters on the information display platform. Specific search behaviors include but are not limited to text input search, voice input search, and history record click search. The specific display location and interface style of the search box are not limited and will not be described in detail here. The logic for obtaining the number of active refreshes is to count the number of information refreshes triggered by the initial user refreshing the page within the precise display frequency as the number of active refreshes; Normalize the number of user clicks on search and the number of active refreshes so that they are in the same dimension and the value range is between 0 and 1; The standardization process has been described in the above content and will not be repeated here; Substitute the standardized number of user clicks and active refreshes into the polynomial regression calculation to obtain the exit group coefficient. The specific formula is as follows: ; In the formula, is the exit group system number, is the normalized user click search number, is the normalized active refresh number, is an adjustment parameter, and is the weight coefficient corresponding to the normalized user click search number and active refresh number; It should be noted that the polynomial regression calculation formula in the present application can select the order and form according to the actual application requirements, and the specific order and function form are not limited here, and those skilled in the art can determine it according to the actual initial user behavior characteristics, which will not be repeated here. Among them, the weight coefficient mentioned in the polynomial regression calculation formula is obtained by training by the experimenters according to the loss function minimization principle and the corresponding optimization algorithm (such as ordinary least squares method, gradient descent method, etc.), which is the common knowledge of those skilled in the art, and will not be repeated here. Specifically, the greater the user click search number and active refresh number, the more it indicates that the initial user's interest in the current display content is not fully satisfied, and the greater the exit group system number, the system determines that the current group division mechanism is not good for user information grabbing effect, and the more it needs to exit the group division mechanism. The exit group system number is compared with the preset group threshold; If the exit group system number exceeds the group threshold, the group division mechanism is exited, and an alarm signal is generated; If the exit group system number is lower than the group threshold, the group division mechanism is retained; It should be noted that the group threshold is set by the experimenters according to the historical user behavior data analysis and system information grabbing strategy, which will not be repeated here. Further, when the alarm signal is generated, the words "user interest not covered", "group division needs to be optimized", "attention frequency is abnormal" and the like are generated and uploaded to the background visualization port at the same time, which is used to prompt the system administrator, trigger the automatic optimization process and record the system running log.

[0026] Finally, it should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0027] Also, the use of "including," "comprising," or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Unless otherwise specified, "or" means "and / or." Unless otherwise noted, the use of the positive is meant to encompass the negative, e.g., the use of "a" is meant to encompass "not a," the use of "at least one" is meant to encompass "zero or more," etc.

[0028] In this document, the terms "a" or "an" are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of "at least one." In this document, the term "or" as used herein is used to mean "and / or," i.e., "A or B" means "A or B or both." Throughout this document, the term "comprising" or "comprises" means "including, but not limited to" or "containing, but not limited to," and the like. The term "consisting essentially of" means "including, but not limited to, integers which do not materially affect the essential characteristics of the subject matter." The term "consisting of" means "including, but not limited to," such that the only integers which can be present are those specifically named. As used herein, unless otherwise clear from context, the term "about" means ±10% of the value of that which follows, for example, about 90% means in the range of 81-99%, unless otherwise stated.

[0029] Embodiments of the present application will now be described, by way of example only, with reference to the attached figures. These embodiments are provided so that this disclosure will be thorough, and will fully convey the scope of the application to those skilled in the art. Numerous specific details are set forth such as quantities, configurations, components, etc. in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to unnecessarily obscure aspects of the present application.

[0030] The above description of disclosed embodiments is not intended to be exhaustive or to be unduly limited by the disclosed embodiments. While specific embodiments of, and examples for, the application are described herein for illustrative purposes, various equivalent modifications are possible within the scope of the application, as those skilled in the relevant art will recognize. The teachings of the present application can be applied to other systems and methods, and can be used for purposes other than the specific examples described above. Accordingly, the present application is not intended to be limited to the examples described herein, but is to be accorded the widest scope consistent with the claims, the principles and the novel features disclosed herein.

Claims

1. A method for controlling the frequency of information display based on user behavior characteristics, characterized in that: Comprising the following steps: Step S1: set the initial user group division mechanism to obtain multiple same potential groups of the initial user, and select the target information of the same potential group according to the information display time of the same potential group; Step S2: extract the word frequency of the target information of the same potential group and select the representative words of the same potential group to obtain the target group, and display the target group information to the initial user interface; Step S3: set the display frequency, real-time monitor the browsing time and browsing volume of the initial user to each target group information and conduct statistics, and comprehensively screen out the target group according to the browsing time and browsing volume, and generate the update rate according to the number of screened target groups; Step S4: after generating the update rate, enter the frequency adjustment mechanism, adjust the display frequency using the update rate and obtain the accurate display frequency, and real-time monitor the screening result of the target group to determine whether to exit the frequency adjustment mechanism; Step S5: when exiting the frequency adjustment mechanism, collect the number of user clicks and active refresh times to determine whether to exit the group division mechanism.

