Method, device, electronic device and storage medium for recommending multi-genre resources

Abstract

The present disclosure provides a method, device, electronic device and storage medium for recommending multi-genre resources, and relates to technical fields such as resource distribution, resource recommendation, artificial intelligence, and large models. The specific implementation scheme is: obtaining the factor values ​​of at least two fusion factors of each genre resource of at least two genres; obtaining the factor parameters of each of the fusion factors based on a pre-learned strategy model; obtaining the corresponding comprehensive factor value of each of the genre resources based on the factor value and the factor parameter; and recommending resources to the user based on the comprehensive factor value. The technology disclosed in the present disclosure can provide an effective implementation scheme for the recommendation of multi-genre resources in immersive recommendation scenarios, and can effectively ensure the recommendation efficiency of multi-genre resource recommendations.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to technical fields such as resource distribution, resource recommendation, artificial intelligence, and large models, and more particularly to a method, device, electronic device, and storage medium for recommending multi-genre resources. Background Art

[0002] Based on the growing demand for consumption efficiency and the popularity of immersive consumption habits, more and more users like to consume resources in an immersive way.

[0003] Existing immersive recommendation scenarios primarily recommend video resources. Users enter the immersive recommendation scene through a video portal. In this immersive recommendation scenario, users do not need to search independently; they simply scroll up and down, and the immersive recommendation system continuously recommends videos to them, allowing them to immersively consume videos. Furthermore, in existing immersive recommendation scenarios, resources can be sorted by content popularity, among other factors, to facilitate resource recommendations. Summary of the Invention

[0004] The present disclosure provides a method, device, electronic device, and storage medium for recommending multi-genre resources.

[0005] According to one aspect of the present disclosure, a method for recommending multi-genre resources is provided, comprising:

[0006] Obtaining factor values ​​of at least two fusion factors of genre resources of at least two genres;

[0007] Based on the pre-learned strategy model, obtaining factor parameters of each of the fusion factors;

[0008] Based on the factor value and the factor parameter, obtaining a corresponding comprehensive factor value of each of the genre resources;

[0009] Based on the comprehensive factor value, resources are recommended to the user.

[0010] According to another aspect of the present disclosure, a device for recommending multi-genre resources is provided, comprising:

[0011] A factor acquisition module, configured to acquire factor values ​​of at least two fusion factors of at least two genre resources;

[0012] A parameter acquisition module, configured to acquire the factor parameters of each fusion factor based on a pre-learned strategy model;

[0013] A comprehensive value acquisition module, configured to acquire the comprehensive factor value of each of the corresponding genre resources based on the factor value and the factor parameter;

[0014] The recommendation module is used to recommend resources to users based on the comprehensive factor value.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0019] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method of the above-mentioned aspect and any possible implementation manner.

[0020] According to yet another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the above-mentioned aspects and methods in any possible implementation manner when executed by a processor.

[0021] According to the technology disclosed in the present invention, an effective solution can be provided for recommending multi-genre resources in an immersive recommendation scenario, and the recommendation efficiency of multi-genre resources can be effectively guaranteed.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0024] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0029] Figure 6 is a block diagram of an electronic device for implementing the method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0031] Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0032] It should be noted that the terminal devices involved in the embodiments of the present disclosure may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0033] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0034] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; Figure 1 As shown, this embodiment provides a method for recommending multi-genre resources, which may specifically include the following steps:

[0035] S101, obtaining factor values ​​of at least two fusion factors of resources of at least two genres;

[0036] The execution subject of the method for recommending multi-genre resources in this embodiment may be a multi-genre resource recommendation device, which may be an electronic entity or a software integrated application.

[0037] The multi-genre resource recommendation method of this embodiment can be applied to immersive resource recommendation scenarios. Moreover, in the immersive resource recommendation scenario of this embodiment, resources of multiple genres can be recommended. The resource genre in this embodiment can refer to the style or format of the resource.

[0038] The immersive resource recommendation of this embodiment specifically refers to proactively and seamlessly recommending multiple resources to the user without any user request. After consuming one resource, the user can directly scroll down and continue to consume the next resource.

