Video material recommendation method, device, storage medium and electronic device
By calculating the evaluation parameters and cycles of the target users for the material, calculating the target score, and pushing the target recommended materials, the problem of lack of time correlation of recommendation methods in the existing technology is solved, and a more accurate video material recommendation effect is achieved.
Patent Information
- Application Number
- CN202411307368.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-19
AI Technical Summary
The existing video material recommendation methods lack time correlation and cannot accurately capture changes in users' interest in materials, resulting in low recommendation accuracy.
By obtaining the target data evaluation of the target material by the target user, extracting evaluation parameters, and calculating the target score based on the evaluation parameters and preset periods, pushing the target recommendation material to the user, increasing the time correlation to improve the accuracy of the recommendation.
It realizes more accurate material recommendations, accurately capture changes in user interests, and improves the accuracy and user experience of recommendations.
Smart Images

Figure CN118842966B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image communication technology, and in particular to a video material recommendation method, device, storage medium and electronic device. Background Art
[0002] The popularity of an electronic product is determined by the market. The influencing factors of the market mainly come from the word of mouth of users. Therefore, in order to improve the popularity of electronic products, it is necessary to pay attention to the user experience and the user's feedback and suggestions. Among them, users generally provide feedback on their needs through two ways: actively submitting feedback and passively submitting feedback. These feedback data are uploaded to the platform server, and the platform server analyzes, processes, refines, screens, recommends, and predicts trends for the received data.
[0003] At present, in existing application scenarios, when users are interested in the highlights of a video and recommend it to other users, feedback data is generated. The platform server obtains this feedback data and recommends homogeneous materials to users based on this feedback data, forming a closed loop. Therefore, obtaining users' interests through technical means and recommending homogeneous materials to similar customer groups is an effective way to improve product vitality, extend product life cycle and iteration cycle.
[0004] However, current recommendation methods lack temporal relevance and have only limited accuracy in capturing changes in user interest in materials, which results in relatively limited accuracy in the materials recommended to users. Summary of the invention
[0005] In view of this, the purpose of the present application is to provide a video material recommendation method, device, storage medium and electronic device, by extracting evaluation parameters based on the target data evaluation of the target user for the target material, and obtaining the target score based on the evaluation parameters and the period, and finally pushing the target recommended material to the target user based on the target score. Due to the increase in time correlation, the user's interest changes in the material can be captured more accurately, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0006] In a first aspect, an embodiment of the present application provides a video material recommendation method, the method comprising:
[0007] Obtaining a target data evaluation of a target user on a target website for a target material; wherein the target website has multiple users and multiple materials; the target data evaluation represents the target user's preference for the target material;
[0008] Extracting evaluation parameters corresponding to the target material based on the target data evaluation; wherein the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters;
[0009] A target score corresponding to the target material is obtained based on the evaluation parameters and a preset period, and a target recommended material is pushed to the target user based on the target score so that the target user obtains the target recommended material; wherein the target score represents a change in the target user's interest in the target material within the period.
[0010] In a possible implementation manner, obtaining the target score corresponding to the target material based on the evaluation parameter and a preset period includes:
[0011] For the server-side evaluation parameter and the user-side evaluation parameter, respectively determine a plurality of corresponding server-side influencing parameters and a plurality of user-side influencing parameters, and determine an influencing weight of each server-side influencing parameter and each user-side influencing parameter; wherein each influencing parameter corresponds to an influencing weight;
[0012] A target score corresponding to the target material is calculated based on the server-side impact parameter, the user-side impact parameter, the impact weight, and the period.
[0013] In a possible implementation manner, the calculating the target score corresponding to the target material based on the server-side impact parameter, the user-side impact parameter, the impact weight, and the period includes:
[0014] Calculate a first score of the target material based on the server-side impact parameter, the user-side impact parameter, and the impact weight;
[0015] Determine and calculate a second score of the target material based on the number of server-side materials on the target website, the number of server-side influencing parameters, the number of registered users, the number of user-side influencing parameters, and the first score;
[0016] A target score for the target material is calculated based on the second score for the target material and the period.
