Training method, device, equipment and storage medium for satisfaction prediction model
By adjusting the parameters of the training data group and the satisfaction prediction model, combined with the genre resource allocation model and the ES algorithm, the problems of single genre and low efficiency in immersive resource recommendation are solved, and the diversity and accuracy of resource recommendation are improved.
Patent Information
- Application Number
- CN202411320870.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-10-03
- Estimated Expiration
- 2044-09-20
AI Technical Summary
Existing technologies have difficulty in effectively enriching resource recommendation genres in immersive resource recommendation, and the recommendation efficiency and accuracy are insufficient.
By configuring the training data group, including the characteristics of training users and resources, the satisfaction prediction model is used to predict the user's satisfaction value for the resources, and the model parameters are adjusted based on the relationship between the predicted satisfaction value and the actual satisfaction. Combined with the pre-trained genre resource allocation model and ES algorithm, the sorting and allocation of resources are optimized.
The richness of resource recommendation genres and the improvement of recommendation efficiency in immersive resource recommendation are achieved, and the accuracy of resource recommendation and user satisfaction prediction are improved.
Smart Images

Figure CN119741078B_ABST
Abstract
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 more particularly to a training method, apparatus, device, and storage medium for a satisfaction prediction model. 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 various resource recommendation scenarios represented by immersive recommendation, resources can be sorted by content popularity and other factors to achieve resource recommendation. Summary of the Invention
[0004] The present disclosure provides a training method, apparatus, device and storage medium for a satisfaction prediction model.
[0005] According to one aspect of the present disclosure, a method for training a satisfaction prediction model is provided, comprising:
[0006] A training data set is configured, wherein the training data set includes characteristics of a training user, characteristics of two training resources, and a true satisfaction relationship between the training user and the two training resources; wherein the true satisfaction relationship is greater than or less than;
[0007] Based on the characteristics of the training user and the characteristics of the two training resources in the training data group, using a satisfaction prediction model to predict the training user's predicted satisfaction values for the two training resources respectively;
[0008] Based on the predicted satisfaction values of the training users for the two training resources and the actual satisfaction relationship of the training users for the two training resources, parameters of the satisfaction prediction model are adjusted.
[0009] According to another aspect of the present disclosure, a method for estimating resource satisfaction is provided, comprising:
[0010] Get user characteristics;
[0011] Get the characteristics of the resource;
[0012] Based on the characteristics of the user and the characteristics of the resource, a pre-trained satisfaction prediction model is used to predict the user's satisfaction value with the resource.
[0013] According to another aspect of the present disclosure, a training device for a satisfaction prediction model is provided, comprising:
[0014] a configuration module configured to configure a training data set, wherein the training data set includes characteristics of a training user, characteristics of two training resources, and a true satisfaction relationship between the training user and the two training resources; wherein the true satisfaction relationship is greater than or less than;
[0015] A prediction module, configured to predict the training user's predicted satisfaction values for the two training resources based on the characteristics of the training user and the characteristics of the two training resources in the training data group and using a satisfaction prediction model;
[0016] The adjustment module is used to adjust parameters of the satisfaction estimation model based on the predicted satisfaction value of the training user for the two training resources and the actual satisfaction relationship between the training user and the two training resources.
[0017] According to another aspect of the present disclosure, a device for estimating satisfaction of electric resources is provided, comprising:
[0018] Acquisition module, used to obtain user characteristics;
[0019] The acquisition module is used to acquire the characteristics of the resource;
[0020] The estimation module is used to predict the user's satisfaction value with the resource based on the characteristics of the user and the characteristics of the resource using a pre-trained satisfaction estimation model.
[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, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method of the aspect and any possible implementation manner described above.
[0027] According to the technology disclosed in the present invention, the satisfaction prediction model can be effectively trained, thereby accurately and efficiently realizing the satisfaction prediction of resources.
[0028] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The accompanying drawings are provided to facilitate a better understanding of the present invention 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 This is an architectural diagram of a resource recommendation device provided by an embodiment of the present disclosure.
[0033] Figure 4 is a schematic diagram according to a third embodiment of the present disclosure;
[0034] Figure 5 is a schematic diagram according to a fourth embodiment of the present disclosure;
[0035] Figure 6 is a schematic diagram according to a fifth embodiment of the present disclosure;
[0036] Figure 7 is a schematic diagram according to a sixth embodiment of the present disclosure;
[0037] Figure 8 is a schematic diagram according to a seventh embodiment of the present disclosure;
[0038] Figure 9 is a schematic diagram according to an eighth embodiment of the present disclosure;
[0039] Figure 10 is a schematic diagram according to a ninth embodiment of the present disclosure;
[0040] Figure 11 is a block diagram of an electronic device for implementing the method according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0041] 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.
[0042] 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.
[0043] 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.
[0044] 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.
[0045] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; Figure 1 As shown, this embodiment provides a resource recommendation method, which is applied to an immersive resource recommendation scenario and may specifically include the following steps:
[0046] S101. Recall resources of various genres based on a user's request, and obtain recall results of resources of various genres.
[0047] The resource recommendation method of this embodiment may be implemented by a resource recommendation device, which may be an electronic entity or a software-integrated application for providing immersive resource recommendations to users. The resource recommendation device may be applied in a resource recommendation system.
[0048] The immersive resource recommendation of this embodiment means that the user does not have specific request content, and the resource recommendation device autonomously recommends resources to the user continuously. For the user, only needing to slide the screen up and down, they can continuously consume different resources and achieve an immersive experience.
[0049] The genre of the resource in this embodiment may refer to the style of the resource or the format of the resource.
[0050] In this embodiment, when a user clicks on an entry resource to enter an immersive recommendation scenario, it can be considered that the user has initiated a resource request; or when the user consumes the next resource by sliding down in the immersive resource recommendation scenario, if the user has consumed a preset proportion of the resources among the currently recommended multiple resources, if he slides up again, it can also be considered that the user has initiated a resource request.
[0051] Since the technical solution of this embodiment is applied in an immersive resource recommendation scenario, the user's request may be an implicit request that does not include any specific request content or request limiting conditions.
[0052] S102: sorting multiple resources of corresponding genres based on the recall results of resources of various genres to obtain a first sorting result of the resources of various genres;
[0053] Specifically, the resource sorting in step 102 is to sort multiple resources within each genre. The multiple resources here can be only some of the relatively high-quality resources in the resource recall results for the genre. After processing in this step, each genre's resources can obtain a first sorting result.
[0054] S103. Based on a pre-trained genre resource allocation model, configure the proportion of various genre resources;
[0055] The genre resource allocation model of this embodiment can reasonably and accurately configure the proportion of various genre resources, and can cater to the personalized needs of users, so that immersive resources can be recommended to users in a more targeted manner in the future, effectively improving the effect of immersive resource recommendations.
[0056] S104: Based on the proportions of resources of various genres and the first ranking results of the resources of various genres, comprehensively ranking a preset number of resources of various genres to obtain a second ranking result;
[0057] The sorting in step S102 is to sort the resources of various genres separately, which is convenient for screening out high-quality resources from the resources of various genres. The difference is that the sorting in step S104 is a comprehensive sorting of resources of various genres mixed together, which is convenient for subsequent screening of several resources to be recommended.
