Information recommendation method and device, electronic device, and storage medium

Abstract

The application provides an information recommendation method and device, an electronic device and a storage medium. The method comprises: obtaining an application operation parameter of a user; calculating an operation level vector of the user according to the application operation parameter, determining a cluster center of at least one clustering cluster corresponding to an application to be recommended, and calculating a distance between the operation level vector and the cluster center; selecting a target clustering cluster from the at least one clustering cluster according to the distance, determining an application to be recommended corresponding to the target clustering cluster, and outputting recommendation information corresponding to the application to be recommended. The application takes the operation ability of the user as a classification dimension, determines the operation level of the user, and determines a clustering cluster closer to the user in the clustering cluster established in a similar manner, so as to select recommendation information in the clustering cluster. In this way, the recommended information is closer to the operation level and selection psychology of the user, and the user can quickly obtain relevant recommendations with an operation burden conforming to the operation ability, thereby improving the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information processing, and in particular to an information recommendation method and device, an electronic device, and a storage medium. BACKGROUND

[0002] With the popularity of smart phones and the development of mobile Internet, mobile games have gradually occupied the main part of the game market. In order to bring better game experience to users, user portrait related technologies have attracted widespread attention. User portrait technology analyzes and models user interest preferences, level capabilities, etc. through a series of logs, and is the basis for personalized recommendation, matching and other businesses.

[0003] User portrait technology generally classifies users by analyzing and modeling user interest preferences and the like through a series of user logs. Traditional user ability evaluation is often based on user settlement data. However, this evaluation method is limited in scene and not intuitive. It is directly affected by user playing results, and the user operation ability is not accurate enough, which ultimately leads to poor user experience when performing recommendation matching and other businesses. SUMMARY

[0004] Therefore, the present application provides an information recommendation method, device, electronic device and storage medium to make the recommended information more in line with the user's operation level and bring better user experience to the user.

[0005] To achieve the above purpose, the present application provides an information recommendation method, comprising:

[0006] obtaining application operation parameters of a user;

[0007] calculating an operation level vector of the user according to the application operation parameters, determining a cluster center of at least one clustering cluster corresponding to a to-be-recommended application, and calculating a distance between the operation level vector and the cluster center;

[0008] selecting a target clustering cluster from the at least one clustering cluster according to the distance, and determining a to-be-recommended application corresponding to the target clustering cluster;

[0009] outputting recommended information corresponding to the to-be-recommended application.

[0010] In some embodiments, the obtaining of the application operation parameters of the user comprises:

[0011] determining a target application program with open access permission, and obtaining corresponding application operation parameters operated by the user in the target application program.

[0012] In some embodiments, the calculating of the operation level vector of the user according to the application operation parameters comprises:

[0013] For each of the application operation parameters, sum all the application operation parameters corresponding to the target application programs;

[0014] In combination with the number of the target application programs, obtain the average value of each of the application operation parameters;

[0015] Generate a target vector with the average value of each of the application operation parameters as three-dimensional coordinates;

[0016] Take the target vector as the operation level vector of the user.

[0017] In some embodiments, the application operation parameters include at least one of the following: touch frequency, touch interval, and touch displacement.

[0018] In some embodiments, the application operation parameters include touch frequency, touch interval, and touch displacement.

[0019] The operation level vector of the user is calculated according to the application operation parameters, specifically:

[0020]

[0021] Wherein, Vector X is the operation level vector of the user X, is the total number of applications G i , G i represents the i-th application, and are the touch interval, touch displacement, and touch frequency of the user X in the i-th application, respectively.

[0022] In some embodiments, before determining the cluster center of at least one cluster corresponding to the application to be recommended, the method comprises:

[0023] For each application to be recommended, determine the score of each application operation parameter corresponding to each of the application to be recommended;

[0024] Establish an information coordinate composed of each of the application operation parameter scores;

[0025] Cluster the application to be recommended by a clustering algorithm and the information coordinate to generate the cluster.

[0026] In some embodiments, the determination of the score of each application operation parameter corresponding to each of the application to be recommended comprises:

[0027] For each of the application to be recommended, obtain all player information and all gameplays corresponding to the application to be recommended;

[0028] For each application operation parameter, determine the application operation parameter score corresponding to each game in each player information;

[0029] According to the application operation parameter score of the player, obtain the application operation parameter score corresponding to the application to be recommended.

