Recommendation processing method based on virtual object interaction, computing equipment and storage medium
By matching the virtual object interaction page with user needs, and using the virtual object dialogue feature feedback information, the problem that existing recommendation systems are difficult to meet personalized needs is solved, and accurate recommendations and user interaction experience are improved.
Patent Information
- Application Number
- CN202310854422.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-12
- Publication Date
- 2025-01-14
AI Technical Summary
The existing information recommendation system is difficult to meet the personalized needs of users. The recommendation form is single, and there is a lack of user interaction, so it cannot provide an accurate and interesting recommendation experience.
By displaying the virtual object interaction page corresponding to user needs, users can talk to the virtual object and provide demand information. The server feedbacks the information based on the dialogue characteristics of the virtual object and determines the items to be recommended, increasing the diversity of user interaction and recommendation forms .
It achieves accurate satisfaction of users' personalized needs, improves user participation and interactive experience, provides immersive interaction methods, enriches recommendation forms, and enhances user interest and stickiness.
Smart Images
Figure CN119311939A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information processing technology, and in particular to a recommendation processing method based on virtual object interaction, a computing device and a storage medium. Background Art
[0002] In existing information recommendation scenarios, the platform's current main push item information and item information that matches the user's historical data are usually added to the page and presented to the user through the page to achieve item information recommendation. However, the recommended item information is determined based on the platform's current main push strategy, user historical data, etc., which makes it difficult to meet the user's potential personalized needs. The recommended item information is usually presented directly to the user in the form of a page, with a single recommendation format and a lack of interaction with the user. Summary of the invention
[0003] In view of the above problems, the present invention is proposed to provide a recommendation processing method based on virtual object interaction, a computing device and a storage medium that overcome the above problems or at least partially solve the above problems.
[0004] According to one aspect of the present invention, a recommendation processing method based on virtual object interaction is provided, the method comprising:
[0005] Displaying interactive pages of target virtual objects corresponding to the target user demand classification;
[0006] In response to a demand sending request carrying user demand information executed by the user in the interactive page, the user's demand processing rights are cancelled, and the user demand information is provided to the server, so that the server can feedback the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the items to be recommended;
[0007] Display object feedback information and information about items to be recommended in the interactive interface.
[0008] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;
[0009] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:
[0010] Displaying interactive pages of target virtual objects corresponding to the target user demand classification;
[0011] In response to a demand sending request carrying user demand information executed by the user in the interactive page, the user's demand processing rights are cancelled, and the user demand information is provided to the server, so that the server can feedback the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the items to be recommended;
[0012] Display object feedback information and information about items to be recommended in the interactive interface.
[0013] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned recommendation processing method based on virtual object interaction.
[0014] According to the technical solution provided by the present invention, the user can enter the interactive page of the virtual object to provide his own user demand information, and obtain object feedback information and information on items to be recommended through analysis and processing of the user demand information, and reply to the user in the form of dialogue with the virtual object. This not only can well meet the user's personalized potential needs and accurately recommend the required item information to the user, but also increases user interaction, greatly enriches the interaction form, enhances the user's interest and enthusiasm in participating in the interaction, and enables the user to have an immersive interactive experience.
[0015] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0017] Figure 1 A schematic flow chart of a recommendation processing method based on virtual object interaction according to Embodiment 1 of the present invention is shown;
[0018] Figure 2a A schematic flow chart of a recommendation processing method based on virtual object interaction according to Embodiment 2 of the present invention is shown;
[0019] Figure 2b A schematic diagram of a user demand classification selection page is shown;
[0020] Figure 2cA schematic diagram of the user demand information input area is shown;
[0021] Figure 2d A schematic diagram of an interactive page showing object feedback information and information of items to be recommended is shown;
[0022] Figure 2e A schematic diagram of an interactive page showing object feedback information and information of electronic books to be recommended is shown;
[0023] Figure 3 A schematic diagram of the structure of a computing device according to a fourth embodiment of the present invention is shown. DETAILED DESCRIPTION
[0024] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0025] The present invention provides a recommendation processing scheme based on virtual object interaction, which provides users with information recommendation scenarios realized by interacting with virtual objects in shopping platforms, e-book reading platforms, etc. Users can enter the interaction page of the virtual object to provide their own user demand information, and obtain object feedback information and information on items to be recommended through analysis and processing of the user demand information, and reply to the user in the form of dialogue with the virtual object, which can not only well meet the user's personalized potential needs and accurately recommend the required item information to the user, but also increase user interaction, greatly enrich the interaction form, and enhance the user's interest and enthusiasm in participating in the interaction, so that the user can obtain an immersive interactive experience. The recommendation processing method based on virtual object interaction provided by the present invention is described below through specific embodiments.