[0058] S105: Based on the second ranking result, push several resources to the user's client in an immersive resource recommendation manner.
[0059] The number of resources in this embodiment can be the first number of resources in the second sorting result. The number of resources can be set based on demand, for example, 6, 8 or other numbers, which are not limited here.
[0060] The resource recommendation method of this embodiment, through the aforementioned steps, can recommend resources of multiple genres together. This effectively addresses the existing immersive resource recommendation scenarios that only recommend video resources, effectively enriching the resource recommendation genres and improving resource recommendation efficiency. Furthermore, this embodiment allows for configuring the proportion of resources of various genres before making recommendations, effectively optimizing the content of resource recommendations, effectively improving the accuracy of resource recommendations, and thus enhancing resource recommendation efficiency.
[0061] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure; the resource recommendation method of 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 resource recommendation method of this embodiment may specifically include the following steps:
[0062] S201: Recall resources of various genres based on user requests to obtain recall results of resources of various genres;
[0063] In this embodiment, to improve the matching degree between the recalled resources and the user, when recalling resources of various genres, the recall can be based on the user's information. This user information can include user attributes, such as the user's age, gender, occupation, etc. Furthermore, the user information can also include the user's interests and hobbies, such as finance, entertainment, sports, etc. The user's interests and hobbies can be identified in the user's attribute information in the form of tags.
[0064] Further optionally, in an embodiment of the present disclosure, when recalling resources of various genres, the popularity of each resource may also be referred to, and resources with high popularity may be recalled preferentially.
[0065] Further optionally, in one embodiment of the present disclosure, if a user is a new user and enters the immersive recommendation scene for the first time, the resource recommendation device can recall resources of various genres according to the popularity of each resource based on the user's request to obtain recall results of resources of various genres.
[0066] It should be noted that the above-mentioned resource recall rules are examples in the embodiments of the present disclosure. In actual applications, other rules can also be used to recall resources, such as based on the distance between the location information published by the resource and the user's location, giving priority to recalling resources whose published location is close to the user's location, etc., and no further examples will be given here.
[0067] The technical solution of this embodiment can be applied to the mixed recommendation of resources of various genres in an immersive recommendation scenario. The various genres in this embodiment may include videos and graphics; wherein the videos may include short videos and / or small videos; wherein the playback time of the small videos is less than the playback time of the short videos. 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.
[0068] S202: Obtain a plurality of resources ranked top from the recall results of resources of various genres;
[0069] In actual applications, the number of resources included in the resource recall results for various genres is very large. To improve the efficiency of resource recommendation, the recalled resources of various genres can be preliminarily sorted. This sorting can be called coarse sorting. The specific sorting mechanism and sorting method can refer to the coarse sorting in existing resource recommendation architectures and will not be described in detail here. In this embodiment, step S202 can select multiple resources with the highest ranking based on the results of the coarse sorting.
[0070] S203: For each resource in the plurality of resources of each genre, obtain resource characteristics and user characteristics;
[0071] In this embodiment, the characteristics of the resource may include at least one of the length of the resource, the identifier of the resource, the tag of the resource, the genre of the resource, the entry genre of the resource, and the estimated effect characteristics of the resource.
[0072] 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.
[0073] 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 the genre of the entry resource of the resource as video or graphic.
[0074] The estimated effect characteristics of the resource in this embodiment may include at least one of the estimated playback time, estimated like value, estimated attention value, estimated forwarding value, estimated completion rate and estimated delayed value of the user for the resource.
[0075] 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.
[0076] The user characteristics of this embodiment may include at least one of the user's attribute characteristics and the user's historical consumption characteristics.
[0077] User attributes may include at least one of basic attributes and preferences. Basic attributes include age, gender, and occupation. Preferences include interests and hobbies. These preferences 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 has a certain correlation 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, etc.
[0078] The historical consumption characteristics of the user may 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 value will be higher. Conversely, 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 value 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 value will be higher. Conversely, 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 value will be lower.
[0079] 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.
[0080] 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 value for the resource can be improved.
[0081] In specific implementation, for each estimated effect feature, a corresponding estimation model can be pre-trained. When in use, at least one of the above-mentioned resource features, user features, scene features, and resource entry genre features can be input into the estimation model, and the estimation model can predict and output the corresponding estimated effect. In this way, the user's estimated playback time, estimated like value, estimated attention value, estimated forwarding value, estimated completion rate, and estimated delayed value of the resource can be estimated. Each feature can be represented by a numerical value, for example, the numerical value can be a value between 0 and 1. The higher the numerical value, the greater the probability of the corresponding effect.
[0082] S204: For each resource in the plurality of resources of each genre, based on the resource characteristics and user characteristics, a pre-trained satisfaction prediction model is used to predict the resource satisfaction value;
[0083] For each resource, the resource's characteristics and user characteristics are input into a satisfaction prediction model. This 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.
[0084] 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 value predicted by the satisfaction prediction model.
[0085] S205: sorting multiple resources of each genre based on the satisfaction value of each resource to obtain a first sorting result of the resources of each genre;
[0086] For example, the specific implementation of step S205 may include the following steps:
[0087] (a1) For each resource in the plurality of resources of each genre, multiply the satisfaction value of the resource by the score of the acquired resource to obtain the updated score of the resource;
[0088] (b1) Sorting each of the plurality of resources of each genre based on the updated score of the resource to obtain a first ranking result of the resources of each genre.
[0089] In this embodiment, the obtained resource scores may refer to the scores corresponding to the coarse ranking of the recalled resources after the resources are recalled. The specific acquisition method may refer to the relevant schemes of the coarse and fine ranking layer of the resource recommendation device, which is not limited here.
[0090] In this embodiment, by estimating the satisfaction value of each resource, the resources can be sorted more accurately, thereby effectively improving the accuracy and efficiency of subsequent resource recommendations.
[0091] Steps S202-S205 are as above Figure 1 This is a specific implementation of step S102 of the embodiment shown. By this method, resources of various genres can be sorted more reasonably, accurately and effectively.
[0092] S206: Obtain user attribute characteristics, resource candidate set characteristics, and user behavior characteristics;
[0093] S207: Based on the user's attribute characteristics, the resource candidate set characteristics, and the user's behavior characteristics, a genre resource allocation model is used to predict the proportion of resources of various genres among the multiple resources recommended to the user based on the resource candidate set;
[0094] The user characteristics in this step may also include at least one of the user's attribute characteristics and the user's historical consumption characteristics. For details, please refer to the above-mentioned related records and will not be repeated here.
[0095] The resource candidate set features of this embodiment include features of a plurality of top-ranked resources obtained from the first ranking results of resources of various genres.
[0096] In this embodiment, during the specific implementation, the number of resource candidate sets can be pre-configured, such as 400. In order to enrich the resource genres in the resource candidate set, it is necessary to select some top-ranked resources from the first ranking results of resources of various genres. For example, if the multi-genre resources include small videos, short videos, dynamic graphics and text graphics, the top 100 resources of each genre can be selected. Alternatively, a lower limit can be set for each genre, such as a minimum of 50, and the remaining number can be supplemented by resources of other genres. Regardless of the method used, as long as the resource candidate set is guaranteed to include genres of various resources, the number of which reaches the number of resource candidate sets.
