Port resource recommendation method and device, equipment and storage medium

Abstract

The invention provides an entry resource recommendation method and device, equipment and a storage medium, and relates to the technical fields of resource distribution, resource recommendation, artificial intelligence and the like. According to the specific implementation scheme, the method comprises the steps of obtaining features of a user and features of to-be-recommended entry resources; based on the characteristics of the user and the characteristics of each entrance resource, evaluating the value of each entrance resource by adopting a pre-trained entrance resource value evaluation model; and recommending at least one entry resource to the user based on the value of each entry resource. According to the technology disclosed by the invention, the recommendation accuracy and recommendation efficiency of the entry resources can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to technical fields such as resource distribution, resource recommendation, and artificial intelligence, and in particular to a method, device, equipment, and storage medium for recommending entry 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] In the existing immersive recommendation scenario, users enter the immersive recommendation scenario through an entry resource. As a very critical resource, the entry resource is very important to filter. Usually, multiple entry resources recalled from the resource library can be sorted; then the entry resources are filtered and recommended according to the sorting. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and storage medium for recommending entry resources.

[0005] According to one aspect of the present disclosure, a method for recommending an entry resource is provided, which includes:

[0006] Obtaining the characteristics of the user and the characteristics of each entry resource to be recommended;

[0007] Based on the characteristics of the user and the characteristics of each of the portal resources, a pre-trained portal resource value evaluation model is used to evaluate the value of each portal resource;

[0008] Based on the value of each of the entry resources, at least one entry resource is recommended to the user.

[0009] According to another aspect of the present disclosure, a method for training an entry resource value assessment model is provided, comprising:

[0010] Generate a training data set, wherein the training data set includes characteristics of a training user, characteristics of two training entry resources, and a true magnitude relationship between the values ​​of the two training entry resources;

[0011] Based on the training data set, using an entry resource value assessment model, predicting a predicted magnitude relationship between the values ​​of the two training entry resources;

[0012] Based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, the parameters of the entry resource value assessment model are adjusted.

[0013] According to another aspect of the present disclosure, there is provided a device for recommending entry resources, comprising:

[0014] An acquisition module, used to acquire the characteristics of the user and the characteristics of each entry resource to be recommended;

[0015] An evaluation module, configured to evaluate the value of each entry resource using a pre-trained entry resource value evaluation model based on the characteristics of the user and the characteristics of each entry resource;

[0016] The recommendation module is used to recommend at least one entry resource to the user based on the value of each entry resource.

[0017] According to another aspect of the present disclosure, a training device for an entry resource value assessment model is provided, comprising:

[0018] A generating module, used to generate a training data set, wherein the training data set includes the characteristics of the training user, the characteristics of the two training entry resources, and the true size relationship of the values ​​of the two training entry resources;

[0019] A prediction module, configured to predict the predicted magnitude relationship of the values ​​of the two training entry resources based on the training data group and using an entry resource value evaluation model;

[0020] The adjustment module is used to adjust the parameters of the entry resource value assessment model based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources.

[0021] According to yet another aspect of the present disclosure, there is provided an electronic device, including:

[0022] at least one processor; and

[0023] a memory communicatively connected to the at least one processor; wherein,

[0024] 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 of any possible implementation manner and the aspects described above.

[0025] 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.

[0026] According to yet another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned aspects and the method of any possible implementation manner.

[0027] According to the technology disclosed in the present invention, the accuracy and efficiency of recommending entry resources can be effectively improved.

[0028] 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

[0029] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0030] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0031] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0032] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0033] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0034] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0035] Figure 6 is a schematic diagram according to a sixth embodiment of the present disclosure;

[0036] Figure 7 is a schematic diagram according to a seventh embodiment of the present disclosure;

[0037] Figure 8 is a schematic diagram according to an eighth embodiment of the present disclosure;

[0038] Fig. 9 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0040] Obviously, the described embodiments are only part of the embodiments of the present disclosure, but not all of them. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present disclosure.

[0041] 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.

[0042] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; Figure 1 As shown, this embodiment provides an entry resource recommendation method, which is applied to the recommendation of entry resources in a resource recommendation scenario, and specifically may include the following steps:

[0044] S101, obtaining characteristics of the user and characteristics of each entry resource to be recommended;

[0045] S102, based on the characteristics of the user and the characteristics of each portal resource, using a pre-trained portal resource value evaluation model to evaluate the value of each portal resource;

[0046] S103: Recommend at least one entry resource to the user based on the value of each entry resource.

