Personalized recommendation method, personalized recommendation device and electronic device

Abstract

Disclosed are a personalized recommendation method, a personalized recommendation device, and an electronic device. The personalized recommendation method comprises: obtaining user selection feature data, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; using the user selection feature data to classify the user to obtain user type feature data; and using the user type feature data to determine a personalized recommendation result. In this way, personalized recommendations that meet user needs are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of customized data processing, and more specifically, to a personalized recommendation method, a personalized recommendation device, a user interaction method, device and electronic device for personalized recommendation. Background Art

[0002] At present, with the continuous iteration of technology and the upgrading of interactive methods, interactive media content is gradually emerging in the field of media content. When watching interactive media content, users can unlock the plot or advance the plot through interactive operations. Users are no longer just viewers of media content but participants. Therefore, interactive media content can stimulate users' curiosity and exploration, and attract users to watch.

[0003] For example, a common interactive form of interactive media content is branching plots, which are also called AB dramas. The form is relatively simple, that is, a branching plot option is set at a certain node in the media content, and the corresponding branching plot is played according to the user's choice. The branching plots can be completely independent of each other, for example, independent story lines and independent endings. Of course, the branching plot can also be just the middle process of the plot, and the branching plot returns to the main plot line at the end.

[0004] Since interactive media content may develop from the main plot to different branch plots, or from different branch plots back to the main plot, interactive media content is generally composed of multiple media content segments (or media content intervals), for example, the main plot is a media content segment, and each branch plot corresponds to a media content segment. In addition, interactive media content also includes interactive components, such as interactive components for presenting interactive options to users, interactive components for receiving user operations on interactive options, etc.

[0005] Therefore, when users select different interactive options, a large amount of user selection data will be generated, and it is desired to provide a solution that can utilize the user selection data. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a personalized recommendation method, a personalized recommendation device and an electronic device, which classify users by using the selection data of the user for the interactive options of the interactive media content, and make personalized recommendations to the users based on the user classification, so as to achieve personalized recommendations that meet the user's needs.

[0007] According to one aspect of the present application, a personalized recommendation method is provided, comprising: obtaining user selection feature data, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; using the user selection feature data to classify users to obtain user type feature data; and using the user type feature data to determine personalized recommendation results.

[0008] In the above-mentioned personalized recommendation method, obtaining user selection feature data includes: obtaining user original selection data; and extracting the user selection feature data from the user original selection data, wherein the user selection feature data includes at least one of selection options, selection speed, selection time, current time, and whether to skip selection.

[0009] In the above-mentioned personalized recommendation method, obtaining the user's original selection data includes: accumulating the user's original selection data within a predetermined time period.

[0010] In the above-mentioned personalized recommendation method, the user type characteristic data includes whether the user type belongs to one of a plurality of preset user types and the similarity between the user type and the preset user type to which it belongs.

[0011] In the above-mentioned personalized recommendation method, the preset user type includes at least one of the user's age, region, gender, and preferences.

[0012] In the above-mentioned personalized recommendation method, using the user selection feature data to classify users to obtain user type feature data includes: obtaining a user classification model sent from a server; and using the user selection feature data to obtain the user type feature data with the user classification model.

[0013] In the above-mentioned personalized recommendation method, using the user type feature data to determine the personalized recommendation result includes: obtaining a personalized recommendation decision model sent from a server; and using the user type feature data to determine the personalized recommendation result with the personalized recommendation decision model.

[0014] In the above-mentioned personalized recommendation method, after using the user type feature data to determine the personalized recommendation result with the personalized recommendation decision model, it further includes: sending a recommended content request to a server based on the personalized recommendation result; obtaining the content to be recommended from the recommended content resource library of the server; and displaying the content to be recommended.

[0015] In the above-mentioned personalized recommendation method, the content to be recommended includes advertisements recommended to the user.

[0016] In the above-mentioned personalized recommendation method, after displaying the content to be recommended, it further includes: obtaining the user's operation on the content to be recommended; and optimizing the issued personalized recommendation decision model based on the operation.

[0017] According to another aspect of the present application, a personalized recommendation method is provided, comprising: obtaining user selection feature data from a terminal, the user selection feature data representing the user's selection of interactive options for interactive media content; using a user classification model to classify users based on the user selection feature data to obtain user type feature data; using a personalized recommendation decision model to determine a personalized recommendation result from the user type feature data; obtaining content to be recommended from a recommended content resource library based on the personalized recommendation result; and sending the content to be recommended to the terminal.

[0018] In the above-mentioned personalized recommendation method, obtaining user selection feature data from the terminal includes: obtaining user original selection data from the terminal; and extracting the user selection feature data from the user original selection data, wherein the user selection feature data includes at least one of selection options, selection speed, selection time, current time, and whether to skip selection.