[0039] For example, the various genres in this embodiment may include video resources and graphic resources. Furthermore, video resources may also include short video resources and / or mini video resources; wherein the playback time of mini videos is shorter than the playback time of short videos. Furthermore, graphic resources may also include dynamic graphic resources and / or text graphic resources. Dynamic graphic resources must include pictures and may also include a small amount of text to describe the pictures. Text graphics must include text and may include a small amount of pictures to explain the text.

[0040] In this embodiment, for each resource of each genre, the values ​​of at least two fusion factors are required; each fusion factor can be considered a characteristic of the resource. To enable a comprehensive assessment of the value of each resource, this implementation requires obtaining at least two fusion factors, or at least two characteristics, for each resource.

[0041] S102. Obtaining factor parameters of each fusion factor based on the pre-learned strategy model;

[0042] Specifically, for each resource type, the obtained factor parameters for the same fusion factor based on the strategy model are the same; for resources of different genres, the obtained factor parameters for the same fusion factor are different. For example, the strategy model of this embodiment can adopt an evolutionary strategy model, which can be learned offline using a large amount of data to evolve to an optimal state. When this step is used online, the evolved optimal parameters can be obtained, and the factor parameters of each fusion factor for each resource type can be accurately obtained.

[0043] S103: Based on the factor value and the factor parameter, obtain the corresponding comprehensive factor value of each genre resource;

[0044] For example, for each resource, based on the acquired factor values ​​of at least two fusion factors of the resource and the factor parameters of each fusion factor, a comprehensive factor value of the resource can be obtained by mathematical calculation.

[0045] S104: Recommend resources to the user based on the comprehensive factor value.

[0046] In this embodiment, the comprehensive factor value of each resource can be used to comprehensively represent the recommendation level of the resource. For example, the higher the comprehensive factor value, the higher the recommendation level, which means that the resource is more worthy of being recommended.

[0047] The multi-genre resource recommendation method of this embodiment obtains a comprehensive factor value for each resource in a variety of genre resources based on the factor values ​​of at least two fusion factors of the resource and the factor parameters of each fusion factor. This allows the various genre resources to be uniformly recommended to users based on the comprehensive factor value. This provides an effective implementation solution for recommending multi-genre resources in immersive recommendation scenarios and effectively ensures the efficiency of multi-genre resource recommendations. Furthermore, the technical solution of this embodiment, by accurately obtaining the comprehensive factor value of each genre resource, can effectively improve the accuracy of resource sorting, thereby effectively improving the efficiency of resource recommendation.

[0048] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure; the method for recommending multi-genre resources in this embodiment, in the above Figure 1 Based on the technical solutions of the embodiments shown, the technical solutions of the present disclosure are further described in more detail. Figure 2 As shown, the method for recommending multi-genre resources in this embodiment may specifically include the following steps:

[0049] S201, obtaining target ranking parameters and first estimated effect characteristics of each genre resource within the corresponding genre type;

[0050] For example, in a resource recommendation scenario of actual application, before the technical solution of this embodiment, resources of various genres are first recalled in the recall layer. Then, they are processed by the coarse and fine ranking layer, which can specifically include a coarse ranking layer and a fine ranking layer. Specifically, within the resources of various genre types, multiple resources of the genre type can be coarsely sorted and finely sorted respectively, and then multiple resources of relatively high quality can be screened out. The technical solution of this embodiment can be considered to be that after the coarse and fine ranking layer, multiple resources of various genre types are put together for comprehensive sorting, and then resource recommendations can be made based on the comprehensive sorting results.

[0051] In this embodiment, the target ranking parameter of each resource in the corresponding genre type can be considered to be obtained based on the ranking parameter of each resource in the corresponding genre type at the refined ranking layer. The ranking parameter may include a ranking score.

[0052] Optionally, in this embodiment, the at least two fusion factors may include target ranking parameters for each resource within the corresponding genre type, and at least one first estimated effect feature. The first estimated effect feature refers to a feature that predicts the effect of a user consuming a resource. User consumption of a resource refers to a user browsing or viewing a resource, such as a user browsing a video resource or a graphic resource.

[0053] For example, the first estimated effect feature of each resource in this embodiment may include at least one of the predicted consumption time, fast scrolling probability, interaction probability, completion probability, quality score, decline rate and exit rate of each genre resource.

[0054] The consumption time indicates the length of time the user consumes the resource. The longer the consumption time, the higher the user's satisfaction with the resource, and the more worthy the resource is to be recommended to the user; and vice versa.