[0026] Embodiment 1
[0027] Figure 1 FIG. 4 is a flow chart showing a recommendation processing method based on virtual object interaction according to Embodiment 1 of the present invention. Figure 1 As shown, the method comprises the following steps:
[0028] Step S101, displaying an interactive page of a target virtual object corresponding to the target user's demand classification.
[0029] In this embodiment, multiple user demand categories can be pre-set for users to choose from. Taking the e-book recommendation field as an example, multiple user demand categories may include academic needs, resource needs, social needs, etc.; among them, academic needs refer to users wanting to make progress or achievements in academics, and wanting to obtain some advice information on enhanced learning, information on e-books to be recommended, etc. through dialogue and interaction with virtual objects; resource needs refer to users wanting to make progress in resources, and wanting to obtain some advice information on value-added and entrepreneurship, information on e-books to be recommended, etc. through dialogue and interaction with virtual objects; social needs refer to users wanting to make progress in social aspects, and wanting to obtain some advice information on increasing social activities and improving social relationships, information on e-books to be recommended, etc. through dialogue and interaction with virtual objects.
[0030] In this embodiment, a corresponding virtual object can be matched for each user demand classification. In this step, the user demand classification selected by the user is called the target user demand classification. After the user selects the target user demand classification, an interactive page of the target virtual object corresponding to the target user demand classification is displayed.
[0031] Step S102, in response to a demand sending request carrying user demand information executed by the user in the interactive page, the user's demand processing rights are cancelled, and the user demand information is provided to the server, so that the server can feedback the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the items to be recommended.
[0032] In this step, the user can enter the user demand information in the pre-set user demand information input area in the interactive page and execute the demand sending request. According to the demand sending request, the demand processing rights in the user account are written off. Generally speaking, the user demand information entered by the user must correspond to the target user demand classification selected in step S101; for example, if the target user demand classification is resource demand, the input user demand information must be related to the resource demand. Among them, the demand processing rights refer to the number of conversations that the user can have with the target virtual object, the conversation duration, or the number of conversations within a unit duration.
[0033] After providing the user demand information to the server, the server will feedback the user demand information based on the dialogue characteristics of the target virtual object to obtain object feedback information. The object feedback information can be regarded as a reply to the user demand information and can be displayed in the interactive page in the form of voice broadcast, graphic display, etc. The server can also further determine the information of the items to be recommended based on the object feedback information and the user demand information using a pre-set recommendation algorithm; wherein the information of the items to be recommended includes: the name, picture, introduction information, etc. of the items corresponding to the information of the items to be recommended. The items can include e-books, other recommended products, such as clothing, daily necessities, snacks, etc.
[0034] Step S103: displaying the object feedback information and the information of the items to be recommended in the interactive interface.
[0035] Specifically, object feedback information and information on items to be recommended can be displayed in the interactive interface in the form of pop-up windows. It should be noted that object feedback information can be played with voice sound effects related to the personality traits and dialogue characteristics of the target virtual object; users can view the information on items to be recommended and choose whether to receive the information on items to be recommended. If the items corresponding to the information on items to be recommended are recommended products such as clothing, they can be added to the user's shopping cart or purchased with one click after the user confirms receipt; if the item is an e-book, it can be added to the user's bookshelf for the user to read after the user confirms receipt, or the user can be redirected to the corresponding e-book reading page for reading.
[0036] By utilizing the recommendation processing method based on virtual object interaction provided in this embodiment, users can enter the interaction page of the virtual object to provide their own user demand information, obtain object feedback information and information on items to be recommended through analysis and processing of the user demand information, and reply to the user in the form of dialogue with the virtual object. This not only can well meet the user's personalized potential needs and accurately recommend the required item information to the user, but also increases user interaction, greatly enriches the interaction form, enhances the user's interest and enthusiasm in participating in the interaction, and enables the user to have an immersive interactive experience.
[0037] Embodiment 2
[0038] Figure 2a FIG. 4 shows a flow chart of a recommendation processing method based on virtual object interaction according to Embodiment 2 of the present invention. Figure 2a As shown, the method comprises the following steps:
[0039] Step S201, displaying a user demand category selection page including selection controls corresponding to a plurality of user demand categories; in response to a selection request executed by a user for any selection control, determining the user demand category corresponding to any selection control as a target user demand category.
[0040] Taking the e-book recommendation field as an example, multiple user demand categories may include social needs, resource needs, academic needs, etc. Taking the commodity recommendation field as an example, multiple user demand categories may include clothing needs, daily necessities needs, food needs, furniture needs, electrical appliance needs, etc. Those skilled in the art may set user demand categories according to specific recommendation fields, which are not limited here.