[0030] In some embodiments, the application operation parameters include touch frequency, touch interval, and touch displacement;

[0031] The determination of each application operation parameter score corresponding to each application to be recommended includes:

[0032]

[0033] Wherein, Score 触摸频率G , Score 触摸间隔G , Score 触摸位移G are the touch frequency score, the touch interval score, and the touch displacement score of application G, Count X is the total number of player information, X a is the a-th player information, Count P is the total number of games, P b is the b-th game information, are the player touch frequency score, the player touch interval score, and the player touch displacement score corresponding to the b-th game of the a-th player information of application G.

[0034] In some embodiments, the determination of the cluster center of at least one cluster corresponding to the application to be recommended includes:

[0035] According to all information coordinates in each cluster, calculate the centroid of the cluster, and take the centroid as the cluster center.

[0036] In some embodiments, the output of the recommendation information corresponding to the application to be recommended includes:

[0037] Randomly select at least one recommendation information in all the recommendation information for output.

[0038] Based on the same concept, the present application also provides an information recommendation device, comprising:

[0039] An acquisition module is configured to acquire application operation parameters of a user;

[0040] A calculation module is configured to calculate an operation level vector of the user according to the application operation parameters, determine a cluster center of at least one cluster corresponding to an application to be recommended, and calculate a distance between the operation level vector and the cluster center.

[0041] determining a target cluster from the at least one cluster according to the distance, and determining an application to be recommended corresponding to the target cluster;

[0042] outputting recommendation information corresponding to the application to be recommended.

[0043] Based on the same idea, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method according to any one of the above when executing the program.

[0044] Based on the same idea, the present application further provides a non-transitory computer readable storage medium, which stores computer instructions for causing the computer to implement the method according to any one of the above.

[0045] As can be seen from the above, the present application provides an information recommendation method, device, electronic device, and storage medium, comprising: obtaining an application operation parameter of a user; calculating an operation level vector of the user according to the application operation parameter, determining a cluster center of at least one cluster corresponding to an application to be recommended, and calculating a distance from the operation level vector to the cluster center; determining a target cluster from the at least one cluster according to the distance, and determining an application to be recommended corresponding to the target cluster; and outputting recommendation information corresponding to the application to be recommended. The present application determines the operation level of the user by taking the operation ability of the user as the classification dimension, and determines the cluster closer to the user in the cluster of information established in a similar manner, so as to select the recommendation information in the cluster. In this way, the recommended information is closer to the operation level and selection psychology of the user, so that the user can quickly obtain the relevant information recommendation with the operation burden conforming to the operation ability, and the user experience is ultimately improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description only constitute the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0047] Figure 1 A flowchart of an information recommendation method according to an embodiment of the present application;

[0048] Figure 2 A structural diagram of an information recommendation device according to an embodiment of the present application;

[0049] Figure 3An electronic device structure diagram is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0050] For the purpose of making the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below with reference to the embodiments and the accompanying drawings.

[0051] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be understood as the common meanings understood by those with ordinary skills in the art to which the embodiments of the present application belong. The terms “first”, “second” and similar terms used in the embodiments of the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms “include”, “contain” and similar terms mean that the components, objects or method steps listed before the terms cover the components, objects or method steps listed after the terms and their equivalents, and do not exclude other components, objects or method steps. The terms “connect” or “connected” and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms “upper”, “lower”, “left”, “right” and the like only represent relative positional relationships, which may change when the absolute positions of the described objects change.

[0052] As described in the background section, user profiling technology analyzes, models user interest preferences, level of ability, etc. through a series of logs, and is the basis for personalized recommendation and other businesses. Among them, the modeling of user operation level in the mobile game scenario is particularly important, and directly supports application matching, information recommendation and other businesses based on user level. The traditional application market, application recommendation and information recommendation scheme in the promotion platform are often based on the classification of the recommended information corresponding to the application or content. Among them, the category information of the application or content is often manually labeled after being obtained. The application market only displays the application according to the application category. Some application markets will also analyze which categories of applications or information the user is most likely to like through the applications installed in the user's mobile phone, and select some applications or information in these categories for recommendation. That is, the general process is: the application market manually obtains (or asks the maker) the category information of the newly entered application A or advertising information B; the application market updates the promotion information, and the user can search for application A or advertising information B in a specific category; or when the user opens the application market, the application market will analyze which categories of applications or information the player is most likely to be interested in according to the applications installed in the player's mobile phone, and select relevant information from these categories for recommendation. In this way, only the large categories of applications or information can be distinguished, and users are generally more concerned about their own use experience or sensory experience when using applications, that is, whether the user's operation level is suitable for the application. Further, the current classification and recommendation methods cannot recommend information to users from this dimension, so users can only determine whether the application or function is suitable after contacting the corresponding application or function, thereby causing poor user experience when performing recommendation matching and other businesses.