[0017] In a possible implementation manner, the calculating the first score of the target material based on the server-side influence parameter, the user-side influence parameter, and the influence weight includes:
[0018] Calculating a first server-side evaluation of the target material based on the server-side evaluation parameter and the server-side impact parameter, and calculating a first user-side evaluation of the target material based on the user-side evaluation parameter and the user-side impact parameter;
[0019] Based on the preset first server weight and the first user-side weight, combined with the first server-side evaluation and the first user-side evaluation, a first score corresponding to the target material is obtained.
[0020] In a possible implementation manner, the period includes a plurality of time points; and calculating the target score of the target material based on the second score of the target material and the period includes:
[0021] Determine a time weight of the target material at each time point, and calculate a product of the second score and the time weight at each time point;
[0022] The sum of the products of the second score and the time weight at each time point is calculated to obtain the target score of the target material.
[0023] In a possible implementation, the pushing the target recommended material to the target user based on the target score includes:
[0024] Sorting the target materials based on the target scores to obtain the sorted target materials;
[0025] Among the sorted target materials, a target number of target materials are screened out as target recommended materials, and the target recommended materials are pushed to the target user.
[0026] In a possible implementation manner, the pushing the target recommended material to the target user includes:
[0027] Displaying the cover of the target recommended material at the target location of the target website; wherein each target recommended material corresponds to a cover;
[0028] In response to the target user logging into the target website, the target recommendation material is obtained.
[0029] In a second aspect, an embodiment of the present application further provides a video material recommendation device, the device comprising:
[0030] An acquisition module is used to acquire a target data evaluation of a target user on a target website for a target material; wherein the target website has multiple users and multiple materials; and the target data evaluation represents the target user's preference for the target material;
[0031] An extraction module, used to extract evaluation parameters corresponding to the target material based on the target data evaluation; wherein the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters;
[0032] A push module is used to obtain a target score corresponding to the target material based on the evaluation parameters and a preset period, and push the target recommended material to the target user based on the target score so that the target user obtains the target recommended material; wherein the target score represents the change in the target user's interest in the target material within the period.
[0033] In a possible implementation manner, the push module is specifically used to:
[0034] For the server-side evaluation parameter and the user-side evaluation parameter, respectively determine a plurality of corresponding server-side influencing parameters and a plurality of user-side influencing parameters, and determine an influencing weight of each server-side influencing parameter and each user-side influencing parameter; wherein each influencing parameter corresponds to an influencing weight;
[0035] A target score corresponding to the target material is calculated based on the server-side impact parameter, the user-side impact parameter, the impact weight, and the period.
[0036] In a possible implementation manner, the push module is specifically used to:
[0037] Calculate a first score of the target material based on the server-side impact parameter, the user-side impact parameter, and the impact weight;
[0038] Determine and calculate a second score of the target material based on the number of server-side materials on the target website, the number of server-side influencing parameters, the number of registered users, the number of user-side influencing parameters, and the first score;
[0039] A target score for the target material is calculated based on the second score for the target material and the period.
[0040] In a possible implementation manner, the push module is specifically used to:
[0041] Calculating a first server-side evaluation of the target material based on the server-side evaluation parameter and the server-side impact parameter, and calculating a first user-side evaluation of the target material based on the user-side evaluation parameter and the user-side impact parameter;
[0042] Based on the preset first server weight and the first user-side weight, combined with the first server-side evaluation and the first user-side evaluation, a first score corresponding to the target material is obtained.
[0043] In a possible implementation manner, the cycle includes multiple time points; and the push module is further used to:
[0044] Determine a time weight of the target material at each time point, and calculate a product of the second score and the time weight at each time point;
[0045] The sum of the products of the second score and the time weight at each time point is calculated to obtain the target score of the target material.
[0046] In a possible implementation manner, the push module is specifically used to:
[0047] Sorting the target materials based on the target scores to obtain the sorted target materials;
[0048] Among the sorted target materials, a target number of target materials are screened out as target recommended materials, and the target recommended materials are pushed to the target user.
[0049] In a possible implementation manner, the push module is specifically used to:
[0050] Displaying the cover of the target recommended material at the target location of the target website; wherein each target recommended material corresponds to a cover;
[0051] In response to the target user logging into the target website, the target recommendation material is obtained.