[0041] Figure 2b A schematic diagram of a user demand classification selection page is shown, such as Figure 2b As shown, the user demand classification selection page includes selection controls corresponding to multiple user demand classifications such as academic needs, resource needs, and social needs. Users can execute selection requests for any selection control according to their own needs, determine the user demand classification corresponding to the user selection control as the target user demand classification, and determine the corresponding target virtual object according to the target user demand classification.
[0042] Step S202: displaying an interactive page of a target virtual object corresponding to the target user's requirement classification.
[0043] Each user demand classification is matched with its corresponding virtual object. The virtual objects corresponding to each user demand classification can be counted based on massive content, and more representative personalized roles can be selected. The information reserves and role identities of each virtual object in its corresponding field can be given by training the dialogue model, and the information interaction method of each virtual object can be trained through the model to make its communication have the personality characteristics, language, intonation and other dialogue characteristics corresponding to its role identity, so that users can obtain a realistic dialogue environment with virtual objects when exchanging information with virtual objects, which helps to increase the interest of users in interacting with virtual objects. Among them, these virtual objects can be popular characters that are familiar to people. For example, if the target user demand is classified as resource demand, the corresponding target virtual object can be a person who has made great achievements in resources in history, or a character related to resources in a book. The dialogue model is trained through historical records or book content to learn the character's personality characteristics, etc., to achieve a usable level of interaction.
[0044] Step S203, in response to the trigger request executed by the user for the rights processing control in the interactive page, the user's virtual items are cancelled and the user is allocated the required processing rights.
[0045] In this step, the interactive interface may display a rights processing control for the user to operate. In response to the user's trigger request for executing the rights processing control, multiple virtual items of different levels are displayed through pop-up windows or other means, the virtual items selected by the user are written off, and the corresponding demand processing rights are allocated to the user. Among them, virtual items are purchased using the user's account resources; virtual items may include items of multiple levels, and the number of account resources required to consume virtual items of each level is different. The value parameters of the items corresponding to the information of recommended items obtained by interacting with virtual objects are associated with the value parameters of virtual items. For example, the more account resources consumed to purchase a virtual item, the higher the value parameter of the virtual item, and the higher the value parameter of the item corresponding to the information of recommended items obtained in the end. Virtual items may include: bouquets, cakes, utensils and other items; when the user selects any virtual item for verification, the virtual item can also be displayed in the interactive page, for example, displayed next to the avatar of the target virtual object, to highlight that the user successfully provides the virtual item to the target virtual object, and obtain a realistic interactive experience.
[0046] Step S204, in response to the demand sending request carrying the user demand information executed by the user in the interactive page, the user's demand processing rights are cancelled, and the user demand information is provided to the server.
[0047] In an optional embodiment, the interactive page includes a user demand information entry area, and the method further includes: in response to a selection request executed by the user in the user demand information entry area for any preset demand information, determining any preset demand information as user demand information; or, in response to an information input request executed by the user in the user demand information entry area, determining the information input by the user as user demand information.
[0048] Figure 2c A schematic diagram of the user demand information input area is shown, such as Figure 2c As shown, after the user selects the virtual item, a user demand information input area is displayed in the interactive page, and the user can enter the user demand information through the user demand information input area, wherein the input method may include two methods, one is to preset a variety of demand information for the user to choose from, for example, for each target user demand classification, there are a variety of common demand information preset for it; the other is that the user independently inputs the specific text information of the user demand; it should be noted that the text information input by the user needs to correspond to the target user demand classification selected by the user; for example, if the user selects academic needs as the target user demand classification, the text information input by the user may be related to the academic needs, for example: "English learning**" and other text information.
[0049] After receiving the user demand information sent by the client, the server feeds back the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information. Specifically, for example, the target virtual object corresponding to the academic demand is a certain character. By training the dialogue model, the main deeds, language style, role image, etc. of the character in its corresponding field are given to the character. The information interaction method of the character is trained through the model so that the communication has the personality characteristics, language, intonation and other dialogue characteristics corresponding to its role identity, and the dialogue characteristics of the character are learned. According to the user demand information selected or input by the user, the object feedback information of the virtual object is obtained through artificial intelligence learning and understanding, and the object feedback information is displayed in the interactive page in the form of dialogue.
[0050] Among them, the dialogue model can be a generative large language model (Generative Large Language Mode), such as ChatGPT (Chat Generative Pre-trained Transformer) model, BERT (Bidirectional Encoder Representation from Transformers) model, or ERNIE (Enhanced Representation through Knowledge Integration) model, etc. The dialogue model is essentially a generative model, which is an AI (Artificial Intelligence) model obtained by training the neural network structure with a large amount of language data. The dialogue model can understand natural language well and output relevant results that conform to natural language instructions.
