Resource display method and device, electronic equipment and storage medium

Abstract

The invention provides a resource display method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of big data, knowledge maps and the like. According to the specific implementation scheme, according to a target set where objects in multiple sets are located, a display mode corresponding to the target set is determined; the plurality of sets are divided according to the preference degree of the objects on the resources of the predetermined category; according to the display mode, determining the maximum display frequency of the predetermined category of resources and the minimum display interval between the predetermined category of resources; and according to the maximum display frequency and the minimum display interval, displaying the predetermined category of resources to the object, wherein the maximum display frequency is positively correlated with the preference degree, and the minimum display interval is negatively correlated with the preference degree.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to technical fields such as big data and knowledge graphs. More specifically, the present disclosure provides a resource display method, device, electronic device, storage medium, and computer program product. Background Art

[0002] In daily life, you can recommend videos, live broadcasts and other resources to users, and you can improve user experience by recommending resources that match users' personal preferences. Summary of the invention

[0003] The present disclosure provides a resource display method, device, electronic device, storage medium and computer program product.

[0004] According to one aspect of the present disclosure, a resource display method is provided, comprising: determining a display mode corresponding to a target set according to a target set in which an object is located in a plurality of sets; the plurality of sets are divided according to the degree of preference of the object for resources of a predetermined category; determining a maximum display frequency of resources of the predetermined category and a minimum display interval between resources of the predetermined category according to the display mode; and displaying the resources of the predetermined category to the object according to the maximum display frequency and the minimum display interval; wherein the maximum display frequency is positively correlated with the degree of preference, and the minimum display interval is negatively correlated with the degree of preference.

[0005] According to another aspect of the present disclosure, a resource display device is provided, comprising: a mode determination module, an information determination module and a first display module. The mode determination module is used to determine a display mode corresponding to a target set according to a target set in which an object is located in a plurality of sets; the plurality of sets are divided according to the degree of preference of the object for resources of a predetermined category. The information determination module is used to determine, according to the display mode, a maximum display frequency of resources of a predetermined category and a minimum display interval between resources of a predetermined category, wherein the maximum display frequency is positively correlated with the degree of preference, and the minimum display interval is negatively correlated with the degree of preference. The first display module is used to display resources of a predetermined category to the object according to the maximum display frequency and the minimum display interval.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided by the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method provided by the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an application scenario of the resource display method and device according to an embodiment of the present disclosure;

[0012] Figure 2 is a schematic flow chart of a resource display method according to an embodiment of the present disclosure;

[0013] Figure 3A is a schematic diagram of a resource display method according to an embodiment of the present disclosure;

[0014] Figure 3B is a schematic diagram of a list of different set objects to be recommended according to an embodiment of the present disclosure;

[0015] Figure 4 is a schematic structural block diagram of a resource display device according to an embodiment of the present disclosure; and

[0016] Figure 5 It is a structural block diagram of an electronic device used to implement the resource display method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] In the technical solutions disclosed in this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the relevant laws and regulations and do not violate public order and good morals. In the technical solutions disclosed in this disclosure, the user's authorization or consent is obtained before obtaining or collecting user personal information.

[0019] For example, if you want to collect the user's personal information (such as the user's behavior data), you can pop up a query page to the user in advance and ask the user whether to agree to collect the user's behavior information for user resource recommendation, and collect the data after obtaining the user's authorization. If the user's authorization is not obtained, the data will not be collected.

[0020] It should be noted that universal resources refer to content that gives most users a good experience, such as cute kitten videos, beautiful scenery, etc. However, some users will have a certain interest in non-universal resources, which refer to resources with special content that may cause some users to have a poor experience. Such content includes but is not limited to scary content (snakes, spiders), etc. Resources include live broadcasts, videos, pictures, and texts.

[0021] In some embodiments, the recommendation algorithm usually builds a recommendation model based on user historical behavior data, resource content features, user portraits and other information. These algorithms include collaborative filtering-based recommendation algorithms, content-based recommendation algorithms, and hybrid recommendation algorithms. Collaborative filtering-based recommendation algorithms make recommendations by analyzing the similarities between users or items, while content-based recommendation algorithms focus on analyzing the matching degree between item features and user preferences. Hybrid recommendation algorithms combine the advantages of both to achieve better recommendation results.