[0053] In view of the above actual situation, the embodiments of the present application propose an information recommendation scheme, which determines the operation level of the user by taking the operation ability of the user as the classification dimension, and determines the cluster closer to the user in the cluster established in a similar manner for the information, so as to select the recommended information in the cluster. In this way, the recommended information is closer to the operation level and selection psychology of the user, so that the user can quickly obtain relevant information recommendation with an operation burden that meets the operation ability, and ultimately improves the user experience.

[0054] As shown in Figure 1 , it is a flowchart of an information recommendation method according to the present application, which specifically includes:

[0055] Step 101, obtaining application operation parameters of the user.

[0056] In this step, the application operation parameter is the user's operation ability parameter or operation level parameter in a specific application, which can generally be the user's touch frequency, touch interval, touch displacement, and other parameters that can reflect the user's operation ability. Among them, the touch frequency is the frequency of the user's effective touch in a certain period of time, which can generally be calculated by the ratio of the number of touches to the time. For touch devices such as mobile phones and pads, both hands can perform touch operations at the same time, and the touch frequency of both hands can be calculated separately. Then, in order to intuitively represent the touch frequency, the touch frequencies of both hands can be assigned respective weights to obtain the comprehensive touch frequency. The touch interval is the average interval between the user's effective adjacent two touches in a certain period of time, which is generally represented by the interval time. Similar to the touch frequency, the touch interval of both hands can be calculated separately, and then the corresponding weights are assigned to obtain the comprehensive touch interval. The touch displacement is the average interval displacement between the user's effective adjacent two touches in a certain period of time, which is generally represented by the interval length. For example, it is the distance interval between the end position of the previous touch and the starting position of the next touch. Similar to the touch frequency, the touch displacement of both hands can be calculated separately, and then the corresponding weights are assigned to obtain the comprehensive touch displacement. Then, the specific application is one or more applications that can or allow to obtain the user's application operation parameter.

[0057] In specific embodiments, the application operation parameter can be a score or a rating, and each application operation parameter of the user can have a corresponding score or rating. Then, the application operation parameter that can reflect the user's comprehensive level can be determined by taking the average value. Of course, in specific application scenarios, a specific application can be specified as a reference, and only the user's application operation parameter in that application is obtained.

[0058] Step 102, calculating the operation level vector of the user according to the application operation parameter, determining the cluster center of at least one cluster corresponding to the application to be recommended, and calculating the distance between the operation level vector and the cluster center.

[0059] In this step, the operation level vector is a multi-dimensional vector function generated with each application operation parameter as a dimension. For example, taking touch frequency, touch interval, and touch displacement as application operation parameters, a three-dimensional coordinate system can be established with these three parameters. Each coordinate axis represents the numerical value or level of a parameter, so that the three-dimensional zero vector of the user in the three-dimensional coordinate system is determined as the operation level vector of the user.

[0060] The information to be recommended then represents all the information that can be recommended. This information can include application recommendations, product recommendations, or recommendations for various functions within an application, among other things, to recommend various applications, products, or functions to users. This information can also be clustered based on the classification of operational levels. For example, by collecting the application operational parameters of all users of a particular application or product, statistically analyzing and averaging them, the corresponding application operational parameters can be obtained. This information can then be used to build a multidimensional model based on the corresponding application operational parameters. Finally, clustering techniques (such as KMeans, hierarchical clustering, DBSCAN, etc.) can be used to cluster this information and generate multiple clusters. Of course, in specific application scenarios, the designer can manually classify the recommended information based on their specific experience to generate clusters. The cluster center is then the central location of the cluster. Each clustering technique generally has one or more methods for determining the location of the cluster center. For example, the coordinates of all points belonging to a cluster can be averaged to obtain a "center of mass" point, which is then used as the cluster center. In specific application scenarios, the "center of mass" may not be real data, so a real data point closest to the center of mass can be selected as the cluster center.

[0061] Finally, after determining the user's operation level vector and the cluster centers of all clusters, the distance relationship between the user's operation level vector and the cluster center of each cluster can be determined by calculating the distance between two points.