[0097] The resource candidate set features include feature expressions of multiple resources; the feature expression of each resource is obtained by vector expression and pooling operation based on at least one of the resource title, resource tag, resource genre, and resource length; and also includes the average feature expression of the resource candidate set.
[0098] User behavior characteristics include user's historical consumption characteristics, user's satisfaction sequence characteristics and / or user's resource consumption scenario characteristics;
[0099] The historical consumption characteristics of the user include at least one of the consumption ratio of the user's consumption of resources of various genres, the duration of consumption of resources of various genres, and the completion rate of resources of various genres in multiple historical time periods before the current time period;
[0100] The user satisfaction sequence feature includes the characteristic expressions of multiple resources that the user was most satisfied with during a preset time period before the current time period. The specific number of resources included can be set based on needs or experience, for example, 10 or 20, and is not limited here. The characteristic expressions of the resources are obtained in the same way as the characteristic expressions of the resources in the resource candidate set features described above.
[0101] Steps S206-S207 are as above Figure 1 This is a specific implementation of step S103 of the embodiment shown. By this method, the proportion of resources of various genres can be accurately predicted, so that resource recommendations can be made more targeted later, thereby effectively improving the accuracy and efficiency of resource recommendations.
[0102] S208. Obtain a second preset number of resources ranked top from the first ranking result of the resources of various genres according to the proportion of the resources of various genres; the second preset number of resources includes resources of various genres;
[0103] S209: Comprehensively sort the second preset number of resources to obtain the second sorting result;
[0104] Specifically, for resources of various genres, the second preset number can be multiplied by the proportion of resources of that genre to obtain the number of resources of that genre. Then, from the first sorted results of resources of that genre, a corresponding number of resources are selected in order from front to back. In this way, a total of the second preset number of resources can be obtained, providing effective resource support for subsequent immersive resource recommendations.
[0105] Further optionally, when step S209 of this embodiment is specifically implemented, the following steps may be included:
[0106] (a2) for each resource in the second preset number of resources, obtaining at least one of a score of the obtained resource, a contextual relevance factor between the resource and a previously recommended resource, a quality value of the resource, an estimated effect characteristic of the resource, an estimated decline rate, and an estimated exit rate;
[0107] The contextual relevance factor between the current resource and the previous recommended resource can be calculated using a pre-trained relevance factor prediction model. During the specific calculation, the feature expression of the current resource and the feature expression of the previous resource are input into the relevance factor prediction model. The model can predict and output the contextual relevance factor between the current resource and the previous recommended resource.
[0108] The obtained resource score may refer to the score updated in step S205.
[0109] The quality value of a resource can be used to comprehensively characterize the quality of the resource, and can be obtained by evaluating using a quality assessment strategy or a quality assessment model.
[0110] The estimated effect characteristics of resources can be referred to the relevant records of the above embodiments and will not be repeated here.
[0111] The estimated swiping rate and estimated exit rate of a resource are used to predict the probability that a user will scroll down and consume the next resource after clicking on the current resource, as well as the probability that the user will exit the current resource after clicking on it. These respectively represent the user's preference for the current resource and the resulting delayed perception.
[0112] Specifically, the estimated decline rate and estimated exit rate of a resource can also be predicted using a pre-trained prediction model, referring to the method for obtaining the estimated effect characteristics of the resource. When making specific predictions, accurate predictions can be made based on user characteristics and resource characteristics.
[0113] (b2) Based on the Evolution Strategies (ES) algorithm, the weight factors of each feature are obtained; different genres of resources have different weight factors;
[0114] Specifically, the ES algorithm is used to optimize and find the optimal weight factor for each feature. For details, please refer to the implementation principle of the ES algorithm.
[0115] Resources of different genres have different focuses on the features considered. In order to improve accuracy, different weighting factors are sought for resources of different genres.
[0116] (c2) Based on the weight factors of each feature, as well as the scores of each resource, the contextual relevance factors of each resource, the quality values of each resource, the estimated effect characteristics of each resource, the estimated decline rate and the estimated exit rate, a second preset number of resources are fused and sorted to obtain a second sorting result.
[0117] For example, in a specific implementation, for each resource in the second preset number of resources, the resource score, the resource context relevance factor, the resource quality value, the estimated effect characteristics of each resource, the estimated decline rate and the estimated exit rate can be multiplied by the weight factor of the corresponding feature respectively as the comprehensive score of the resource; then, based on the comprehensive score of each resource, the second preset number of resources are fused and sorted to obtain the second sorting result.
[0118] Similarly, when fusion sorting is performed, the more features are referenced, the higher the accuracy of the sorting is. Preferably, when fusion sorting is performed, all features including the score of the above-mentioned resources, the contextual relevance factor of the resources, the quality value of the resources, the estimated effect characteristics of the resources, the estimated decline rate and the estimated exit rate are referred to.
[0119] Steps S208-S209 are as above Figure 1 This is a specific implementation of step S104 of the embodiment shown. By this method, the weight factor of each feature of each resource can be accurately obtained, and the second preset number of resources can be sorted more reasonably and accurately.
[0120] S210: Obtain several resources ranked top from the second sorting result;
[0121] S211. Push several resources to the user's client in an immersive resource recommendation manner.
[0122] In this embodiment, since the second sorting result is a comprehensive sorting of resources of multiple genres, the genres of the multiple resources pushed to the user can be the same or different, which can effectively enrich the types of resources recommended in the immersive resource recommendation scenario.
[0123] 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.
[0124] The resource recommendation method of this embodiment uses the example of recommending multiple resources in a single request. In actual applications, if a user consumes a preset ratio of resources in an immersive recommendation scenario and then continues to consume resources, a next request will be triggered. The resource recommendation device will continue to recommend resources to the user according to the resource recommendation method of this embodiment. However, the user will not be aware of this and will only experience the immersive resource consumption.
[0125] Figure 3This is an architectural diagram of a resource recommendation device provided by an embodiment of the present disclosure, which may specifically include a recall layer, a coarse and fine ranking layer, a resource proportion configuration layer, and a reordering layer. Specifically, the solution of the above-mentioned step S201 of this embodiment can be performed in the recall layer of the resource recommendation device. The solution of steps S202-S205 can be performed in the coarse and fine ranking layer of the resource recommendation device. The solution of steps S208-S209 can be performed in the reordering layer of the resource recommendation device. Steps S206-S207 can be considered as predicting the proportion of various genre resources based on the resources of the coarse and fine ranking layer, thereby effectively providing data support for the resources of the reordering layer, and specifically can be performed in the resource proportion configuration layer. Finally, based on the sorting result of the reordering layer, that is, the second sorting result, several resources with the highest sorting can be selected to push resources to the user.
[0126] The resource recommendation method of this embodiment, by adopting the above technical solution, can effectively enrich the genres of resource recommendations in immersive recommendation scenarios.
[0127] Furthermore, in this embodiment, at the coarse-fine ranking layer, a pre-trained satisfaction model can be used to predict the satisfaction of each resource, so that resources of each genre can be accurately ranked within each genre.