[0052] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the video material recommendation method as described in any one of the first aspects.
[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video material recommendation method described in any one of the first aspects are executed.
[0054] The embodiments of the present application provide a method, device, storage medium and electronic device for recommending video materials, which obtain the target data evaluation of the target user on the target website for the target material, extract the evaluation parameters corresponding to the target material based on the target data evaluation, obtain the target score corresponding to the target material based on the evaluation parameters and a preset period, and push the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material. In the present application, by extracting the evaluation parameters according to the target data evaluation of the target user for the target material, and obtaining the target score according to the evaluation parameters and the period, and finally pushing the target recommended material to the target user according to the target score, the change of the user's interest in the material can be captured more accurately due to the increase of time correlation, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0055] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0057] Figure 1 is a flowchart of a video material recommendation method according to an embodiment of the present application;
[0058] Figure 2 is a flowchart of a video material recommendation method according to another embodiment of the present application;
[0059] Figure 3 is a flowchart of a video material recommendation method according to another embodiment of the present application;
[0060] Figure 4 is a flowchart of a video material recommendation method according to another embodiment of the present application;
[0061] Figure 5 It is a schematic diagram of the video material recommendation process;
[0062] Figure 6 is a structural diagram of a video material recommendation device according to an embodiment of the present application;
[0063] Figure 7 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0064] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.
[0065] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0066] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.
[0067] The popularity of an electronic product is determined by the market. The influencing factors of the market mainly come from the word of mouth of users. Therefore, in order to improve the popularity of electronic products, it is necessary to pay attention to the user experience and the user's feedback and suggestions. Among them, users generally provide feedback on their needs through two ways: actively submitting feedback and passively submitting feedback. These feedback data are uploaded to the platform server, and the platform server analyzes, processes, refines, screens, recommends, and predicts trends for the received data.
[0068] At present, in existing application scenarios, when users become interested in the highlights of a video and recommend it to other users, feedback data is generated. The platform server obtains this feedback data and recommends homogeneous materials to users based on this feedback data, forming a closed loop. Therefore, obtaining users' interests through technical means and recommending homogeneous materials to similar customer groups is an effective way to improve product vitality, extend product life cycle and iteration cycle. However, the current recommendation method lacks time correlation, and the accuracy of capturing changes in users' interest in materials is average, which leads to the relatively average accuracy of the materials recommended to users.
[0069] To address this problem, the present application provides a video material recommendation method, device, storage medium and electronic device, which extracts evaluation parameters based on the target user's target data evaluation of the target material, obtains the target score based on the evaluation parameters and the period, and finally pushes the target recommended material to the target user based on the target score. Due to the added time correlation, the user's interest changes in the material can be captured more accurately, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0070] Figure 1 FIG. 1 is a flowchart of a video material recommendation method according to an embodiment of the present application. Figure 1 As shown, the video material recommendation method of the embodiment of the present application may specifically include:
[0071] S101, obtaining target data evaluation of target users on target materials on target websites.
[0072] S102: Extract evaluation parameters corresponding to the target material based on the target data evaluation.
[0073] S103: Obtain a target score corresponding to the target material based on the evaluation parameters and a preset period, and push the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material.
[0074] In the above method, evaluation parameters are extracted based on the target data evaluation of the target user on the target material, and the target score is obtained based on the evaluation parameters and the period, and finally the target recommended material is pushed to the target user based on the target score. Due to the increase in time correlation, the change of user interest in the material can be captured more accurately, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0075] The above exemplary steps of the embodiment of the present application are described below with reference to specific examples:
[0076] S101, obtaining target data evaluation of a target user on a target website for a target material.