[0062] Step 103 : Select a target cluster from the at least one cluster according to the distance, and determine an application to be recommended corresponding to the target cluster.

[0063] In this step, after determining the distance between the user's horizontal operation vector and the cluster center of each cluster in step 102, the cluster center whose distance from the horizontal operation vector to the cluster center is less than a preset distance is selected based on the distance. Optionally, the cluster center with the closest distance to the user's horizontal operation vector is selected, and the cluster corresponding to this cluster center is used as the recommended cluster for the user. All the information to be recommended within this cluster is the recommended information.

[0064] In specific embodiments, after the recommendation clustering cluster is determined, i.e., the recommendation information is determined, the amount of recommendation information can be controlled, and a part of the information can be selected for recommendation, so that the user does not see too much recommendation information and feel disgusted. The screening method can be directly and completely random selection, or targeted selection according to importance, etc. Specifically, an importance mark can be set for each to-be-recommended information. After the recommendation clustering cluster is determined, all information in the cluster can be arranged or classified according to the importance mark, and then the information can be selected in sequence according to the queue or a specific number of information in each classification, etc.

[0065] Step 104, output the recommendation information corresponding to the to-be-recommended application.

[0066] In this step, the recommendation information is finally output for storage, display, use or further processing. According to different application scenarios and implementation needs, the output method of the recommendation information can be flexibly selected.

[0067] For example, for the application scenario in which the method of the embodiment is executed on a single device, the recommendation information can be directly output in a display manner on the display component (display, projector, etc.) of the current device, so that the operator of the current device can directly see the content of the recommendation information from the display component.

[0068] For example, for the application scenario in which the method of the embodiment is executed on a system composed of multiple devices, the recommendation information can be sent to other preset devices in the system as receiving parties, i.e., synchronization terminals, through any data communication method (wired connection, NFC, Bluetooth, wifi, cellular mobile network, etc.), so that the synchronization terminals can perform subsequent processing. Optionally, the synchronization terminal can be a preset server, which is generally set in the cloud as a data processing and storage center, and can store and distribute the recommendation information. The recipients of the distribution are terminal devices, and the holders or operators of the terminal devices can be the current user, the manager of the application program, the promoter of the application program, etc.

[0069] For example, for the application scenario in which the method of the embodiment is executed on a system composed of multiple devices, the recommendation information can be directly sent to a preset terminal device through any data communication method. The terminal device can be one or more of the devices listed in the foregoing paragraphs.

[0070] It can be seen from the above that the information recommendation method of the embodiment of the application comprises: acquiring application operation parameters of a user; calculating an operation level vector of the user according to the application operation parameters, determining a cluster center of at least one cluster corresponding to to-be-recommended information, and calculating a distance from the operation level vector to the cluster center; selecting a cluster corresponding to the nearest cluster center as a recommended cluster, determining to-be-recommended information corresponding to the recommended cluster as recommended information, and outputting the recommended information. The operation ability of the user is taken as a classification dimension, the operation level of the user is determined, and the cluster closer to the user is determined in the cluster of information established in a similar manner, so that the recommended information is selected in the cluster. In this way, the recommended information is closer to the operation level and the selection psychology of the user, so that the user can quickly obtain relevant information recommendations with an operation burden conforming to the operation ability, and the user experience is ultimately improved.

[0071] It should be noted that the method of the embodiment of the application can be executed by a single device, such as a computer or a server. The method of the embodiment of the application can also be applied to a distributed scenario and completed by multiple devices in cooperation. In the distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiment of the application, and the multiple devices can interact with each other to complete the method.

[0072] It should be noted that the above describes specific embodiments of the application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than described above and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous.

[0073] In an optional example embodiment, the application operation parameters comprise touch frequency, touch interval, and touch displacement; and the acquiring the application operation parameters of the user comprises: determining an application program capable of acquiring the application operation parameters, and acquiring the touch frequency, the touch interval, and the touch displacement of the user in the application program. The touch frequency, the touch interval, and the touch displacement of the user in the corresponding application program are acquired, which provides a basis for accurately determining the operation level of the user in subsequent steps.