[0047] The executor of the entry resource recommendation method in this embodiment may be an entry resource recommendation device, which may be an electronic entity or a software integrated application. By adopting an entry resource value assessment model, entry resources can be recommended accurately and effectively.

[0048] In this embodiment, before recommending entry resources, the resource recommendation system has detected that the user is browsing the current homepage. At this time, the resource recommendation system needs to first recall some entry resources to be recommended from the resource library, and perform coarse and fine sorting to obtain the ranking of the entry resources to be recommended. The specific process of resource recall and coarse and fine sorting can refer to the relevant technology, which will not be repeated here.

[0049] Normally, portal resources can be recommended directly based on the ranking of portal resources after coarse and fine sorting. However, this method of recommending portal resources does not take the value of each portal resource into consideration, resulting in low accuracy of the recommended portal resources.

[0050] In order to overcome the above technical problems, this embodiment introduces a pre-trained entry resource value evaluation model, which evaluates the value of each entry resource to be recommended, and then more accurately recommends at least one entry resource to the user based on the value of each entry resource.

[0051] In this embodiment, the entry resources to be recommended may be a plurality of entry resources ranked at the top in the coarse and fine sorting in the conventional technology, such as the top 100, or 200 entry resources in the sorting.

[0052] The entry resource recommendation method of this embodiment can be applied to the recommendation of entry resources in immersive resource recommendation scenarios, and can also be applied to the recommendation of entry resources in other resource recommendation scenarios, which is not limited here.

[0053] The entry resource recommendation method of this embodiment adopts an entry resource value evaluation model to evaluate the value of each entry resource to be recommended, and then based on the value of each entry resource, it can more accurately recommend at least one entry resource to the user, which can effectively improve the accuracy and efficiency of entry resource recommendations.

[0054] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure; the entry resource recommendation method of this embodiment, in the above Figure 1 Based on the technical solutions of the illustrated embodiments, the technical solutions of the present disclosure are further described in more detail. Figure 2 As shown, the entry resource recommendation method of this embodiment may specifically include the following steps:

[0055] S201, obtaining at least one of a user's attribute characteristics and a user's historical consumption characteristics;

[0056] In this embodiment, the attribute characteristics of the user may include at least one of the basic attribute characteristics of the user and the preference characteristics of the user; the basic attribute characteristics of the user include the age, gender, occupation, etc. of the user. The preference characteristics of the user include the interests and hobbies of the user. The preference characteristics of the user can be identified in the attribute information of the user in the form of tags. For example, the interests and hobbies can include travel, entertainment, football, etc. The attribute characteristics of the user have a certain correlation with the resources, which can provide a reference for the prediction of the user's satisfaction with the resources. For example, different ages have different resource preferences. For example, middle-aged and elderly people like to consume video resources; middle-aged office workers like to consume graphic resources; middle-aged women like to consume fashion resources, while middle-aged men like to consume financial resources; and the elderly like to consume health resources, and so on.

[0057] The historical consumption characteristics of users include at least one of the consumption proportion of portal resources of various genres consumed by users in multiple historical time periods before the current period, the click rate of portal resources of various genres, and the comprehensive consumption time of portal resources of various genres. Among them, the comprehensive consumption time of each portal resource in each genre may include the consumption time of the portal resource and the consumption time of immersive consumption of all resources after the user clicks into the portal resource. The comprehensive consumption time of portal resources of a genre in a historical time period may be equal to the sum of the comprehensive consumption time of all portal resources of the genre in the historical time period.

[0058] If the genre of a resource to be recommended is a resource genre with a relatively high consumption ratio in multiple historical time periods, the corresponding value will be higher. Conversely, if the genre of the resource to be recommended is a resource genre with the lowest consumption ratio in multiple historical time periods, the corresponding value will be lower. Similarly, if the comprehensive consumption time of the resources to be recommended of a certain genre is relatively high in multiple historical time periods, the value of the resources of this genre will be higher. Conversely, if the comprehensive consumption time of the resources to be recommended of this genre is relatively low in multiple historical time periods, the corresponding value will be lower, and so on.

[0059] The length of the current time period can be a preset time length defined in the resource recommendation scenario, such as the current time period can be the current day, the current week, etc. Multiple historical time periods can be configured according to demand, for example, including historical one day, historical three days, historical seven days, etc. The length and number of specific historical time periods are not limited here. The consumption proportion of users' consumption of resources of various genres in each historical time period, the click rate of portal resources of various genres, and the comprehensive consumption time of portal resources of various genres can be obtained by statistically analyzing the user's historical consumption information.