[0077] In the embodiment of the present application, the target user is the user to whom material recommendation is to be made, the target material is the material used as a sample, the target website is the website where the target user is located, there are multiple users and multiple materials on the target website, the target user is also the user to whom material recommendation is to be made among the users registered on the target website, the target data evaluation is the data evaluation of the target material by the target user, the target data evaluation represents the target user's preference for the target material and can be understood as user (user) data, the target data evaluation includes active data evaluation and passive data evaluation, wherein the active data evaluation is the data evaluation actively submitted by the user, the active data evaluation includes at least subjective preferences, ratings, download volumes, etc., the passive data evaluation is the data evaluation passively submitted by the user, the passive data evaluation includes at least the frequency, quantity, published materials, number of errors, etc. used by the target user, the target data evaluation of the target user on the target website for the target material is obtained for subsequent processing.
[0078] S102: extracting evaluation parameters corresponding to the target material based on the target data evaluation.
[0079] In an embodiment of the present application, the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters, wherein the server-side evaluation parameters are statistics on the download volume of the target material on the target website by the target user and the user recommendation index; the user-side evaluation parameters are statistics on the number of uses of the target material by the target user, which may specifically include the number of changes to the ID (Identifier) (original ID), for example, the number of processed and edited IDs, and also the number of material IDs submitted by users. If the material submitted by the user has no ID, the system automatically generates a material ID. It also includes the number of material IDs extracted through engineering. If the material of the target website is used, it is the material ID. The target data evaluation in step S101 is extracted to extract the evaluation parameters corresponding to the target material for subsequent processing.
[0080] S103, obtaining a target score corresponding to the target material based on the evaluation parameter and a preset period, and pushing the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material.
[0081] In the embodiment of the present application, the period is a preset period for the target material, for example, the period is one month, and the period range can be 2, 3, 5, 7. The target score is the score of the target material. The target score represents the change in the target user's interest in the target material within the period. The target recommended material is the material that the target user is interested in. The evaluation parameters extracted in step S102 and the preset period are used to obtain the target score of the target material, and the corresponding target recommended material is pushed to the target user based on the target score. The target user obtains the target recommended material, and the material recommendation is completed.
[0082] The video material recommendation method provided in the embodiment of the present application obtains the target data evaluation of the target material by the target user on the target website, extracts the evaluation parameters corresponding to the target material based on the target data evaluation, obtains the target score corresponding to the target material based on the evaluation parameters and a preset period, and pushes the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material. The video material recommendation method of the present application extracts the evaluation parameters according to the target data evaluation of the target material by the target user, obtains the target score according to the evaluation parameters and the period, and finally pushes the target recommended material to the target user according to the target score. Due to the increase in time correlation, the user's interest changes in the material can be captured more accurately, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0083] Further, such as Figure 2 As shown, the step S103 in the above embodiment of “obtaining a target score corresponding to the target material based on the evaluation parameters and the preset period” may specifically include the following steps:
[0084] S201 , for the server-side evaluation parameters and the user-side evaluation parameters, respectively determine a corresponding plurality of server-side influencing parameters and a plurality of user-side influencing parameters, and determine an influencing weight of each server-side influencing parameter and each user-side influencing parameter.
[0085] In the embodiments of the present application, the server-side influencing parameters are parameters that affect the server-side evaluation, the user-side influencing parameters are parameters that affect the user-side evaluation, the influencing weights are the weights of these influencing parameters, and each influencing parameter corresponds to an influencing weight. For the server-side evaluation parameters in the above embodiments, multiple server-side influencing parameters corresponding to the server-side evaluation parameters are determined. For the user-side evaluation parameters in the above embodiments, multiple user-side influencing parameters corresponding to the user-side evaluation parameters are determined, and the influencing weights of each server-side influencing parameter and each user-side influencing parameter are determined for subsequent processing.
[0086] It should be noted that, among the server-side influencing parameters and the user-side influencing parameters, the weight of the parameter with a large influence may be close to 1, and the weight of the parameter with a relatively small influence may be close to 0.
[0087] Optionally, the server-side influencing parameters may include click-through rate (represented by X1), download volume (represented by X2), score (represented by X3), forwarding volume (represented by X4), etc., and the user-side influencing parameters may include the number of used materials (represented by Y1), the number of references to materials used in other projects (represented by Y2), the number of cross-references (represented by Y3), the number of negative references (represented by Y4), etc. At this time, there are 4 server-side influencing parameters and 4 user-side influencing parameters, namely X1-X4 and Y1-Y4, and each of these parameters has a corresponding weight.