[0022] Although the above recommendation algorithms have been able to achieve a certain degree of personalized recommendations and provide users with a content experience that is more in line with their preferences, these recommendation algorithms have a limitation: they are highly dependent on users' a posteriori feedback behavior. In other words, these recommendation algorithms require users to first watch non-universal resources that may not be suitable for everyone, and then gradually learn and adjust the recommendation algorithms based on user feedback data, such as click-through rate, fast scrolling rate, and viewing time, to make them more accurate.

[0023] However, the content of non-universal resources is likely to cause some users to have a poor experience. The reason for the poor user experience may be due to the sensitivity, controversy, or serious inconsistency of the content with the user's personal interests. In this case, the user may quickly choose to leave and avoid further exposure to such content, resulting in the user being unable to provide any a posteriori feedback. This results in the recommendation system being unable to effectively learn and grasp the user's true interests and preferences through the user's a posteriori behavior. Therefore, due to the inability to accurately capture and adapt to the user's true feelings and needs, the above recommendation algorithm has obvious shortcomings when dealing with non-universal resources, and its applicability in the field of non-universal resources is severely limited.

[0024] The disclosed embodiments aim to provide a resource display method, which is suitable for recommending non-universal resources, such as recommending non-universal live broadcasts, and quickly finding the target population without affecting the user experience, thereby solving the problem of poor user experience caused by inaccurate recommendation of non-universal resources.

[0025] The technical solution provided by the present disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Figure 1 It is a schematic diagram of an application scenario of the resource display method and device according to an embodiment of the present disclosure.

[0027] It should be noted that Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0028] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0029] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptops, desktop computers, etc.

[0030] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as resources determined according to the user request, etc.) to the terminal device.

[0031] It should be noted that the resource display method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the resource display device provided in the embodiment of the present disclosure can generally be set in the server 105. The resource display method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the resource display device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0032] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0033] Figure 2 It is a schematic flow chart of a resource display method according to an embodiment of the present disclosure.

[0034] like Figure 2 As shown, the resource display method 200 may include operations S210 to S230.

[0035] In operation S210, a display mode corresponding to a target set is determined according to a target set in which an object is located among a plurality of sets, wherein the plurality of sets are divided according to a preference degree of the object for resources of a predetermined category.

[0036] For example, the object may be a user.

[0037] For example, the resources of the predetermined category may be non-universal resources, such as non-universal live broadcast, non-universal video, non-universal graphics, etc. Non-universal resources refer to resources with special content that may easily cause poor user experience for some users, including but not limited to scary content (snakes, spiders), etc.

[0038] For example, a set may include an interested set, an uninterested set, and an intermediate set. The number of intermediate sets may be multiple, for example, multiple intermediate sets may include a potentially interested set, an indifferent set, and a potentially uninterested set. It can be seen that a set may reflect an object's attitude toward a predetermined category of resources, whether it likes, hates, or is indifferent. For example, the corresponding relationship between an object and a set may be predetermined, and the set in which the object is located may be used as a target set.

[0039] For example, a correspondence between a set and a presentation mode may be preconfigured, and the presentation mode of the object may be determined based on the correspondence.

[0040] In operation S220 , a maximum display frequency of resources of a predetermined category and a minimum display interval between resources of the predetermined category are determined according to the display mode.

[0041] Exemplarily, the maximum display frequency is positively correlated with the preference degree. For example, if the subject prefers resources of a predetermined category, the maximum display frequency is higher, such as 5 times a day at most. If the subject prefers resources of a predetermined category less, the maximum display frequency is lower, such as 1 time a day at most.

[0042] In one example, the minimum display interval may include the shortest interval between two adjacent resources of the predetermined category. For example, if the subject prefers resources of the predetermined category, the interval between the two resources of the predetermined category is at least 30 minutes. If the subject prefers resources of the predetermined category less, the interval between the two resources of the predetermined category is at least 3 hours.

[0043] In another example, the minimum display interval may include displaying a minimum number of resources of other categories between two adjacent resources of the predetermined categories. For example, if the subject prefers resources of the predetermined category, there are at least 20 resources of other categories between the two resources of the predetermined category. If the subject prefers resources of the predetermined category less, there are at least 100 resources of other categories between the two resources of the predetermined category.

[0044] In operation S230 , resources of a predetermined category are displayed to the object according to the maximum display frequency and the minimum display interval.

[0045] For example, resources of a predetermined category are displayed to the object on the basis of satisfying a maximum display frequency and a minimum display interval.