[0055] The fast sliding probability indicates the probability of a user quickly sliding the resource when consuming the resource. The greater the fast sliding probability, the lower the user's satisfaction with the resource, and the less worthy the resource is to be recommended to the user; vice versa.

[0056] The interaction in this embodiment may include at least one of the following operations: like, forward, follow, share, and comment. When a user consumes a resource, the greater the probability of interaction, the higher the user's attention to the resource, and the more worthy the resource is to be recommended to the user; and vice versa.

[0057] The completion probability indicates the probability of a resource being played completely when consumed by a user. The greater the completion probability, the higher the user's satisfaction with the resource, and the more worthy the resource is to be recommended to the user; and vice versa.

[0058] The quality score can be considered as a score that comprehensively represents the quality of the resource. A higher quality score indicates a higher quality resource and is more worthy of recommendation to the user, and vice versa. Specifically, the quality score can be obtained by using a quality assessment strategy or a quality assessment model.

[0059] The swipe-down rate indicates the probability that a user will swipe down to consume the next resource after clicking on the current resource. A higher swipe-down rate indicates greater user satisfaction with the current resource and a more recommended resource. The reverse is true for the same resource.

[0060] The exit rate indicates the probability that a user will exit the current resource. A higher exit rate indicates a higher user dissatisfaction with the current resource and a lower recommendation value for the resource; vice versa.

[0061] In actual applications, other estimated effect features may also be included, such as estimated delayed value, etc. The estimated delayed value is used to indicate whether the user will continue to want to view other resources of the author of the resource after consuming the resource, or whether the user will continue to want to view other related resources of the resource, such as related content resources or resources with related tags.

[0062] In this embodiment, each first estimated effect feature can be pre-trained with a corresponding estimation model. During use, the estimation model can be fed with inputs such as resource features of the resource, user features of the user intending to consume the resource, and at least one of the following: scene features and resource entry genre features. The estimation model can then predict and output the corresponding estimated effect feature based on the input information. Each feature can be represented by a numerical value, where fast scrolling probability, interaction probability, completion probability, quality score, decline rate, and exit rate can be values ​​between 0 and 1, with higher values ​​indicating a greater probability of the corresponding effect.

[0063] In this embodiment, by obtaining the target ranking parameters of each resource within the resources of the corresponding genre type and at least one of the consumption time, fast scrolling probability, interaction probability, completion probability, quality score, decline rate and exit rate of each resource, at least two fusion factors of each resource are constituted together, which can effectively ensure that the obtained fusion factors are very reasonable and accurate, and provide effective support for the subsequent calculation of the comprehensive factor values ​​of each resource.

[0064] For example, in this embodiment, obtaining the ranking score of each genre resource among multiple genre resources of multiple genres within the resources of the corresponding genre type may include the following two situations:

[0065] Case 1: The target ranking parameters include the original ranking parameters of the corresponding genre resources in the refined ranking layer within the corresponding genre resource type.

[0066] This approach, i.e., using the original ranking parameters of each resource in the refined ranking layer within the resources of the corresponding genre type as the target ranking parameters of the resource, can effectively ensure the accuracy of the target ranking parameters of the resource.

[0067] Scenario 2: Consider not only the ranking parameters of each resource within the corresponding genre type, but also the satisfaction level of each resource. For example, the following steps may be included:

[0068] (1) obtaining original ranking parameters of each genre resource in the corresponding genre type in the refined ranking layer;

[0069] (2) Obtaining the satisfaction of resources in each genre based on the pre-trained satisfaction prediction model;

[0070] (3) Based on the satisfaction and original ranking parameters, obtain the corresponding ranking parameters of each target;

[0071] For example, in this embodiment, for each genre resource, the target ranking parameter for that resource can be calculated by multiplying the original ranking parameter of that genre resource within the corresponding genre type in the refined ranking layer by the resource's satisfaction rating. This approach updates the ranking parameters of each resource based on its satisfaction rating, making the target ranking parameters more reasonable and accurate.

