A resource recommendation method and apparatus

Abstract

This disclosure provides a resource recommendation method and apparatus, relating to the field of data processing, and particularly to the field of information flow. The specific implementation scheme is as follows: Based on a diversity threshold corresponding to the target user's historical resource types, resources to be recommended to the target user are determined. The historical resource types refer to the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics refer to statistics on the information displayed to the target user regarding the historical resources, and the access statistics refer to statistics on the target user's access to the historical resources. The determined resources are then recommended to the client used by the target user. Applying the resource recommendation scheme provided by this disclosure allows for personalized setting of diversity thresholds for users, thereby enabling personalized resource recommendations.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, particularly to the field of information flow technology, and especially to a resource recommendation method and apparatus. Background Technology

[0002] When a user accesses resources such as images, videos, and audio using a client, the client sends a resource retrieval request to the server. In response to the resource retrieval request, the server determines the resources to be recommended to the user from the candidate resources and recommends the determined resources to the client. In this way, the client can display the determined resources to the user.

[0003] To recommend a wide variety of resources to users, the server can set the same diversity threshold for each resource type. This diversity threshold refers to the maximum percentage of resources of that type among the resources to be recommended to the user. Thus, when determining which resources to recommend, the server can use the diversity threshold for each resource type to select the appropriate resources. Summary of the Invention

[0004] This disclosure provides a resource recommendation method and apparatus.

[0005] In a first aspect, embodiments of this disclosure provide a resource recommendation method, including:

[0006] Based on the diversity threshold corresponding to the target user's historical resource types, resources to be recommended to the target user are determined. The historical resource types are the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics are the statistics of information on the historical resources displayed to the target user. The access statistics are the statistics of the target user accessing the historical resources.

[0007] Recommend the identified resources to the client used by the target user.

[0008] Secondly, embodiments of this disclosure provide a resource recommendation device, including:

[0009] The resource determination module is used to determine the resources to be recommended to the target user based on the diversity threshold corresponding to the historical resource types of the target user. The historical resource types are the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics are the statistics of information on the historical resources displayed to the target user. The access statistics are the statistics of the target user accessing the historical resources.

[0010] The resource recommendation module is used to recommend determined resources to the client used by the target user.

[0011] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0015] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described in the first aspect above.

[0016] Fifthly, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0017] As can be seen from the above, when recommending resources using the solution provided in this embodiment, the diversity threshold corresponding to the historical resource type is determined based on the display statistics and access statistics. The display statistics are the statistics on the information of historical resources displayed to the target user, and the access statistics are the statistics on the target user's access to historical resources. Therefore, the display statistics and access statistics can reflect the user's preferences and habits in accessing resources. Based on these two types of statistics, the diversity threshold of the historical resource type can be set for the target user in a personalized way, and thus, based on the diversity threshold, resources can be recommended to the target user in a personalized way.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0019] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0020] Figure 1 A flowchart illustrating the first resource recommendation method provided in this embodiment of the disclosure;

[0021] Figure 2 A flowchart illustrating a threshold determination method provided in an embodiment of this disclosure;

[0022] Figure 3 A flowchart illustrating the second resource recommendation method provided in this embodiment of the disclosure;

[0023] Figure 4 This is a schematic diagram of the structure of a resource recommendation device provided in an embodiment of the present disclosure;

[0024] Figure 5 This is a schematic diagram of the structure of a threshold determination device provided in an embodiment of the present disclosure;

[0025] Figure 6 This is a block diagram of an electronic device used to implement the resource recommendation method of the embodiments of this disclosure. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] First, the application scenarios of the solutions provided in the embodiments of this disclosure will be explained.

[0028] 1. Users refresh the accessed resources during the access process.

[0029] When users access resources displayed in the client, they can refresh those resources, such as by clicking the refresh button or scrolling down the page. Upon detecting this refresh, the client can send a resource retrieval request to the server. In response, the server recommends new resources to the client, allowing the client to display these new resources to the user; in other words, the server recommends resources to the user.

[0030] 2. User login or online

[0031] After a user logs in or goes online, the client can send a resource request to the server, which then recommends resources to the client, and the client displays the resources to the user.

[0032] 3. The user opens the resource recommendation page provided by the client.

[0033] The client can provide various pages, including a resource recommendation page, which displays resource information. When a user uses the client, they can open the resource recommendation page provided by the client. When a user opens the resource recommendation page, the client can send a resource retrieval request to the server, and the server will then recommend resources to the client. The client then displays the resources to the user on the resource recommendation page.

[0034] The above three application scenarios are only some of the application scenarios of the resource recommendation scheme provided in this disclosure. This disclosure does not limit other application scenarios.

[0035] Secondly, the implementing entity of the resource recommendation scheme provided in the embodiments of this disclosure will be described.

[0036] The resource recommendation scheme provided in this embodiment is implemented by a server. The server determines the resources to be recommended to the user based on the diversity threshold corresponding to the resource type, and then recommends the determined resources to the client used by the user.

[0037] In addition, the entity that performs the determination of the diversity threshold corresponding to the resource type can be a server, or other devices other than a server that have the function of determining the diversity threshold.

[0038] When the aforementioned other devices determine the diversity threshold corresponding to the resource type, the aforementioned other devices can determine the diversity threshold corresponding to the historical resource type based on the statistical information of historical resources before the server responds to the client's resource acquisition request, and send the determined diversity threshold to the server.

[0039] When the server determines the diversity threshold corresponding to the resource type, in addition to determining the diversity threshold corresponding to the historical resource type before responding to the resource acquisition request, the server can also first determine the diversity threshold corresponding to the historical resource type during the process of responding to the resource acquisition request, and then determine the resource to be recommended to the user based on the diversity threshold corresponding to the historical resource type, and recommend the determined resource to the server.

[0040] The resource recommendation scheme will be described in detail below through specific embodiments.

[0041] In one embodiment of this disclosure, see [link to embodiment]. Figure 1 The present invention provides a flowchart of the first resource recommendation method. In this embodiment, the above method includes the following steps S101-S102.

[0042] Step S101: Determine the resources to be recommended to the target user based on the diversity threshold corresponding to the target user's historical resource types.

[0043] These resources can be images, videos, audio, etc. Taking video resources as an example, there are various types of resources, such as sports, finance, and film and television.

[0044] The above-mentioned historical resource type refers to the type of historical resources recommended to the target user.

[0045] The aforementioned historical resources are those previously recommended by the server to the client, and these historical resources can be resources recommended by the server to the client within a past period. For example, the aforementioned historical resources could be resources recommended by the server to the client within the past week.

[0046] The diversity threshold corresponding to a resource type can be viewed as the proportion of resources of that resource type among the resources recommended to the target user. The larger the diversity threshold, the larger the proportion of resources of that resource type among the resources recommended to the target user; the smaller the diversity threshold, the smaller the proportion of resources of that resource type among the resources recommended to the target user.

[0047] The aforementioned diversity thresholds are determined based on display statistics and access statistics. Display statistics refer to the statistics on the information of historical resources displayed to the target user, while access statistics refer to the statistics on the target user's access to historical resources.

[0048] For details on displaying and accessing statistical information, as well as the specific implementation method for determining the diversity threshold, please refer to the subsequent embodiments, which will not be detailed here.

[0049] Specifically, the server can determine the total number of resources to be recommended to the client. Based on the diversity threshold corresponding to the historical resource type, the server can multiply the total number by the diversity threshold corresponding to the historical resource type. The product is the maximum number of historical resource types to be recommended to the client. Then, from the candidate historical resource types, resources whose number does not exceed the maximum number are selected as the resources to be recommended to the target user.