[0019] In the above-mentioned personalized recommendation method, obtaining the user's original selection data from the terminal includes: accumulating the user's original selection data obtained from the terminal within a predetermined time period.

[0020] In the above-mentioned personalized recommendation method, it further includes: optimizing at least one interactive option based on the user classification model and the personalized recommendation decision model; editing an interactive script using the optimized interactive option; and sending the edited interactive script to the terminal.

[0021] According to another aspect of the present application, a user interaction method for personalized recommendation is provided, comprising: receiving a user's selection operation on an interactive option of interactive media content to obtain original user selection data; extracting user selection feature data from the original user selection data, wherein the user selection feature data represents the user's selection of the interactive option; sending the user selection feature data to a server; and receiving a personalized recommendation result based on the user selection feature data from the server.

[0022] In the above-mentioned user interaction method for personalized recommendation, the user's selection operation on the interactive option of the interactive media content includes the user's selection operation on the interactive option of the interactive media content made by at least one of gesture, voice, sensor, and camera.

[0023] According to another aspect of the present application, a personalized recommendation device is provided, comprising: a data acquisition unit for acquiring user selection feature data, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; a user classification unit for using the user selection feature data to classify users to obtain user type feature data; and a personalized recommendation unit for using the user type feature data to obtain personalized recommendation results.

[0024] According to another aspect of the present application, a personalized recommendation device is provided, comprising: a terminal receiving unit, used to obtain user selection feature data from a terminal, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; a classification model unit, used to classify users based on the user selection feature data using a user classification model to obtain user type feature data; a recommendation model unit, used to obtain personalized recommendation results from the user type feature data using a personalized recommendation decision model; a content retrieval unit, used to obtain content to be recommended from a recommended content resource library based on the personalized recommendation result; and a content sending unit, used to send the content to be recommended to the terminal.

[0025] According to another aspect of the present application, a user interaction device for personalized recommendation is provided, comprising: an operation receiving unit, for receiving a user's selection operation on an interactive option of interactive media content to obtain original user selection data; a feature extraction unit, for extracting user selection feature data from the original user selection data, wherein the user selection feature data represents the user's selection of the interactive option; a feature sending unit, for sending the user selection feature data to a server; and a recommendation receiving unit, for receiving a personalized recommendation result based on the user selection feature data from the server.

[0026] According to another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the personalized recommendation method and the user interaction method for personalized recommendation as described above.

[0027] According to another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the personalized recommendation method and the user interaction method for personalized recommendation as described above.

[0028] The personalized recommendation method, personalized recommendation device, user interaction method, device and electronic device for personalized recommendation provided in the present application classify users by using the user's selection data for interactive options of interactive media content, and make personalized recommendations to users based on the user classification, so as to achieve personalized recommendations that meet user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0030] Figure 1 A schematic diagram illustrating an application scenario of a personalized recommendation method according to an embodiment of the present application is illustrated.

[0031] Figure 2 The figure illustrates a flowchart of a first example of a personalized recommendation method according to an embodiment of the present application.

[0032] Figure 3 The figure illustrates a flowchart of a second example of the personalized recommendation method according to an embodiment of the present application.

[0033] Figure 4 The figure illustrates a flow chart of a user interaction method for personalized recommendation according to an embodiment of the present application.

[0034] Figure 5 The figure illustrates a schematic process of an application example of the personalized recommendation method according to an embodiment of the present application.

[0035] Figure 6 The figure illustrates a schematic system architecture of an application example of the personalized recommendation method according to an embodiment of the present application.

[0036] Figure 7 A block diagram of a first example of a personalized recommendation device according to an embodiment of the present application is illustrated.

[0037] Figure 8 A block diagram of a second example of a personalized recommendation device according to an embodiment of the present application is illustrated.

[0038] Fig. 9 The figure illustrates a block diagram of a user interaction device for personalized recommendation according to an embodiment of the present application.

[0039] Fig.10 A block diagram of an electronic device according to an embodiment of the present application is illustrated. DETAILED DESCRIPTION

[0040] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0041] Scenario Overview

[0042] Figure 1 A schematic diagram illustrating an application scenario of a personalized recommendation method according to an embodiment of the present application is illustrated.

[0043] like Figure 1 As shown, the interactive media content is played on the display interface of the interactive media content player, such as the user's terminal device T, such as a smart phone. As described above, the interactive media content includes different interactive options presented to the user, so that the terminal device T obtains the user selection data by receiving a selection operation of selecting one of the interactive options from the user U.

[0044] In the embodiment of the present application, the user selection data includes some key data that can reflect the user's characteristics. Figure 1 As shown, after obtaining the user selection data, the user selection feature data is extracted and input into the user classification model.