[0072] S202: normalize the factor value of the specified type according to the standard of the corresponding resource genre type; the fusion factor of the specified type includes: fusion factors with different consideration standards for resources of different genre types;

[0073] In actual application scenarios, the consideration criteria for the factor value of the same fusion factor for resources of different genre types may be different, or in other words, the dimensions may be different. For example, for the same fusion factor f1, the value range of the fusion factor in the video genre is 0-150, while in the graphic genre, the value range of the fusion factor is 0-100. The standards of the two are different. If the comprehensive factor value of the resource is calculated according to their respective values, it will lead to unfair and inaccurate recommendations for resources of various genre types. Therefore, in order to solve this problem, in this embodiment, the factor values ​​of fusion factors of resources of different genre types and with different consideration criteria can be normalized according to the standards of the genre of the corresponding resource.

[0074] For example, for the fusion factor f1 of the video genre, all values ​​within the range of 0-150 are normalized to between 0-1. For the fusion factor f1 of the graphic genre, all values ​​within the range of 0-100 are also normalized to between 0-1. This way, the standards for resources of different genres are unified for the same fusion factor f1, ensuring that the standards for the same fusion factor for resources of different genres are the same. This allows for fair, reasonable, and accurate calculation of comprehensive factor values ​​for resources of various genres, enabling fair, reasonable, and accurate multi-genre resource recommendations.

[0075] S203. Based on a pre-learned Evolution Strategies (ES) model, obtain factor parameters of various fusion factors of various genre resources;

[0076] In this embodiment, a pre-learned Covariance Matrix Adaptation (CMA) ES algorithm may be used to obtain factor parameters of various fusion factors of various genre resources.

[0077] Specifically, in at least two fusion factors of each genre resource, the factor parameters of the same fusion factor are the same, and in at least two fusion factors of different genre resources, the factor parameters of the same fusion factor are different.

[0078] For each resource genre, the factor parameters of at least two fusion factors can be pre-learned offline using an evolutionary strategy model based on historical traffic. During the learning process, multiple sets of parameters for at least two fusion factors can be configured for each resource genre. Traffic is then allocated to each parameter set, and the effectiveness of each parameter set is measured. For example, the total consumption time associated with each parameter set can be used as the performance indicator. Each parameter set is then evolved to achieve optimal results. Through rounds of iterative learning and evolution of multiple parameter sets, the optimal parameters for at least two fusion factors can be obtained and used as the factor parameters.

[0079] Optionally, in one embodiment of the present disclosure, the parameters of each fusion factor of various genre resources may include a factor index of each fusion factor.

[0080] Further optionally, in the case where the genre resources include graphic and text resources, the factor parameters of the fusion factor may further include a bias value.

[0081] That is, when the step S203 is specifically implemented, it may include the following steps: based on the evolutionary strategy model, obtaining the index of each fusion factor of various genre resources. The index here refers to the power. For example, f1 a In the equation, f1 represents the fusion factor, and a represents the exponent of the fusion factor; or f1^a can be used to represent the relationship.

[0082] Furthermore, when the resource genre includes graphic and text resources, the bias values ​​of the fusion factors of the graphic and text resources can be obtained based on the evolutionary strategy model.

[0083] Specifically, the traditional immersive resource recommendation scenario is mainly used to recommend resources of video genre. However, in the immersive resource recommendation scenario of this embodiment, it can be used to recommend resources of multiple genres, for example, resources of video genre and resources of graphic and text genre. Compared with resources of video genre, resources of graphic and text genre are newly added genres in this embodiment. In order to enable resources of different genres to be put together and sorted more objectively, fairly and accurately, in this embodiment, bias values ​​can be set for each fusion factor of graphic and text resources. Specifically, the bias values ​​of each fusion factor of graphic and text resources can also be pre-learned through the evolutionary strategy model.

[0084] In addition, in one embodiment of the present disclosure, if the resources of multiple genres include resources of text and graphic genres and resources of dynamic graphic genres, the resources of text and graphic genres and the resources of dynamic graphic genres need to be pre-learned separately through the evolutionary strategy model.

[0085] S204: For each resource among the multiple resources of multiple genres, obtain a comprehensive factor value of the resource based on the factor values ​​of each fusion factor corresponding to the resource and the factor parameters of each fusion factor;

[0086] Specifically, for a resource of a video genre, the comprehensive factor value of the resource may be obtained according to the factor values ​​of at least two fusion factors of the resource and the index of each fusion factor.