[0074] In the embodiment, the concepts of touch frequency, touch interval and touch displacement are similar to those in the foregoing embodiments. Not all application operation parameters of all application programs are suitable for information recommendation, or not all application programs allow other programs to count or transmit the data generated by the application programs. Therefore, it is necessary to determine which application program data can be provided or which application program data can be used in the present solution. Then, the application operation parameters of the determined application programs are acquired, and the data of touch frequency, touch interval and touch displacement of the user in the application programs are acquired. Finally, each application program corresponds to a group of touch frequency, touch interval and touch displacement, so that in the specific embodiment, these groups of data can be used as application operation parameters for the next calculation, or the average value of each application operation parameter can be determined to obtain the overall touch frequency, touch interval and touch displacement of the user, which is used as the final application operation parameter of the user.

[0075] In an optional example embodiment, the calculation of the operation level vector of the user according to the application operation parameters comprises: respectively counting the touch frequency, the touch interval and the touch displacement of all the application programs, counting the sum of the application operation parameters corresponding to all the target application programs, and combining the total number of the application programs to obtain the average value of each application operation parameter; generating a target vector with the average values of the touch frequency, the touch interval and the touch displacement as three-dimensional coordinates, and taking the target vector as the operation level vector of the user.

[0076] In the embodiment, after the application operation parameters of the user in each application program are directly acquired, the number of the acquired application programs is determined, and the average performance of all available data application programs is taken as the operation level vector of the user operation level in the calculation of the operation level vector. Specifically, it can be:

[0077] wherein, Vector X is the operation level vector of the user X, is the total number of application programs G i , G i represents the i-th application program, and are the touch interval, the touch displacement and the touch frequency of the user X in the i-th application program, respectively.

[0078] In an optional exemplary embodiment, before determining the cluster center of at least one cluster corresponding to the information to be recommended, the method includes: determining the touch frequency score, touch interval score, and touch displacement score corresponding to each piece of information to be recommended; establishing a three-dimensional space with the touch frequency score, touch interval score, and touch displacement score as coordinates, determining the information coordinates of each piece of information to be recommended within the three-dimensional space; and clustering the information coordinates within the three-dimensional space using a clustering algorithm to generate the clusters. In this way, cluster analysis is quickly performed on all the information to be recommended, quickly generating the corresponding clusters.

[0079] In this embodiment, each piece of information to be recommended can also correspond to a corresponding touch frequency score, touch interval score, and touch displacement score. In a specific application scenario, a corresponding touch frequency score, touch interval score, and touch displacement score can be set for each piece of information to be recommended by manual setting in advance; similarly, the touch frequency score, touch interval score, and touch displacement score corresponding to the information to be recommended can be obtained by counting the response touch frequency, touch interval, and touch displacement of the users of the application or function corresponding to the information to be recommended; further, the touch frequency score, touch interval score, and touch displacement score corresponding to the information to be recommended can be more accurately determined by screening the users. After that, after determining the touch frequency score, touch interval score, and touch displacement score corresponding to each piece of information to be recommended, a three-dimensional space with the touch frequency score, touch interval score, and touch displacement score as coordinates is established to determine the position of each piece of information to be recommended in this three-dimensional space. Finally, a corresponding clustering algorithm (such as KMeans, hierarchical clustering, DBSCAN, etc.) is used to solve the problem, and at least one cluster can be obtained, thereby completing the establishment of the cluster and making the information to be recommended correspond to the cluster. Finally, each piece of information to be recommended in the cluster is represented by three score coordinates, specifically:

[0080] Vector G =[Score 触摸频率G ,Score 触摸间隔G ,Score 触摸位移G ]

[0081] Among them, Vector G is the clustering vector of the information G to be recommended, Score 触摸频率G 、Score 触摸间隔G 、Score 触摸位移G are the touch frequency score, touch interval score, and touch displacement score of the information G to be recommended, respectively.

[0082] In an optional exemplary embodiment, the information to be recommended is game application information; the determination of the touch frequency score, touch interval score, and touch displacement score corresponding to each piece of information to be recommended includes: obtaining all player information and all gameplay information corresponding to the game application information, determining the player touch frequency score, player touch interval score, and player touch displacement score corresponding to each gameplay information under each player information; calculating the touch frequency score based on all the player touch frequency scores, calculating the touch interval score based on all the player touch interval scores, and calculating the touch displacement score based on all the player touch displacement scores. Of course, it will be understood by those skilled in the art that the all player information is not all in an absolute sense, and may also be player information that satisfies a certain sample size required by this embodiment.