[0045] The user classification model classifies users based on user selection feature data to obtain user type feature data. Figure 1 As shown, user type feature data is input into the personalized recommendation decision model to obtain personalized recommendation results based on user type personalization.

[0046] Furthermore, if Figure 1 As shown, the server S retrieves the recommended content resource library L based on the personalized recommendation result, sends the obtained content to be recommended to the terminal device T, and displays it to the user on the terminal device T.

[0047] In an embodiment of the present application, at least one of the user classification model and the personalized recommendation decision model can be set in the terminal device T, which will be further described in detail below.

[0048] Below, an exemplary personalized recommendation method according to an embodiment of the present application will be further described with reference to the accompanying drawings.

[0049] Exemplary Method 1

[0050] Figure 2 The figure illustrates a flowchart of a first example of a personalized recommendation method according to an embodiment of the present application.

[0051] like Figure 2As shown, the first example of the personalized recommendation method according to an embodiment of the present application is applied to the terminal device T as described above, which includes the following steps.

[0052] Step S110, obtaining user selection feature data, wherein the user selection feature data represents the user's selection of interactive options for interactive media content. As described above, when the interactive media content is played to an interactive node, different interactive options will be presented to the user, and the user can enter different interactive branches based on the selection of the interactive options. Through these user selections, the user's preferences can be reflected to a certain extent, thereby serving as a basis for personalized recommendations to the user. In other words, through the user's selection data, a user profile can be created for the user, thereby reflecting the user in a digital form.

[0053] However, not all data can be used as reference data for effective user portraits. Preliminary screening is required to obtain data that can be used to describe user behavior characteristics. These data used to describe user behavior characteristics can include the options selected by the user, the speed at which the user makes the selection, the time it takes the user to make the selection, such as 2 seconds, 5 seconds, 10 seconds, etc., and whether the user skips the selection.

[0054] In addition, the user selection feature data also includes the time dimension when the user makes the selection, that is, whether the user makes the selection in the morning, at noon or at night. Therefore, the user selection feature data also includes the current time.

[0055] That is, in an embodiment of the present application, obtaining user selection characteristic data includes: obtaining user original selection data; and extracting the user selection characteristic data from the user original selection data, wherein the user selection characteristic data includes at least one of selection options, selection speed, selection time, current time, and whether to skip selection.

[0056] In addition, individual user selections cannot be used as reference data for effective user portraits, and sufficient user selection data must be accumulated. Moreover, there will be a certain degree of correlation between the accumulated user selection data, so that it can be used to accurately judge the user's preferred choices. Therefore, in the embodiment of the present application, obtaining the user's original selection data includes: accumulating the user's original selection data within a predetermined time period.

[0057] Step S120, using the user selection feature data to classify the user to obtain user type feature data. That is, based on the user selection feature data, a user classification model can be used to classify the user to obtain user type feature data. Here, the user classification model can be similar to an ending judgment model for interactive videos, or can be similar to a user personality judgment model for entertainment.

[0058] In the user classification model, multiple user types can be preset, and the user type can be determined to which of the multiple preset user types the user type belongs through user classification. Here, the preset user type can include at least one of the user's age, region, gender, and preferences. In addition, the model may also give the similarity between the user type and the preset user type to which it belongs. That is, the user type feature data includes whether the user type belongs to one of the multiple preset user types and the similarity between the user type and the preset user type to which it belongs.

[0059] Step S130, using the user type feature data to determine the personalized recommendation result. That is, by inputting the above user type feature data into the personalized recommendation decision model, the personalized recommendation result for the user can be determined. Here, the personalized recommendation decision model can be a personalized recommendation content judgment algorithm model, or other personalized recommendation algorithm models.

[0060] In addition, the personalized recommendation decision model may not only use the user type feature data as described above, but also use additional input parameters according to the needs of the scenario, and make personalized recommendations based on the actual usage scenarios. In addition, the recommended content includes but is not limited to games, interactive dramas, videos, advertisements, etc.

[0061] In the first example of the personalized recommendation method according to the embodiment of the present application, the user allocation model and the personalized recommendation decision model are both set in the terminal device, for example, Figure 1 The terminal device T is shown. In this way, by performing inference operations of user types and personalized recommendations locally on the terminal device, higher real-time performance can be achieved.

[0062] In this case, the user classification model and the personalized recommendation decision model may be pre-installed in the terminal device, or may be installed from the server, for example Figure 1 The server S shown sends it to the terminal device.

[0063] That is, in the personalized recommendation method according to the embodiment of the present application, using the user selection feature data to classify users to obtain user type feature data includes: obtaining a user classification model sent from a server; and using the user selection feature data to obtain the user type feature data with the user classification model.