[0050] The total quantity mentioned above can be a pre-set, fixed quantity, in which the server recommends a fixed number of resources to the client each time; or the total quantity mentioned above can be the number of resources carried by the client in the resource acquisition request, in which the server can obtain the number of resources carried in the resource acquisition request when responding to the resource acquisition request and use it as the total quantity mentioned above.

[0051] Since the historical resources recommended to the target user may be of one or more types, the aforementioned historical resource types may also be one or more. For each historical resource type, the server can determine the maximum number of resources of that type based on the diversity threshold corresponding to that historical resource type.

[0052] For example, if the server wants to recommend 50 resources to the client, and the diversity threshold for type T1 is 0.3, then the server can calculate that the maximum number of resources for type T1 is 15. That is, the server can determine a maximum of 15 resources from the candidate resources of type T1 as resources to recommend to the client.

[0053] After determining the maximum number of resources for a historical resource type, you can select any number of resources not exceeding the maximum from the candidate historical resource types as resources to recommend to the target users. Alternatively, you can select any number of resources not exceeding the maximum from the candidate historical resource types according to preset rules.

[0054] For example, the preset rules could be to select resources in descending order of data volume, or to select resources in sorting order by name, and so on.

[0055] Furthermore, when selecting resources from candidate historical resource types, if the number of resources in a candidate historical resource type does not exceed the maximum, all resources of that candidate historical resource type can be selected; if the number of resources in a candidate historical resource type exceeds the maximum, the maximum number of resources can be selected, and the remaining unselected resources are used as a resource supplement set. After selecting resources from each candidate historical resource type using this selection method, if the total number of selected resources is insufficient to recommend resources to the client, resources are then selected from the resource supplement set to make up the difference.

[0056] Step S102: Recommend the determined resources to the client used by the target user.

[0057] Specifically, the server can recommend resources to the client using either of the following two implementation methods.

[0058] In the first implementation, after the server determines the resource, it can obtain the address information of the determined resource and send the obtained address information of the resource to the client. After the client receives the address information sent by the server, it can determine the resource at the location indicated by the address information and obtain the preview information of the determined resource, thereby displaying the preview information of the obtained resource to the target user on the page.

[0059] In the second implementation, after the server determines the resource, it can obtain the preview information of the determined resource and send the obtained preview information of the resource to the client. In this way, after the client receives the preview information of the resource, it can directly display the preview information of the obtained resource to the target user on the page.

[0060] In addition, after determining the resources, the server can sort the resources and then recommend the sorted resources to the client.

[0061] As can be seen from the above, when recommending resources using the solution provided in this embodiment, the diversity threshold corresponding to the historical resource type is determined based on the display statistics and access statistics. The display statistics are the statistics on the information of historical resources displayed to the target user, and the access statistics are the statistics on the target user's access to historical resources. Therefore, the display statistics and access statistics can reflect the user's preferences and habits in accessing resources. Based on these two types of statistics, the diversity threshold of the historical resource type can be set for the target user in a personalized way, and thus, based on the diversity threshold, resources can be recommended to the target user in a personalized way.

[0062] Furthermore, the diversity threshold corresponding to a historical resource type refers to the maximum proportion of resources of that historical resource type in the resources to be recommended to the user. After determining the diversity threshold corresponding to each historical resource type, the proportion of resources of each resource type in the resources to be recommended to the user can be allocated according to the diversity threshold corresponding to each historical resource type, while conforming to the user's preferences and habits. This ensures that users are recommended a rich variety of resources without causing aesthetic fatigue or loss of novelty for the target users. Moreover, the resource recommendation scheme provided by this disclosure can provide personalized resource recommendations for users. Different resources can be recommended to different users, thereby achieving personalized resource recommendations and optimizing the recommendation effect.

[0063] In one embodiment of this disclosure, the server may include multiple resource aggregation modules, each of which is used to recall resources using different recall strategies.

[0064] After receiving a resource acquisition request, the server can call various resource aggregation modules to recall resources in response to the request. The recalled resources are then used as candidate resources. Based on the diversity threshold corresponding to the historical resource types, the server determines the resources to be recommended to the target user from among the candidate resources.

[0065] In addition, after calling the resource aggregation module to recall resources, the recalled resources can be deduplicated, merged, and filtered, and the processed resources can be used as the aforementioned candidate resources.

[0066] The following section will first explain the display of statistical information and access statistics mentioned in step S101 above.

[0067] a. Displaying statistical information

[0068] The displayed statistics are: statistics on the information of historical resources shown to the target users. They can be seen as information obtained by statistically analyzing the behavior of showing historical resources to the target users.

[0069] The information about the aforementioned resources can include the resource's content, description, cover, etc. Displaying information about historical resources to the target user means showing them the content, description, cover, etc. of the historical resources.

[0070] For example, if the resource is an image, the image can be displayed directly to the target user; if the resource is a video, the video cover, video description, etc., can be displayed to the target user, or the video or video clips can be displayed directly to the target user.

[0071] The above-mentioned statistics may include the number of resources displayed, the resource display rate, etc.

[0072] The above resource display quantity refers to the quantity of historical resource information displayed to the target user.

[0073] Historical resources may be of various types. The number of resources displayed can be divided into the total number of resources displayed and the number of resources displayed for each resource type. The total number of resources displayed is the number of all historical resource information displayed to the target user, and the number of resources displayed for each resource type is the number of historical resource information of that resource type displayed to the target user.

[0074] In addition, each resource type corresponds to a resource display rate, which is the ratio of the number of displays of that resource type to the total number of resource displays.

[0075] b. Access statistics

[0076] Access statistics are: statistics on target users' access to historical resources. They can be seen as information obtained by statistically analyzing the target users' access to historical resources.

[0077] The above access statistics may include the number of times a resource is accessed and the resource access rate.

[0078] The number of times the above resources were accessed is: the number of historical resources accessed by the target user.

[0079] The number of resources accessed can also be divided into the total number of resources accessed and the number of resources accessed for each resource type. The total number of resources accessed is the number of all historical resources accessed by the target user, and the number of resources accessed for each resource type is the number of resources accessed by the target user for that specific resource type.

[0080] In addition, each resource type corresponds to a resource access rate, which is the percentage of resources of that resource type accessed by the target user in the historical data.

[0081] Secondly, the specific implementation method of determining the diversity threshold mentioned in step S101 above will be explained.

[0082] The diversity threshold can be determined by the server, or by other devices that have the function of determining the diversity threshold. The following explanation uses the example of the server determining the diversity threshold.

[0083] In one embodiment of this disclosure, see [link to embodiment]. Figure 2 This document provides a flowchart illustrating a threshold determination method. In this embodiment, the diversity threshold corresponding to the historical resource types of a target user can be determined through the following steps S201-S204.

[0084] Step S201: Obtain resource information of historical resources recommended to the target user.

[0085] The resource information of the aforementioned historical resources may include the attributes of the historical resources, such as resource name, resource type, etc.

[0086] Specifically, each time a server recommends a resource to a client, it can record the resource information or index information of the recommended resource. If the server has recorded the resource information, it can directly read the resource information it has recorded; if the server has recorded the index information of the resource, it can determine the historical resource based on the index information and obtain the resource information of the determined historical resource.

[0087] Step S202: Based on the obtained resource information, determine the historical resource type of the historical resources.

[0088] For example, the resource information obtained by the server can include the resource type of the resource. In this way, the resource type contained in the resource information can be read directly, and the read resource type is the historical resource type.

[0089] For example, the server can pre-obtain the correspondence between resource types and keywords. For instance, for the resource type "sports," there might be a correspondence with keywords like "football," "basketball," "sprint," and "swimming." In this case, the resource information obtained by the server can include the resource name. The server can then perform keyword detection on the resource name to obtain the target keywords contained within it. Then, it can check the pre-obtained correspondences for those containing the target keywords, thereby determining the resource type within that correspondence and using it as the historical resource type for historical resources.