[0060] S202, obtaining at least one of the length, title, tag, genre, and obtained score of each entry resource;

[0061] When the genre of the entry resource is a video resource, the length of the entry resource refers to the length of the video; when the genre of the entry resource is a graphic resource, the length of the entry resource refers to the length of the text included in the entry resource and the number of pictures included. When the genre of the entry resource of this embodiment is a video, it may specifically include short videos and / or small videos; when the genre of the entry resource of this embodiment is a graphic, it may specifically include dynamic graphics and / or text graphics. The playback time of the small video is less than the playback time of the short video. Graphics include dynamic graphics and / or text graphics. Dynamic graphics must include pictures and may 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.

[0062] The entry genre feature of the resource in this embodiment may refer to the genre feature of the entry resource of the resource, which can identify that the genre of the entry resource of the resource is video or graphic.

[0063] The label of the entry resource is used to indicate the category of the content of the entry resource.

[0064] The score of the entry resource may refer to the score of the entry resource in the coarse and fine sorting process.

[0065] Steps S201-S202 are as described above. Figure 1 A specific implementation of step S101 in the illustrated embodiment. In this way, comprehensive, rich and accurate user characteristics and portal resource characteristics can be obtained.

[0066] S203, based on the characteristics of the user and the characteristics of each portal resource, using a pre-trained portal resource value evaluation model to evaluate the value of each portal resource;

[0067] Specifically, for each entry resource, the user's characteristics and the characteristics of the entry resource are input into the entry resource value assessment model, and the entry resource value assessment model can predict and output the value of the entry resource.

[0068] S204, obtaining an updated score of each entry resource based on the value of each entry resource and the score of each entry resource that has been obtained;

[0069] For example, in specific implementation, the value of the entry resource and the score of the entry resource may be multiplied to obtain the updated score of the entry resource. Alternatively, the updated score of each entry resource may be updated based on the value of each entry resource and other mathematical algorithms, which will not be described in detail here.

[0070] S205: Recommend at least one entry resource to the user based on the updated score of each entry resource.

[0071] Specifically, according to the update scores of the portal resources, the portal resources may be sorted from large to small, and then at least one portal resource at the top may be obtained for recommendation according to the sorting.

[0072] Steps S204-S205 are as above Figure 1 A specific implementation of step S103 of the illustrated embodiment.

[0073] The portal resource recommendation method of this embodiment can obtain rich and comprehensive user characteristics and characteristics of each portal resource to be recommended; further, by adopting a portal resource value evaluation model, the value of each portal resource can be accurately and efficiently evaluated based on the acquired characteristics, and then more accurate and effective portal resource recommendations can be made based on the value of each portal resource.

[0074] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure; Figure 3 As shown, this embodiment provides a method for training an entry resource value assessment model, which may specifically include the following steps:

[0075] S301, generating a training data set, the training data set including the characteristics of the training user, the characteristics of two training entry resources, and the true size relationship of the values ​​of the two training entry resources;

[0076] The execution subject of the training method of the portal resource value assessment model of this embodiment is the training device of the portal resource value assessment model, and the device may be an electronic entity or a software integrated application.

[0077] In this embodiment, the generated training data set may be generated based on the user's historical consumption information.

[0078] In this embodiment, the actual size relationship between the values ​​of the two training entry resources in the training data group is greater than or less than, and cannot be equal.

[0079] S302, based on the training data set, using the entry resource value assessment model to predict the predicted size relationship of the values ​​of two training entry resources;

[0080] S303: Based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, adjust the parameters of the entry resource value assessment model.

[0081] The training method of the entry resource value assessment model of the present embodiment, during training, trains the entry resource value assessment model based on the actual size relationship between the values ​​of two training entry resources in the training data group. This can effectively reduce the training difficulty of the entry resource value assessment model, ensure the training accuracy, and effectively improve the training efficiency of the entry resource value assessment model.

[0082] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure; Figure 4 As shown, the training method of the entry resource value assessment model of this embodiment is as follows: Figure 3 Based on the technical solutions of the embodiments shown in the figure, the technical solutions of the present disclosure are further described in more detail. Figure 4As shown, the training method of the entry resource value assessment model of this embodiment may specifically include the following steps:

[0083] S401, constructing features of the training user based on the historical consumption information of the training user;

[0084] For example, it may specifically include constructing at least one of the attribute characteristics of the training user and the historical consumption characteristics of the user based on the historical consumption information of the training user.