[0064] Furthermore, in the personalized recommendation method according to the embodiment of the present application, using the user type feature data to determine the personalized recommendation result includes: obtaining a personalized recommendation decision model sent from a server; and using the user type feature data to determine the personalized recommendation result with the personalized recommendation decision model.

[0065] Furthermore, after obtaining the personalized recommendation result, the terminal device needs to send a recommended content request to the server based on the personalized recommendation result, and obtain the content to be recommended from the recommended content resource library of the server, such as recommended games, interactive dramas, videos, advertisements, etc.

[0066] Then, the terminal device displays the content to be recommended to the user through an output unit, such as a display screen, a speaker, etc. For example, the terminal device can pre-set a promotion position for the recommended content as a display position for the recommended content, for automatically playing the recommended content.

[0067] Furthermore, after displaying the content to be recommended, the terminal device may further obtain the user's operation on the content to be recommended, such as a click operation on the recommended advertisement, and optimize the issued personalized recommendation decision model based on the operation.

[0068] That is, in the embodiment of the present application, by setting the personalized recommendation decision model on the terminal device side, in addition to reducing the pressure on the server side, a faster response can be made according to the user's real-time behavior, thereby further improving the algorithm model and improving the intelligent personalized recommendation based on the playback of interactive media content.

[0069] Exemplary Method 2

[0070] Figure 3 The figure illustrates a flowchart of a second example of the personalized recommendation method according to an embodiment of the present application.

[0071] like Figure 3 As shown, the second example of the personalized recommendation method according to the embodiment of the present application is applied to the server S as described above, which includes the following steps.

[0072] Step S210, obtaining user selection feature data from a terminal, wherein the user selection feature data represents a user's selection of an interactive option for interactive media content; Step S220, obtaining user type feature data from the user selection feature data using a user classification model; Step S230, obtaining personalized recommendation results from the user type feature data using a personalized recommendation decision model; Step S240, obtaining content to be recommended from a recommended content resource library based on the personalized recommendation results; and Step S250, sending the content to be recommended to the terminal.

[0073] That is, in the second example of the personalized recommendation method according to the embodiment of the present application, the user classification model and the personalized recommendation decision model are set on the server side, for example, Figure 1 The server S shown uses the user selection data obtained from the terminal to make personalized recommendations.

[0074] In one example, in the above-mentioned personalized recommendation method, obtaining user selection feature data from a terminal includes: obtaining user original selection data from a terminal; and extracting the user selection feature data from the user original selection data, wherein the user selection feature data includes at least one of selection options, selection speed, and whether to skip a selection.

[0075] That is, in the second example of the personalized recommendation method according to the embodiment of the present application, the original selection data of the user can be directly obtained from the terminal, and then the user selection feature data can be extracted on the server side.

[0076] Furthermore, as described above, the user's original selection data can be acquired from the terminal in real time, and the user's original selection data acquired from the terminal within a predetermined period of time can be accumulated on the server side.

[0077] Therefore, in one example, in the above-mentioned personalized recommendation method, obtaining the user's original selection data from the terminal includes: accumulating the user's original selection data obtained from the terminal within a predetermined time period.

[0078] Furthermore, in the second example of the personalized recommendation method according to the embodiment of the present application, the interactive options for user selection can be optimized based on at least one of the user classification model and the personalized recommendation decision model. Here, because the purposeful option design is easier to generate judgment results, and not all choices and results can be used to profile the user, in order to make a more accurate user profile for the user, it is necessary to optimize the design of the interactive option selection. For example, some professional assessments, such as psychological assessments, professional assessments, etc., or entertainment test selections can be referred to to package the options, making it easier to achieve the purpose of determining the user type.

[0079] Furthermore, after optimizing the interactive options, it is necessary to edit the interactive script using the optimized interactive options and send the edited interactive script to the terminal.

[0080] In addition, if the user classification model and the personalized recommendation decision model are set on the terminal device side, the interaction options can also be optimized on the terminal device side or the server side based on the user classification model and the personalized recommendation decision model, and the interaction script can be edited on the server side based on the optimized interaction options.

[0081] Here, those skilled in the art can understand that other aspects of the second example of the personalized recommendation method according to the embodiment of the present application are exactly the same as the corresponding parts of the first example of the personalized recommendation method according to the embodiment of the present application described in the "Exemplary Method One" section above, and will not be repeated here to avoid redundancy.

[0082] Exemplary Method Three

[0083] Figure 4 The figure illustrates a flow chart of a user interaction method for personalized recommendation according to an embodiment of the present application.