[0090] Step S203: Obtain display statistics and access statistics.

[0091] Each time the server recommends resources to the client, it can record the total number of recommended resources and the number of resources of each resource type. Therefore, when obtaining display statistics, the server can use the recorded total number and the number of resources of each resource type as display statistics. Furthermore, the server can also calculate the resource display rate corresponding to each resource type based on the total number and the number of resources of each resource type, which is also used as display statistics.

[0092] Furthermore, each time a target user accesses a resource using the client, the client can send a notification to the server. This allows the server to record the total number of resource accesses. The notification sent by the client can include the resource type accessed by the target user, allowing the server to record the number of accesses for each resource type. Therefore, when obtaining access statistics, the server can use the recorded total number of resource accesses and the number of accesses for each resource type as the access statistics. The server can also calculate the resource access rate for each resource type based on the total number of resource accesses and the number of accesses for each resource type, which is also included in the access statistics.

[0093] Step S204: Based on the displayed statistics and access statistics, determine the diversity threshold corresponding to the historical resource types of the target user.

[0094] If the display statistics and access statistics obtained in step S203 are different, then the method for determining the diversity threshold in step S204 will also be different. For details, please refer to the following embodiments, which will not be described in detail here.

[0095] Furthermore, when classifying resources, multiple levels of classification can be used. For historical resources, each level has its own historical classification. In this case, when determining the diversity threshold for a historical resource type, the diversity threshold corresponding to the historical classification type at each level can be determined.

[0096] For example, if a historical resource belongs to the ball game category under the sports category, then the historical resource type is both sports and ball game. In this way, when determining the diversity threshold corresponding to the historical resource type, the diversity threshold corresponding to the sports type can be determined based on the display statistics and access statistics corresponding to the sports type; and the diversity threshold corresponding to the ball game type can be determined based on the display statistics and access statistics corresponding to the ball game type.

[0097] As can be seen from the above, when recommending resources using the solution provided in this embodiment, the server can accurately determine the historical resource type of the historical resources based on the resource information of the historical resources recommended to the target user. Thus, after obtaining the display statistics and access statistics, the server can determine the diversity threshold that matches the target user's preferences and habits based on the display statistics and access statistics that reflect the user's preferences and habits when accessing resources. Therefore, by using the determined diversity threshold to recommend resources, personalized resource recommendations can be made for the target user.

[0098] In one embodiment of this disclosure, see [link to embodiment]. Figure 3 This illustrates the process by which the server determines the resources to recommend to the target user. Figure 3 The process shown consists of two stages: a diversity threshold calculation stage and a diversity screening stage.

[0099] In the diversity threshold calculation stage, the server or other device with diversity threshold determination function obtains resource information of historical resources recommended to the target user, determines the historical resource type of the historical resource based on the obtained resource information, obtains display statistics and access statistics, and finally determines the diversity threshold corresponding to the historical resource type based on the display statistics and access statistics.

[0100] During the diversity screening phase, the server calls each resource aggregation module to obtain candidate resources. Then, based on the diversity threshold obtained in the diversity threshold calculation phase, it calculates the upper limit (i.e., the maximum number) of the corresponding number of each historical resource type. For each historical resource type, among the resources of that historical resource type included in the candidate resources, at most the above-mentioned upper limit of resources are selected to enter the diversity candidate set. Resources that are not selected are entered into the supplementary set.

[0101] After performing the above processing for each historical resource type, if the number of resources in the diversity candidate set is insufficient to meet the total number of resources to be recommended to the client, resources are selected from the supplementary set and added to the diversity candidate set to make up for the missing parts of the diversity candidate set, thus obtaining the candidate set for the next stage.

[0102] After obtaining the candidate set for the next stage, the server can directly recommend resources from the candidate set to the client; alternatively, it can sort the resources in the candidate set and recommend the sorted resources to the client.

[0103] The following explains steps S203 and S204.

[0104] In one embodiment of this disclosure, when obtaining display statistics and access statistics, the number of resources displayed and the access rate of resources can be obtained.

[0105] The implementation methods for obtaining the number of resources displayed and the resource access rate can be found in the aforementioned embodiments, and will not be repeated here.

[0106] In this solution, the number of resources displayed reflects the amount of resources shown to the target user, while the resource access rate reflects the target user's preference for accessing resources. The higher the resource access rate for a resource type, the more interested the target user is in the resources of that type corresponding to the resource access rate. Conversely, the lower the resource access rate for a resource type, the less interested the target user is in the resources of that type corresponding to the resource access rate. Therefore, based on the number of resources displayed and the resource access rate, a personalized diversity threshold that matches the target user's preferences and habits can be determined. By using the determined diversity threshold to recommend resources, personalized resource recommendations can be made for the target user.

[0107] After obtaining the number of resources displayed and the access rate of resources, the diversity threshold corresponding to the historical resource type can be determined based on these two pieces of information using either of the following two implementation methods.

[0108] In the first implementation, the first parameter corresponding to the historical resource type is determined based on the number of resources displayed, and the diversity threshold corresponding to the historical resource type of the target user is determined based on the determined first parameter and the resource access rate.

[0109] For each type of historical resource, the way resources of that type are displayed will affect whether the target user will be interested in the resources of that type.

[0110] For example, if the number of historical resources of a certain type displayed is small, the target user will have access to fewer resources of that type, making it difficult to arouse their interest. In other words, a target user's lack of interest in a particular historical resource type may not be due to any inherent reason related to the user, but rather because the limited number of such resources recommended to them is insufficient.

[0111] The first parameter mentioned above represents the degree to which the display of historical resource types affects the recommendation of historical resource types.

[0112] If fewer resources of a certain historical resource type are displayed, it is more likely that users are not interested in resources of that historical resource type because there are few resources available. In this case, more resources of that historical resource type need to be recommended. That is, the higher the influence of recommending resources of that historical resource type, the higher the first parameter should be.

[0113] In one embodiment of this disclosure, the first parameter corresponding to the historical resource type is calculated according to the following expression:

[0114]

[0115] Where inver_show_ratio represents the first parameter corresponding to the historical resource type, total_show represents the total number of resources displayed for all historical resource types, show represents the number of resources displayed for the historical resource type, and f1() represents the square root operation.

[0116] In the above expression, the fewer historical resource types displayed, the better. The larger, The larger the square root, the larger the first parameter. Therefore, according to the above expression, the first parameter can be accurately calculated, and resources can be recommended based on the first parameter, thus improving the accuracy of resource recommendations.

[0117] In another embodiment of this disclosure, when calculating the first parameter, the total number of resources displayed can be divided by the number of resources displayed for historical resource types, and the quotient can be multiplied by a preset coefficient to obtain the multiplication result, which is used as the first parameter.

[0118] The access rate of the above resources represents the degree of interest that target users have in historical resource types based on their own interests. The higher the access rate of a resource corresponding to a historical resource type, the more interested users are in that historical resource type. In this case, the server needs to recommend more resources of that historical resource type to the target users.

[0119] In one embodiment of this disclosure, the diversity threshold corresponding to the historical resource types of a target user is calculated according to the following expression:

[0120] ratio=α*click_ratio+β*inver_show_ratio

[0121] Wherein, ratio represents the diversity threshold corresponding to the historical resource types of the target user, click_ratio represents the resource access rate of the historical resource types, α represents the first preset weight, and β represents the second preset weight.

[0122] The first and second preset weights mentioned above are predetermined weight coefficients. These two preset weights can be two independent weights, that is, two weight coefficients set separately; or they can be two related weights.