[0085] The attribute characteristics of the training user include at least one of the basic attribute characteristics of the user and the preference characteristics of the user; the historical consumption characteristics of the training user include at least one of the consumption ratio of the user's consumption of resources of various genres in multiple historical time periods before the training user consumed the corresponding entry resource characteristics, the click rate of the entry resources of various genres, and the comprehensive consumption time of the entry resources of various genres. Figure 2 The relevant records of the illustrated embodiment will not be repeated here.

[0086] S402: construct features and consumption information of two training entry resources based on historical consumption information of the training user;

[0087] For example, the features of two training entry resources are collected from the historical consumption information of the training user, which may specifically include:

[0088] At least one of the length, title, tag, genre, and acquired score of each of the two training entry resources is collected from the historical consumption information of the training user.

[0089] Among them, when the genre of the training entry resource is a video resource, the length of the training entry resource refers to the length of the video; when the genre of the training entry resource is a graphic resource, the length of the training entry resource refers to the length of the text included in the training entry resource and the number of pictures included.

[0090] The label of the training entry resource is used to indicate the category of the content of the entry resource. The detailed acquisition process can also be referred to above Figure 2 The relevant records of the illustrated embodiment will not be repeated here.

[0091] S403: Based on the consumption information of the two training entry resources, configure the real size relationship of the values ​​of the two training entry resources;

[0092] For example, in this embodiment, the specific configuration process may include the following methods:

[0093] (1) Based on the duration of each of the two training entry resources consumed by the training user, the value of the training entry resource with a longer consumption duration is configured to be greater than the value of the training entry resource with a shorter consumption duration;

[0094] (2) Based on the consumption step length of each of the two training entry resources consumed by the training user, the value of the training entry resource with a larger consumption step length is configured to be greater than the value of the training entry resource with a smaller consumption step length;

[0095] (3) based on the click information of the training user consuming each of the two training entry resources, the value of the training entry resource clicked by the training user is configured to be greater than the value of the training entry resource not clicked by the training user; or

[0096] (4) Based on the sliding information after the training user clicks on each of the two training entry resources, the value of the training entry resource that slides after the training user clicks is configured to be greater than the value of the training entry resource that does not slide after the training user clicks.

[0097] Through the above method, the true size relationship between the values ​​of the two training entry resources can be accurately and reasonably identified.

[0098] Steps S401-S403 are as above Figure 3 The generation process of the training data set of the embodiment shown in the figure. In this way, the training data set can be generated accurately and reasonably.

[0099] S404, based on the characteristics of the training user and the characteristics of each training entry resource, using an entry resource value evaluation model to predict the value of each training entry resource;

[0100] S405, based on the value of each of the two training entry resources, obtaining a predicted magnitude relationship between the values ​​of the two training entry resources;

[0101] S406, detecting whether the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent;

[0102] S407: In response to the inconsistency between the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, adjust the parameters of the entry resource value assessment model so that the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent.

[0103] In addition, in this embodiment, if the predicted size relationship and the actual size relationship of the values ​​of two training entry resources are consistent, the parameters of the entry resource value assessment model are not adjusted at this time, and the next training data group is used to train the entry resource value assessment model until the training cutoff condition is met. The training is completed and a trained entry resource value assessment model is obtained.

[0104] The training method of the entry resource value assessment model of the present embodiment, during training, trains the entry resource value assessment model based on the actual size relationship between the values ​​of two training entry resources in the training data group. This can effectively reduce the training difficulty of the entry resource value assessment model, ensure the training accuracy, and effectively improve the training efficiency of the entry resource value assessment model.

[0105] Figure 5 is a schematic diagram according to the fifth embodiment of the present disclosure; Figure 5 As shown, this embodiment provides a portal resource recommendation device 500, which is applied to recommend portal resources in a resource recommendation scenario, including:

[0106] The acquisition module 501 is used to acquire the characteristics of the user and the characteristics of each entry resource to be recommended;

[0107] An evaluation module 502, configured to evaluate the value of each entry resource using a pre-trained entry resource value evaluation model based on the characteristics of the user and the characteristics of each entry resource;

[0108] The recommendation module 503 is used to recommend at least one entry resource to the user based on the value of each entry resource.