[0046] The technical solution provided by the embodiments of the present disclosure is suitable for recommending non-universal resources. Since the display mode is determined according to the target set in which the object is located, and the maximum display frequency and the minimum display interval of the resources of the predetermined category are limited based on the display mode, it is avoided that the object has negative emotions such as aversion to the recommended resources of the predetermined category, and the target population is quickly found without affecting the user experience, thereby solving the problem of poor user experience caused by inaccurate recommendation of non-universal resources to the target population.

[0047] Next, the determination of the set in which the object is located is described. The set includes an interested set, an uninterested set, and an intermediate set, and the number of the intermediate sets can be one or more. The set in which the object is located can reflect the object's preference for resources of a predetermined category.

[0048] Exemplarily, if the object is in the interest set, the object has a positive attitude toward the resources of the predetermined category, and a positive attitude means that the object likes the resources of the predetermined category and can accept and display a large number of resources of the predetermined category. Next, the process of determining the interest set is described.

[0049] In one example, if the object has subscribed to a resource of a predetermined category, the object may be added to the interest set.

[0050] For example, the object that publishes the resources of the predetermined category is called the third reference object, and the object that follows the third reference object is called the first reference object. Subscribing to the resources of the predetermined category includes: following the third reference object. Taking the resource of the predetermined category as non-universal live broadcast as an example, the third reference object can be a host of a non-universal live broadcast, and the first reference object can be a user who follows the host, that is, the user is a fan of the host, and the user can be added to the interest set.

[0051] For another example, subscribing to resources of a predetermined category includes: generating actions such as liking, collecting, and sharing the resources of the predetermined category. Taking the resource of the predetermined category as non-ubiquitous live broadcast as an example, if a user generates a liking action for the non-ubiquitous live broadcast, the user can be added to the interest set.

[0052] It is understandable that the user's subscription behavior can reflect that the user is interested in resources of a predetermined category, so adding objects subscribing to resources of a predetermined category to the interest set can improve the accuracy of dividing the set in which the object is located.

[0053] In another example, the similarity between the object and the first reference object can be determined based on the features of the object and the features of the first reference object, and if the similarity is greater than or equal to a first threshold, the object can be added to the set of interest. It can be seen that in this example, objects similar to the first reference object are added to the set of interest, and this method can also improve the accuracy of dividing the set in which the object is located.

[0054] In another example, for each third reference object, multiple first reference objects that focus on the same third reference object can be used to form an object set. Then, the similarity between the object and each first reference object in the object set can be determined, and when the similarity between the object and each first reference object in the object set is greater than or equal to a first threshold, the object can be added to the interest set. For example, a host has 100 fans, and the similarity between the 100 fans and the object can be determined. If the similarity between the object and only some of the fans is greater than or equal to the first threshold, the object will not be added to the interest set; if the similarity between the object and all the fans is greater than or equal to the first threshold, the object will be added to the interest set. This method can ensure that the object has a positive attitude towards resources of a predetermined category, and avoid mistakenly adding the object to the interest set due to the object's low interest in resources of a predetermined category.

[0055] In another example, if the click rate of the object for resources of a predetermined category is greater than a click rate threshold, and the average viewing time is greater than or equal to a time threshold, the object can be added to the interested set. It can be understood that the user's click rate and average viewing time can effectively reflect the user's preferences, thereby improving the accuracy of dividing the set in which the object is located.

[0056] The above describes the process of determining the set of interest.

[0057] Exemplarily, if the object is in the uninterested set, the object has a negative attitude toward the resources of the predetermined category, and a negative attitude means that the object hates the resources of the predetermined category and cannot accept any resources of the predetermined category. Next, the process of determining the uninterested set is described.

[0058] In one example, if the object generates a predetermined negative feedback behavior for a resource of a predetermined category, the object may be added to the uninterested set. For example, the predetermined negative feedback behavior includes clicking "not interested", "blacklisting the author", "not reading this content", "reporting", etc.

[0059] In another example, the object that has been added to the uninterested set is called the second reference object. The similarity between the object and the second reference object can be determined based on the characteristics of the object and the characteristics of the second reference object. If it is greater than or equal to a second threshold, the object can be added to the uninterested set.

[0060] In another example, if the click rate of the object on the resources of the predetermined category is less than the click rate threshold, or the average viewing time of the object on the resources of the predetermined category is less than the time threshold, the object can be added to the uninterested set. It can be understood that if the user clicks on the predetermined category less times, or exits the page soon after clicking, it can indicate that the user has a low preference for the resources of the predetermined category.