[0123] For example, when the two preset weights mentioned above are correlated, α and β are determined according to the following expression:

[0124] α+β=1

[0125] As can be seen from this expression, if α is larger, β will be smaller, thus focusing on the target user's interests when calculating the diversity threshold; if α is smaller, β will be larger, thus focusing on the display of historical resource types when calculating the diversity threshold. Therefore, by applying this expression, the above two preset weights can be set according to the aspects to be emphasized according to actual needs. This can determine a diversity threshold that meets actual needs, and thus recommend resources to the target user based on the diversity threshold, thereby improving the accuracy of resource recommendations.

[0126] The higher the first parameter mentioned above, the more historical resource types need to be recommended, meaning the diversity threshold corresponding to historical resource types needs to be higher. Furthermore, the higher the resource access rate, the more interested users are in historical resource types, so the server also needs to recommend more historical resource types to the target user; that is, the diversity threshold corresponding to historical resource types also needs to be higher. In the expression for calculating the diversity threshold, the higher the click_ratio and / or inver_show_ratio, the higher the ratio. Therefore, using the above expression for calculating the diversity threshold, the diversity threshold corresponding to historical resource types can be accurately calculated. Based on the calculated diversity threshold, resources can be recommended to the target user, thus improving the accuracy of resource recommendations.

[0127] As can be seen from the above, in this solution, the diversity threshold is determined by combining the first parameter and the resource access rate. This is equivalent to considering both the historical resource display situation and the target user's own interests when determining the diversity threshold. This can improve the accuracy of determining the diversity threshold, and thus improve the accuracy of resource recommendation when recommending resources to the target user based on the diversity threshold.

[0128] In the second implementation method, weights can be directly assigned to the number of historical resource types displayed and the access rate of resources, and weighted summation can be performed to obtain the calculation result, which can be used as the aforementioned diversity threshold.

[0129] In the first implementation of determining the diversity threshold based on the number of resources displayed and the access rate of resources, after calculating the above-mentioned first parameter, the diversity threshold can also be determined through the following embodiments.

[0130] In one embodiment of this disclosure, an initial diversity threshold corresponding to a historical resource type is determined based on a determined first parameter and the resource access rate; if the initial diversity threshold is less than or equal to a preset first threshold, the first threshold is determined as the diversity threshold corresponding to the historical resource type of the target user; if the initial diversity threshold is greater than the first threshold and less than a preset second threshold, the initial diversity threshold is determined as the diversity threshold corresponding to the historical resource type of the target user; if the initial diversity threshold is greater than or equal to the second threshold, the second threshold is determined as the diversity threshold corresponding to the historical resource type of the target user.

[0131] The first threshold and the second threshold mentioned above are preset thresholds, and the first threshold is less than the second threshold.

[0132] The specific implementation method for determining the initial diversity threshold is similar to that for determining the diversity threshold in the previous embodiments. The only difference is that the threshold determined in the previous embodiments is called the diversity threshold, while the threshold determined here is called the initial diversity threshold. This will not be elaborated further here.

[0133] After calculating the initial diversity threshold, the initial diversity threshold, the first threshold, and the second threshold can be compared. If the initial diversity threshold is less than or equal to the first threshold, it means that the initial diversity threshold is too small, which will result in fewer resources of historical resource types being recommended to the user. If the initial diversity threshold is greater than or equal to the second threshold, it means that the initial diversity threshold is too large, which will result in more resources of historical resource types being recommended to the user, thus causing aesthetic fatigue and a decrease in novelty for the user. Therefore, by setting the first threshold and the second threshold, it is possible to avoid the diversity threshold being too small or too large, and thus recommend a rich variety of resources to the target user based on the diversity threshold.

[0134] When obtaining display statistics and access statistics in step S203 above, in addition to obtaining the number of resources displayed and the resource access rate, the resource display rate can also be obtained. The resource display rate is the ratio of historical resource types of resources displayed to the target user in the historical resources.

[0135] The method for obtaining resource display rate can be found in the description of step S203 above, and will not be repeated here.

[0136] After obtaining the number of resources displayed, the resource display rate, and the resource access rate, you can determine the diversity threshold corresponding to the historical resource types by following steps one through three.

[0137] Step 1: Based on the resource display rate and resource access rate, predict the probability of target users accessing resources of historical resource types.

[0138] The higher the resource display rate, the higher the likelihood that target users will repeatedly browse the same historical resource type. This makes it easier for users to experience aesthetic fatigue, causing them to be unwilling to access resources of that historical resource type. On the other hand, the higher the resource access rate, the higher the target users' interest in historical resource types. This makes them more willing to access resources of that historical resource type.

[0139] Based on the resource display rate and the resource access rate, the above access probability can be predicted using either of the following two methods.

[0140] In the first implementation, a second parameter representing the target user's interest in historical resource types is first determined based on the resource display rate and the resource access rate; then, based on the second parameter and the resource display rate, the probability of the target user accessing historical resource types is predicted.

[0141] Specifically, the higher the resource display rate, the more likely target users are to experience aesthetic fatigue with historical resource types, and thus become less interested in them. Conversely, the higher the resource access rate, the more interested target users are in historical resource types. Thus, based on the resource display rate and resource access rate, the second parameter mentioned above can be accurately determined from two aspects. Based on the second parameter and the resource display rate, the access probability can be accurately predicted, and by utilizing the access probability, the accuracy of resource recommendations can be improved.

[0142] Therefore, the second parameter can be determined according to the following expression:

[0143] reward=click_ratio-f2(show_ratio)

[0144] Here, click_ratio represents the access rate of resources of the historical resource type, show_ratio represents the display rate of resources of the historical resource type, reward represents the second parameter corresponding to the historical resource type, and f2() represents the operation of taking the exponent with a preset base.

[0145] The above preset base values ​​are pre-set values, such as 1.3, 1.4, etc.

[0146] In the above expression for calculating the second parameter, the higher the resource access rate, the higher the target user's interest in historical resource types, and the larger the second parameter. Conversely, the higher the resource display rate, the more likely the target user is to experience aesthetic fatigue with historical resource types, and the smaller the second parameter. It is evident that by applying the above expression for calculating the second parameter, the second parameter can be accurately calculated. Based on the second parameter, the diversity threshold can be accurately determined, and further, based on the diversity threshold, the accuracy of resource recommendations can be improved.

[0147] Based on the second parameter mentioned above and the resource display rate, the access probability can be predicted using the following expression:

[0148]

[0149] Where x represents the access probability corresponding to the historical resource type, reward represents the second parameter corresponding to the historical resource type, and show_ratio represents the resource display rate of the historical resource type.

[0150] In the above expression for calculating access probability, the larger the second parameter, the higher the target user's interest in historical resource types, and the greater the probability of the target user accessing historical resource types. Conversely, the higher the resource display rate, the more likely the target user is to experience aesthetic fatigue with historical resource types, thus reducing the probability of the target user accessing historical resource types. Therefore, by applying the above expression for calculating access probability, the access probability can be accurately calculated, thereby accurately determining the diversity threshold. Based on the diversity threshold, the accuracy of resource recommendations can be improved.

[0151] In the second implementation, the resource access rate can be divided by the resource display rate to obtain the division result, which can be used as the access probability mentioned above.

[0152] Step 2: Based on the access probability and the number of resources displayed, determine the target number of historical resource types to be recommended to the target users.

[0153] After calculating the above access probabilities, based on the access probabilities and the number of resources displayed, it is possible to predict the number of historical resource types that the target user will access after recommending resources to the target user.

[0154] For example, the target number of historical resource types to be recommended to the target user can be determined using the following expression:

[0155] w = show*exp(γ*x)

[0156] Where w represents the number of target resources corresponding to the historical resource type, show represents the number of resources displayed for the historical resource type, x represents the access probability corresponding to the historical resource type, and γ represents the third preset weight.