[0087] For example, if a resource includes three fusion factors, f1, f2, and f3, and the index of fusion factor f1 is a1, the index of fusion factor f2 is a2, and the index of fusion factor f3 is a3, the comprehensive score of the resource can be expressed as follows:

[0088] S=f1 a1 *f2 a2 *f3 a3

[0089] Specifically, for a resource of graphic and text genre, the comprehensive factor value of the resource may be obtained according to the factor values ​​of at least two fusion factors of the resource, the index of each fusion factor, and the bias value of each fusion factor.

[0090] For example, a resource includes f1, f2, and f3, and three fusion factors. The index of fusion factor f1 is a1, the index of fusion factor f2 is a2, the index of fusion factor f3 is a3, the bias value of fusion factor f1 is b1, the index of fusion factor f2 is b2, and the index of fusion factor f3 is b3. The comprehensive score of the resource can be expressed as follows:

[0091] S=(f1-b1) a1 *(f2-b2) a2 *(f3-b3) a3

[0092] S205, sorting multiple resources of multiple genres according to comprehensive factor values;

[0093] S206 , based on the ranking of comprehensive factor values ​​of multiple resources of multiple genres, obtain N top-ranked resources and recommend immersive resources to the user.

[0094] Steps S205-S206 of this embodiment are as described above. Figure 1A specific implementation of step S104 in the illustrated embodiment is shown. The number N can be set based on the requirements of the immersive resource recommendation scenario, for example, it can be 6 or 8, etc., and is not limited here.

[0095] The method for recommending multi-genre resources of this embodiment, by adopting the above-mentioned technical solution, can normalize the factor values ​​of fusion factors of resources of different genres and different consideration criteria within the resources of each genre type, so that the standards of the values ​​of each fusion factor of resources of different genre types are unified, thereby being able to make subsequent multi-genre resource recommendations more reasonable, fair, accurate and effective. Moreover, by adopting the above-mentioned technical solution, it is also possible to accurately and efficiently calculate the comprehensive factor value of each resource, and then more accurately recommend multi-genre resources based on the ranking of the comprehensive factor values ​​of each resource. The technical solution of this embodiment can further effectively improve the accuracy of resource ranking, and thus effectively improve the efficiency of resource recommendation.

[0096] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure; the method for recommending multi-genre resources in this embodiment, in the above Figure 2 Based on the technical solutions of the embodiments shown, the technical solutions of the present disclosure are further described in more detail. Figure 3 As shown, this embodiment provides a Figure 2 The specific implementation of “predicting the satisfaction of each resource based on a pre-trained satisfaction prediction model” in the illustrated embodiment may include the following steps:

[0097] S301, obtaining user characteristics of the user;

[0098] In this embodiment, the acquisition and use of user characteristics are known and agreed to by the user.

[0099] For example, when this step is specifically implemented, it may include: obtaining at least one of the user's attribute characteristics and the user's historical consumption characteristics;

[0100] User attributes include at least one of basic attributes and preference characteristics. Basic attributes include age, gender, and occupation. Preference characteristics include interests and hobbies. User preference characteristics can be identified in the user's attribute information as tags. For example, interests and hobbies may include travel, entertainment, and football. Each user's attribute characteristics are correlated with resources and can provide a reference for predicting user satisfaction with resources. For example, different age groups may have different resource preferences. For example, middle-aged and elderly people prefer video resources; middle-aged office workers prefer graphic resources; middle-aged women prefer fashion resources, while middle-aged men prefer financial resources; and the elderly prefer health resources.

[0101] The historical consumption characteristics of the user include at least one of the consumption proportion of resources of various genres consumed by the user in multiple historical time periods before the current period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres. If the genre of the currently predicted resource belongs to the resource genre with a relatively high consumption proportion in multiple historical time periods, the corresponding satisfaction will be higher. On the contrary, if the genre of the currently predicted resource belongs to the resource genre with the lowest consumption proportion in multiple historical time periods, the corresponding satisfaction will be lower. Similarly, if the genre of the currently predicted resource belongs to the resource genre with a relatively high completion rate in multiple historical time periods, the corresponding satisfaction will be higher. On the contrary, if the genre of the currently predicted resource belongs to the resource genre with a relatively low completion rate in multiple historical time periods, the corresponding satisfaction will be lower.