[0128] Furthermore, in this embodiment, a pre-trained genre resource allocation model can be used to accurately predict the proportion of various genre resources, which can improve the funnel efficiency of the resource allocation stage, provide more accurate resources to the downstream, and effectively improve the efficiency of resource recommendation.
[0129] Furthermore, in this embodiment, at the re-ranking layer, the ES algorithm can be used to find the optimal feature weight factor, thereby more reasonably and accurately calculating the score of each resource, and further more reasonably and accurately ranking the resources of each genre.
[0130] Figure 4 is a schematic diagram according to the third embodiment of the present disclosure; Figure 4 As shown, this embodiment provides a Figure 1 or Figure 2 The training method of the satisfaction prediction model in the illustrated embodiment may specifically include the following steps:
[0131] S401: Configuring a training data set, wherein the training data set includes characteristics of a training user, characteristics of two training resources, and the actual satisfaction relationship between the training user and the two training resources;
[0132] S402: Based on the characteristics of the training user and the characteristics of the two training resources in the training data set, using a satisfaction prediction model, respectively predict the training user's predicted satisfaction values for the two training resources;
[0133] S403: Adjust parameters of a satisfaction estimation model based on the predicted satisfaction values of the training users for the two training resources and the actual satisfaction relationship of the training users for the two training resources.
[0134] The execution subject of the training method of the satisfaction prediction model in this embodiment is the training device of the satisfaction prediction model.
[0135] During the training process of the satisfaction prediction model of this embodiment, training data sets are used to train the satisfaction prediction model. Specifically, each training data set includes the characteristics of a training user, the characteristics of two training resources, and the actual satisfaction relationship between the training user and the two training resources. Furthermore, within a training data set, the training user's satisfaction with the two training resources cannot be at the same level, so the actual satisfaction relationship cannot be equal; it must be greater than or less than.
[0136] During the training process, for each training resource, the characteristics of the training user and the training resource are input into a satisfaction prediction model. This model then predicts and outputs the training user's predicted satisfaction with the training resource. The predicted satisfaction value can be a number between 0 and 1, with larger values indicating higher satisfaction and smaller values indicating lower satisfaction.
[0137] In the training of this embodiment, only the actual satisfaction relationship of the training users with the two training resources is used for supervision, which can effectively learn the size relationship of the user's satisfaction with different resources, effectively reducing the training difficulty of the satisfaction prediction model and improving the training efficiency of the model.
[0138] The training method of the satisfaction prediction model of this embodiment configures a training data group and adjusts the parameters of the satisfaction prediction model based on the predicted satisfaction value of the training user for the two training resources and the actual satisfaction relationship between the training user and the two training resources, thereby making the prediction of the satisfaction prediction model more accurate.
[0139] Figure 5 is a schematic diagram according to a fourth embodiment of the present disclosure; Figure 5 As shown, the training method of the satisfaction prediction model of this embodiment is as follows: Figure 4 Based on the technical solutions of the illustrated embodiments, the technical solutions of the present disclosure are further described in more detail, which may specifically include the following steps:
[0140] S501. Collecting characteristics of a training user and consumption information of the training user from the user's historical consumption information;
[0141] S502: extracting information on two training resources with different consumption satisfaction levels from the training user's consumption information based on a pre-configured resource satisfaction strategy table;
[0142] S503: Based on the information of the two extracted training resources, obtain features of the two training resources;
[0143] S504: Based on the consumer satisfaction levels of the two training resources, configure a true satisfaction relationship between the two training resources;
[0144] For example, before step S502, it may also include: configuring a resource satisfaction strategy table, the resource satisfaction strategy table including an identification strategy for satisfactory consumption; an identification strategy for insensitive consumption; and an identification strategy for unsatisfactory consumption; the satisfaction level of intentional consumption is greater than the satisfaction level of insensitive consumption; the satisfaction level of insensitive consumption is greater than the satisfaction level of unsatisfactory consumption.
[0145] Optionally, in an embodiment of the present disclosure, configuring the resource satisfaction policy table may specifically include the following steps:
[0146] (a3) Based on the preset satisfaction behavior judgment conditions, configure the identification strategy of satisfied consumption and the identification strategy of indifferent consumption;
[0147] For example, if the user's consumption behavior meets the preset satisfaction behavior judgment conditions, the user's consumption level is determined to be a satisfied consumption level; if the user's consumption behavior does not meet the preset satisfaction behavior judgment conditions, the user's consumption level is determined to be an insensitive consumption level.
[0148] For example, satisfaction behavior judgment conditions may include: if the user's consumption time is greater than a first preset time or a preset time ratio, and if the user has at least one interactive behavior, the user is considered satisfied.
[0149] The first preset duration and the preset duration ratio can be set according to the actual scenario and are not limited here. For example, the duration can be 10 seconds, 15 seconds, or 20 seconds. The preset duration ratio can also be set to 60%, 70%, or 80% based on experience and is not limited here.
[0150] The user's interactive behavior may include at least one of liking, commenting, following, and sharing.
[0151] (b3) Based on the preset dissatisfaction behavior judgment conditions, configure the identification strategy of dissatisfied consumption.
[0152] In this embodiment, a separate preset dissatisfaction judgment condition is required. If this condition is met, the user's consumption level can be determined to be unsatisfactory. For example, the dissatisfaction judgment condition can be: if the consumption duration exceeds a second preset duration threshold, or the user logs out, the user is determined to be unsatisfied with the resource; the second preset duration threshold is less than the first preset duration threshold. For example, the second preset duration threshold can be 2 seconds, 3 seconds, or other time lengths.
[0153] The characteristics of the training user in this embodiment include: at least one of the attribute characteristics of the training user and the historical consumption characteristics of the training user;
[0154] The attribute characteristics of the training user include: at least one of the basic attribute characteristics of the training user and the preference characteristics of the training user; the historical consumption characteristics of the training user include at least one of the consumption ratio of resources of various genres consumed by the training user in multiple historical time periods before the consumption period of the corresponding training resource, the duration of consumption of resources of various genres, and the completion rate of resources of various genres;
[0155] The characteristics of the training resource include at least one of the length of the training resource, the identifier of the training resource, the label of the training resource, the genre of the training resource, the entry genre of the training resource, and the estimated effect characteristics of the training resource;
[0156] When the training resource is a video resource, the length of the training resource refers to the length of the video. When the training resource is a graphic resource, the length of the training resource refers to the length of the text and the number of images included.
[0157] The entry genre of the training resource refers to the genre of the entry resource of the training resource, and can identify the genre of the entry resource of the training resource as video or image and text;
[0158] The effect characteristics of the training resources include at least one of the playing time, likes, attention, forwarding, completion rate and delayed value of the training resources by the training users.
[0159] Steps S501-S504 are as above Figure 4 A specific implementation of step S401 of the illustrated embodiment.
[0160] S505: Based on the characteristics of the training user and the characteristics of the two training resources in the training data group, using a satisfaction prediction model, respectively predict the training user's predicted satisfaction values for the two training resources;
[0161] S506: Based on the predicted satisfaction values of the training user for the two training resources, obtain the predicted satisfaction relationship of the training user for the two training resources;
[0162] S507 : Adjust parameters of the satisfaction estimation model based on the predicted satisfaction relationship of the training user with the two training resources and the actual satisfaction relationship of the training user with the two training resources.