[0088] S202: Calculate a target score corresponding to the target material based on the server-side impact parameter, the user-side impact parameter, the impact weight and the period.
[0089] In the embodiment of the present application, based on the server-side impact parameter, user-side impact parameter, impact weight and period determined in step S201, the target score corresponding to the target material is calculated for subsequent processing.
[0090] It should be noted that the target material is divided into user-side material and server-side material. Before calculating the target score corresponding to the target material, the user-side material can be integrated to pre-process the user-side material, and the server-side material can be integrated to pre-process the server-side material. In simple terms, the integration of the user-side material and the server-side material is reset to zero. For example, for the user-side material integration USER_END [1,N] = 0, for the server-side material integration SERVER_END [1,M] = 0, where N is the number of users registered on the target website, and M is the number of server-side materials.
[0091] To continue, for example, the definition of active data evaluation (rating, evaluation) actively submitted by the target user: on the website side, it is SERVER_END[1,m] = 1 / 2 / 3 / 4, where m is the number of parameters on the server side; for passive data evaluation passively submitted by the target user, the server parses and obtains the definition: on the user side, USER_END[1,n]=10, where n is the number of parameters on the user side.
[0092] Further, such as Figure 3 As shown, step S202 in the above embodiment, “calculating the target score corresponding to the target material based on the server-side impact parameter, the user-side impact parameter, the impact weight and the period”, may specifically include the following steps:
[0093] S301, calculating a first score of a target material based on a server-side impact parameter, a user-side impact parameter, and an impact weight.
[0094] In the embodiment of the present application, based on the server-side influence parameter, user-side influence parameter and influence weight in the above embodiment, the first score of the target material is calculated for subsequent processing. The first score is the first basic score of the target material, and the first score represents the change of the target user's interest in the target material when there is no time correlation.
[0095] It should be noted that the present application does not impose excessive restrictions on the specific method of calculating the first score of the target material based on the server-side impact parameter, the user-side impact parameter and the impact weight, and it can be set according to actual conditions.
[0096] In some embodiments, a first server-side evaluation of the target material is calculated based on the server-side evaluation parameter and the server-side influence parameter, and a first user-side evaluation of the target material is calculated based on the user-side evaluation parameter and the user-side influence parameter; based on the preset first server weight and the first user-side weight, the first server-side evaluation and the first user-side evaluation are combined to obtain a first score corresponding to the target material. The first server-side evaluation is the evaluation of the target material on the server side, the first user-side evaluation is the evaluation of the target material on the user side, the first server weight is the weight preset for the server side, and the first user-side weight is the weight preset for the user side.
[0097] To continue, for example, for target material i, the first score is calculated by the following formula: F[i] = all alpha*SERVER_END evaluations of i + all belta*USER_END evaluations of i. In which, alpha represents the first server weight, belta represents the first user-side weight, SERVER_END evaluation of i represents the first server-side evaluation, and USER_END evaluation of i represents the first user-side evaluation, thereby calculating the first score of the material.
[0098] S302, determining and calculating a second score of the target material based on the number of server-side materials on the target website, the number of server-side influencing parameters, the number of registered users, the number of user-side influencing parameters and the first score.
[0099] In the embodiment of the present application, the number of server-side materials, the number of server-side influencing parameters, the number of registered users, and the number of user-side influencing parameters on the target website are determined, and based on the number of server-side materials, the number of server-side influencing parameters, the number of registered users, the number of user-side influencing parameters on the target website and the first score in step S301, the second score of the target material is calculated. The second score represents the score after weighted summation based on the above-mentioned quantity parameters on the basis of the first score.
[0100] For example, continuing, the second score is calculated according to the following formula:
[0101] +
[0102] in, is the cumulative integral value of the current material i, j is the number of influencing parameters on the server side or user side of material i, α and β are the weights of the influencing parameters on the server side and the user side respectively, and the explanations of other parameters are the same as above and will not be repeated here.
[0103] S303: Calculate a target score of the target material based on the second score and the period of the target material.