[0084] like Figure 4 As shown, the user interaction method for personalized recommendation according to an embodiment of the present application includes: S310, receiving a user's selection operation on an interactive option of interactive media content to obtain original user selection data; S320, extracting user selection feature data from the original user selection data, wherein the user selection feature data represents the user's selection of the interactive option; S330, sending the user selection feature data to a server; and, S340, receiving a personalized recommendation result based on the user selection feature data from the server.

[0085] like Figure 1 As shown, the terminal device T receives the user's selection operation from the user U to obtain the user's original selection data from the selection operation. Here, the user's selection operation can be in various forms, such as gestures, voice, etc. In addition, the user's selection operation can be obtained in various ways, such as sensors, cameras, etc.

[0086] Therefore, in the user interaction method for personalized recommendation according to an embodiment of the present application, the user's selection operation on the interactive option of the interactive media content includes the user's selection operation on the interactive option of the interactive media content made by at least one of gesture, voice, sensor, and camera.

[0087] After receiving the user's selection operation, the user selection feature data can be extracted according to the process described in the previous "Example Method One" section, and the user selection feature data can be sent to the server, which uses the user classification model and the personalized recommendation decision model to generate personalized recommendation results.

[0088] Application Examples

[0089] Figure 5 The figure illustrates a schematic process of an application example of the personalized recommendation method according to an embodiment of the present application.

[0090] like Figure 5 As shown, the personalized recommendation method according to the embodiment of the present application is applied to recommend promotional content to the user based on the user's selection of the interactive video.

[0091] First, users will have various forms of choices during the interactive video viewing process, which can trigger different selection results. Next, by accumulating individual user choices, sufficient user selection data is obtained. For example, user selection data may include selection options, selection consumption time, whether to skip playback, and other data.

[0092] After that, the user feature raw data that can be used to describe the user behavior characteristics is extracted through preliminary screening as the input parameter of the user classification model. The user classification model determines the type of user based on the user feature raw data through a predetermined algorithm model and outputs the user type feature key data. The user type feature key data is used to describe the user type and similarity, which can be composed of multiple established user types and their similarities.

[0093] Next, the user type feature key data is used as an input parameter of the personalized recommendation content decision model, and the personalized recommendation content decision model determines the personalized recommendation content for the user based on the user type feature key data. Here, the input parameters of the personalized recommendation content decision model are not limited to the user type feature key data, but can also include additional operation parameters according to the needs of the scenario. In addition, the personalized recommendation content decision model can also recommend different content according to different actual usage scenarios.

[0094] Here, the personalized recommended content includes but is not limited to games, interactive dramas, videos, advertisements, etc. Finally, the promotion position content is displayed, that is, the promotion content is automatically played through the display position of the personalized recommended content.

[0095] In this way, user preferences can be analyzed and judged based on the branch selection of interactive videos, so as to make personalized recommendations.

[0096] Figure 6 The figure illustrates a schematic system architecture of an application example of the personalized recommendation method according to an embodiment of the present application.

[0097] like Figure 6 As shown, in this system architecture, the server side sends interactive scripts and reasoning algorithm models, where the reasoning algorithm model may include a user classification model and a recommended content decision model. In addition, the server side includes a promotional content resource library, which is used to send the recommended promotional content to the client based on the recommended content decided. In addition, the server side can also perform basic interactive playback configuration and user asset reporting.

[0098] In addition, on the client side, user selection data is collected, and based on the user selection data, the user classification model and the recommended content decision model are used to decide the recommended content. In addition, the client side displays the promotional content based on the promotional content sent by the server side. In addition, the client side can also perform basic interactive playback, basic interactive playback reporting, and interactive playback data collection.

[0099] Through the above system architecture, the branch options of interactive videos can be designed based on the video content on the server side, making it easier to determine the user type.

[0100] In addition, the client can perform reasoning based on the dynamically issued decision model, and further improve the algorithm based on feedback information of the recommended content, such as exposure and click data, to improve intelligent personalized recommendations based on interactive playback.

[0101] Exemplary device 1

[0102] Figure 7 A block diagram of a first example of a personalized recommendation device according to an embodiment of the present application is illustrated.

[0103] like Figure 7 As shown, according to the first example of an embodiment of the present application, a personalized recommendation device 400 includes: a data acquisition unit 410, used to acquire user selection feature data, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; a user classification unit 420, used to classify users using the user selection feature data to obtain user type feature data; and a personalized recommendation unit 430, used to determine personalized recommendation results using the user type feature data.

[0104] In one example, in the above-mentioned personalized recommendation device 400, the data acquisition unit 410 is used to: obtain the user's original selection data; and extract the user selection feature data from the user's original selection data, wherein the user selection feature data includes at least one of selection options, selection speed, selection time, current time, and whether to skip the selection.

[0105] In one example, in the personalized recommendation device 400 , the data acquisition unit 410 acquires the user's original selection data, including: accumulating the user's original selection data within a predetermined time period.