[0163] Specifically, it is detected whether the predicted satisfaction relationship of the training user with respect to the two training resources is consistent with the actual satisfaction relationship of the training user with respect to the two training resources. If not, the parameters of the satisfaction prediction model are adjusted so that the satisfaction prediction model can learn to predict the actual satisfaction relationship of the user with respect to the two training resources.
[0164] The training method of the satisfaction prediction model of this embodiment configures a training data group and adjusts the parameters of the satisfaction prediction model based on the predicted satisfaction value of the training user for the two training resources and the actual satisfaction relationship between the training user and the two training resources, thereby making the prediction of the satisfaction prediction model more accurate.
[0165] Figure 6 is a schematic diagram according to the fifth embodiment of the present disclosure; Figure 6 As shown, this embodiment provides a method for estimating resource satisfaction, which may specifically include the following steps:
[0166] S601, obtaining user characteristics;
[0167] S602, obtaining resource characteristics;
[0168] S603: Based on the characteristics of the user and the characteristics of the resource, a pre-trained satisfaction prediction model is used to predict the user's satisfaction value with the resource.
[0169] During specific use, the user's characteristics and resource characteristics are input into the satisfaction prediction model, and the satisfaction prediction model can predict and output the user's satisfaction value for the resource.
[0170] The resource satisfaction estimation method implemented in this paper can be used for the above Figure 4 or Figure 5 Application of the satisfaction prediction model trained in the embodiment shown. Specifically, the satisfaction prediction method of this embodiment can be applied to the above Figure 1 or Figure 2 The immersive resource recommendation scenario shown can also be applied to other resource recommendation scenarios.
[0171] The resource satisfaction estimation method of this embodiment can adopt a satisfaction estimation model to efficiently and accurately estimate the user's satisfaction value for a resource, thereby providing effective support for resource recommendation.
[0172] Further optionally, in the above Figure 6 Based on the technical solution of the embodiment shown, after step S603, the following steps may also be included:
[0173] In the recommendation of multiple resources, the multiple resources are ranked based on the satisfaction value of each resource.
[0174] For example, based on the satisfaction value of each resource and the obtained score of each resource, an updated score of each resource may be obtained; and then, based on the updated score of each resource, multiple resources may be sorted.
[0175] Specifically, the resource scores may be scores used by the resource recommendation apparatus when ranking resources in the coarse and fine ranking stages.
[0176] For example, for each resource, the resource satisfaction value and the resource score are multiplied together to obtain the updated score of the resource.
[0177] Alternatively, in actual applications, resources may be ranked and recommended directly based on the satisfaction value of each resource.
[0178] Further optionally, step S601 in the above embodiment, obtaining user characteristics, may specifically include:
[0179] Obtaining at least one of a user's attribute characteristics and a user's historical consumption characteristics;
[0180] 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 consumption proportion of various genres of resources consumed by the user in multiple historical time periods before the current period, the duration of consumption of various genres of resources, and the completion rate of various genres of resources.
[0181] Further optionally, in step S602 of the above embodiment, obtaining the characteristics of the resource includes:
[0182] Obtaining at least one of a length of a resource, an identifier of a resource, a tag of a resource, a genre of a resource, an entry genre of a resource, and an estimated effect feature of a resource;
[0183] When the resource type is video, the resource length refers to the duration of the video. When the resource type is graphic and text, the resource length refers to the length of the text and the number of images included in the resource.
[0184] The entry genre of a resource refers to the genre of the entry resource of the resource, and can identify the genre of the entry resource of the resource as video or graphic.
[0185] The estimated effect characteristics of a resource include at least one of the estimated user's playback time, likes, follows, reposts, completion rate, and delayed value of the resource.
[0186] In this embodiment, the characteristics of the user and the characteristics of the resource can also be referred to above for details. Figure 2 The relevant records in the illustrated embodiments are not repeated here.
[0187] Figure 7 is a schematic diagram according to the sixth embodiment of the present disclosure; Figure 6 As shown, this embodiment provides a resource recommendation device 700, which is applied to an immersive resource recommendation scenario, including:
[0188] The recall module 701 is used to recall resources of various genres based on user requests and obtain recall results of resources of various genres;
[0189] A first sorting module 702 is configured to sort multiple resources of corresponding genres based on the recall results of resources of various genres, and obtain a first sorting result of the resources of various genres;
[0190] A proportion configuration module 703 is used to configure the proportion of various genre resources based on a pre-trained genre resource allocation model;
[0191] A second sorting module 704 is configured to comprehensively sort a preset number of resources of various genres based on the proportions of the resources of various genres and the first sorting results of the resources of various genres to obtain a second sorting result;
[0192] The recommendation module 705 is configured to push a plurality of resources to the user's client in an immersive resource recommendation manner based on the second ranking result.
[0193] The resource recommendation device 700 of this embodiment implements the resource recommendation by adopting the above modules, and its implementation principle and technical effect 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.
[0194] Figure 8 is a schematic diagram according to the seventh embodiment of the present disclosure; Figure 8 As shown, this embodiment provides a resource recommendation device 800. Figure 7 Based on the technical solutions of the embodiments shown, the technical solutions of the present disclosure are further described in more detail. Figure 8 As shown, the resource recommendation device 800 of this embodiment includes the above Figure 7 Modules with the same name and function are shown as follows: recall module 801 , first sorting module 802 , proportion configuration module 803 , second sorting module 804 and recommendation module 805 .
[0195] like Figure 8 As shown, in the resource recommendation device 800 of this embodiment, the first sorting module 802 includes:
[0196] The first resource acquisition unit 8021 is configured to acquire a plurality of resources ranked top from the recall results of resources of various genres;
[0197] A first feature acquisition unit 8022 is configured to acquire, for each resource in the plurality of resources of each genre, at least one of a resource feature, a user feature, a scene feature, an entry genre feature of the resource, and a resource estimated effect feature;
[0198] A first prediction unit 8023 is configured to predict, for each resource among the plurality of resources of each genre, a satisfaction value of the resource using a pre-trained satisfaction prediction model based on the resource's characteristics and at least one of the user characteristics, the scenario characteristics, the resource's entry genre characteristics, and the resource's estimated effect characteristics;
[0199] The first sorting unit 8024 is configured to sort the multiple resources of each genre based on the satisfaction value of each resource, and obtain a first sorting result of the resources of each genre.
[0200] Further optionally, in one embodiment of the present disclosure, the first sorting unit 8024 is configured to:
[0201] For each resource in the plurality of resources of each genre, multiply the satisfaction value of the resource by the obtained score of the resource to obtain the updated score of the resource;
[0202] For each resource in the plurality of resources of each genre, sorting is performed based on the updated score of the resource to obtain a first sorting result of the resources of each genre.