[0157] In the above expression for calculating the number of target resources, the higher the access probability of the historical resource type, the more likely the target user is to access the historical resource type, and thus the larger the number of target resources. It can be seen that the above expression for calculating the number of target resources can accurately calculate the number of target resources, thereby accurately determining the diversity threshold, and further improving the accuracy of resource recommendations based on the diversity threshold.

[0158] Step 3: Calculate the proportion of the target resource quantity corresponding to each historical resource type, and use it as the diversity threshold for each historical resource type.

[0159] After calculating the number of target resources corresponding to each historical resource type, the total number of target resources corresponding to all historical resource types can be calculated. Then, the proportion of the total number of target resources corresponding to each historical resource type can be calculated as the diversity threshold for each historical resource type.

[0160] As can be seen from the above, this solution utilizes multiple information such as the number of resources displayed, the resource display rate, and the resource access rate to determine the diversity threshold, which can improve the accuracy of the diversity threshold. Furthermore, the resource display rate and the resource access rate can reflect the user's interest in historical resource types from two different perspectives. Thus, predicting the access probability based on the resource display rate and the resource access rate can improve the prediction accuracy. In turn, using the predicted access probability can improve the accuracy of determining the diversity threshold, thereby improving the accuracy of resource recommendation.

[0161] After calculating the target resource quantity corresponding to each of the above historical resource types in step two, the diversity threshold can also be determined through the following examples.

[0162] In one embodiment of this disclosure, for each historical resource type, a target percentage of the target resource quantity corresponding to that historical resource type is calculated; if the target percentage is less than or equal to a preset first percentage, the first percentage is determined as the diversity threshold corresponding to that historical resource type; if the target percentage is greater than the first percentage and less than a preset second percentage, the target percentage is determined as the diversity threshold corresponding to that historical resource type; if the target percentage is greater than or equal to the second percentage, the second percentage is determined as the diversity threshold corresponding to that historical resource type.

[0163] The first and second percentages mentioned above are pre-set quantities, and the first percentage is less than the second percentage.

[0164] The specific implementation method for calculating the target percentage is similar to the specific implementation method for calculating the quantity percentage in the previous embodiment. The only difference is that the percentage calculated in the previous embodiment is called the quantity percentage, while the percentage calculated here is called the target percentage. This will not be elaborated further here.

[0165] After calculating the target percentage, the target percentage, the first percentage, and the second percentage can be compared. If the target percentage is less than or equal to the first percentage, the target percentage is set as the diversity threshold. If the diversity threshold is too small, it will result in fewer historical resource types being recommended to the user. If the target percentage is greater than or equal to the second percentage, the target percentage is set as the diversity threshold. If the diversity threshold is too large, it will result in a large number of historical resource types being recommended to the user, leading to user fatigue and a decrease in novelty. Therefore, by setting the first percentage and the second percentage, the diversity threshold can be avoided from being too small or too large, and a rich variety of resources can be recommended to the target user based on the diversity threshold.

[0166] Different display statistics and access statistics can be used to determine the diversity threshold for different users.

[0167] In one embodiment of this disclosure, before obtaining display statistics and access statistics, it is determined whether the target user is an active user; if the target user is an active user, the number of resources displayed and the resource access rate are obtained; if the target user is an inactive user, the number of resources displayed, the resource display rate, and the resource access rate are obtained.

[0168] Specifically, when determining whether a target user is an active user, information such as the number of consecutive login days, client usage time, number of client usages, number of resource displays, and number of resource accesses can be obtained to determine whether the target user is an active user.

[0169] If the values ​​of the information obtained above are large, the target user can be determined to be an active user; otherwise, the target user can be determined to be an inactive user.

[0170] Taking consecutive login days as an example, if the number of consecutive login days of a target user exceeds the preset threshold, the target user is determined to be an active user; if the number of consecutive login days of a target user does not exceed the threshold, the target user is determined to be an inactive user.

[0171] If the target users are active users, obtain the number of resources displayed and the access rate of the resources, and determine the diversity threshold based on the number of resources displayed and the access rate of the resources.

[0172] For details on how to determine the diversity threshold based on the number of resources displayed and the access rate of resources, please refer to the aforementioned embodiments, which will not be repeated here.

[0173] When the target users are inactive users, obtain the above-mentioned resource display quantity, resource display rate, and resource access rate, and determine the diversity threshold based on the above-mentioned resource display quantity, resource display rate, and resource access rate.

[0174] For details on how to determine the diversity threshold based on the number of resources displayed, the resource display rate, and the resource access rate, please refer to the aforementioned embodiments, which will not be repeated here.

[0175] As can be seen from the above, when recommending resources using the solution provided in this embodiment of the present disclosure, different information is obtained for different users, and different methods are used to determine the diversity threshold, which can improve the accuracy of determining the diversity threshold and thus improve the accuracy of resource recommendation.

[0176] Corresponding to the resource recommendation method described above, this disclosure also provides a resource recommendation device.

[0177] In one embodiment of this disclosure, see [link to embodiment]. Figure 4 A schematic diagram of a resource recommendation device is provided. In this embodiment, the device includes:

[0178] The resource determination module 401 is used to determine the resources to be recommended to the target user based on the diversity threshold corresponding to the historical resource types of the target user. The historical resource types are the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics are the statistics of information on the historical resources displayed to the target user. The access statistics are the statistics of the target user accessing the historical resources.

[0179] The resource recommendation module 402 is used to recommend determined resources to the client used by the target user.

[0180] As can be seen from the above, when recommending resources using the solution provided in this embodiment, the diversity threshold corresponding to the historical resource type is determined based on the display statistics and access statistics. The display statistics are the statistics on the information of historical resources displayed to the target user, and the access statistics are the statistics on the target user's access to historical resources. Therefore, the display statistics and access statistics can reflect the user's preferences and habits in accessing resources. Based on these two types of statistics, the diversity threshold of the historical resource type can be set for the target user in a personalized way, and thus, based on the diversity threshold, resources can be recommended to the target user in a personalized way.

[0181] Furthermore, the diversity threshold corresponding to a historical resource type refers to the maximum proportion of resources of that historical resource type in the resources to be recommended to the user. After determining the diversity threshold corresponding to each historical resource type, the proportion of resources of each resource type in the resources to be recommended to the user can be allocated according to the diversity threshold corresponding to each historical resource type, while conforming to the user's preferences and habits. This ensures that users are recommended a rich variety of resources without causing aesthetic fatigue or loss of novelty for the target users. Moreover, the resource recommendation scheme provided by this disclosure can provide personalized resource recommendations for users. Different resources can be recommended to different users, thereby achieving personalized resource recommendations and optimizing the recommendation effect.

[0182] In one embodiment of this disclosure, see [link to embodiment]. Figure 5 A schematic diagram of a threshold determination device is provided. In this embodiment, the following modules are used to determine the diversity threshold corresponding to the historical resource type of the target user:

[0183] The resource information acquisition module 501 is used to acquire resource information of the historical resources recommended to the target user;

[0184] The type determination module 502 is used to determine the historical resource type of the historical resource based on the obtained resource information;

[0185] The statistics information acquisition module 503 is used to acquire the display statistics information and the access statistics information;

[0186] The threshold determination module 504 is used to determine the diversity threshold corresponding to the historical resource type of the target user based on the display statistics and the access statistics.

[0187] As can be seen from the above, when recommending resources using the solution provided in this embodiment, the server can accurately determine the historical resource type of the historical resources based on the resource information of the historical resources recommended to the target user. Thus, after obtaining the display statistics and access statistics, the server can determine the diversity threshold that matches the target user's preferences and habits based on the display statistics and access statistics that reflect the user's preferences and habits when accessing resources. Therefore, by using the determined diversity threshold to recommend resources, personalized resource recommendations can be made for the target user.