[0061] The above describes the process of determining the uninteresting set.

[0062] Exemplarily, if the object is in the middle set, the object's attitude toward the resources of the predetermined category is neutral, and a neutral attitude means that the object has neither a clear like nor a clear dislike for the resources of the predetermined category, and the object can accept a small amount of resources of the predetermined category.

[0063] In one example, the remaining objects outside the interesting set and the uninteresting set may be added to the intermediate set.

[0064] In another example, the number of intermediate sets is multiple, and the features of the third reference object can be first determined based on the features of multiple first reference objects that subscribe to the third reference object. For example, if a host has 100 fans, the features of the 100 fans can be weighted averaged and the result can be used as the features of the host. The weights of each fan can be the same or different. Next, the similarity between the object and the third reference object can be determined based on the features of the object and the features of the third reference object, and the object can be divided into the corresponding intermediate set based on the similarity.

[0065] For example, the number of intermediate sets is three, and the three intermediate sets are respectively called a potentially interesting set, an insensitive set, and a potentially uninteresting set. If the similarity between the object and the third reference object is greater than a first value, the object is added to the potentially interesting set. If the similarity between the object and the third reference object is less than or equal to the first value, and greater than or equal to the second value, the object is added to the insensitive set. If the similarity between the object and the third reference object is less than the second value, the object is added to the potentially uninteresting set.

[0066] It can be seen that in this embodiment, there are multiple intermediate sets, and the objects are divided into corresponding intermediate sets according to the similarity between the user and the third reference object. In this way, the remaining objects outside the interesting set and the uninteresting set can be classified more accurately, thereby improving the accuracy of the intermediate set division, and further improving the accuracy of subsequent recommendations and user experience.

[0067] According to another embodiment of the present disclosure, different sets correspond to different display strategies. This embodiment describes the display strategy corresponding to each set.

[0068] For example, if the object is in the interest set, a predetermined display method can be used to display resources of a predetermined category to the object. For example, non-universal live broadcasts can be normally recalled and issued according to the recommendation system algorithm model.

[0069] For example, if the object is in the uninterested set, it may be determined that the number of resources of the predetermined category displayed to the object is 0, that is, no resources of the predetermined category are recalled.

[0070] For example, if the object is in an intermediate set, since there are multiple intermediate sets, the operation of determining the maximum display frequency and the minimum display interval according to the display mode is triggered, wherein the minimum display interval may include the shortest interval duration between two adjacent resources of the predetermined category, and may also include the minimum number of resources of other categories displayed between two adjacent resources of the predetermined category, thereby selecting different display strategies according to the intermediate set in which the object is located. The following takes the resource of the predetermined category as non-universal live broadcast as an example to illustrate the display process of the intermediate set.

[0071] For example, if the object is in a potential interest set, the maximum display frequency of the user's non-universal live broadcast in a single day can be controlled to be a maximum of 5 times a day, the time interval between two non-universal live broadcasts is not less than 10 minutes, and the distance interval between two non-universal live broadcasts is not less than 20 videos.

[0072] For example, if the object is in an insensitive set, the maximum display frequency of the user's non-universal live broadcast in a single day can be controlled to be a maximum of 2 times a day, the time interval between two non-universal live broadcasts is not less than 20 minutes, and the distance interval between two non-universal live broadcasts is not less than 50 videos.

[0073] For example, if the object is in a potentially uninterested set, the maximum display frequency of the user's non-universal live broadcast in a single day can be controlled to be once a day at most, the time interval between two non-universal live broadcasts should be no less than 30 minutes, and the distance interval between two non-universal live broadcasts should be no less than 100 videos.

[0074] It can be seen that in this embodiment, the minimum display interval includes the shortest interval between two adjacent resources of the predetermined category, which can prevent users from browsing multiple resources of the predetermined category in a short time, thereby preventing the high frequency of pushing resources of the predetermined category from causing user disgust, and improving user experience. In addition, in this embodiment, the minimum display interval also includes the minimum number of resources of other categories displayed between two adjacent resources of the predetermined category, which can prevent users from continuously browsing multiple resources of the predetermined category, further improving user experience.

[0075] Figure 3A It is a schematic diagram of a resource display method according to an embodiment of the present disclosure.

[0076] In this embodiment, a feature library 304 including features 302 of multiple objects 301 may be constructed first.