[0104] In the embodiment of the present application, the target score of the target material is calculated based on the second score of the target material calculated in step S302 and the period in the above embodiment for subsequent processing. The target score represents the time-related score of the target material; the period includes multiple time points.
[0105] In some implementations, the time weight of the target material at each time point is determined, and the product of the second score at each time point and the time weight is calculated; the sum of the products of the second score at each time point and the time weight is calculated to obtain the target score of the target material. The closer the time point of the target material is to the period, the greater the time weight; the farther away from the period, the smaller the time weight.
[0106] Continuing, for example, with a period of T, The formula related to the second score and time is:
[0107]
[0108] in, for The weight at time t, T>=2. It should be noted that, , T is the total number of all cycles. The closer t and T are, the closer the value is. , otherwise the closer the value is .For example, Optionally, the length of each period unit T may range from [2, 3, 5, 7] days, that is, the length of a period unit may be 2 days, 3 days, 5 days or 7 days.
[0109] In this way, a target score related to the time of the target material is achieved, reflecting the relevance to historical data, and different time weights are applied according to the distance close to and far from the cycle, which also makes the target score more accurate and more time-relevant.
[0110] Further, such as Figure 4 As shown, the “pushing target recommended material to the target user based on the target score” in step S103 in the above embodiment may specifically include the following steps:
[0111] S401, sorting the target materials based on the target scores to obtain sorted target materials.
[0112] In the embodiment of the present application, the target materials are sorted based on the target scores of the multiple target materials calculated in the above embodiment to obtain sorted target materials for subsequent processing. Sort the values.
[0113] S402: Filter out a target number of target materials from the sorted target materials as target recommended materials, and push the target recommended materials to the target user.
[0114] In the embodiment of the present application, among the sorted target materials obtained in step S401, a target number of target materials are screened out as target recommended materials, and the target recommended materials are pushed to the target user. For example, among the sorted target materials, the first four target materials are screened out as hot recommended materials, i.e., target recommended materials, and the target recommended materials are pushed to the target user.
[0115] Optionally, the cover of the target recommended material is displayed at the target location of the target website; in response to the target user logging into the target website, the target recommended material is obtained. Each target recommended material corresponds to a cover. For example, the cover of each target recommended material is displayed at a prominent target location of the target website, for example, the four covers of the four target recommended materials mentioned above, and when the target user logs into the target website, the target recommended material can be obtained.
[0116] Furthermore, based on the target score, homogeneous users are screened out on the target website; and the target recommendation materials are pushed to homogeneous users. Homogeneous users are users with the same or similar target data evaluation as the target user. In this way, the scope of recommended materials can be expanded and the recommendation efficiency can be improved.
[0117] Specifically, for example, the video material recommendation method of the present application is as follows: Figure 5 As shown, Figure 5 The process of the video material recommendation method is shown. According to the obtained user data, the evaluation parameters are extracted through the platform server, and then the data is processed, that is, the score is calculated, and then the material is recommended to the user. This application will not go into details about this.
[0118] Therefore, by increasing the time correlation, the user's focus can be captured and located more accurately, and the user's interest changes in the material can be determined. Through adjustment, more accurate material recommendations can be achieved, and by using the user's historical behavior data, the user's future interests and preferences can be predicted. Compared with the traditional recommendation method, this application not only considers the user's historical behavior, but also takes into account the time factor. It can effectively use the user's historical behavior data and more accurately capture the user's interest changes, thereby providing users with more personalized recommendations, thereby attracting more users and maintaining the continued competitiveness of the product.
[0119] Figure 6 is a flow chart of a video material recommendation device according to an embodiment of the present application. Figure 6As shown, the video material recommendation device 600 of the embodiment of the present application may specifically include:
[0120] The acquisition module 601 is used to acquire the target data evaluation of the target user on the target website for the target material; wherein the target website has multiple users and multiple materials; the target data evaluation represents the target user's preference for the target material.
[0121] The extraction module 602 is used to extract evaluation parameters corresponding to the target material based on the target data evaluation; wherein the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters.
[0122] The push module 603 is used to obtain the target score corresponding to the target material based on the evaluation parameters and the preset period, and push the target recommended material to the target user based on the target score so that the target user can obtain the target recommended material; wherein the target score represents the change in the target user's interest in the target material within the period.