[0051] Optionally, after receiving the object feedback information, the user can continue to communicate with the target virtual object in the form of a dialogue on the interaction page, forming multiple dialogue records, wherein the information entered by the user is called user demand information, and the information replied by the target virtual object is called object feedback information; wherein, in order to further enhance the interactive experience, the object feedback information can be played in the form of voice playback.
[0052] In an optional implementation, the server may determine the recommendation demand information based on the user demand information and / or the object feedback information; based on the recommendation demand information, call the item recommendation model to perform recommendation processing to obtain the item information to be recommended. For example, at least part of the user demand information and / or at least part of the object feedback information is determined as the recommendation demand information; feature extraction is performed on the recommendation demand information to obtain a feature vector; the feature vector is input into the item recommendation model to perform recommendation processing to obtain the item information to be recommended.
[0053] Specifically, user demand information and / or object feedback information in the interactive page are collected, part or all of the user demand information and / or object feedback information is sent to the server, the server calls the item recommendation model, takes part or all of the user demand information and / or object feedback information as input, applies the item recommendation algorithm according to the user demand information and / or object feedback information through the item recommendation model, and outputs the information of the item to be recommended; specifically, the recommendation demand information can be information feature vectorized (embedding) to obtain multiple feature vectors; the feature vectors are input into the item recommendation model for recommendation processing to obtain the information of the item to be recommended. Those skilled in the art can select the item recommendation model according to actual needs, which is not limited here.
[0054] Taking the e-book recommendation field as an example, the information of items to be recommended includes the information of e-books to be recommended, which may specifically include the name, cover image and other information of one or more e-books. Among them, the value parameters of the items corresponding to the information of items to be recommended are associated with the value parameters of virtual items, and the value parameters of the e-book information to be recommended include: the payment amount of the e-book corresponding to the information of e-book to be recommended and / or the reading rights of each chapter of the e-book. For example, different virtual items can represent different consumption powers selected by users, and can also be further bound to corresponding items to be recommended, such as reading rights of e-books. The more account resources consumed by the virtual items selected by the user, it may indicate that the user has more consumption attributes. When the algorithm generates the information of items to be recommended, it may tend to recommend e-books with higher value or give priority to paid e-books among free e-books and paid e-books, or it may correspond the consumed account resources to reading rights, etc.
[0055] Step S205: displaying the object feedback information and the information of the items to be recommended in the interactive interface in the form of voice broadcast.
[0056] Figure 2d A schematic diagram of an interactive page showing object feedback information and information about items to be recommended is shown in FIG. Figure 2d As shown, after the object feedback information and the information of the items to be recommended are determined, the object feedback information and the information of the items to be recommended are played by voice playback in the interactive page. The interactive page may also include a playback control, and the user can repeat the voice playback by triggering the playback control.
[0057] Figure 2e A schematic diagram of an interactive page showing object feedback information and e-book information to be recommended is shown in FIG. Figure 2e As shown, the interactive page also displays a "Receive this book" control, and the user can trigger the control to add the e-book corresponding to the recommended e-book information to the user's bookshelf for subsequent reading by the user.
[0058] Step S206, obtaining the user's interaction behavior data for the item corresponding to the item information to be recommended, and allocating corresponding account resources to the user based on the interaction behavior data.
[0059] Taking the example of an e-book as the item corresponding to the information on recommended items, the user can be allocated corresponding account resources based on the interactive behavior data generated when the user reads the recommended e-book (such as reading time data, completed chapter data, e-book payment data, like data, comment data, sharing data, etc.). These account resources can be used to purchase virtual items, so that the user can obtain more demand processing rights and interests to interact with the target virtual object; obtaining the information on recommended items through artificial intelligence can well meet the user's personalized potential needs, accurately recommend the required item information to the user, and avoid the user's difficulty in choosing an e-book suitable for their own reading when they do not understand the content of the e-book.
[0060] Optionally, the method further includes: in response to a virtual object switching request executed by the user in the interactive interface, displaying switching rejection information in the interactive interface, or not displaying any information.
[0061] The dialogue model training process is strictly trained according to the language characteristics of each virtual object. Therefore, in the interactive interface, the target virtual object should strictly play the virtual character corresponding to the role characteristics. If the user executes a virtual object switching request in the interactive interface, in order to avoid role confusion and maintain the role setting of the target virtual object, the interactive interface can display a switching rejection message, or no information is displayed for the virtual object switching request.
[0062] In order to better enhance the interactive experience, when displaying interactive pages and / or user demand classification selection pages, you can play preset background audio to create an interactive atmosphere. It takes a certain amount of time for the server to apply the item recommendation model to perform calculations. During this waiting period, playing the preset background audio can prevent users from feeling bored and improve the user experience.