[0109] The entry resource recommendation device 500 of this embodiment implements the implementation principle and technical effect of entry resource recommendation by adopting the above modules, which is the same as the implementation of the above related method embodiments. For details, please refer to the records of the above related method embodiments, which will not be repeated here.

[0110] Figure 6 is a schematic diagram according to the sixth embodiment of the present disclosure; Figure 6 As shown, the entry resource recommendation device 600 of this embodiment, in the above Figure 5 Based on the technical solutions of the embodiments shown in the figure, the technical solutions of the present disclosure are further described in more detail. Figure 6 As shown, the entry resource recommendation device 600 of this embodiment includes the above Figure 5 The modules with the same name and function are shown as: an acquisition module 601 , an evaluation module 602 and a recommendation module 603 .

[0111] In this embodiment, the acquisition module 601 is used to:

[0112] Acquire at least one of the attribute characteristics of the user and the historical consumption characteristics of the user;

[0113] The user's attribute characteristics include at least one of the user's basic attribute characteristics and the user's preference characteristics; the user's historical consumption characteristics include at least one of the user's consumption proportion of portal resources of various genres, the click rate of portal resources of various genres, and the comprehensive consumption time of portal resources of various genres in multiple historical time periods before the current period.

[0114] Further optionally, in one embodiment of the present disclosure, the acquisition module 601 is used to:

[0115] Obtaining at least one of the length, title, tag, genre, and obtained score of each of the entry resources;

[0116] When the genre of the entry resource is a video resource, the length of the entry resource refers to the duration of the video; when the genre of the entry resource is a graphic resource, the length of the entry resource refers to the length of the text included in the entry resource and the number of pictures included;

[0117] The label of the entry resource is used to indicate the category of the content of the entry resource.

[0118] Further optionally, if Figure 6 As shown, in one embodiment of the present disclosure, the recommendation module 603 includes:

[0119] An updating unit 6031, configured to obtain an updated score of each of the entry resources based on the value of each of the entry resources and the obtained score of each of the entry resources;

[0120] The recommendation unit 6032 is configured to recommend at least one entry resource to the user based on the updated score of each entry resource.

[0121] Further optionally, in one embodiment of the present disclosure, the updating unit 6031 is used to:

[0122] For each of the entry resources, the value of the entry resource and the score of the entry resource are multiplied together to obtain an updated score of the entry resource.

[0123] The entry resource recommendation device 600 of this embodiment implements the implementation principle and technical effect of entry resource recommendation by adopting the above modules, which is the same as the implementation of the above related method embodiments. For details, please refer to the records of the above related method embodiments, which will not be repeated here.

[0124] Figure 7 is a schematic diagram according to the seventh embodiment of the present disclosure; Figure 7 As shown, this embodiment provides a training device 700 for an entry resource value assessment model, including:

[0125] A generating module 701 is used to generate a training data set, wherein the training data set includes the characteristics of the training user, the characteristics of the two training entry resources, and the true size relationship of the values ​​of the two training entry resources;

[0126] A prediction module 702, configured to predict the predicted magnitude relationship of the values ​​of the two training entry resources based on the training data set and using an entry resource value evaluation model;

[0127] The adjustment module 703 is used to adjust the parameters of the entry resource value assessment model based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources.

[0128] The training device 700 of the entry resource value assessment model of this embodiment realizes the implementation principle and technical effect of the training of the entry resource value assessment model by adopting the above-mentioned modules, which is the same as the implementation of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0129] Figure 8 is a schematic diagram according to an eighth embodiment of the present disclosure; Figure 8 As shown, the training device 800 of the entry resource value assessment model of this embodiment, in the above Figure 7 Based on the technical solutions of the embodiments shown in the figure, the technical solutions of the present disclosure are further described in more detail. Figure 8 As shown, the entry resource recommendation device 800 of this embodiment includes the above Figure 7 The modules with the same name and function are shown as: generation module 801 , prediction module 802 and adjustment module 803 .

[0130] In this embodiment, the generating module 801 is used to:

[0131] constructing features of the training user based on the historical consumption information of the training user;

[0132] Based on the historical consumption information of the training user, construct the characteristics and consumption information of the two training entry resources;

[0133] Based on the consumption information of the two training entry resources, the actual size relationship of the values ​​of the two training entry resources is configured.