[0188] In one embodiment of this disclosure, the resource information acquisition module 501 includes:

[0189] The information acquisition submodule is used to acquire the number of resources displayed and the resource access rate. The number of resources displayed is the number of historical resource information displayed to the target user, and the resource access rate is the ratio of the resources accessed by the target user in the historical resources.

[0190] In this solution, the number of resources displayed reflects the amount of resources shown to the target user, while the resource access rate reflects the target user's preference for accessing resources. The higher the resource access rate for a resource type, the more interested the target user is in the resources of that type corresponding to the resource access rate. Conversely, the lower the resource access rate for a resource type, the less interested the target user is in the resources of that type corresponding to the resource access rate. Therefore, based on the number of resources displayed and the resource access rate, a personalized diversity threshold that matches the target user's preferences and habits can be determined. By using the determined diversity threshold to recommend resources, personalized resource recommendations can be made for the target user.

[0191] In one embodiment of this disclosure, the threshold determination module 504 includes:

[0192] The parameter determination submodule is used to determine a first parameter corresponding to the historical resource type based on the number of resources displayed, wherein the first parameter characterizes the degree of influence of the display status of the historical resource type on the recommendation of the historical resource type.

[0193] The threshold determination submodule is used to determine the diversity threshold corresponding to the historical resource type of the target user based on the determined first parameter and the resource access rate.

[0194] As can be seen from the above, in this solution, the diversity threshold is determined by combining the first parameter and the resource access rate. This is equivalent to considering both the historical resource display situation and the target user's own interests when determining the diversity threshold. This can improve the accuracy of determining the diversity threshold, and thus improve the accuracy of resource recommendation when recommending resources to the target user based on the diversity threshold.

[0195] In one embodiment of this disclosure, the parameter determining submodule is specifically used for:

[0196] The first parameter corresponding to the historical resource type is calculated according to the following expression:

[0197]

[0198] Where inver_show_ratio represents the first parameter corresponding to the historical resource type, total_show represents the total number of resources displayed for all historical resource types, show represents the number of resources displayed for the historical resource type, and f1() represents the square root operation.

[0199] As can be seen from the above, in this scheme, the first parameter can be accurately calculated according to the above expression, and resources can be recommended based on the first parameter, thereby improving the accuracy of resource recommendation.

[0200] In one embodiment of this disclosure, the threshold determination submodule is specifically used for:

[0201] The diversity threshold corresponding to the historical resource type of the target user is calculated according to the following expression:

[0202] ratio=α*click_ratio+β*inver_show_ratio

[0203] Wherein, ratio represents the diversity threshold corresponding to the historical resource types of the target user, click_ratio represents the resource access rate of the historical resource types, α represents the first preset weight, and β represents the second preset weight.

[0204] In this solution, the above expression for calculating the diversity threshold can be used to accurately calculate the diversity threshold corresponding to historical resource types. Based on the calculated diversity threshold, resources can be recommended to target users, thereby improving the accuracy of resource recommendations.

[0205] In one embodiment of this disclosure, α and β are determined according to the following expression:

[0206] α+β=1

[0207] In this solution, by applying this expression, the two preset weights mentioned above can be set according to the aspects that need to be emphasized in actual needs. This allows for the determination of a diversity threshold that meets actual requirements, thereby recommending resources to target users based on the diversity threshold and improving the accuracy of resource recommendations.

[0208] In one embodiment of this disclosure, the threshold determination submodule is specifically used for:

[0209] Based on the determined first parameter and the resource access rate, determine the initial diversity threshold corresponding to the historical resource type;

[0210] If the initial diversity threshold is less than or equal to a preset first threshold, then the first threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user;

[0211] If the initial diversity threshold is greater than the first threshold and less than the preset second threshold, then the initial diversity threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user, wherein the first threshold is less than the second threshold;

[0212] If the initial diversity threshold is greater than or equal to the second threshold, then the second threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user.

[0213] In this scheme, after calculating the initial diversity threshold, the initial diversity threshold, the first threshold, and the second threshold can be compared. If the initial diversity threshold is less than or equal to the first threshold, it means that the initial diversity threshold is too small, which will result in fewer resources of the historical resource type recommended to the user. If the initial diversity threshold is greater than or equal to the second threshold, it means that the initial diversity threshold is too large, which will result in more resources of the historical resource type recommended to the user, thus causing aesthetic fatigue and a decrease in novelty for the user. Therefore, by setting the first threshold and the second threshold, the diversity threshold can be avoided from being too small or too large, so that a rich variety of resources can be recommended to the target user based on the diversity threshold.

[0214] In one embodiment of this disclosure, the information acquisition submodule is specifically used for:

[0215] The resource display quantity, resource display rate, and resource access rate are obtained, wherein the resource display rate is the ratio of resources of the historical resource type displayed to the target user in the historical resources.

[0216] The threshold determination module 504 includes:

[0217] The probability prediction submodule is used to predict the probability of the target user accessing the resource of the historical resource type based on the resource display rate and the resource access rate.

[0218] The quantity determination submodule is used to determine the target quantity of the historical resource type of resources to be recommended to the target user based on the access probability and the resource display quantity.

[0219] The threshold calculation submodule is used to calculate the proportion of the target resource quantity corresponding to each historical resource type, which serves as the diversity threshold for each historical resource type.

[0220] As can be seen from the above, this solution utilizes multiple information such as the number of resources displayed, the resource display rate, and the resource access rate to determine the diversity threshold, which can improve the accuracy of the diversity threshold. Furthermore, the resource display rate and the resource access rate can reflect the user's interest in historical resource types from two different perspectives. Thus, predicting the access probability based on the resource display rate and the resource access rate can improve the prediction accuracy. In turn, using the predicted access probability can improve the accuracy of determining the diversity threshold, thereby improving the accuracy of resource recommendation.

[0221] In one embodiment of this disclosure, the probability prediction submodule includes:

[0222] The parameter determination unit is used to determine a second parameter that characterizes the target user's interest in the historical resource type of resources based on the resource display rate and the resource access rate.

[0223] The probability prediction unit is used to predict the probability of the target user accessing the resource of the historical resource type based on the second parameter and the resource display rate.

[0224] In this scheme, the higher the resource display rate, the more likely the target users are to experience aesthetic fatigue with historical resource types, and thus the less interested they are in those types of resources. Conversely, the higher the resource access rate, the more interested the target users are in historical resource types. Thus, based on the resource display rate and resource access rate, the second parameter mentioned above can be accurately determined from two aspects. Based on the second parameter and the resource display rate, the access probability can be accurately predicted, and by utilizing the access probability, the accuracy of resource recommendations can be improved.

[0225] In one embodiment of this disclosure, the parameter determining unit is specifically used for:

[0226] The second parameter is determined according to the following expression:

[0227] reward=click_ratio-f2(show_ratio)

[0228] Here, click_ratio represents the access rate of resources of the historical resource type, show_ratio represents the display rate of resources of the historical resource type, reward represents the second parameter corresponding to the historical resource type, and f2() represents the operation of taking the exponent with a preset base.

[0229] In this scheme, by applying the above expression for calculating the second parameter, the second parameter can be accurately calculated. Based on the second parameter, the diversity threshold can be accurately determined, and based on the diversity threshold, the accuracy of resource recommendation can be improved.

[0230] In one embodiment of this disclosure, the probability prediction unit is specifically used to include:

[0231] Predict the probability of access using the following expression:

[0232]

[0233] Where x represents the access probability corresponding to the historical resource type, reward represents the second parameter corresponding to the historical resource type, and show_ratio represents the resource display rate of the historical resource type.

[0234] In this solution, by applying the above expression for calculating access probability, the access probability can be accurately calculated, thereby accurately determining the diversity threshold. Based on the diversity threshold, the accuracy of resource recommendation can be improved.