[0123] In a possible implementation manner, the push module is specifically used to:
[0124] For the server-side evaluation parameters and the user-side evaluation parameters, respectively determine a plurality of corresponding server-side influencing parameters and a plurality of user-side influencing parameters, and determine an influencing weight of each server-side influencing parameter and each user-side influencing parameter; wherein each influencing parameter corresponds to an influencing weight;
[0125] Based on the server-side impact parameters, user-side impact parameters, impact weights and cycles, the target score corresponding to the target material is calculated.
[0126] In a possible implementation manner, the push module is specifically used to:
[0127] Calculate a first score of the target material based on the server-side impact parameter, the user-side impact parameter, and the impact weight;
[0128] Determine and calculate a second score of the target material based on the number of server-side materials, the number of server-side influencing parameters, the number of registered users, the number of user-side influencing parameters and the first score on the target website;
[0129] A target score for the target material is calculated based on the second score for the target material and the period.
[0130] In a possible implementation manner, the push module is specifically used to:
[0131] Calculating a first server-side evaluation of the target material based on the server-side evaluation parameter and the server-side impact parameter, and calculating a first user-side evaluation of the target material based on the user-side evaluation parameter and the user-side impact parameter;
[0132] Based on the preset first server weight and the first user-side weight, combined with the first server-side evaluation and the first user-side evaluation, a first score corresponding to the target material is obtained.
[0133] In a possible implementation, the cycle includes multiple time points; the push module is further used to:
[0134] Determine the time weight of the target material at each time point, and calculate the product of the second score and the time weight at each time point;
[0135] The sum of the products of the second score and the time weight at each time point is calculated to obtain the target score of the target material.
[0136] In a possible implementation manner, the push module is specifically used to:
[0137] The target materials are sorted based on the target scores to obtain sorted target materials;
[0138] Among the sorted target materials, a target number of target materials are screened out as target recommended materials, and the target recommended materials are pushed to target users.
[0139] In a possible implementation manner, the push module is specifically used to:
[0140] Displaying the cover of the target recommended material at the target location of the target website; wherein each target recommended material corresponds to one cover;
[0141] In response to the target user logging into the target website, a target recommendation material is obtained.
[0142] The video material recommendation device provided in the embodiment of the present application obtains the target data evaluation of the target material by the target user on the target website, extracts the evaluation parameters corresponding to the target material based on the target data evaluation, obtains the target score corresponding to the target material based on the evaluation parameters and a preset period, and pushes the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material. The video material recommendation device of the present application extracts the evaluation parameters according to the target data evaluation of the target material by the target user, obtains the target score according to the evaluation parameters and the period, and finally pushes the target recommended material to the target user according to the target score. Due to the increase in time correlation, the user's interest changes in the material can be captured more accurately, thereby improving the accuracy of the material recommended to the user and achieving a more accurate material recommendation effect.
[0143] like Figure 7As shown, an electronic device 700 provided in an embodiment of the present application includes: a processor 701, a memory 702 and a bus, wherein the memory 702 stores machine-readable instructions executable by the processor 701. When the electronic device is running, the processor 701 communicates with the memory 702 through the bus, and the processor 701 executes the machine-readable instructions to perform the steps of the above-mentioned video material recommendation method.
[0144] Specifically, the memory 702 and the processor 701 can be general-purpose memories and processors, which are not specifically limited here. When the processor 701 runs the computer program stored in the memory 702, the video material recommendation method can be executed.
[0145] Corresponding to the above-mentioned video material recommendation method, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned video material recommendation method are executed.
[0146] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0147] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0149] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the deployment method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.