[0077] For example, when it is necessary to recommend resources of a certain resource site (such as live broadcast) to object 301, the behavior data of object 301 on other resource sites such as forums, browsers, and video sites can be collected in advance. The behavior of object 301 includes clicks, reading time, completion rate, likes, comments, attention, and sharing, etc. Then, based on the feature processing algorithm, each object 301 can be modeled based on these behaviors to obtain the features 302 of object 301 and the features of the resources. In addition, for the same third reference object (such as a host), the average value of the features 302 of multiple first reference objects that pay attention to the third reference object among multiple objects 301 can be used as the features 303 of the third reference object.

[0078] After obtaining the features 302 of each first reference object and the features 303 of the third reference object, a feature library 304 may be constructed. For example, taking the feature 302 as a vector, a more time- and space-efficient data structure may be constructed for the vector data based on a mathematical model, so as to efficiently query similar objects of a certain object 301. For example, the Annoy (Approximate Nearest Neighbors Oh Yeah) algorithm may be used to construct a vector index library as the feature library 304. The feature library 304 may only contain the features 302 of the object 301, but not the features of the resources. The vector index may be used to query several objects that are most similar to a specific object 301, and the returned results include the IDs and similarity values ​​of the similar objects.

[0079] It should be noted that, since the interest of the object 301 may change dynamically, the operation may be performed every predetermined time period to update the feature library 304 of the object 301. The predetermined time period may be one day, which is not limited in this embodiment.

[0080] Next, each object 301 can be divided into corresponding sets according to the features 302 of the object 301, and the sets include an interested set 307, an uninterested set 309, and an intermediate set 308. The number of intermediate sets 308 can be multiple, for example, multiple intermediate sets 308 can include a potential interested set, an insensitive set, and a potential uninterested set. The set in which the object 301 is located can be used as a label of the object 301 and written into the object label system 305. The method for determining the set in which the object 301 is located can refer to the above, and will not be repeated in this embodiment.

[0081] Next, the recommendation system can read the identifier of the set where the object 301 is located from the object tag system 305, and can also obtain resources of a predetermined category from the resource library 306. The recommendation system can then use different recommendation strategies to recommend resources of a predetermined category based on the identifier of the set where the object 301 is located. For example, for the object 301 in the interested set 307, the recommendation system can normally recall and issue resources of a predetermined category. For the object 301 in the uninterested set 309, no resources of any predetermined category may be recalled. For the object 301 in the intermediate set 308, resources of a predetermined category are displayed to the object 301 based on the maximum display frequency and the minimum display interval.

[0082] Next, the a posteriori behaviors of the object 301 on the resources of the predetermined category may be collected, so as to update the collection in which the object 301 is located based on the a posteriori behaviors, and update the data in the object tag system 305 .

[0083] Figure 3B 4 is a schematic diagram of a list of different set objects to be recommended according to an embodiment of the present disclosure.

[0084] For example, if object 3011 is in the potential interest set, the maximum display frequency of the non-universal live broadcast of object 3011 in a single day can be controlled to be a maximum of 5 times a day, the time interval between two non-universal live broadcasts is not less than 10 minutes, and the distance interval between two non-universal live broadcasts is not less than 20 videos.

[0085] For example, if object 3012 is in the insensitive set, the maximum display frequency of the non-universal live broadcast of object 3012 in a single day can be controlled to be a maximum of 2 times a day, the time interval between two non-universal live broadcasts is not less than 20 minutes, and the distance interval between two non-universal live broadcasts is not less than 50 videos.

[0086] For example, if object 3013 is in the potential uninterested set, the maximum display frequency of the non-universal live broadcast of object 3013 in a single day can be controlled to be displayed once a day at most, the time interval between two non-universal live broadcasts should be no less than 30 minutes, and the distance interval between two non-universal live broadcasts should be no less than 100 videos.

[0087] According to another embodiment of the present disclosure, the above embodiment needs to first determine the characteristics of the object in the process of building the feature library of the object. This embodiment provides a method for determining the characteristics of the object. Next, taking the object as a user as an example, the method for determining the characteristics of the object is explained.