[0235] In one embodiment of this disclosure, the quantity determination submodule is specifically used for:

[0236] The target number of historical resource types to be recommended to the target user is determined according to the following expression:

[0237] w = show*exp(γ*x)

[0238] Where w represents the number of target resources corresponding to the historical resource type, show represents the number of resources displayed for the historical resource type, x represents the access probability corresponding to the historical resource type, and γ represents the third preset weight.

[0239] In this scheme, the target resource quantity can be accurately calculated according to the above expression, thereby accurately determining the diversity threshold. Based on the diversity threshold, the accuracy of resource recommendation can be improved.

[0240] In one embodiment of this disclosure, the threshold calculation submodule is specifically used for:

[0241] The diversity threshold for each historical resource type is determined as follows:

[0242] Calculate the target percentage of the target resource quantity corresponding to this historical resource type;

[0243] If the target percentage is less than or equal to a preset first percentage, then the first percentage is determined to be the diversity threshold corresponding to the historical resource type;

[0244] If the target percentage is greater than the first percentage and less than the preset second percentage, then the target percentage is determined to be the diversity threshold corresponding to the historical resource type, wherein the first percentage is less than the second percentage;

[0245] If the target percentage is greater than or equal to the second percentage, then the second percentage is determined to be the diversity threshold corresponding to the historical resource type.

[0246] In this scheme, after calculating the target percentage, the target percentage, the first percentage, and the second percentage can be compared. If the target percentage is less than or equal to the first percentage, the target percentage is set as the diversity threshold. If the diversity threshold is too small, it will result in a small number of historical resource types recommended to the user. If the target percentage is greater than or equal to the second percentage, the target percentage is set as the diversity threshold. If the diversity threshold is too large, it will result in a large number of historical resource types recommended to the user, which will cause aesthetic fatigue and a decrease in novelty for the user. Therefore, by setting the first percentage and the second percentage, the diversity threshold can be avoided from being too small or too large, so that a rich variety of resources can be recommended to the target user based on the diversity threshold.

[0247] In one embodiment of this disclosure, the apparatus further includes:

[0248] The user determination module is used to determine whether the target user is an active user before obtaining the display statistics information and the access statistics information;

[0249] The statistical information acquisition module 503 is specifically used for:

[0250] If the target user is an active user, then the number of resources displayed and the resource access rate are obtained, wherein the number of resources displayed is: the number of pieces of information about the historical resources displayed to the target user, and the resource access rate is: the ratio of the resources accessed by the target user in the historical resources;

[0251] If the target user is an inactive user, then the number of resources displayed, the resource display rate, and the resource access rate are obtained, wherein the resource display rate is the ratio of historical resource types of resources displayed to the target user in the historical resources.

[0252] As can be seen from the above, when recommending resources using the solution provided in this embodiment of the present disclosure, different information is obtained for different users, and different methods are used to determine the diversity threshold, which can improve the accuracy of determining the diversity threshold and thus improve the accuracy of resource recommendation.

[0253] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0254] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0255] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0256] In one embodiment of this disclosure, an electronic device is provided, comprising:

[0257] At least one processor; and

[0258] A memory communicatively connected to the at least one processor; wherein,

[0259] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform any of the resource recommendation methods in the foregoing method embodiments.

[0260] In one embodiment of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform any of the resource recommendation methods in the foregoing method embodiments.

[0261] In one embodiment of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the resource recommendation methods described in the foregoing method embodiments.

[0262] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. 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 processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0263] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0264] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0265] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the resource recommendation method. For example, in some embodiments, the resource recommendation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the resource recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the resource recommendation method by any other suitable means (e.g., by means of firmware).

[0266] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0267] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0268] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0269] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0270] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0271] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0272] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0273] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A resource recommendation method, comprising: Based on the diversity threshold corresponding to the target user's historical resource types, resources to be recommended to the target user are determined. The historical resource types are the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics are the statistics of information on the historical resources displayed to the target user. The access statistics are the statistics of the target user accessing the historical resources. Recommend the identified resources to the client used by the target user; The diversity threshold is determined as follows: Based on the number of resources displayed, a first parameter corresponding to the historical resource type is determined, wherein the number of resources displayed is the amount of information about the historical resources shown to the target user, and the first parameter characterizes the degree of influence of the display of resources of the historical resource type on the recommendation of resources of the historical resource type; based on the determined first parameter and the resource access rate, a diversity threshold corresponding to the historical resource type for the target user is determined, wherein the resource access rate is the ratio of resources accessed by the target user in the historical resources; Alternatively, based on the resource display rate and the resource access rate, predict the probability of the target user accessing resources of the historical resource type, where the resource display rate is the ratio of resources of the historical resource type displayed to the target user in the historical resources; determine the target number of resources of the historical resource type to be recommended to the target user based on the access probability and the number of resource displays; calculate the proportion of the target resource quantity corresponding to each historical resource type as the diversity threshold corresponding to each historical resource type.

2. The method according to claim 1, further comprising, before determining the diversity threshold: Obtain resource information for the historical resources recommended to the target user; Based on the obtained resource information, determine the historical resource type of the historical resource; Obtain the display statistics and the access statistics.

3. The method according to claim 2, wherein, The acquisition of the display statistics and the access statistics includes: Get the number of resources displayed and the resource access rate.

4. The method according to claim 1, wherein, The step of determining the first parameter corresponding to the historical resource type based on the number of resources displayed includes: The first parameter corresponding to the historical resource type is calculated according to the following expression: ； Among them, the The first parameter corresponding to the historical resource type is the... This represents the total number of resources displayed across all historical resource types. This indicates the number of resources of the aforementioned historical resource type displayed. This indicates the square root operation.

5. The method according to claim 1 or 4, wherein, The step of determining the diversity threshold corresponding to the historical resource type of the target user based on the determined first parameter and the resource access rate includes: The diversity threshold corresponding to the historical resource type of the target user is calculated according to the following expression: ； Among them, the This represents the diversity threshold corresponding to the historical resource type of the target user. This represents the resource access rate of the historical resource type. Indicates the first preset weight, the This represents the second preset weight, the The first parameter represents the type of historical resource.

6. The method according to claim 5, wherein, The and stated Determined according to the following expression: 。 7. The method according to claim 1 or 4, wherein, The step of determining the diversity threshold corresponding to the historical resource type of the target user based on the determined first parameter and the resource access rate includes: Based on the determined first parameter and the resource access rate, determine the initial diversity threshold corresponding to the historical resource type; If the initial diversity threshold is less than or equal to a preset first threshold, then the first threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user; If the initial diversity threshold is greater than the first threshold and less than the preset second threshold, then the initial diversity threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user, wherein the first threshold is less than the second threshold; If the initial diversity threshold is greater than or equal to the second threshold, then the second threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user.

8. The method according to claim 3, wherein, The acquisition of the number of resources displayed and the resource access rate includes: Get the number of resources displayed, the resource display rate, and the resource access rate.

9. The method according to claim 8, wherein, The step of predicting the probability of a target user accessing a resource of the historical resource type based on the resource display rate and the resource access rate includes: Based on the resource display rate and the resource access rate, a second parameter is determined that characterizes the target user's interest in the historical resource type. Based on the second parameter and the resource display rate, the probability of the target user accessing the resource of the historical resource type is predicted.

10. The method according to claim 9, wherein, The second parameter, which characterizes the target user's interest in resources of the historical resource type based on the resource display rate and the resource access rate, includes: The second parameter is determined according to the following expression: ； Among them, the This represents the resource access rate of the historical resource type. This represents the resource display rate of the historical resource type. The second parameter represents the type of historical resource. This indicates the operation of taking the exponent of a preset base.

11. The method according to claim 9 or 10, wherein, The step of predicting the probability of the target user accessing the resource of the historical resource type based on the second parameter and the resource display rate includes: Predict the probability of access using the following expression: ； Among them, the This represents the access probability corresponding to the historical resource type. The second parameter represents the type of historical resource. This indicates the resource display rate of the historical resource type.