[0134] Optionally, in one embodiment of the present disclosure, the generating module 801 is used to:

[0135] Based on the historical consumption information of the training user, collecting at least one of the attribute characteristics of the training user and the historical consumption characteristics of the user;

[0136] The attribute characteristics of the training user include at least one of the user's basic attribute characteristics and the user's preference characteristics; the historical consumption characteristics of the training 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 training user consumed the corresponding entry resource characteristics, the click rate of entry resources of various genres, and the comprehensive consumption time of entry resources of various genres.

[0137] Optionally, in one embodiment of the present disclosure, the generating module 801 is used to:

[0138] Collecting at least one of the length, title, label, genre, and acquired score of each of the two training entry resources from the historical consumption information of the training user;

[0139] When the genre of the training entry resource is a video resource, the length of the training entry resource refers to the duration of the video; when the genre of the training entry resource is a graphic resource, the length of the training entry resource refers to the length of the text and the number of pictures included in the training entry resource;

[0140] The label of the training entry resource is used to indicate the category of the content of the entry resource.

[0141] Optionally, in one embodiment of the present disclosure, the generating module 801 is used to:

[0142] Based on the consumption time of each of the two training entry resources consumed by the training user, the value of the training entry resource with a longer consumption time is configured to be greater than the value of the training entry resource with a shorter consumption time;

[0143] Based on the consumption step length of each of the two training entry resources consumed by the training user, configuring the value of the training entry resource with a larger consumption step length to be greater than the value of the training entry resource with a smaller consumption step length;

[0144] Based on the click information of each of the two training entry resources consumed by the training user, configure the value of the training entry resource clicked by the training user to be greater than the value of the training entry resource not clicked by the training user; or

[0145] Based on the sliding information after the training user clicks on each of the two training entry resources, the value of the training entry resource with sliding after the training user clicks is configured to be greater than the value of the training entry resource without sliding after the training user clicks.

[0146] Further optionally, if Figure 8As shown, in one embodiment of the present disclosure, the prediction module 802 includes:

[0147] A prediction unit 8021, configured to predict the value of each of the training entry resources by using the entry resource value evaluation model based on the characteristics of the training user and the characteristics of each of the training entry resources;

[0148] The acquiring unit 8022 is configured to acquire a predicted magnitude relationship between the values ​​of the two training entry resources based on the value of each of the two training entry resources.

[0149] Further optionally, if Figure 8 As shown, in one embodiment of the present disclosure, the adjustment module 803 includes:

[0150] A detection unit 8031 ​​is used to detect whether the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent;

[0151] The adjustment unit 8032 is used to adjust the parameters of the entry resource value assessment model in response to the inconsistency between the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, so that the predicted size relationship of the values ​​of the two training entry resources is consistent with the actual size relationship.

[0152] The training device 800 of the entry resource value assessment model of this embodiment realizes the implementation principle and technical effect of the training of the entry resource value assessment model by adopting the above-mentioned modules, which is the same as the implementation of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0153] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0154] 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.

[0155] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment 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 processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0156] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0157] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0158] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 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 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the above-mentioned methods of the present disclosure described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the above-mentioned methods of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0159] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0161] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] 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).

[0163] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0164] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for recommending entry resources, wherein: include: Obtaining the characteristics of the user and the characteristics of each entry resource to be recommended; Based on the characteristics of the user and the characteristics of each of the portal resources, a pre-trained portal resource value evaluation model is used to evaluate the value of each portal resource; Based on the value of each of the entry resources, at least one entry resource is recommended to the user.

2. The method according to claim 1, wherein: Get the user's characteristics, including: Acquire at least one of the attribute characteristics of the user and the historical consumption characteristics of the user; The user's attribute characteristics include at least one of the user's basic attribute characteristics and the user's preference characteristics; the user's historical consumption characteristics include at least one of the user's consumption proportion of portal resources of various genres, the click rate of portal resources of various genres, and the comprehensive consumption time of portal resources of various genres in multiple historical time periods before the current period.

3. The method according to claim 1, wherein: Get the characteristics of each entry resource to be recommended, including: Obtaining at least one of the length, title, tag, genre, and obtained score of each of the entry resources; When the genre of the entry resource is a video resource, the length of the entry resource refers to the duration of the video; when the genre of the entry resource is a graphic resource, the length of the entry resource refers to the length of the text included in the entry resource and the number of pictures included; The label of the entry resource is used to indicate the category of the content of the entry resource.

4. The method according to any one of claims 1 to 3, wherein: Recommending at least one entry resource to the user based on the recommendation value of each entry resource includes: Based on the value of each of the entry resources and the obtained scores of each of the entry resources, obtaining an updated score of each of the entry resources; Based on the updated scores of the entry resources, at least one entry resource is recommended to the user.