[0106] In one example, in the personalized recommendation device 400 , the user type characteristic data includes whether the user type belongs to one of a plurality of preset user types and the similarity between the user type and the preset user type to which it belongs.

[0107] In one example, in the personalized recommendation device 400 , the preset user type includes at least one of the user's age, region, gender, and preferences.

[0108] In one example, in the above-mentioned personalized recommendation device 400, the user classification unit 420 is used to: obtain a user classification model sent from a server; and obtain the user type feature data using the user selection feature data with the user classification model.

[0109] In one example, in the personalized recommendation device 400, the personalized recommendation unit 430 is used to: obtain a personalized recommendation decision model sent from a server; and determine the personalized recommendation result using the personalized recommendation decision model using the user type feature data.

[0110] In one example, the above-mentioned personalized recommendation device 400 further includes: a content request unit, which is used to send a recommended content request to the server based on the personalized recommendation result; a content acquisition unit, which is used to acquire the content to be recommended from the recommended content resource library of the server; and a content display unit, which is used to display the content to be recommended.

[0111] In one example, in the above-mentioned personalized recommendation device 400, the content to be recommended includes advertisements recommended to the user.

[0112] In one example, the personalized recommendation device 400 further includes: an operation receiving unit for obtaining a user's operation on the content to be recommended; and a model optimization unit for optimizing the issued personalized recommendation decision model based on the operation.

[0113] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the personalized recommendation device 400 have been described in detail above. Figure 2 The personalized recommendation method has been described in detail in the description of , and therefore, its repeated description will be omitted.

[0114] As described above, the personalized recommendation device 400 according to the embodiment of the present application can be implemented in various terminal devices, such as a user's smart phone, etc. In one example, the personalized recommendation device 400 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the personalized recommendation device 400 can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the personalized recommendation device 400 can also be one of the many hardware modules of the terminal device.

[0115] Alternatively, in another example, the personalized recommendation apparatus 400 and the terminal device may also be separate devices, and the personalized recommendation apparatus 400 may be connected to the terminal device via a wired and / or wireless network, and transmit the interaction information in a predetermined data format.

[0116] Exemplary device 2

[0117] Figure 8 A block diagram of a second example of a personalized recommendation device according to an embodiment of the present application is illustrated.

[0118] like Figure 8 As shown, according to the second example of the embodiment of the present application, the personalized recommendation device 500 includes: a terminal receiving unit 510, used to obtain user selection feature data from the terminal, wherein the user selection feature data represents the user's selection of interactive options for interactive media content; a perception model unit 520, used to obtain user type feature data from the user selection feature data using a user classification model; a recommendation model unit 530, used to determine a personalized recommendation result from the user type feature data using a personalized recommendation decision model; a content retrieval unit 540, used to obtain content to be recommended from a recommended content resource library based on the personalized recommendation result; and a content sending unit 550, used to send the content to be recommended to the terminal.

[0119] In one example, in the above-mentioned personalized recommendation device 500, the terminal receiving unit 510 is used to: obtain the user's original selection data from the terminal; and extract the user selection feature data from the user's original selection data, wherein the user selection feature data includes at least one of selection options, selection speed, selection time, current time, and whether to skip the selection.

[0120] In one example, in the above-mentioned personalized recommendation device 500, the terminal receiving unit 510 acquires the user original selection data from the terminal, including: accumulating the user original selection data acquired from the terminal within a predetermined time period.

[0121] In one example, the above-mentioned personalized recommendation device 500 further includes: an option optimization unit, which is used to optimize the interactive options based on at least one of the user classification model and the personalized recommendation decision model; a script editing unit, which is used to edit the interactive script using the optimized interactive options; and a script sending unit, which is used to send the edited interactive script to the terminal.

[0122] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the personalized recommendation device 500 have been described in detail above. Figure 3 The personalized recommendation method has been described in detail in the description of , and therefore, its repeated description will be omitted.

[0123] As described above, the personalized recommendation device 500 according to the embodiment of the present application can be implemented in various server devices, such as a server of a video service provider. In one example, the personalized recommendation device 500 according to the embodiment of the present application can be integrated into the server device as a software module and / or a hardware module. For example, the personalized recommendation device 500 can be a software module in the operating system of the server device, or can be an application developed for the server device; of course, the personalized recommendation device 500 can also be one of the many hardware modules of the server device.

[0124] Alternatively, in another example, the personalized recommendation apparatus 500 and the server device may also be separate devices, and the personalized recommendation apparatus 500 may be connected to the server device via a wired and / or wireless network, and transmit the interaction information in a predetermined data format.

[0125] Exemplary device three

[0126] Fig. 9 The figure illustrates a block diagram of a user interaction device for personalized recommendation according to an embodiment of the present application.