[0063] By utilizing the recommendation processing method based on virtual object interaction provided in this embodiment, object feedback information and information on items to be recommended are obtained through analysis and processing of user demand information, and the information is replied to the user in the form of dialogue with the virtual object. This not only satisfies the user's personalized potential needs and accurately recommends the required item information to the user, but also increases user interaction, and enhances the interactive experience by playing object feedback information by voice. During user interaction, background music is used to create a scene atmosphere to prevent users from feeling bored while waiting for responses, greatly enriching the platform scenes and further improving user stickiness. Information on items to be recommended is obtained through artificial intelligence, and the required item information can be accurately recommended to users, preventing users from having difficulty choosing suitable items when they do not understand the item information. Account resources are allocated to users based on the interactive behavior data generated by users for the items to be recommended, so that users can obtain more demand processing rights and interests to interact with virtual objects, forming a closed-loop link and optimizing the recommendation processing method.
[0064] Embodiment 3
[0065] Embodiment 3 of the present invention provides a non-volatile storage medium, wherein the storage medium stores at least one executable instruction, and the executable instruction can execute the recommendation processing method based on virtual object interaction in any of the above method embodiments.
[0066] The executable instructions can be specifically used to enable the processor to perform the following operations: display an interactive page of a target virtual object corresponding to the target user demand classification; respond to a demand sending request carrying user demand information executed by the user in the interactive page, verify the user's demand processing rights, and provide the user demand information to the server, so that the server can feedback the user demand information based on the dialogue characteristics of the target virtual object to obtain object feedback information, and determine the information of items to be recommended; display the object feedback information and the information of items to be recommended in the interactive interface.
[0067] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: display a user demand category selection page containing selection controls corresponding to multiple user demand categories; and in response to a selection request executed by the user for any selection control, determine the user demand category corresponding to any selection control as a target user demand category.
[0068] In an optional embodiment, the interactive page includes a user demand information entry area, and the executable instructions further cause the processor to perform the following operations: in response to a selection request executed by the user in the user demand information entry area for any preset demand information, determine any preset demand information as user demand information; or, in response to an information input request executed by the user in the user demand information entry area, determine the information input by the user as user demand information.
[0069] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: in response to a trigger request executed by the user for a benefit processing control in the interactive page, cancel the user's virtual items and allocate demand processing benefits to the user.
[0070] In an optional implementation, the virtual item is purchased using the user's account resources.
[0071] In an optional implementation, the value parameter of the item corresponding to the to-be-recommended item information is associated with the value parameter of the virtual item.
[0072] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: determine recommendation demand information based on user demand information and / or object feedback information; and call the item recommendation model to perform recommendation processing based on the recommendation demand information to obtain information on items to be recommended.
[0073] In an optional implementation, the executable instructions further cause the processor to perform the following operations: determine at least part of the user demand information and / or at least part of the object feedback information as recommended demand information.
[0074] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: extract features from the recommendation demand information to obtain a feature vector; input the feature vector into an item recommendation model for recommendation processing to obtain information on items to be recommended.
[0075] In an optional implementation, the executable instructions further cause the processor to perform the following operations: displaying the object feedback information and the information of the items to be recommended in the interactive interface in the form of voice broadcast.
[0076] In an optional implementation, the executable instructions further cause the processor to perform the following operations: obtaining interactive behavior data generated by the user for the item corresponding to the information of the item to be recommended, and allocating corresponding account resources to the user based on the interactive behavior data.
[0077] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: in response to a virtual object switching request executed by the user in the interactive interface, display switching rejection information in the interactive interface, or do not display any information.
[0078] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: when displaying the interactive page and / or the user demand classification selection page, play the preset background audio.
[0079] In an optional implementation, the information of items to be recommended includes: information of e-books to be recommended; the value parameters of the e-books to be recommended include: the payment amount of the e-book corresponding to the e-book information to be recommended and / or the reading rights of each chapter of the e-book.
[0080] In an optional implementation, the executable instructions further cause the processor to perform the following operations: adding the e-book corresponding to the e-book information to be recommended to the user's bookshelf.
[0081] Embodiment 4
[0082] Figure 3 A schematic diagram of the structure of a computing device according to Embodiment 4 of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.
[0083] like Figure 3 As shown, the computing device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .
[0084] in:
[0085] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .
[0086] The communication interface 304 is used to communicate with other devices such as clients or other servers.
[0087] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned embodiment of the recommendation processing method based on virtual object interaction.
[0088] Specifically, the program 310 may include program codes, which include computer operation instructions.