5. The method according to claim 4, wherein: Based on the recommendation value of each of the entry resources and the obtained scores of each of the entry resources, obtaining an updated score of each of the entry resources includes: For each of the entry resources, the value of the entry resource and the score of the entry resource are multiplied together to obtain an updated score of the entry resource.

6. A method for training an entry resource value assessment model, comprising: Generate a training data set, wherein the training data set includes characteristics of a training user, characteristics of two training entry resources, and a true magnitude relationship between the values ​​of the two training entry resources; Based on the training data set, using an entry resource value assessment model, predicting a predicted magnitude relationship between the values ​​of the two training entry resources; Based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, the parameters of the entry resource value assessment model are adjusted.

7. The method according to claim 6, wherein: Generate a training data set, including: constructing features of the training user based on the historical consumption information of the training user; Based on the historical consumption information of the training user, construct the characteristics and consumption information of the two training entry resources; Based on the consumption information of the two training entry resources, the actual size relationship of the values ​​of the two training entry resources is configured.

8. The method according to claim 7, wherein: Based on the historical consumption information of the training user, constructing the characteristics of the training user includes: Based on the historical consumption information of the training user, collecting at least one of the attribute characteristics of the training user and the historical consumption characteristics of the user; The attribute characteristics of the training user include at least one of the user's basic attribute characteristics and the user's preference characteristics; the historical consumption characteristics of the training 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 training user consumed the corresponding entry resource characteristics, the click rate of entry resources of various genres, and the comprehensive consumption time of entry resources of various genres.

9. The method according to claim 7, wherein: Based on the historical consumption information of the training user, the features of the two training entry resources are constructed, including: Collecting at least one of the length, title, label, genre, and acquired score of each of the two training entry resources from the historical consumption information of the training user; When the genre of the training entry resource is a video resource, the length of the training entry resource refers to the duration of the video; when the genre of the training entry resource is a graphic resource, the length of the training entry resource refers to the length of the text and the number of pictures included in the training entry resource; The label of the training entry resource is used to indicate the category of the content of the entry resource.

10. The method according to claim 7, wherein: Based on the consumption information of the two training entry resources, configure the actual size relationship of the values ​​of the two training entry resources, including: Based on the consumption time of each of the two training entry resources consumed by the training user, the value of the training entry resource with a longer consumption time is configured to be greater than the value of the training entry resource with a shorter consumption time; Based on the consumption step length of each of the two training entry resources consumed by the training user, configuring the value of the training entry resource with a larger consumption step length to be greater than the value of the training entry resource with a smaller consumption step length; Based on the click information of each of the two training entry resources consumed by the training user, configure the value of the training entry resource clicked by the training user to be greater than the value of the training entry resource not clicked by the training user; or Based on the sliding information after the training user clicks on each of the two training entry resources, the value of the training entry resource with sliding after the training user clicks is configured to be greater than the value of the training entry resource without sliding after the training user clicks.

11. The method according to any one of claims 6 to 10, wherein: Based on the training data set, using an entry resource value assessment model, predicting the predicted magnitude relationship of the values ​​of the two training entry resources includes: Based on the characteristics of the training user and the characteristics of each training entry resource, the entry resource value evaluation model is used to predict the value of each training entry resource; Based on the value of each of the two training entry resources, a predicted magnitude relationship between the values ​​of the two training entry resources is obtained.

12. The method according to any one of claims 6 to 10, wherein: Based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, the parameters of the entry resource value assessment model are adjusted, including: Detecting whether the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent; In response to the inconsistency between the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, the parameters of the entry resource value assessment model are adjusted so that the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent.

13. A device for recommending entry resources, comprising: An acquisition module, used to acquire the characteristics of the user and the characteristics of each entry resource to be recommended; An evaluation module, configured to evaluate the value of each entry resource using a pre-trained entry resource value evaluation model based on the characteristics of the user and the characteristics of each entry resource; The recommendation module is used to recommend at least one entry resource to the user based on the value of each entry resource.

14. The device according to claim 13, wherein: The acquisition module is used to: Acquire at least one of the attribute characteristics of the user and the historical consumption characteristics of the user; The user's attribute characteristics include at least one of the user's basic attribute characteristics and the user's preference characteristics; the user's historical consumption characteristics include at least one of the user's consumption proportion of portal resources of various genres, the click rate of portal resources of various genres, and the comprehensive consumption time of portal resources of various genres in multiple historical time periods before the current period.