[0127] like Fig. 9 As shown, according to an embodiment of the present application, a user interaction device 600 for personalized recommendation includes: an operation receiving unit 610, used to receive a user's selection operation on an interactive option of interactive media content to obtain original user selection data; a feature extraction unit 620, used to extract user selection feature data from the original user selection data, wherein the user selection feature data represents the user's selection of the interactive option; a feature sending unit 630, used to send the user selection feature data to a server; and a recommendation receiving unit 640, used to receive a personalized recommendation result based on the user selection feature data from the server.

[0128] In one example, in the above-mentioned user interaction device 600 for personalized recommendation, the user's selection operation on the interactive option of the interactive media content includes the user's selection operation on the interactive option of the interactive media content made by at least one of gesture, voice, sensor, and camera.

[0129] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the above-mentioned user interaction device 600 for personalized recommendation have been described in detail above. Figure 4 It has been described in detail in the description of the user interaction method for personalized recommendation, and therefore, its repeated description will be omitted.

[0130] As described above, the user interaction device 600 for personalized recommendation according to the embodiment of the present application can be implemented in various terminal devices, such as a user's smart phone, etc. In one example, the user interaction device 600 for personalized recommendation according to the embodiment of the present application can be integrated into a server device as a software module and / or a hardware module. For example, the user interaction device 600 for personalized recommendation can be a software module in the operating system of the server device, or can be an application developed for the server device; of course, the user interaction device 600 for personalized recommendation can also be one of the many hardware modules of the server device.

[0131] Alternatively, in another example, the user interaction device 600 for personalized recommendation and the server device may also be separate devices, and the user interaction device 600 for personalized recommendation may be connected to the server device via a wired and / or wireless network and transmit interaction information in accordance with an agreed data format.

[0132] Exemplary Electronic Devices

[0133] Below, reference Fig.10 To describe an electronic device according to an embodiment of the present application.

[0134] Fig.10 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0135] like Fig.10 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0136] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0137] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the personalized recommendation method and user interaction method for personalized recommendation of the various embodiments of the present application described above and / or other desired functions. Various contents such as user classification models, personalized recommendation decision models, etc. may also be stored in the computer-readable storage medium.

[0138] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0139] The input device 13 may include, for example, a keyboard, a mouse, etc.

[0140] The output device 14 can output various information to the outside, including personalized recommendation results, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0141] Of course, to simplify, Fig.10 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0142] Exemplary computer program products and computer-readable storage media

[0143] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the personalized recommendation method and the user interaction method for personalized recommendation according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0144] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the first user computing device, partially on the first user computing device, as an independent software package, partially on the first user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0145] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps of the personalized recommendation method and the user interaction method for personalized recommendation according to various embodiments of the present application described in the above “Exemplary Method” section of this specification.

[0146] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.

[0147] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0148] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0149] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0150] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0151] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A personalized recommendation method, comprising: Acquiring user selection feature data, wherein the user selection feature data represents a user's selection of an interactive option for the interactive media content, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; Using the user selection feature data and the user classification model to classify the user to obtain user type feature data; and Determine a personalized recommendation result using the user type feature data and a personalized recommendation decision model; The method further comprises: Optimize interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

2. The personalized recommendation method according to claim 1, wherein: Obtaining user-selected feature data includes: Get the user's original selection data; The user selection feature data is extracted from the user original selection data, and the user selection feature data includes at least one of a selection option, a selection speed, a selection time, a current time, and whether to skip a selection.

3. The personalized recommendation method according to claim 1, wherein: Obtaining the user's original selection data includes: The user's original selection data within a predetermined period of time is accumulated.

4. The personalized recommendation method according to claim 1, wherein: The user type characteristic data includes whether the user type belongs to one of a plurality of preset user types and the similarity between the user type and the preset user type to which it belongs.

5. The personalized recommendation method according to claim 4, wherein: The preset user type includes at least one of the user's age, region, gender, and preferences.

6. The personalized recommendation method according to claim 1, further comprising: Get the user classification model sent from the server.

7. The personalized recommendation method according to claim 1, further comprising: Get the personalized recommendation decision model sent from the server.

8. The personalized recommendation method according to claim 7, wherein: After using the user type feature data to determine the personalized recommendation result with the personalized recommendation decision model, the method further includes: Sending a recommendation content request to a server based on the personalized recommendation result; Acquire the content to be recommended from the recommended content resource library of the server; and Display the recommended content.

9. The personalized recommendation method according to claim 8, wherein: The content to be recommended includes advertisements recommended to the user.

10. The personalized recommendation method according to claim 8, wherein: After displaying the content to be recommended, further comprising: Obtaining the user's operation on the content to be recommended; The issued personalized recommendation decision model is optimized based on the operation.