[0089] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0090] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0091] Program 310 can be specifically used to enable processor 302 to perform the following operations: display an interactive page of a target virtual object corresponding to the target user demand classification; respond to a demand sending request carrying user demand information executed by the user in the interactive page, verify the user's demand processing rights, and provide the user demand information to the server, so that the server can feedback the user demand information based on the dialogue characteristics of the target virtual object to obtain object feedback information, and determine the information of items to be recommended; display the object feedback information and the information of items to be recommended in the interactive interface.
[0092] In an optional embodiment, program 310 further causes processor 302 to perform the following operations: display a user demand category selection page including selection controls corresponding to multiple user demand categories; and in response to a selection request executed by a user for any selection control, determine the user demand category corresponding to any selection control as a target user demand category.
[0093] In an optional embodiment, the interactive page includes a user demand information entry area, and the program 310 further enables the processor 302 to perform the following operations: in response to a selection request executed by the user in the user demand information entry area for any preset demand information, determine any preset demand information as user demand information; or, in response to an information input request executed by the user in the user demand information entry area, determine the information input by the user as user demand information.
[0094] In an optional embodiment, the program 310 further causes the processor 302 to perform the following operations: in response to a trigger request executed by the user for a benefit processing control in the interactive page, cancel the user's virtual items and allocate demand processing benefits to the user.
[0095] In an optional implementation, the virtual item is purchased using the user's account resources.
[0096] In an optional implementation, the value parameter of the item corresponding to the to-be-recommended item information is associated with the value parameter of the virtual item.
[0097] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: determine recommendation demand information based on user demand information and / or object feedback information; and call the item recommendation model to perform recommendation processing based on the recommendation demand information to obtain information on items to be recommended.
[0098] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: determine at least part of the user demand information and / or at least part of the object feedback information as recommended demand information.
[0099] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations: extract features from the recommendation demand information to obtain a feature vector; and input the feature vector into an item recommendation model for recommendation processing to obtain information on items to be recommended.
[0100] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: displaying the object feedback information and the information of the items to be recommended in the interactive interface in a voice broadcast manner.
[0101] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: obtaining the interaction behavior data generated by the user for the item corresponding to the information of the item to be recommended, and allocating corresponding account resources to the user based on the interaction behavior data.
[0102] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations: in response to a virtual object switching request executed by the user in the interactive interface, display switching rejection information in the interactive interface, or display no information.
[0103] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: when displaying the interactive page and / or the user demand classification selection page, play a preset background audio.
[0104] In an optional implementation, the information of items to be recommended includes: information of e-books to be recommended; the value parameters of the e-books to be recommended include: the payment amount of the e-book corresponding to the e-book information to be recommended and / or the reading rights of each chapter of the e-book.
[0105] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: adding the e-book corresponding to the e-book information to be recommended to the user's bookshelf.
[0106] The specific implementation of each step in program 310 can refer to the description of the corresponding steps in the above-mentioned recommendation processing embodiment based on virtual object interaction, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the device described above can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.
[0107] Through the solution provided in this embodiment, object feedback information and information on items to be recommended are obtained by analyzing and processing user demand information, and are replied to the user in the form of dialogue with a virtual object. This not only can well meet the user's personalized potential needs and accurately recommend the required item information to the user, but also increases user interaction and greatly enriches the interaction form.
[0108] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to realize the content of the present invention described herein, and the description of the above specific languages is for disclosing the best mode of the present invention.
[0109] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0110] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.
[0111] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.
[0112] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.
[0113] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including a number of different elements and by means of a suitably programmed computer. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.
[0114] A1. A recommendation processing method based on virtual object interaction, comprising:
[0115] Displaying interactive pages of target virtual objects corresponding to the target user demand classification;
[0116] In response to a demand sending request carrying user demand information executed by the user in the interactive page, the demand processing rights of the user are cancelled, and the user demand information is provided to the server, so that the server can feed back the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the item to be recommended;
[0117] The object feedback information and the information of the items to be recommended are displayed in the interactive interface.
[0118] A2. The method according to A1, wherein, before displaying the interactive page of the target virtual object corresponding to the target user demand classification, the method further comprises:
[0119] Display a user demand category selection page containing selection controls corresponding to multiple user demand categories;
[0120] In response to a selection request executed by the user for any selection control, a user demand category corresponding to the any selection control is determined as a target user demand category.
[0121] A3. The method according to A1 or A2, wherein the interactive page includes a user demand information input area, and the method further includes:
[0122] In response to a selection request performed by the user in the user demand information input area for any preset demand information, determining the any preset demand information as the user demand information;
[0123] Alternatively, in response to an information input request performed by the user in the user requirement information input area, the information input by the user is determined as the user requirement information.