[0083] In this embodiment, for specific game application information, since each existing game generally contains multiple modes of play, such as competitive mode, cooperative mode, casual mode, single-player mode, etc., and the operations corresponding to each mode are generally different, when determining the touch frequency score, touch interval score, and touch displacement score corresponding to a game application information, it is necessary to consider the operation level of each user under each mode of play. Therefore, in a specific application scenario, for a game application information, its corresponding game application G, player X i How to play the game i When the touch interval, touch displacement, touch frequency and other indicators are generated, the average value of the statistical indicators of all player sets X and all gameplays P can be used as the indicator value of the game.

[0084]

[0085] Among them, Score 触摸频率G 、Score 触摸间隔G 、Score 触摸位移G They are the touch frequency score, touch interval score, and touch displacement score of game application G, respectively. X is the total number of player information, X a For the ath player information, Count P is the total number of gameplay information, P b For the b-th gameplay information, They are respectively the player touch frequency score and the player touch interval score / player touch displacement score corresponding to the b-th gameplay information under the a-th player information of the game application G.

[0086] In specific application scenarios, a random sampling method can also be used to randomly sample players or part of the gameplay to calculate the index value of the game G.

[0087] In an optional example embodiment, the determining of the cluster center of the at least one cluster corresponding to the recommended information comprises: calculating a centroid of each of the clusters according to all the information coordinates in the cluster, and taking the centroid as the cluster center.

[0088] In the embodiment, the centroid of each of the clusters can be determined by adding and averaging the coordinate values of all the information coordinates in the cluster, and the centroid can be taken as the cluster center. In a specific application scenario, the centroid can not correspond to an actual information coordinate, and the centroid can be directly taken as the cluster center, or the actual information coordinate closest to the centroid in the cluster can be further calculated to take the information coordinate as the cluster center.

[0089] In an optional example embodiment, the outputting of the recommended information comprises: randomly selecting at least one of the recommended information for outputting from all the recommended information. This facilitates the user to obtain information and prevents the user experience from being affected by too much information.

[0090] In the embodiment, a cluster can contain a large amount of recommended information, but the number of information that the user can receive or the user is willing to view without feeling repulsed is limited. Therefore, in order to adapt to the user experience, a specific number of recommended information can be selected from the recommended cluster for recommendation in combination with historical statistical data. The selection method can be completely random selection, or the recommended information can be sequentially selected for recommendation by setting an importance level in advance, and the like. Specifically, the recommended information can be arranged according to importance, and the first several recommended information can be selected for information recommendation, and then all the recommended information can be output according to the user operation, for example, when the user selects a “load more” option, and the like. Several selection pools can also be divided according to the importance, and the weight of the important selection pool can be set to be higher when the recommended information is output each time, so that more recommended information in the important selection pool can be output.

[0091] Based on the same concept, the application also provides an information recommendation device corresponding to the method of any of the above embodiments.

[0092] Reference Figure 2 The information recommendation device comprises:

[0093] The acquisition module 210 is configured to acquire an application operation parameter of the user.

[0094] The computing module 220 is configured to calculate the operation level vector of the user according to the application operation parameters, determine a cluster center of at least one cluster corresponding to the application to be recommended, and calculate a distance from the operation level vector to the cluster center.

[0095] The determining module 230 is configured to select a target cluster from the at least one cluster according to the distance, and determine the application to be recommended corresponding to the target cluster.

[0096] The output module 240 is configured to output recommendation information corresponding to the application to be recommended.

[0097] For the convenience of description, the above device is described in various modules in terms of functions. Of course, the functions of the modules can be implemented in one or more software and / or hardware in the implementation of the embodiments of the present application.

[0098] The device of the above embodiments is used to implement the corresponding information recommendation method in the foregoing embodiments, and has the beneficial effects of the corresponding information recommendation method embodiments, which will not be described herein.

[0099] In an optional example embodiment, the application operation parameters include: touch frequency, touch interval and touch displacement.

[0100] The obtaining module 210 is further configured to:

[0101] Determine an application program capable of obtaining the application operation parameters, and obtain the touch frequency, the touch interval and the touch displacement of the user in the application program.

[0102] In an optional example embodiment, the computing module 220 is further configured to:

[0103] Statistically analyze the touch frequency, the touch interval and the touch displacement of all the application programs respectively, and generate the operation level vector taking the touch frequency, the touch interval and the touch displacement as three-dimensional coordinates in combination with the total number of the application programs.