11. A personalized recommendation method, comprising: Acquiring user selection feature data from a terminal, the user selection feature data indicating a user's selection of an interactive option for the interactive media content, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; Using a user classification model to classify the user based on the user selection feature data to obtain user type feature data; Determine a personalized recommendation result from the user type feature data using a personalized recommendation decision model; Acquiring content to be recommended from a recommended content resource library based on the personalized recommendation result; and Sending the content to be recommended to the terminal; The method further comprises: Optimize interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

12. The personalized recommendation method according to claim 11, wherein: Acquiring user selection feature data from the terminal includes: Get the user's original selection data from the terminal; The user selection feature data is extracted from the user original selection data, and the user selection feature data includes at least one of a selection option, a selection speed, a selection time, a current time, and whether to skip a selection.

13. The personalized recommendation method according to claim 11, wherein: Obtaining the user's original selection data from the terminal includes: The user original selection data acquired from the terminal within a predetermined time period is accumulated.

14. The personalized recommendation method according to claim 11, further comprising: Edit interactive scripts with optimized interactive options; as well as The edited interactive script is sent to the terminal.

15. A user interaction method for personalized recommendation, comprising: Receiving a user's selection operation on an interactive option of the interactive media content to obtain original user selection data, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; Extracting user selection feature data from the user original selection data, wherein the user selection feature data represents the user's selection of the interactive option; sending the user selected feature data to a server; and receiving a personalized recommendation result based on the user selection feature data from the server; the server is used to classify the user based on the user selection feature data using a user classification model to obtain user type feature data, and determine the personalized recommendation result from the user type feature data using a personalized recommendation decision model; The method further comprises: Optimize interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

16. The user interaction method for personalized recommendation according to claim 15, wherein: The user's selection operation on the interactive option of the interactive media content includes the user's selection operation on the interactive option of the interactive media content made by at least one of gesture, voice, sensor, and camera.

17. A personalized recommendation device, comprising: a data acquisition unit, configured to acquire user selection feature data, wherein the user selection feature data represents a user's selection of an interactive option for the interactive media content, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; A user classification unit, configured to classify users using the user selection feature data and a user classification model to obtain user type feature data; and A personalized recommendation unit, used to obtain personalized recommendation results using the user type feature data and a personalized recommendation decision model; An option optimization unit is used to optimize the interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

18. A personalized recommendation device, comprising: A terminal receiving unit, configured to obtain user selection characteristic data from a terminal, wherein the user selection characteristic data indicates a user's selection of an interactive option for the interactive media content, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; A classification model unit, configured to classify the user based on the user selection feature data using a user classification model to obtain user type feature data; A recommendation model unit, configured to obtain a personalized recommendation result from the user type feature data using a personalized recommendation decision model; A content retrieval unit, configured to obtain content to be recommended from a recommended content resource library based on the personalized recommendation result; and A content sending unit, used for sending the content to be recommended to the terminal; An option optimization unit is used to optimize the interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

19. A user interaction device for personalized recommendation, comprising: An operation receiving unit, used for receiving a user's selection operation on an interactive option of the interactive media content to obtain original selection data of the user, wherein when the interactive media content is played to an interactive node, different interactive options are displayed, and the different interactive options are used to enter different interactive branches; A feature extraction unit, configured to extract user selection feature data from the user original selection data, wherein the user selection feature data represents the user's selection of the interactive option; a feature sending unit, configured to send the user selected feature data to a server; and a recommendation receiving unit, configured to receive a personalized recommendation result based on the user selection feature data from the server; the server is configured to classify the user based on the user selection feature data using a user classification model to obtain user type feature data, and determine the personalized recommendation result from the user type feature data using a personalized recommendation decision model; An option optimization unit is used to optimize the interactive options for user selection based on at least one of the user classification model and the personalized recommendation decision model.

20. An electronic device, comprising: processor; as well as A memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the personalized recommendation method as described in any one of claims 1 to 10, or the personalized recommendation method as described in any one of claims 11 to 14, or the user interaction method for personalized recommendation as described in claim 15 or 16.

21. A computer-readable storage medium storing computer program instructions, which, when executed by a processor, cause the processor to execute the personalized recommendation method as described in any one of claims 1-10, or the personalized recommendation method as described in any one of claims 11-14, or the user interaction method for personalized recommendation as described in claim 15 or 16.

22. A computer program product, comprising computer program instructions, which, when executed by a processor, cause the processor to execute the personalized recommendation method as described in any one of claims 1-10, or the personalized recommendation method as described in any one of claims 11-14, or the user interaction method for personalized recommendation as described in claim 15 or 16.

Images