[0124] A4. The method according to any one of A1 to A3, wherein after displaying the interactive page of the target virtual object corresponding to the target user demand classification, the method further comprises:
[0125] In response to a trigger request executed by the user for a benefit processing control in the interactive page, the virtual item of the user is cancelled and a demand processing benefit is allocated to the user.
[0126] A5. The method according to A4, wherein the virtual item is purchased using the user's account resources.
[0127] A6. The method according to A4 or A5, wherein the value parameter of the item corresponding to the item information to be recommended is associated with the value parameter of the virtual item.
[0128] A7. The method according to any one of A1 to A6, wherein determining the information of items to be recommended further comprises:
[0129] Determining recommended demand information according to the user demand information and / or the object feedback information;
[0130] Based on the recommendation demand information, the item recommendation model is called to perform recommendation processing to obtain the information of the item to be recommended.
[0131] A8. The method according to A7, wherein determining the recommended demand information based on the user demand information and / or the object feedback information further comprises:
[0132] At least part of the user demand information and / or at least part of the object feedback information is determined as recommended demand information.
[0133] A9. The method according to A7 or A8, wherein the step of calling an item recommendation model to perform recommendation processing based on the recommendation demand information to obtain the item information to be recommended further comprises:
[0134] Extracting features of the recommendation demand information to obtain a feature vector;
[0135] The feature vector is input into the item recommendation model for recommendation processing to obtain the item information to be recommended.
[0136] A10. The method according to any one of A1 to A9, wherein displaying the object feedback information and the information of the recommended items in the interactive interface further comprises:
[0137] The object feedback information and the information of the items to be recommended are displayed in the interactive interface in a voice broadcast manner.
[0138] A11. The method according to any one of A1 to A10, wherein after displaying the object feedback information and the information of the item to be recommended in the interactive interface, the method further comprises:
[0139] The interactive behavior data generated by the user for the item corresponding to the information of the item to be recommended is obtained, and the corresponding account resources are allocated to the user according to the interactive behavior data.
[0140] A12. The method according to any one of A1 to A11, wherein the method further comprises:
[0141] In response to a virtual object switching request executed by the user in the interactive interface, switching rejection information is displayed in the interactive interface, or no information is displayed.
[0142] A13. The method according to any one of A1 to A12, wherein the method further comprises:
[0143] When displaying the interactive page and / or the user demand classification selection page, play the preset background audio.
[0144] A14. A method according to any one of A1-A13, wherein the information of the item to be recommended includes: information of the e-book to be recommended; the value parameters of the e-book information to be recommended include: the payment amount of the e-book corresponding to the e-book information to be recommended and / or the reading rights of each chapter of the e-book.
[0145] A15. The method according to A14, wherein, after displaying the object feedback information and the information of the item to be recommended in the interactive interface, the method further comprises:
[0146] The e-book corresponding to the e-book information to be recommended is added to the user's bookshelf.
[0147] B16. A computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;
[0148] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:
[0149] Displaying interactive pages of target virtual objects corresponding to the target user demand classification;
[0150] In response to a demand sending request carrying user demand information executed by the user in the interactive page, the demand processing rights of the user are cancelled, and the user demand information is provided to the server, so that the server can feed back the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the item to be recommended;
[0151] The object feedback information and the information of the items to be recommended are displayed in the interactive interface.
[0152] B17. The computing device according to B16, wherein the executable instructions further cause the processor to perform the following operations:
[0153] Display a user demand category selection page containing selection controls corresponding to multiple user demand categories;
[0154] In response to a selection request executed by the user for any selection control, a user demand category corresponding to the any selection control is determined as a target user demand category.
[0155] B18. The computing device according to B16 or B17, wherein the interactive page includes a user demand information entry area, and the executable instructions further cause the processor to perform the following operations:
[0156] In response to a selection request performed by the user in the user demand information input area for any preset demand information, determining the any preset demand information as the user demand information;
[0157] Alternatively, in response to an information input request performed by the user in the user requirement information input area, the information input by the user is determined as the user requirement information.
[0158] B19. The computing device according to any one of B16-B18, wherein the executable instructions further cause the processor to perform the following operations:
[0159] In response to a trigger request executed by the user for a benefit processing control in the interactive page, the virtual item of the user is cancelled and a demand processing benefit is allocated to the user.
[0160] B20. According to the computing device described in B19, the virtual item is purchased using the user's account resources.
[0161] B21. According to the computing device described in B19 or B20, the value parameter of the item corresponding to the item information to be recommended is associated with the value parameter of the virtual item.
[0162] B22. The computing device according to any one of B16-B21, wherein the executable instructions further cause the processor to perform the following operations:
[0163] Determining recommended demand information according to the user demand information and / or the object feedback information;
[0164] Based on the recommendation demand information, the item recommendation model is called to perform recommendation processing to obtain the information of the item to be recommended.