[0102] The length of the current time period can be a preset time length defined in the resource recommendation scenario, such as the current day, the current week, etc. Multiple historical time periods can be configured as needed, for example, including one historical day, three historical days, seven historical days, etc. The length and number of specific historical time periods are not limited here. The consumption ratio of users consuming resources of various genres, the duration of consumption of resources of various genres, and the completion rate of resources of various genres in each historical time period can be obtained by statistically analyzing the user's historical consumption information.

[0103] Furthermore, in this embodiment, scene features can be obtained. Scene features can identify whether the current immersive resource recommendation scene belongs to a recommendation scene or a discovery scene. In this embodiment, the recommendation scene and discovery scene can be two different sections in the application. Different users may have different scene preferences. Based on this scene feature, the accuracy of the predicted user satisfaction with the resource can be improved.

[0104] S302: For each resource, obtain resource characteristics of the resource;

[0105] For example, the resource characteristics of the resource may include: at least one of resource length, resource identifier, resource tag, resource genre type, resource entry genre, and a second estimated effect characteristic of the resource;

[0106] When the resource type is a video resource, the resource length refers to the duration of the video; when the resource type is a graphic resource, the resource length refers to the length of the text and the number of images included in the resource;

[0107] The resource entry genre feature of this embodiment may refer to the genre type feature of the resource entry resource, which can identify the genre type of the resource entry resource as video or graphic text;

[0108] The second estimated effect feature of the resource in this embodiment may include at least one of the predicted resource consumption time, fast scrolling probability, interaction probability, completion probability, quality score, decline rate, and exit rate.

[0109] Specifically, the second estimated effect feature of the resource may also include an estimated delayed value, which is used to characterize whether the user will continue to want to watch other resources of the author of the resource after consuming the resource, or whether the user will continue to want to watch other related resources of the resource; such as related content resources, or resources with related tags, etc.

[0110] S303: For each resource, based on the user characteristics of the user and the resource characteristics of the resource, a pre-trained satisfaction prediction model is used to predict the user's satisfaction with the resource as the satisfaction of the corresponding resource.

[0111] For each resource, the resource characteristics and user characteristics are input into the satisfaction prediction model. The model then predicts and outputs a satisfaction score. In practice, this satisfaction score can be a value between 0 and 1. A higher value indicates a higher satisfaction level for the resource, making it more recommended.

[0112] Optionally, if scenario features are obtained at the same time, the scenario features, resource features, and user features are also input into the satisfaction prediction model to improve the accuracy of the satisfaction predicted by the satisfaction prediction model.

[0113] The resource satisfaction estimation method of this embodiment can use a satisfaction estimation model to efficiently and accurately estimate user satisfaction with a resource, providing effective support for resource recommendation. Furthermore, the accurate resource satisfaction obtained through this embodiment can further effectively improve the accuracy of resource ranking, thereby effectively improving the efficiency of resource recommendation.

[0114] Moreover, in this embodiment, the user characteristics of users and resource characteristics of resources used in satisfaction estimation are very rich, which can effectively improve the accuracy of satisfaction estimation.

[0115] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure; this embodiment provides a device 400 for recommending multi-genre resources, including:

[0116] A factor acquisition module 401 is configured to acquire factor values ​​of at least two fusion factors of resources of at least two genres;

[0117] A parameter acquisition module 402 is configured to acquire the factor parameters of each fusion factor based on a pre-learned strategy model;

[0118] A comprehensive value acquisition module 403 is configured to acquire a comprehensive factor value of each of the genre resources based on the factor value and the factor parameter;

[0119] The recommendation module 404 is configured to recommend resources to the user based on the comprehensive factor value.

[0120] The device 400 for recommending multi-genre resources in this embodiment implements the implementation principle and technical effects of recommending multi-genre resources by adopting the above modules, which are the same as those of the above-mentioned related method embodiments. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0121] Figure 5 is a schematic diagram of a fifth embodiment of the present disclosure; the device 500 for recommending multi-genre resources in this embodiment, in the above Figure 4 Based on the technical solutions of the embodiments shown, the technical solutions of the present disclosure are further described in more detail. Figure 5 As shown, the multi-genre resource recommendation device 500 of this embodiment includes the above Figure 4 Modules with the same name and function are shown as follows: factor acquisition module 501 , parameter acquisition module 502 , comprehensive value acquisition module 503 , and recommendation module 504 .