[0203] Further optionally, in one embodiment of the present disclosure, the resource feature includes at least one of a length of the resource, an identifier of the resource, a tag of the resource, and a genre of the resource;
[0204] When the resource is a video resource, the length of the resource refers to the duration of the video; when the resource is a graphic resource, the length of the resource refers to the length of the text and the number of pictures included in the resource;
[0205] The user characteristics include: at least one of the user's attribute characteristics and the user's historical consumption characteristics; 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 resources of various genres, the duration of consumption of resources of various genres, and the completion rate of resources of various genres in multiple historical time periods before the current period;
[0206] The scene feature identifier currently belongs to a recommended scene or a discovered scene;
[0207] The resource entry genre feature refers to the genre feature of the resource entry resource, which can identify the genre of the resource entry resource as video or graphic;
[0208] The estimated effect characteristics of the resource include at least one of the estimated playback time, estimated like value, estimated attention value, estimated forwarding value, estimated completion rate and estimated delayed value of the user for the resource.
[0209] Further optionally, as Figure 8 As shown, in one embodiment of the present disclosure, the proportion configuration module 803 includes:
[0210] The second feature acquisition unit 8031 is used to acquire user attribute features, resource candidate set features, and user behavior features;
[0211] The second prediction unit 8032 is used to use a pre-trained genre resource allocation model to predict the proportion of various genre resources in the multiple resources recommended to the user based on the resource candidate set based on the user's attribute characteristics, the resource candidate set characteristics and the user behavior characteristics.
[0212] Further optionally, in an embodiment of the present disclosure, the resource candidate set features include feature expressions of a plurality of top-ranked resources obtained from the first ranking results of various genre resources;
[0213] The user's satisfaction sequence characteristics include characteristic expressions of multiple resources that the user is most satisfied with within a preset time period before the current period;
[0214] The ranking average value of the resource candidate set includes an average value of the obtained scores of the multiple resources included in the resource candidate set.
[0215] Further optionally, as Figure 8 As shown, in one embodiment of the present disclosure, the second sorting module 804 includes:
[0216] The second resource acquisition unit 8041 is configured to acquire, from the first sorting result of the resources of various genres, a second preset number of resources ranked top according to the proportion of the resources of various genres; the second preset number of resources includes resources of various genres;
[0217] The second sorting unit 8042 is configured to perform comprehensive sorting on the second preset number of resources to obtain the second sorting result.
[0218] Further optionally, in one embodiment of the present disclosure, the second sorting unit 8042 is configured to:
[0219] For each resource in the second preset number of resources, obtaining at least one of a score of the resource obtained, a contextual relevance factor between the resource and a previously recommended resource, a quality value of the resource, an estimated effect characteristic of the resource, an estimated decline rate, and an estimated exit rate;
[0220] Based on the evolutionary strategy algorithm, the weight factor of each feature is obtained; different genres of resources have different weight factors;
[0221] Based on the weight factors of each of the characteristics, as well as the scores of each of the resources, the context relevance factors of each of the resources, the quality values of each of the resources, the estimated effect characteristics of each of the resources, the estimated decline rate and at least one of the estimated exit rate, the second preset number of resources are fused and sorted to obtain the second sorting result.
[0222] Further optionally, in one embodiment of the present disclosure, the second sorting unit 8042 is configured to:
[0223] For each resource in the second preset number of resources, multiplying the score of the resource, the contextual relevance factor of the resource, the quality value of the resource, at least one of the estimated effect feature, the estimated decline rate, and the estimated exit rate of each resource by a weight factor of the corresponding feature to obtain a comprehensive score for the resource;
[0224] Based on the comprehensive score of each of the resources, the second preset number of resources are integrated and sorted to obtain the second sorting result.
[0225] Further optionally, as Figure 8 As shown, in one embodiment of the present disclosure, the recommendation module 805 includes:
[0226] The third resource acquisition unit 8051 is configured to acquire a number of resources ranked high from the second sorting result;
[0227] The push unit 8052 is configured to push a plurality of resources to the user's client in an immersive resource recommendation manner.
[0228] Further optionally, in one embodiment of the present disclosure, the various genres include videos and graphics; the videos include short videos and / or small videos; the graphics include dynamic graphics and / or text graphics.
[0229] The resource recommendation device 800 of this embodiment implements the resource recommendation by adopting the above modules, and its implementation principle and technical effect 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.
[0230] Figure 9 is a schematic diagram according to the eighth embodiment of the present disclosure; Figure 9 As shown, this embodiment provides a training device 900 for a satisfaction prediction model, including:
[0231] Configuration module 901 is used to configure a training data set, wherein the training data set includes characteristics of a training user, characteristics of two training resources, and a true satisfaction relationship between the training user and the two training resources; wherein the true satisfaction relationship is greater than or less than;
[0232] Prediction module 902, configured to predict the training user's predicted satisfaction values for the two training resources based on the characteristics of the training user and the characteristics of the two training resources in the training data set and using a satisfaction prediction model;
[0233] The adjustment module 903 is configured to adjust parameters of the satisfaction estimation model based on the predicted satisfaction values of the training users for the two training resources and the actual satisfaction relationship between the training users for the two training resources.
[0234] The training device 900 of the satisfaction prediction model of this embodiment realizes the implementation principle and technical effect of the training of the satisfaction prediction 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.
[0235] Further optionally, in the above Figure 9 Based on the technical solutions of the illustrated embodiments, in one embodiment of the present disclosure, the adjustment module 903 is configured to:
[0236] Based on the predicted satisfaction values of the training user for the two training resources, obtaining a predicted satisfaction relationship between the training user and the two training resources;
[0237] Based on the predicted satisfaction relationship of the training user with respect to the two training resources and the actual satisfaction relationship of the training user with respect to the two training resources, parameters of the satisfaction estimation model are adjusted.
[0238] Further optionally, in one embodiment of the present disclosure, the configuration module 901 is configured to:
[0239] Collecting the characteristics of the training user and the consumption information of the training user from the user's historical consumption information;
[0240] Based on a pre-configured resource satisfaction strategy table, extracting information of two training resources with different consumption satisfaction levels from the consumption information of the training user;
[0241] Based on the extracted information of the two training resources, obtaining features of the two training resources;
[0242] Based on the consumption satisfaction levels of the two training resources, the real satisfaction relationship between the two training resources is configured.
[0243] Further optionally, in one embodiment of the present disclosure, the configuration module 901 is further configured to:
[0244] The resource satisfaction strategy table is configured, and the resource satisfaction strategy table includes an identification strategy for satisfactory consumption; an identification strategy for unconscious consumption; and an identification strategy for unsatisfactory consumption; the satisfaction level of the intended consumption is greater than the satisfaction level of the unconscious consumption; the satisfaction level of the unconscious consumption is greater than the satisfaction level of the unsatisfactory consumption.
[0245] Further optionally, in one embodiment of the present disclosure, the configuration module 901 is configured to:
[0246] Based on the preset satisfaction behavior judgment conditions, configure the identification strategy of the satisfied consumption and the identification strategy of the insensitive consumption;
[0247] Based on the preset dissatisfaction behavior judgment conditions, the identification strategy of the dissatisfaction consumption is configured.