[0088] Taking the non-universal live broadcast as an example, the user's interest preferences can be learned and understood based on the user's a posteriori behavior on non-live content such as pictures, texts, and videos, and then the user's characteristics can be accurately constructed. The user's click, reading time, completion rate, likes, comments, attention, and sharing behavior data when browsing pictures, texts, videos, novels, dynamics and other resources can be collected. If the user has interactive behaviors such as clicks and likes on the resources, there is an interactive relationship between the user and the resource. It should be noted that the collection of user behavior information requires the user's authorization to be pre-selected. For example, when displaying pictures, texts, videos, novels, dynamics and other resources to the user, an inquiry page will pop up to the user and ask the user whether he agrees to collect the user's behavior information for user resource recommendation, and collect data after obtaining the user's authorization. If the user's authorization is not obtained, the data will not be collected.

[0089] Next, a point-edge graph can be constructed based on users, resources, and the interaction relationship between users and resources. The point-edge graph includes multiple nodes, including user nodes corresponding to users and resource nodes corresponding to resources. User nodes and resource nodes with interactive relationships are connected via edges. Edges can only connect user nodes and resource nodes, but not directly connect two user nodes or two resource nodes. A point-edge graph can be constructed based on the GraphSAGE model.

[0090] Next, sampling can be performed. For example, for each node in the point-edge graph (the node can be a resource node or a user node), a sampling node set can be determined based on the node's neighbor nodes. The sampling node set can include at least one of a resource node and a user node. For example, a certain number of nodes are randomly sampled from its neighbor nodes as a sampling node set. During the sampling process, the number of neighbors to be sampled can be determined first, and then a resampling method with replacement can be used for sampling. The purpose of sampling is to explore the local structure of the node in order to better capture the characteristics of the node.

[0091] Next, the nodes in the point-edge graph are encoded by an encoder, which can be a fully connected layer, a convolutional neural network, etc. Taking node A as an example, H(A) can be used to represent the encoded vector of node A.

[0092] Next, for a certain node, the encoded vector of each node in the sampling node set and the encoded vector of the node may be aggregated based on the aggregation parameter to obtain the aggregated feature of the node.

[0093] For example, for a node A, its sampling node set includes nodes B, C, and D. N(A) can be used to represent all neighbor nodes of node A, then N(A) = {B, C, D}. Then, average pooling or maximum pooling is used to aggregate the neighbor nodes of each node, and the aggregation result is represented by HN(A). Taking the maximum pooling method as an example, the maximum pooling takes the maximum value element by element. For example, the encoded vector of node B is [1,2,3], the encoded vector of node C is [3,5,1], and the encoded vector of node D is [2,3,4], then HN(A)=[3,5,4].

[0094] Then the vector of each node can be updated. For example, taking node A as an example, concatenate the aggregation result HN(A) and the encoded vector H(A), for example: HN(A)=[3,5,4], H(A)=[4,5,6], then the concatenated vector is [3,5,4,4,5,6]. Then the concatenated vector can be transformed nonlinearly. For example, the calculation formula is as follows:

[0095] fc(X)=sigmoid(W*X+B)

[0096] Among them, fc is the result of nonlinear transformation, sigmoid is the nonlinear transformation function, W and B are the parameters for linear change, that is, the aggregation parameters mentioned above, and X is the concatenated vector, such as [3,5,4,4,5,6] above.

[0097] Next, the new value generated by the nonlinear transformation is assigned to H(A), and the dimension of the new H(A) is the same as the original H(A). This step is to weight the node vector and the neighbor vector so that the node vector contains important information about its neighbor nodes.

[0098] The above describes an aggregation process once. In practical applications, the above aggregation operation can be performed twice, and the second aggregation result is used as the post-aggregation feature.

[0099] After obtaining the aggregated features, the parameter learning process can be performed.

[0100] For example, the feature pair is input into a multilayer perceptron (MLP) to obtain the output confidence, wherein the feature pair includes the aggregated features of the user and the aggregated features of the resource, and the label represents whether there is an interactive relationship between the user and the resource corresponding to the feature pair. For example, if there is an interactive relationship, the value of the label is 1, and if there is no interactive relationship, the value of the label is 0. Then, the loss value can be determined according to the difference between the output confidence and the label, and the aggregation parameters, the parameters of the multilayer perceptron and the features of the node can be adjusted based on the loss value until the predetermined termination condition is met. The predetermined termination condition may include that the number of iterations reaches a threshold or the loss value is less than the loss threshold. Then, the features of the node are determined based on the adjusted features of the node that meets the predetermined termination condition. After obtaining the features of the user node and the features of the resource node, the features of the user node can be added to the feature library, thereby realizing the construction of the feature library.