[0104] In an optional example embodiment, the computing module 220 calculates the operation level vector of the user according to the application operation parameters, and specifically:

[0105] Vector (X) = (G X is the operation level vector of the user X, is the total number of the application program G i , G i represents the i-th application program, and touch interval, touch displacement and touch frequency of user X in the i-th application, respectively.

[0106] In an optional example embodiment, the computing module 220 is further configured to:

[0107] determine a touch frequency score, a touch interval score and a touch displacement score corresponding to each of the information to be recommended;

[0108] establish a three-dimensional space with the touch frequency score, the touch interval score and the touch displacement score as coordinates, and determine an information coordinate of each of the information to be recommended in the three-dimensional space;

[0109] perform clustering on the information coordinates in the three-dimensional space by using a clustering algorithm, and generate the clustering cluster.

[0110] In an optional example embodiment, the information to be recommended is game application information.

[0111] The computing module 220 is further configured to:

[0112] obtain all player information and all play information corresponding to the game application information, and determine a player touch frequency score, a player touch interval score and a player touch displacement score corresponding to each play information under each player information; of course, those skilled in the art can understand that the all player information is not absolutely all, but also can be a certain sample number of player information required by the embodiment.

[0113] The touch frequency score is calculated according to all the player touch frequency scores, the touch interval score is calculated according to all the player touch interval scores, and the touch displacement score is calculated according to all the player touch displacement scores.

[0114] In an optional example embodiment, the computing module 220 calculates the touch frequency score according to all the player touch frequency scores, calculates the touch interval score according to all the player touch interval scores, and calculates the touch displacement score according to all the player touch displacement scores, specifically:

[0115]

[0116] wherein, Score 触摸频率G , Score 触摸间隔G , Score 触摸位移G are the touch frequency score, the touch interval score and the touch displacement score of the game application G, respectively, Count X is the total number of player information, X a is the a-th player information, Count PP is the total number of play information b is the bth play information, are respectively the player touch frequency score, the player touch interval score / the player touch displacement score corresponding to the bth play information of the a th player information of the game application G.

[0117] In an optional example embodiment, the computing module 220 is further configured to:

[0118] According to all the information coordinates in each of the cluster clusters, the centroid of the cluster cluster is calculated, and the centroid is taken as the cluster center.

[0119] In an optional example embodiment, the output module 240 is further configured to:

[0120] Randomly selecting at least one of the recommendation information from all the recommendation information for output.

[0121] Based on the same concept, the present application also provides an electronic device corresponding to the method of any of the above embodiments, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to realize the information recommendation method of any one of the embodiments.

[0122] Figure 3 A more specific hardware structure of an electronic device is shown, which can include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040 and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030 and the communication interface 1040 are connected to each other through the bus 1050 for communication within the device.

[0123] The processor 1010 can be implemented by a general CPU (Central Processing Unit, central processor), a microprocessor, an application specific integrated circuit (ASIC) or one or more integrated circuits, etc., for executing related programs to realize the technical solutions provided by the embodiments of the present application.

[0124] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0125] The input / output interface 1030 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0126] The communication interface 1040 is configured to connect a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or through a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0127] The bus 1050 includes a channel for transmitting information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0128] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only include components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0129] The electronic device of the above embodiments is used to implement the corresponding information recommendation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here again.

[0130] Based on the same concept, corresponding to any of the above embodiment methods, the present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the information recommendation method according to any of the above embodiments.

[0131] The computer readable media of the embodiments can include permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0132] The storage medium of the above embodiments stores computer instructions for causing the computer to execute the information recommendation method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here.

[0133] Those skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application (including claims) is limited to these examples; the above embodiments or technical features between different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of the different aspects of the embodiments of the present application as described above. In order to be brief, they are not provided in detail.

[0134] In addition, in order to simplify the description and discussion, and so as not to make the embodiments of the present application difficult to understand, the well-known power / ground connections of integrated circuit (IC) chips and other components can or can not be shown in the provided drawings. In addition, the devices can be shown in the form of block diagrams in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented the embodiments of the present application (i.e. these details should be fully within the understanding of those skilled in the art). Where specific details (e.g. circuits) are set forth in order to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than limiting.

[0135] While the present application has been described in connection with certain embodiments thereof, many modifications, substitutions, changes, and of forms will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0136] Embodiments of the present application are intended to cover all such alterations, modifications, and variations as they can come within the scope of the appended claims. Accordingly, although specific embodiments have been furthered in connection with the present application, any omission, substitution, change, improvement, etc. made by one of ordinary skill in the art to the disclosed embodiments should be considered to be within the scope of the present application.