15. The device according to claim 13, wherein: The acquisition module is used to: Obtaining at least one of the length, title, tag, genre, and obtained score of each of the entry resources; When the genre of the entry resource is a video resource, the length of the entry resource refers to the duration of the video; when the genre of the entry resource is a graphic resource, the length of the entry resource refers to the length of the text included in the entry resource and the number of pictures included; The label of the entry resource is used to indicate the category of the content of the entry resource.

16. The device according to any one of claims 13 to 15, wherein: The recommendation module includes: An updating unit, configured to obtain an updated score of each of the entry resources based on the value of each of the entry resources and the obtained score of each of the entry resources; A recommendation unit is used to recommend at least one entry resource to the user based on the updated score of each entry resource.

17. The device according to claim 16, wherein: The updating unit is used for: For each of the entry resources, the value of the entry resource and the score of the entry resource are multiplied together to obtain an updated score of the entry resource.

18. A training device for an entry resource value assessment model, comprising: A generating module, used to generate a training data set, wherein the training data set includes the characteristics of the training user, the characteristics of the two training entry resources, and the true size relationship of the values ​​of the two training entry resources; A prediction module, configured to predict the predicted magnitude relationship of the values ​​of the two training entry resources based on the training data group and using an entry resource value evaluation model; The adjustment module is used to adjust the parameters of the entry resource value assessment model based on the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources.

19. The device according to claim 18, wherein: The generating module is used for: constructing features of the training user based on the historical consumption information of the training user; Based on the historical consumption information of the training user, construct the characteristics and consumption information of the two training entry resources; Based on the consumption information of the two training entry resources, the actual size relationship of the values ​​of the two training entry resources is configured.

20. The device according to claim 19, wherein The generating module is used for: Based on the historical consumption information of the training user, collecting at least one of the attribute characteristics of the training user and the historical consumption characteristics of the user; The attribute characteristics of the training user include at least one of the user's basic attribute characteristics and the user's preference characteristics; the historical consumption characteristics of the training 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 training user consumed the corresponding entry resource characteristics, the click rate of entry resources of various genres, and the comprehensive consumption time of entry resources of various genres.

21. The device according to claim 19, wherein The generating module is used for: Collecting at least one of the length, title, label, genre, and acquired score of each of the two training entry resources from the historical consumption information of the training user; When the genre of the training entry resource is a video resource, the length of the training entry resource refers to the duration of the video; when the genre of the training entry resource is a graphic resource, the length of the training entry resource refers to the length of the text and the number of pictures included in the training entry resource; The label of the training entry resource is used to indicate the category of the content of the entry resource.

22. The device according to claim 19, wherein The generating module is used for: Based on the consumption time of each of the two training entry resources consumed by the training user, the value of the training entry resource with a longer consumption time is configured to be greater than the value of the training entry resource with a shorter consumption time; Based on the consumption step length of each of the two training entry resources consumed by the training user, configuring the value of the training entry resource with a larger consumption step length to be greater than the value of the training entry resource with a smaller consumption step length; Based on the click information of each of the two training entry resources consumed by the training user, the value of the training entry resource clicked by the training user is configured to be greater than the value of the training entry resource not clicked by the training user; or Based on the sliding information after the training user clicks on each of the two training entry resources, the value of the training entry resource with sliding after the training user clicks is configured to be greater than the value of the training entry resource without sliding after the training user clicks.

23. The device according to any one of claims 18 to 22, wherein: The prediction module comprises: A prediction unit, configured to predict the value of each of the training entry resources by using the entry resource value evaluation model based on the characteristics of the training user and the characteristics of each of the training entry resources; The acquiring unit is used to acquire the predicted size relationship between the values ​​of the two training entry resources based on the value of each of the two training entry resources.

24. The device according to any one of claims 18 to 22, wherein: The adjustment module comprises: A detection unit, used to detect whether the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources are consistent; The adjustment unit is used to adjust the parameters of the entry resource value assessment model in response to the inconsistency between the predicted size relationship and the actual size relationship of the values ​​of the two training entry resources, so that the predicted size relationship of the values ​​of the two training entry resources is consistent with the actual size relationship.

25. 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 of any one of claims 1-5 or 6-12.

26. 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 1-5 or 6-12.

27. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1-5, or 6-12.

Images