[0165] B23. The computing device according to B22, wherein the executable instructions further cause the processor to perform the following operations:
[0166] At least part of the user demand information and / or at least part of the object feedback information is determined as recommended demand information.
[0167] B24. The computing device according to B22 or B23, wherein the executable instructions further cause the processor to perform the following operations:
[0168] Extracting features of the recommendation demand information to obtain a feature vector;
[0169] The feature vector is input into the item recommendation model for recommendation processing to obtain the item information to be recommended.
[0170] B25. The computing device according to any one of B16-B24, wherein the executable instructions further cause the processor to perform the following operations:
[0171] The object feedback information and the information of the items to be recommended are displayed in the interactive interface in a voice broadcast manner.
[0172] B26. The computing device according to any one of B16-B25, wherein the executable instructions further cause the processor to perform the following operations:
[0173] The interactive behavior data generated by the user for the item corresponding to the information of the item to be recommended is obtained, and the corresponding account resources are allocated to the user according to the interactive behavior data.
[0174] B27. The computing device according to any one of B16-B26, wherein the executable instructions further cause the processor to perform the following operations:
[0175] In response to a virtual object switching request executed by the user in the interactive interface, switching rejection information is displayed in the interactive interface, or no information is displayed.
[0176] B28. The computing device according to any one of B16-B27, wherein the executable instructions further cause the processor to perform the following operations:
[0177] When displaying the interactive page and / or the user demand classification selection page, play the preset background audio.
[0178] B29. According to the computing device described in any one of items B16-B28, the information of the item to be recommended includes: the information of the e-book to be recommended; the value parameters of the e-book information to be recommended include: the payment amount of the e-book corresponding to the e-book information to be recommended and / or the reading rights of each chapter of the e-book.
[0179] B30. The computing device according to B29, wherein the executable instructions further cause the processor to perform the following operations:
[0180] The e-book corresponding to the e-book information to be recommended is added to the user's bookshelf.
[0181] C31. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to a recommendation processing method based on virtual object interaction as described in any one of A1-A15.
Claims
1. A recommendation processing method based on virtual object interaction, comprising: Displaying interactive pages of target virtual objects corresponding to the target user demand classification; In response to a demand sending request carrying user demand information executed by the user in the interactive page, the demand processing rights of the user are cancelled, and the user demand information is provided to the server, so that the server can feed back the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the item to be recommended; The object feedback information and the information of the items to be recommended are displayed in the interactive interface.
2. The method according to claim 1, wherein: Before displaying the interactive page of the target virtual object corresponding to the target user demand classification, the method further includes: Display a user demand category selection page containing selection controls corresponding to multiple user demand categories; In response to a selection request executed by the user for any selection control, a user demand category corresponding to the any selection control is determined as a target user demand category.
3. The method according to claim 1 or 2, wherein: The interactive page includes a user demand information input area, and the method further includes: In response to a selection request performed by the user in the user demand information input area for any preset demand information, determining the any preset demand information as the user demand information; Alternatively, in response to an information input request performed by the user in the user requirement information input area, the information input by the user is determined as the user requirement information.
4. The method according to any one of claims 1 to 3, wherein: After displaying the interactive page of the target virtual object corresponding to the target user demand classification, the method further includes: In response to a trigger request executed by the user for a benefit processing control in the interactive page, the virtual item of the user is cancelled and a demand processing benefit is allocated to the user.
5. The method according to claim 4, wherein: The virtual item is purchased using the user's account resources.
6. The method according to claim 4 or 5, wherein: The value parameter of the item corresponding to the to-be-recommended item information is associated with the value parameter of the virtual item.
7. The method according to any one of claims 1 to 6, wherein: The determining of the information of items to be recommended further comprises: Determining recommended demand information according to the user demand information and / or the object feedback information; Based on the recommendation demand information, the item recommendation model is called to perform recommendation processing to obtain the information of the item to be recommended.
8. The method according to claim 7, wherein: The determining of the recommended demand information according to the user demand information and / or the object feedback information further includes: At least part of the user demand information and / or at least part of the object feedback information is determined as recommended demand information.
9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: Displaying interactive pages of target virtual objects corresponding to the target user demand classification; In response to a demand sending request carrying user demand information executed by the user in the interactive page, the demand processing rights of the user are cancelled, and the user demand information is provided to the server, so that the server can feed back the user demand information according to the dialogue characteristics of the target virtual object to obtain object feedback information and determine the information of the item to be recommended; The object feedback information and the information of the items to be recommended are displayed in the interactive interface.
10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the recommendation processing method based on virtual object interaction as described in any one of claims 1 to 8.