[0248] Further optionally, in one embodiment of the present disclosure, the characteristics of the training user include: at least one of the attribute characteristics of the training user and the historical consumption characteristics of the training user;
[0249] The attribute characteristics of the training user include: at least one of the basic attribute characteristics of the training user and the preference characteristics of the training user; the historical consumption characteristics of the training user include at least one of the consumption ratio of the training user's consumption of resources of various genres, the duration of consumption of resources of various genres, and the completion rate of resources of various genres in multiple historical time periods before the corresponding training resource consumption period;
[0250] Further optionally, in one embodiment of the present disclosure, the characteristics of the training resource include at least one of the length of the training resource, the identification of the training resource, the label of the training resource, the genre of the training resource, the entry genre of the training resource, and the effect characteristics of the training resource;
[0251] When the genre of the training resource is a video resource, the length of the training resource refers to the duration of the video; when the genre of the training resource is a graphic resource, the length of the training resource refers to the length of the text included in the resource and the number of pictures included;
[0252] The entry genre of the training resource refers to the genre of the entry resource of the training resource, which can identify the genre of the entry resource of the training resource as video or graphic;
[0253] The effect characteristics of the training resources include at least one of the playing time, likes, attention, forwarding, completion rate and delayed value of the training resources by the training users.
[0254] In the above embodiment, the implementation principle and technical effect of training the satisfaction prediction model by adopting the above module are the same as those 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.
[0255] Figure 10 is a schematic diagram according to the ninth embodiment of the present disclosure; Figure 10 As shown, this embodiment provides a resource satisfaction estimation device 1000, including:
[0256] Acquisition module 1001, used to acquire user characteristics;
[0257] Acquisition module 1001, used to obtain the characteristics of the resource;
[0258] The estimation module 1002 is configured to predict the user's satisfaction with the resource based on the user's characteristics and the resource's characteristics using a pre-trained satisfaction estimation model.
[0259] The resource satisfaction estimation device 1000 of this embodiment realizes resource satisfaction estimation by adopting the above modules, and its implementation principle and technical effect are the same as those 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.
[0260] Further optionally, in the above Figure 10 Based on the illustrated embodiment, in one embodiment of the present disclosure, the resource satisfaction estimation device 1000 further includes:
[0261] The ranking module is used to rank the multiple resources based on the satisfaction value of each resource in the recommendation of the multiple resources.
[0262] Further optionally, in one embodiment of the present disclosure, the sorting module is configured to:
[0263] Based on the satisfaction value of each resource and the obtained score of each resource, obtaining an updated score of each resource;
[0264] The plurality of resources are sorted based on the updated score of each of the resources.
[0265] Further optionally, in one embodiment of the present disclosure, the sorting module is configured to:
[0266] For each resource, the satisfaction value of the resource and the score of the resource are multiplied together to obtain an updated score of the resource.
[0267] Further optionally, in one embodiment of the present disclosure, the acquisition module 1001 is configured to:
[0268] Obtaining at least one of a user's attribute characteristics and a user's historical consumption characteristics;
[0269] 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 consumption proportion of various genres of resources consumed by the user in multiple historical time periods before the current period, the duration of consumption of various genres of resources, and the completion rate of various genres of resources.
[0270] Further optionally, in one embodiment of the present disclosure, the acquisition module 1001 is configured to:
[0271] Obtaining at least one of a length of a resource, an identifier of a resource, a tag of a resource, a genre of a resource, an entry genre of a resource, and an estimated effect feature of a resource;
[0272] When the resource is a video resource, the length of the resource refers to the duration of the video; when the resource is a graphic resource, the length of the resource refers to the length of the text and the number of pictures included in the resource;
[0273] The entry genre of the resource refers to the genre of the entry resource of the resource, which can identify the genre of the entry resource of the resource as video or graphic;
[0274] The estimated effect characteristics of the resource include at least one of the estimated user's playback time, likes, attention, forwarding, completion rate and delayed value of the resource.
[0275] In the above embodiment, the implementation principle and technical effect of training the satisfaction prediction model by adopting the above module are the same as those 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.
[0276] 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.
[0277] 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.
[0278] Figure 11A schematic block diagram of an example electronic device 1100 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.
[0279] like Figure 11 As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. Various programs and data required for the operation of the device 1100 can also be stored in the RAM 1103. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.
[0280] Various components in device 1100 are connected to I / O interface 1105, including an input unit 1106, such as a keyboard and mouse; an output unit 1107, such as various types of displays and speakers; a storage unit 1108, such as a magnetic disk and optical disk; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0281] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 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 1101 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 11011. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, 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 1101 may be configured to execute the above method of the present disclosure in any other appropriate manner (for example, by means of firmware).
[0282] 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.
[0283] 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.
[0284] 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.
[0285] 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).
[0286] 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.
[0287] 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.
[0288] 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.
[0289] 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 training method for a satisfaction prediction model, comprising: Collecting the characteristics of the training user and the consumption information of the training user from the user's historical consumption information; Based on the preset satisfaction behavior judgment conditions, configure the identification strategy of satisfied consumption and the identification strategy of indifferent consumption; Based on the preset dissatisfaction behavior judgment condition, an identification strategy for dissatisfaction consumption is configured to obtain a configured resource satisfaction strategy table, wherein the satisfaction level of the satisfactory consumption is greater than the satisfaction level of the insensitive consumption; and the satisfaction level of the insensitive consumption is greater than the satisfaction level of the dissatisfaction consumption; Extracting information of two training resources with different satisfaction levels from the consumption information of the training user based on the resource satisfaction strategy table; Based on the extracted information of the two training resources, obtaining features of the two training resources; Based on the satisfaction levels of the two training resources, configuring a true satisfaction relationship between the two training resources to obtain a configured training data set; the true satisfaction relationship is greater than or less than; Based on the characteristics of the training user and the characteristics of the two training resources in the training data group, using a satisfaction prediction model to predict the training user's predicted satisfaction values for the two training resources respectively; Based on the predicted satisfaction values of the training users for the two training resources and the actual satisfaction relationship of the training users for the two training resources, parameters of the satisfaction prediction model are adjusted.
2. The method according to claim 1, wherein Based on the predicted satisfaction values of the training users for the two training resources and the actual satisfaction relationship of the training users for the two training resources, the parameters of the satisfaction prediction model are adjusted, including: Based on the predicted satisfaction values of the training user for the two training resources, obtaining a predicted satisfaction relationship between the training user and the two training resources; Based on the predicted satisfaction relationship of the training user with respect to the two training resources and the actual satisfaction relationship of the training user with respect to the two training resources, parameters of the satisfaction estimation model are adjusted.
3. The method according to any one of claims 1-2, wherein: The characteristics of the training user include: at least one of the attribute characteristics of the training user and the historical consumption characteristics of the training user; The attribute characteristics of the training user include: at least one of the basic attribute characteristics of the training user and the preference characteristics of the training user; the historical consumption characteristics of the training user include at least one of the consumption proportion of resources of various genres consumed by the training user in multiple historical time periods before the corresponding training resource consumption period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres.
4. The method according to any one of claims 1-2, wherein: The characteristics of the training resource include at least one of the length of the training resource, the identifier of the training resource, the label of the training resource, the genre of the training resource, the entry genre of the training resource, and the effect characteristics of the training resource; When the genre of the training resource is a video resource, the length of the training resource refers to the duration of the video; when the genre of the training resource is a graphic resource, the length of the training resource refers to the length of the text included in the resource and the number of pictures included; The entry genre of the training resource refers to the genre of the entry resource of the training resource, which can identify the genre of the entry resource of the training resource as video or graphic; The effect characteristics of the training resources include at least one of the playing time, likes, attention, forwarding, completion rate and delayed value of the training resources by the training users.