Claims

1. An information recommendation method, characterized in that: include: Get the user's application operation parameters; Calculating the user's operation level vector based on the application operation parameters, determining the cluster center of at least one cluster corresponding to the application to be recommended, and calculating the distance from the operation level vector to the cluster center, wherein the cluster is the cluster corresponding to the application to be recommended established according to the classification method of the operation level vector; Selecting a target cluster from the at least one cluster according to the distance, and determining an application to be recommended corresponding to the target cluster; Outputting recommendation information corresponding to the application to be recommended; The calculating the user's operation level vector according to the application operation parameter includes: For each of the application operation parameters, summing the application operation parameters corresponding to all target applications, wherein the target applications are target applications with open access permissions; In combination with the number of the target applications, obtaining an average value of each of the application operation parameters; generating a target vector with an average value of each of the application operation parameters as a three-dimensional coordinate; The target vector is used as the user's operation horizontal vector.

2. The method according to claim 1, characterized in that The obtaining of the user's application operation parameters includes: A target application program for which access rights are to be opened is determined, and application operation parameters corresponding to the operation of the user in the target application program are obtained.

3. The method according to claim 1, characterized in that The application operation parameter includes at least one of the following: touch frequency, touch interval, and touch displacement.

4. The method according to claim 1, wherein The application operation parameters include touch frequency, touch interval and touch displacement; The calculating of the user's operation level vector according to the application operation parameter is specifically: Among them, Vector X is the horizontal vector of user X’s operation, For application G i The total number of G i represents the i-th application, and are the touch interval, touch displacement, and touch frequency of user X in the i-th application, respectively.

5. The method according to claim 1, wherein Before determining the cluster center of at least one cluster corresponding to the application to be recommended, the method includes: For each application to be recommended, determining a score of each application operation parameter corresponding to each application to be recommended; Establishing an information coordinate composed of scores of each of the application operation parameters; The applications to be recommended are clustered using a clustering algorithm and the information coordinates to generate the clusters.

6. The method according to claim 5, characterized in that Determining the score of each application operation parameter corresponding to each application to be recommended includes: For each application to be recommended, obtain all player information and all gameplay corresponding to the application to be recommended; For each of the application operation parameters, determining the application operation parameter score corresponding to each play method in each of the player information; The application operation parameter score corresponding to the application to be recommended is obtained according to the application operation parameter scores of all the players.

7. The method according to claim 6, characterized in that The application operation parameters include touch frequency, touch interval and touch displacement; Determining the score of each application operation parameter corresponding to each application to be recommended includes: Among them, Score 触摸频率G 、Score 触摸间隔G 、Score 触摸位移G They are the touch frequency score, touch interval score, and touch displacement score of application G, respectively. X is the total number of player information, X a For the ath player information, Count P is the total number of gameplays, P b For the b-th gameplay information, They are respectively the player touch frequency score, player touch interval score, and player touch displacement score corresponding to the b-th gameplay under the a-th player information of application G.

8. The method according to claim 5, characterized in that The determining of the cluster center of at least one cluster corresponding to the application to be recommended includes: The centroid of each cluster is calculated according to all the information coordinates in each cluster, and the centroid is used as the cluster center.

9. The method according to claim 1, characterized in that The outputting the recommendation information corresponding to the application to be recommended includes: At least one piece of recommendation information is randomly selected from all the recommendation information and outputted.

10. An information recommendation device, characterized in that: include: The acquisition module is used to obtain the user's application operation parameters; A calculation module is configured to calculate the user's operation level vector based on the application operation parameters, determine the cluster center of at least one cluster corresponding to the application to be recommended, and calculate the distance from the operation level vector to the cluster center; wherein the operation level vector is determined by: for each application operation parameter, counting the sum of the application operation parameters corresponding to all target applications, wherein the target application is a target application with open access rights; obtaining the average value of each application operation parameter based on the number of target applications; generating a target vector with the average value of each application operation parameter as a three-dimensional coordinate; and using the target vector as the user's operation level vector; wherein the cluster is a cluster corresponding to the application to be recommended established according to the classification method of the operation level vector; a determination module, configured to select a target cluster from the at least one cluster according to the distance, and determine an application to be recommended corresponding to the target cluster; The output module is used to output the recommendation information corresponding to the application to be recommended.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

12. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to implement the method according to any one of claims 1 to 9.

Images