[0122] The factor acquisition module 501 is used to:

[0123] Obtaining a target ranking parameter and a first estimated effect feature of each of the genre resources within the corresponding genre type;

[0124] The first estimated effect feature includes at least one of the predicted consumption time, fast scrolling probability, interaction probability, completion probability, quality score, decline rate, and exit rate of each of the genre resources.

[0125] Further optionally, in one embodiment of the present disclosure, the factor acquisition module 501 is configured to:

[0126] Obtaining original sorting parameters of each genre resource in the refined ranking layer within the corresponding genre type;

[0127] Obtaining satisfaction ratings of resources of each genre based on a pre-trained satisfaction prediction model;

[0128] Based on the satisfaction level and the original ranking parameters, the corresponding target ranking parameters are obtained.

[0129] Further optionally, in one embodiment of the present disclosure, the factor acquisition module 501 is configured to:

[0130] Obtaining user characteristics of the user;

[0131] Obtaining resource characteristics of each of the genre resources;

[0132] Based on the user characteristics and the resource characteristics, the satisfaction level corresponding to the genre resource is acquired by using the satisfaction level prediction model.

[0133] Further optionally, in one embodiment of the present disclosure, the user characteristics include: at least one of attribute characteristics and historical consumption characteristics;

[0134] The attribute characteristics include: at least one of basic attribute characteristics and preference characteristics; the historical consumption characteristics include at least one of the consumption proportion of resources of various genres consumed by users in at least two historical time periods before the current period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres.

[0135] Further optionally, in an embodiment of the present disclosure, the resource feature includes: at least one of resource length, resource identifier, resource tag, resource genre type, resource entry genre, and second estimated effect feature;

[0136] In the case where the resource genre type includes a video type, the resource length includes the duration of the video;

[0137] In the case that the resource genre type includes a picture and text type, the resource length includes the length of the text in the picture and text and the number of pictures.

[0138] Further optionally, as Figure 5 As shown, in an embodiment, the device 500 for recommending multi-genre resources further includes:

[0139] The normalization module 505 is configured to normalize the factor value of a specified type according to the standard of the corresponding resource genre type. The fusion factor of the specified type includes fusion factors with different resource consideration standards for different genre types.

[0140] Further optionally, in one embodiment of the present disclosure, the factor parameter includes a factor index.

[0141] Further optionally, in one embodiment of the present disclosure, when the genre resource includes a graphic resource, the factor parameter includes a bias value.

[0142] The device 500 for recommending multi-genre resources in this embodiment adopts the above modules to implement the implementation principle and technical effects of recommending multi-genre resources, which are the same as those of the above-mentioned related method embodiments. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0143] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0144] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0145] 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0146] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0147] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0148] The computing unit 601 can be a variety of general and / or special 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 dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the above-mentioned methods of the present disclosure. For example, in some embodiments, the above-mentioned methods of the present disclosure can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the above-mentioned methods of the present disclosure described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the above-mentioned methods of the present disclosure by any other appropriate means (e.g., by means of firmware).

[0149] Various embodiments of the systems and techniques described above 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), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0151] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0152] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0153] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0154] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0155] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0156] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for recommending multi-genre resources, comprising: Obtaining factor values ​​of at least two fusion factors of genre resources of at least two genres; Based on the pre-learned strategy model, factor parameters of each fusion factor are obtained; the factor parameters include factor indexes; when the genre resources include graphic resources, the factor parameters include bias values; Based on the factor value and the factor parameter, obtaining a corresponding comprehensive factor value of each of the genre resources; Recommending resources to the user based on the comprehensive factor value; The obtaining of the factor values ​​of at least two fusion factors of the resources of at least two genres includes: Obtaining a target ranking parameter and a first estimated effect feature of each of the genre resources within the corresponding genre type; The first estimated effect feature includes: at least one of the predicted consumption duration, fast scrolling probability, interaction probability, completion probability, quality score, decline rate, and exit rate of each of the genre resources; The obtaining of target ranking parameters of each genre resource within the corresponding genre type includes: Obtaining original sorting parameters of each genre resource in the refined ranking layer within the corresponding genre type; Obtaining satisfaction ratings of resources of each genre based on a pre-trained satisfaction prediction model; Based on the satisfaction level and the original ranking parameters, the corresponding target ranking parameters are obtained.