[0150] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A video material recommendation method, characterized in that: The method comprises: Obtaining a target data evaluation of a target user on a target website for a target material; wherein the target website has multiple users and multiple materials; the target data evaluation represents the target user's preference for the target material; Extracting evaluation parameters corresponding to the target material based on the target data evaluation; wherein the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters; Obtaining a target score corresponding to the target material based on the evaluation parameter and a preset period, and pushing a target recommended material to the target user based on the target score, so that the target user obtains the target recommended material; wherein the target score represents a change in the target user's interest in the target material within the period; The step of obtaining the target score corresponding to the target material based on the evaluation parameters and the preset period includes: determining a plurality of corresponding server-side influence parameters and a plurality of user-side influence parameters for the server-side evaluation parameters and the user-side evaluation parameters, respectively, and determining an influence weight of each server-side influence parameter and each user-side influence parameter; wherein each influence parameter corresponds to an influence weight; and calculating the target score corresponding to the target material based on the server-side influence parameter, the user-side influence parameter, the influence weight and the period; The method of calculating the target score corresponding to the target material based on the server-side influence parameter, the user-side influence parameter, the influence weight and the period includes: calculating the first score of the target material based on the server-side influence parameter, the user-side influence parameter and the influence weight; determining and calculating the second score of the target material based on the number of server-side materials on the target website, the number of server-side influence parameters, the number of registered users, the number of user-side influence parameters and the first score; and calculating the target score of the target material based on the second score of the target material and the period.
2. The method according to claim 1, characterized in that The calculating the first score of the target material based on the server-side influence parameter, the user-side influence parameter and the influence weight includes: Calculating a first server-side evaluation of the target material based on the server-side evaluation parameter and the server-side impact parameter, and calculating a first user-side evaluation of the target material based on the user-side evaluation parameter and the user-side impact parameter; Based on the preset first server weight and the first user-side weight, combined with the first server-side evaluation and the first user-side evaluation, a first score corresponding to the target material is obtained.
3. The method according to claim 1, characterized in that The period includes a plurality of time points; and calculating the target score of the target material based on the second score of the target material and the period includes: Determine a time weight of the target material at each time point, and calculate a product of the second score and the time weight at each time point; The sum of the products of the second score and the time weight at each time point is calculated to obtain the target score of the target material.
4. The method according to claim 1, characterized in that: The pushing the target recommended material to the target user based on the target score includes: Sorting the target materials based on the target scores to obtain the sorted target materials; Among the sorted target materials, a target number of target materials are screened out as target recommended materials, and the target recommended materials are pushed to the target user.
5. The method according to claim 4, characterized in that The pushing of target recommended material to the target user includes: Displaying the cover of the target recommended material at the target location of the target website; wherein each target recommended material corresponds to a cover; In response to the target user logging into the target website, the target recommendation material is obtained.
6. A video material recommendation device, characterized in that: Applicable to the video material recommendation method according to any one of claims 1 to 5; the device comprises: An acquisition module is used to acquire a target data evaluation of a target user on a target website for a target material; wherein the target website has multiple users and multiple materials; and the target data evaluation represents the target user's preference for the target material; An extraction module, used to extract evaluation parameters corresponding to the target material based on the target data evaluation; wherein the evaluation parameters include server-side evaluation parameters and user-side evaluation parameters; a push module, configured to obtain a target score corresponding to the target material based on the evaluation parameter and a preset period, and push the target recommended material to the target user based on the target score, so that the target user obtains the target recommended material; wherein the target score represents a change in the target user's interest in the target material within the period; The push module is further used to determine the corresponding multiple server-side impact parameters and multiple user-side impact parameters respectively for the server-side evaluation parameters and the user-side evaluation parameters, and determine the impact weights of each server-side impact parameter and each user-side impact parameter; wherein each impact parameter corresponds to an impact weight; based on the server-side impact parameter, the user-side impact parameter, the impact weight and the period, calculate the target score corresponding to the target material; The push module is also used to calculate the first score of the target material based on the server-side influence parameter, the user-side influence parameter and the influence weight; determine and calculate the second score of the target material based on the number of server-side materials on the target website, the number of server-side influence parameters, the number of registered users, the number of user-side influence parameters and the first score; calculate the target score of the target material based on the second score of the target material and the period.
7. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the video material recommendation method as described in any one of claims 1 to 5 are performed.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the video material recommendation method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Video recommendation method, video recommendation equipment and server
CN110248249A
Content recommendation method and device, storage medium and electronic equipment
CN113469752A