2. The information display frequency control method based on user behavior characteristics according to claim 1, characterized in that: In step S1, the initial user is substituted into the set group division mechanism, and the initial information filled in by the initial user during registration is collected; The initial information is substituted into the preset group division mechanism to divide the initial user into multiple preset groups, and the preset group into which the initial user is divided is marked to obtain multiple same potential groups of the initial user; The information display time of each information in each same potential group is counted by the built-in clock, and the information with the longest information display time in each same potential group is selected as the target information of the same potential group.

3. The information display frequency control method based on user behavior characteristics according to claim 1, characterized in that: In step S2, the frequency of each word in the target information of the same potential group is calculated by counting the number of times each word appears in the target information and the total number of times each word appears, and the frequency of each word in the target information of the same potential group is calculated by comparing the number of times each word appears with the total number of times each word appears; The word frequency of each word in the target information of the same potential group is sorted in descending order according to the numerical value, and the word with the largest word frequency value is selected as the representative word of the same potential group; The word frequency of the representative word of the same potential group is called, and the representative words are sorted in descending order according to the word frequency value, and the preset number of representative words are selected as the comparison representative words according to the arrangement order, and the remaining representative words are selected as the candidate representative words; The same potential group corresponding to the comparison representative word is marked as the target group by default.

4. The information display frequency control method based on user behavior characteristics according to claim 2, characterized in that: In step S2, each candidate representative vocabulary is vectorized with each comparison representative vocabulary, and the similarity between all candidate representative vocabularies and each comparison representative vocabulary is calculated by substituting the cosine similarity calculation formula; The similarity between each candidate representative vocabulary and each comparison representative vocabulary is grouped according to the number of candidate representative vocabularies to obtain each candidate representative vocabulary similarity group; The target value of each candidate representative vocabulary is obtained by averaging each candidate representative vocabulary similarity group; The target value of each candidate representative vocabulary is compared with the preset similarity threshold; If the target value of the candidate representative vocabulary exceeds the similarity threshold, the same type of potential group corresponding to the current candidate representative vocabulary is excluded; If the target value of the candidate representative vocabulary is lower than the similarity threshold, the same type of potential group corresponding to the current candidate representative vocabulary is marked as the target group; The information corresponding to the target group obtained by screening is used for interface display of the initial user.

5. The information display frequency control method based on user behavior characteristics according to claim 1, characterized in that: In step S3, the browsing time and the browsing volume of the initial user to each target group information are monitored in real time within the set display frequency; During the browsing process of the initial user within the display frequency, the single stay time of each information belonging to the current target group is recorded, and the stay time of all information under the current target group within the display frequency is accumulated to obtain the browsing time of the target group information; Each time the initial user clicks into any information of the current target group within the display frequency is counted as one browsing and is counted to obtain the browsing volume of the target group information.

6. The information display frequency control method based on user behavior characteristics according to claim 5, characterized in that: In step S3, the browsing time and the browsing volume of each target group information after standardization are substituted into the geometric mean method to obtain the activity coefficient of each target group; The activity coefficient of each target group is compared with the activity threshold; If the activity coefficient of the target group exceeds the activity threshold, the current target group is retained; If the activity coefficient of the target group is lower than the activity threshold, the current target group is excluded; The number of excluded target groups is counted to obtain the total number of excluded target groups, and the total number of excluded target groups is multiplied by the preset adjustment coefficient to obtain an update ratio.

7. The information display frequency control method based on user behavior characteristics according to claim 1, characterized in that: In step S4, after entering the frequency adjustment mechanism, the update ratio is multiplied by the display frequency to obtain a display frequency adjustment amount, and the display frequency is subtracted from the display frequency adjustment amount to obtain a precise display frequency; After obtaining the precise display frequency, the browsing time and the browsing volume of the initial user to each target group information are monitored again within the precise display frequency and are counted, and the target group is excluded by comprehensively considering the browsing time and the browsing volume.

8. The information display frequency control method based on user behavior characteristics according to claim 7, characterized in that: In step S4, the number of screened target groups is detected, and if the number of screened target groups is zero, an exit signal is generated and executed, and an exit frequency adjustment mechanism is performed; If the number of screened target groups is not zero, an update rate is generated, and the accurate display frequency is adjusted again according to the update rate to obtain the updated accurate display frequency; After obtaining the updated accurate display frequency, the initial user's browsing time and browsing volume of each target group information are repeatedly monitored and counted, and the target group is screened according to the browsing time and browsing volume until the exit signal is generated.

9. The information display frequency control method based on user behavior characteristics according to claim 1, characterized in that: In step S5, when the exit frequency adjustment mechanism is executed, the number of user search clicks and the number of active refreshes are collected within the accurate display frequency according to the accurate display frequency; The total number of initial user search clicks within the accurate display frequency is counted to obtain the number of user search clicks. The number of information refreshes triggered by the initial user within the accurate display frequency is counted as the number of active refreshes.

10. The information display frequency control method based on user behavior characteristics according to claim 9, characterized in that: In step S5, the number of user search clicks and the number of active refreshes are standardized and then put into a polynomial regression calculation to obtain a group system coefficient; The group system coefficient is compared with a preset group threshold value; If the group system coefficient exceeds the group threshold value, the group division mechanism is exited, and an alarm signal is generated; If the group system coefficient is lower than the group threshold value, the group division mechanism is retained.

Images