2. The method according to claim 1, wherein The target ranking parameter can also be replaced by the original ranking parameter of the genre resource in the corresponding genre resource type in the refined ranking layer.

3. The method according to claim 1, wherein The obtaining of the satisfaction of each genre resource based on the pre-trained satisfaction prediction model includes: Obtaining user characteristics of the user; Obtaining resource characteristics of each of the genre resources; Based on the user characteristics and the resource characteristics, the satisfaction level corresponding to the genre resource is acquired by using the satisfaction level prediction model.

4. The method according to claim 3, wherein: The user characteristics include: at least one of attribute characteristics and historical consumption characteristics; The attribute characteristics include: at least one of basic attribute characteristics and preference characteristics; the historical consumption characteristics include at least one of the consumption proportion of resources of various genres consumed by users in at least two historical time periods before the current period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres.

5. The method according to claim 3, wherein: The resource characteristics include: at least one of resource length, resource identifier, resource tag, resource genre type, resource entry genre, and second estimated effect characteristics; In the case where the resource genre type includes a video type, the resource length includes the duration of the video; In the case that the resource genre type includes a picture and text type, the resource length includes the length of the text in the picture and text and the number of pictures.

6. The method according to claim 1, wherein After obtaining the factor values ​​of at least two fusion factors of each genre resource of at least two genres, and before obtaining the corresponding comprehensive factor value of each genre resource based on the factor values ​​and the factor parameters, the method further includes: The factor value of the specified type is normalized according to the standard of the corresponding resource genre type. The fusion factor of the specified type includes: fusion factors with different resource consideration standards for different genre types.

7. A device for recommending multi-genre resources, comprising: A factor acquisition module, configured to acquire factor values ​​of at least two fusion factors of at least two genre resources; A parameter acquisition module, configured to acquire factor parameters of each fusion factor based on a pre-learned strategy model; the factor parameters include factor indexes; and when the genre resources include graphic resources, the factor parameters include bias values; A comprehensive value acquisition module, configured to acquire the comprehensive factor value of each of the corresponding genre resources based on the factor value and the factor parameter; A recommendation module, configured to recommend resources to users based on the comprehensive factor value; The factor acquisition module is used to: Obtaining a target ranking parameter and a first estimated effect feature of each of the genre resources within the corresponding genre type; The first estimated effect feature includes: at least one of the predicted consumption duration, fast scrolling probability, interaction probability, completion probability, quality score, decline rate, and exit rate of each of the genre resources; The factor acquisition module is used to: Obtaining original sorting parameters of each genre resource in the refined ranking layer within the corresponding genre type; Obtaining satisfaction ratings of resources of each genre based on a pre-trained satisfaction prediction model; Based on the satisfaction level and the original ranking parameters, the corresponding target ranking parameters are obtained.

8. The device according to claim 7, wherein The target ranking parameter can also be replaced by the original ranking parameter of the genre resource in the corresponding genre resource type in the refined ranking layer.

9. The device according to claim 7, wherein The factor acquisition module is used to: Obtaining user characteristics of the user; Obtaining resource characteristics of each of the genre resources; Based on the user characteristics and the resource characteristics, the satisfaction level corresponding to the genre resource is acquired by using the satisfaction level prediction model.

10. The device according to claim 9, wherein The user characteristics include: at least one of attribute characteristics and historical consumption characteristics; The attribute characteristics include: at least one of basic attribute characteristics and preference characteristics; the historical consumption characteristics include at least one of the consumption proportion of resources of various genres consumed by users in at least two historical time periods before the current period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres.

11. The device according to claim 9, wherein The resource characteristics include: at least one of resource length, resource identifier, resource tag, resource genre type, resource entry genre, and second estimated effect characteristics; In the case where the resource genre type includes a video type, the resource length includes the duration of the video; In the case that the resource genre type includes a picture and text type, the resource length includes the length of the text in the picture and text and the number of pictures.

12. The device according to claim 7, wherein The device further comprises: The normalization module is used to normalize the factor value of the specified type according to the standard of the corresponding resource genre type. The fusion factor of the specified type includes: fusion factors with different resource consideration standards for different genre types.

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

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

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

Images