12. The method according to any one of claims 8-10, wherein, The step of determining the target number of historical resource types to be recommended to the target user based on the access probability and the number of resources displayed includes: The target number of historical resource types to be recommended to the target user is determined according to the following expression: ； Among them, the This indicates the number of target resources corresponding to the historical resource type. This indicates the number of resources displayed for the historical resource type. This represents the access probability corresponding to the historical resource type. This indicates the third preset weight.

13. The method according to any one of claims 8-10, wherein, The calculation of the proportion of the target resource quantity corresponding to each historical resource type, as the diversity threshold corresponding to each historical resource type, includes: The diversity threshold for each historical resource type is determined as follows: Calculate the target percentage of the target resource quantity corresponding to this historical resource type; If the target percentage is less than or equal to a preset first percentage, then the first percentage is determined to be the diversity threshold corresponding to the historical resource type; If the target percentage is greater than the first percentage and less than the preset second percentage, then the target percentage is determined to be the diversity threshold corresponding to the historical resource type, wherein the first percentage is less than the second percentage; If the target percentage is greater than or equal to the second percentage, then the second percentage is determined to be the diversity threshold corresponding to the historical resource type.

14. The method according to claim 2, further comprising, before obtaining the display statistics and the access statistics: Determine whether the target user is an active user; The acquisition of the display statistics and the access statistics includes: If the target user is an active user, then obtain the number of resources displayed and the resource access rate; If the target user is an inactive user, then the number of resources displayed, the resource display rate, and the resource access rate are obtained, wherein the resource display rate is the ratio of historical resource type resources displayed to the target user in the historical resources.

15. A resource recommendation device, comprising: The resource determination module is used to determine the resources to be recommended to the target user based on the diversity threshold corresponding to the historical resource types of the target user. The historical resource types are the resource types of historical resources recommended to the target user. The diversity threshold is determined based on display statistics and access statistics. The display statistics are the statistics of information on the historical resources displayed to the target user. The access statistics are the statistics of the target user accessing the historical resources. The resource recommendation module is used to recommend determined resources to the client used by the target user; The threshold determination module is used for: Based on the number of resources displayed, a first parameter corresponding to the historical resource type is determined, wherein the number of resources displayed is the amount of information about the historical resources shown to the target user, and the first parameter characterizes the degree of influence of the display of resources of the historical resource type on the recommendation of resources of the historical resource type; based on the determined first parameter and the resource access rate, a diversity threshold corresponding to the historical resource type for the target user is determined, wherein the resource access rate is the ratio of resources accessed by the target user in the historical resources; Alternatively, based on the resource display rate and the resource access rate, predict the probability of the target user accessing resources of the historical resource type, where the resource display rate is the ratio of resources of the historical resource type displayed to the target user in the historical resources; determine the target number of resources of the historical resource type to be recommended to the target user based on the access probability and the number of resource displays; calculate the proportion of the target resource quantity corresponding to each historical resource type as the diversity threshold corresponding to each historical resource type.

16. The apparatus of claim 15, further comprising: The resource information acquisition module is used to acquire resource information of the historical resources recommended to the target user; The type determination module is used to determine the historical resource type of the historical resource based on the obtained resource information; The statistics acquisition module is used to acquire the display statistics and the access statistics.

17. The apparatus according to claim 16, wherein, The resource information acquisition module includes: The information acquisition submodule is used to obtain the number of resources displayed and the access rate of resources.

18. The apparatus according to claim 15, wherein, The parameter determination submodule is specifically used for: The first parameter corresponding to the historical resource type is calculated according to the following expression: ； Among them, the The first parameter corresponding to the historical resource type is the... This represents the total number of resources displayed across all historical resource types. This indicates the number of resources of the aforementioned historical resource type displayed. This indicates the square root operation.

19. The apparatus according to claim 15 or 18, wherein, The threshold determination submodule is specifically used for: The diversity threshold corresponding to the historical resource type of the target user is calculated according to the following expression: ； Among them, the This represents the diversity threshold corresponding to the historical resource type of the target user. This represents the resource access rate of the historical resource type. Indicates the first preset weight, the This represents the second preset weight, the The first parameter represents the type of historical resource.

20. The apparatus according to claim 19, wherein, The and stated Determined according to the following expression: 。 21. The apparatus according to claim 15 or 18, wherein, The threshold determination submodule is specifically used for: Based on the determined first parameter and the resource access rate, determine the initial diversity threshold corresponding to the historical resource type; If the initial diversity threshold is less than or equal to a preset first threshold, then the first threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user; If the initial diversity threshold is greater than the first threshold and less than the preset second threshold, then the initial diversity threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user, wherein the first threshold is less than the second threshold; If the initial diversity threshold is greater than or equal to the second threshold, then the second threshold is determined to be the diversity threshold corresponding to the historical resource type of the target user.

22. The apparatus according to claim 17, wherein, The information acquisition submodule is specifically used for: Get the number of resources displayed, the resource display rate, and the resource access rate.

23. The apparatus according to claim 22, wherein, The probability prediction submodule includes: The parameter determination unit is used to determine a second parameter that characterizes the target user's interest in the historical resource type of resources based on the resource display rate and the resource access rate. The probability prediction unit is used to predict the probability of the target user accessing the resource of the historical resource type based on the second parameter and the resource display rate.

24. The apparatus according to claim 23, wherein, The parameter determination unit is specifically used for: The second parameter is determined according to the following expression: ； Among them, the This represents the resource access rate of the historical resource type. This represents the resource display rate of the historical resource type. The second parameter represents the type of historical resource. This indicates the operation of taking the exponent of a preset base.

25. The apparatus according to claim 23 or 24, wherein, The probability prediction unit is specifically used for, including: Predict the probability of access using the following expression: ； Among them, the This represents the access probability corresponding to the historical resource type. The second parameter represents the type of historical resource. This indicates the resource display rate of the historical resource type.

26. The apparatus according to any one of claims 22-24, wherein, The quantity determination submodule is specifically used for: The target number of historical resource types to be recommended to the target user is determined according to the following expression: ； Among them, the This indicates the number of target resources corresponding to the historical resource type. This indicates the number of resources displayed for the historical resource type. This represents the access probability corresponding to the historical resource type. This indicates the third preset weight.

27. The apparatus according to any one of claims 22-24, wherein, The threshold calculation submodule is specifically used for: The diversity threshold for each historical resource type is determined as follows: Calculate the target percentage of the target resource quantity corresponding to this historical resource type; If the target percentage is less than or equal to a preset first percentage, then the first percentage is determined to be the diversity threshold corresponding to the historical resource type; If the target percentage is greater than the first percentage and less than the preset second percentage, then the target percentage is determined to be the diversity threshold corresponding to the historical resource type, wherein the first percentage is less than the second percentage; If the target percentage is greater than or equal to the second percentage, then the second percentage is determined to be the diversity threshold corresponding to the historical resource type.

28. The apparatus of claim 16, further comprising: The user determination module is used to determine whether the target user is an active user before obtaining the display statistics information and the access statistics information; The statistical information acquisition module is specifically used for: If the target user is an active user, then the number of resources displayed and the resource access rate are obtained, wherein the number of resources displayed is: the number of pieces of information about the historical resources displayed to the target user, and the resource access rate is: the ratio of the resources accessed by the target user in the historical resources; If the target user is an inactive user, then the number of resources displayed, the resource display rate, and the resource access rate are obtained, wherein the resource display rate is the ratio of historical resource type resources displayed to the target user in the historical resources.

29. 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 to enable the at least one processor to perform the method of any one of claims 1-14.

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

31. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-14.

Images