[0101] Figure 4 It is a schematic structural block diagram of a resource display device according to an embodiment of the present disclosure.

[0102] like Figure 4 As shown, the resource display device 400 may include a mode determination module 410 , an information determination module 420 and a first display module 430 .

[0103] The mode determination module 410 is used to determine a display mode corresponding to a target set according to the target set in which the object in the multiple sets is located; the multiple sets are divided according to the degree of preference of the object for resources of a predetermined category.

[0104] The information determination module 420 is used to determine the maximum display frequency of resources of a predetermined category and the minimum display interval between resources of the predetermined category according to the display mode, wherein the maximum display frequency is positively correlated with the preference degree and the minimum display interval is negatively correlated with the preference degree.

[0105] The first display module 430 is used to display resources of a predetermined category to the object according to the maximum display frequency and the minimum display interval.

[0106] According to another embodiment of the present disclosure, the minimum display interval includes at least one of the following: the shortest interval duration between two adjacent resources of a predetermined category; and the minimum number of resources of other categories displayed between two adjacent resources of a predetermined category.

[0107] According to another embodiment of the present disclosure, the above-mentioned device further includes: a second display module, a third display module and a trigger module. The second display module is used for displaying resources of a predetermined category to the object in a predetermined display manner in response to determining that the target set is an interested set. The third display module is used for determining that the number of resources of the predetermined category displayed to the object is 0 in response to determining that the target set is an uninterested set. The trigger module is used for triggering an operation of determining the maximum display frequency and the minimum display interval according to the display mode in response to determining that the target set is an intermediate set other than the interested set and the uninterested set.

[0108] According to another embodiment of the present disclosure, multiple sets include an interested set; the interested set is determined by the following modules: a first adding module, used to add an object to the interested set in response to determining that the object satisfies one of the following conditions: the object has subscribed to resources of a predetermined category; the similarity between the object and a first reference object is greater than or equal to a first threshold, and the first reference object belongs to the interested set; and the object's click-through rate for resources of a predetermined category is greater than a click-through rate threshold, and the average viewing time is greater than or equal to a time threshold.

[0109] According to another embodiment of the present disclosure, multiple sets include a not-interested set, which is determined by the following modules: a second adding module, used to add the object to the not-interested set in response to determining that the object satisfies one of the following conditions: the object generates a predetermined negative feedback behavior for resources of a predetermined category; the similarity between the object and a second reference object is greater than or equal to a second threshold, and the second reference object belongs to the not-interested set; and the object's click-through rate for resources of a predetermined category is less than a click-through rate threshold or the average viewing time is less than a time threshold.

[0110] According to another embodiment of the present disclosure, multiple sets include at least two intermediate sets, and the at least two intermediate sets are determined by the following modules: an intermediate set determination module is used to determine, for objects outside the interested set and the uninterested set, the intermediate set in which the object is located from at least two intermediate sets based on the similarity between the characteristics of the object and the characteristics of a third reference object; wherein the characteristics of the third reference object are determined based on the characteristics of multiple first reference objects that subscribe to the third reference object.

[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned resource display method.

[0112] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned resource display method.

[0113] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, and the computer program implements the above-mentioned resource display method when executed by a processor.

[0114] Figure 5 1 is a block diagram of an electronic device for implementing the resource display method of an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0115] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0116] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0117] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the resource display method. For example, in some embodiments, the resource display method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the resource display method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the resource display method in any other appropriate manner (e.g., by means of firmware).

[0118] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0120] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0123] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0124] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0125] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A resource display method, comprising: Determining, according to a target set in which an object in a plurality of sets is located, a display mode corresponding to the target set; The multiple sets are divided according to the object's preference for resources of a predetermined category; Determine, according to the display mode, a maximum display frequency of the resources of the predetermined category and a minimum display interval between the resources of the predetermined category; as well as Displaying the resources of the predetermined category to the object according to the maximum display frequency and the minimum display interval; The maximum display frequency is positively correlated with the preference degree, and the minimum display interval is negatively correlated with the preference degree.

2. The method according to claim 1, wherein: The minimum display interval includes at least one of the following: The shortest interval between two adjacent resources of the predetermined category; as well as Between two adjacent resources of a predetermined category, a minimum number of resources of other categories are displayed.