5. A method for estimating resource satisfaction, comprising: Get user characteristics; Get the characteristics of the resource; Based on the characteristics of the user and the characteristics of the resource, a pre-trained satisfaction prediction model is used to predict the user's satisfaction value with the resource; the satisfaction prediction model is a satisfaction prediction model trained according to any one of claims 1-4 above.
6. The method according to claim 5, wherein: After predicting the user's satisfaction with the resource using a pre-trained satisfaction prediction model based on the user's characteristics and the resource's characteristics, the method further includes: In the recommendation of multiple resources, the multiple resources are ranked based on the satisfaction value of each resource.
7. The method according to claim 6, wherein: Sorting the plurality of resources based on the satisfaction value of each resource includes: Based on the satisfaction value of each resource and the obtained score of each resource, obtaining an updated score of each resource; The plurality of resources are sorted based on the updated score of each of the resources.
8. The method according to claim 7, wherein: Obtaining an updated score for each resource based on the satisfaction value of each resource and the obtained score for each resource includes: For each resource, the satisfaction value of the resource and the score of the resource are multiplied together to obtain an updated score of the resource.
9. The method according to any one of claims 5 to 8, wherein: Get user characteristics, including: Obtaining at least one of a user's attribute characteristics and a user's historical consumption characteristics; 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 consumption proportion of various genres of resources consumed by the user in multiple historical time periods before the current period, the duration of consumption of various genres of resources, and the completion rate of various genres of resources.
10. The method according to any one of claims 5 to 8, wherein: Get the characteristics of the resource, including: Obtaining at least one of a length of a resource, an identifier of a resource, a tag of a resource, a genre of a resource, an entry genre of a resource, and an estimated effect feature of a resource; When the resource is a video resource, the length of the resource refers to the duration of the video; when the resource is a graphic resource, the length of the resource refers to the length of the text and the number of pictures included in the resource; The estimated effect characteristics of the resource include at least one of the estimated user's playback time, likes, attention, forwarding, completion rate and delayed value of the resource.
11. A training device for a satisfaction prediction model, comprising: Configuration modules for: Collecting the characteristics of the training user and the consumption information of the training user from the user's historical consumption information; Based on the preset satisfaction behavior judgment conditions, configure the identification strategy of satisfied consumption and the identification strategy of indifferent consumption; Based on the preset dissatisfaction behavior judgment condition, an identification strategy for dissatisfaction consumption is configured to obtain a configured resource satisfaction strategy table, wherein the satisfaction level of the satisfactory consumption is greater than the satisfaction level of the insensitive consumption; and the satisfaction level of the insensitive consumption is greater than the satisfaction level of the dissatisfaction consumption; Extracting information of two training resources with different satisfaction levels from the consumption information of the training user based on the resource satisfaction strategy table; Based on the extracted information of the two training resources, obtaining features of the two training resources; Based on the satisfaction levels of the two training resources, configuring a true satisfaction relationship between the two training resources, and obtaining the configured training data group, the true satisfaction relationship being greater than or less than; A prediction module, configured to predict the training user's predicted satisfaction values for the two training resources based on the characteristics of the training user and the characteristics of the two training resources in the training data group and using a satisfaction prediction model; The adjustment module is used to adjust parameters of the satisfaction estimation model based on the predicted satisfaction value of the training user for the two training resources and the actual satisfaction relationship between the training user and the two training resources.
12. The device according to claim 11, wherein The configuration module is used to: Based on the preset satisfaction behavior judgment conditions, configure the identification strategy of the satisfied consumption and the identification strategy of the insensitive consumption; Based on the preset dissatisfaction behavior judgment conditions, the identification strategy of the dissatisfaction consumption is configured.
13. The device according to any one of claims 11-12, wherein: The characteristics of the training user include: at least one of the attribute characteristics of the training user and the historical consumption characteristics of the training user; The attribute characteristics of the training user include: at least one of the basic attribute characteristics of the training user and the preference characteristics of the training user; the historical consumption characteristics of the training user include at least one of the consumption proportion of resources of various genres consumed by the training user in multiple historical time periods before the corresponding training resource consumption period, the duration of consumption of resources of various genres, and the completion rate of resources of various genres.
14. The device according to any one of claims 11-12, wherein: The characteristics of the training resource include at least one of the length of the training resource, the identifier of the training resource, the label of the training resource, the genre of the training resource, the entry genre of the training resource, and the effect characteristics of the training resource; When the genre of the training resource is a video resource, the length of the training resource refers to the duration of the video; when the genre of the training resource is a graphic resource, the length of the training resource refers to the length of the text included in the resource and the number of pictures included; The entry genre of the training resource refers to the genre of the entry resource of the training resource, which can identify the genre of the entry resource of the training resource as video or graphic; The effect characteristics of the training resources include at least one of the playing time, likes, attention, forwarding, completion rate and delayed value of the training resources by the training users.
15. A resource satisfaction estimation device, comprising: Acquisition module, used to obtain user characteristics; The acquisition module is used to acquire the characteristics of the resource; An estimation module is used to predict the user's satisfaction value with the resource based on the characteristics of the user and the characteristics of the resource using a pre-trained satisfaction estimation model; the satisfaction estimation model is a satisfaction estimation model trained according to any one of claims 11-14 above.
16. The device according to claim 15, wherein The device further comprises: The ranking module is used to rank the multiple resources based on the satisfaction value of each resource in the recommendation of the multiple resources.
17. The device according to claim 16, wherein The sorting module is used to: Based on the satisfaction value of each resource and the obtained score of each resource, obtaining an updated score of each resource; The plurality of resources are sorted based on the updated score of each of the resources.
18. The device according to claim 17, wherein The sorting module is used to: For each resource, the satisfaction value of the resource and the score of the resource are multiplied together to obtain an updated score of the resource.
19. The device according to any one of claims 15 to 18, wherein: The acquisition module is used to: Obtaining at least one of a user's attribute characteristics and a user's historical consumption characteristics; 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 consumption proportion of various genres of resources consumed by the user in multiple historical time periods before the current period, the duration of consumption of various genres of resources, and the completion rate of various genres of resources.
20. The device according to any one of claims 15 to 18, wherein: The acquisition module is used to: Obtaining at least one of a length of a resource, an identifier of a resource, a tag of a resource, a genre of a resource, an entry genre of a resource, and an estimated effect feature of a resource; When the resource is a video resource, the length of the resource refers to the duration of the video; when the resource is a graphic resource, the length of the resource refers to the length of the text and the number of pictures included in the resource; The estimated effect characteristics of the resource include at least one of the estimated user's playback time, likes, attention, forwarding, completion rate and delayed value of the resource.
21. 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 4 or 5 to 10.
22. 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 1-4 or 5-10.
23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1-4 or 5-10.
Citation Information
Patent Citations
Man-machine chat experience evaluation system
CN111985751A
Resource recommendation and prediction model acquisition method and device, electronic equipment and medium
CN116450940A