3. The method according to claim 1, further comprising: In response to determining that the target set is an interested set, displaying resources of the predetermined category to the object in a predetermined display manner; In response to determining that the target set is an uninterested set, determining that the number of resources of the predetermined category displayed to the object is 0; as well as In response to determining that the target set is an intermediate set other than the interested set and the uninterested set, an operation of determining the maximum display frequency and the minimum display interval according to the display mode is triggered.

4. The method according to claim 1, wherein: The multiple sets include an interest set; the interest set is determined in the following manner: In response to determining that the object satisfies one of the following conditions, the object is added to the interest set: The object has subscribed to the resources of the predetermined category; The similarity between the object and a first reference object is greater than or equal to a first threshold, and the first reference object belongs to the set of interest; as well as The click rate of the object for the resources of the predetermined category is greater than a click rate threshold, and the average viewing time is greater than or equal to a time threshold.

5. The method according to claim 1, wherein: The multiple sets include a not-interesting set, and the not-interesting set is determined in the following manner: In response to determining that the object satisfies one of the following conditions, the object is added to the uninteresting set: The object generates a predetermined negative feedback behavior for the predetermined category of resources; The similarity between the object and a second reference object is greater than or equal to a second threshold, and the second reference object belongs to the uninterested set; as well as The click rate of the object for the resources of the predetermined category is less than a click rate threshold or the average viewing time is less than a time threshold.

6. The method according to claim 1, wherein: The multiple sets include an interested set, a not interested set, and at least two intermediate sets, and the at least two intermediate sets are determined in the following manner: For the object outside the interest set and the uninterest set, determining the intermediate set in which the object is located from the at least two intermediate sets according to the similarity between the feature of the object and the feature of the third reference object; The characteristic of the third reference object is determined according to the characteristics of a plurality of first reference objects subscribing to the third reference object.

7. A resource display device, comprising: A mode determination module, configured to determine a display mode corresponding to a target set according to the target set in which the objects in the multiple sets are located; The multiple sets are divided according to the object's preference for resources of a predetermined category; An information determination module, configured to determine, according to the display mode, a maximum display frequency of the resources of the predetermined category and a minimum display interval between the resources of the predetermined category; as well as A first display module, configured to display the resources of the predetermined category to the object according to the maximum display frequency and the minimum display interval; The maximum display frequency is positively correlated with the preference degree, and the minimum display interval is negatively correlated with the preference degree.

8. The device according to claim 7, wherein: The minimum display interval includes at least one of the following: The shortest interval between two adjacent resources of the predetermined category; as well as Between two adjacent resources of a predetermined category, a minimum number of resources of other categories are displayed.

9. The apparatus according to claim 7, further comprising: A second display module, configured to display the resources of the predetermined category to the object in a predetermined display manner in response to determining that the target set is an interested set; A third display module, configured to, in response to determining that the target set is an uninterested set, determine that the number of resources of the predetermined category displayed to the object is 0; as well as A trigger module is used for triggering the operation of determining the maximum display frequency and the minimum display interval according to the display mode in response to determining that the target set is an intermediate set other than the interested set and the uninterested set.

10. The device according to claim 7, wherein: The multiple sets include an interest set; the interest set is determined by the following modules: A first adding module is configured to add the object to the interest set in response to determining that the object satisfies one of the following conditions: The object has subscribed to the resources of the predetermined category; The similarity between the object and a first reference object is greater than or equal to a first threshold, and the first reference object belongs to the set of interest; as well as The click rate of the object for the resources of the predetermined category is greater than a click rate threshold, and the average viewing time is greater than or equal to a time threshold.

11. The device according to claim 7, wherein: The multiple sets include a set of no interest, and the set of no interest is determined by the following modules: The second adding module is configured to add the object to the uninterested set in response to determining that the object satisfies one of the following conditions: The object generates a predetermined negative feedback behavior for the predetermined category of resources; The similarity between the object and a second reference object is greater than or equal to a second threshold, and the second reference object belongs to the uninterested set; as well as The click rate of the object for the resources of the predetermined category is less than a click rate threshold or the average viewing time is less than a time threshold.

12. The device according to claim 7, wherein: The multiple sets include an interested set, a not interested set, and at least two intermediate sets, and the at least two intermediate sets are determined by the following modules: an intermediate set determining module, for determining, for an object outside the interest set and the uninterest set, the intermediate set in which the object is located from the at least two intermediate sets according to a similarity between a feature of the object and a feature of a third reference object; The characteristic of the third reference object is determined according to the characteristics of a plurality of first reference objects subscribing to the third reference object.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images