CN111523981A

CN111523981A - Virtual trial method and device, electronic equipment and storage medium

Info

Publication number: CN111523981A
Application number: CN202010355520.XA
Authority: CN
Inventors: 常向月
Original assignee: Shenzhen Zhuiyi Technology Co Ltd
Current assignee: Shenzhen Zhuiyi Technology Co Ltd
Priority date: 2020-04-29
Filing date: 2020-04-29
Publication date: 2020-08-11

Abstract

The embodiment of the application discloses a virtual trial method and device, electronic equipment and a storage medium. The method comprises the following steps: when a target user performs virtual trial of an article, acquiring video data containing the target user; performing intention analysis on audio data in the video data to obtain intention information of the target user; performing image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user; and generating feedback content aiming at the virtual trial according to the intention information and the attribute information. According to the embodiment of the application, when the target user performs virtual trial of the object, the intention information and the attribute information of the person can be acquired according to the speaking video of the user, virtual trial feedback matched with the intention information and the attribute information is generated, and trial experience of the user is improved.

Description

Virtual trial method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of human-computer interaction, in particular to a virtual trial method and device, electronic equipment and a storage medium.

Background

With the continuous improvement of living standard, the ability of consumers to purchase goods is also continuously improved. In order to buy a proper and mental product, a consumer usually performs a trial experience on a plurality of products before purchasing the product, so as to observe whether the trial effect of the product is expected. However, for some articles with complicated and troublesome trial process, such as cosmetics, clothes, etc., the trial process needs to be performed continuously, that is, the trial process and the unloading process are performed continuously, and the trial experience is not good.

Disclosure of Invention

In view of the foregoing problems, embodiments of the present application provide a virtual trial method, apparatus, electronic device, and storage medium, which can improve trial experience.

In a first aspect, an embodiment of the present application provides a virtual trial method, where the virtual trial method may include: when a target user performs virtual trial of an article, acquiring video data containing the target user; performing intention analysis on audio data in the video data to obtain intention information of the target user; performing image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user; and generating feedback content aiming at the virtual trial according to the intention information and the attribute information.

Optionally, generating feedback content for the virtual trial according to the intention information and the attribute information includes: searching similar users of the same type as the target user from a database according to the attribute information; acquiring an article transaction record of the similar user; and generating feedback content aiming at the virtual trial according to the intention information and the item transaction record.

Optionally, generating feedback content for the virtual trial according to the intention information and the item transaction record, including: searching one or more transaction items matched with the intention information from the item transaction record; and generating recommended content aiming at the virtual trial according to the one or more transaction items.

Optionally, the intention information includes a plurality of intentions, and the generating feedback content for the virtual trial according to the intention information and the item transaction record includes: obtaining a prioritization of the plurality of intents; according to the priority ranking, one or more transaction items matched with the intentions are searched from the item transaction records; generating recommended content for the virtual trial based on the one or more transactional items, the recommended content being displayed in the prioritization.

Optionally, according to the attribute information, searching for similar users of the same type as the target user from a database, including: acquiring an attribute record of each user in a database; matching the attribute information with the attribute record of each user; determining similarity of the target user and each user based on matching results; and determining one or more users with the similarity larger than a preset threshold value from each user as similar users of the same type as the target user.

Optionally, the attribute information includes a plurality of feature information, the attribute record includes a plurality of feature records, and matching the attribute information with the attribute record of each user includes: and when the feature information of a specified type in the feature information is successfully matched with the feature record corresponding to the specified type in the feature records of the current user, matching other feature information in the feature information with other feature records in the feature records, wherein the current user is any user in each user.

Optionally, the virtual trial method may further include: and when the feature information of the specified type in the feature information is unsuccessfully matched with the feature record corresponding to the specified type in the feature records of the current user, determining that the current user and the target user are different types of users.

Optionally, the attribute information includes an emotional characteristic, and the generating feedback content for the virtual trial according to the intention information and the attribute information includes: determining the preference degree value of the user to the current virtual trial article according to the emotional characteristics; and generating feedback content aiming at the current virtual trial according to the intention information and the preference degree value.

Optionally, generating feedback content for the current virtual trial according to the intention information and the preference degree value includes: and when the preference degree value is smaller than a first threshold value, generating first feedback content aiming at the current virtual trial, wherein the first feedback content is used for recommending other articles which are different from the articles on the current virtual trial.

Optionally, generating feedback content for the current virtual trial according to the intention information and the preference degree value includes: and when the preference degree value is larger than a second threshold value, generating second feedback content aiming at the current virtual trial, wherein the second feedback content is used for recommending other articles of the same type as the articles on the current virtual trial, and the second threshold value is larger than the first threshold value.

Optionally, the attribute information includes identity information, and the generating feedback content for the virtual trial according to the intention information and the attribute information includes: acquiring a historical transaction record of the target user according to the identity information; and generating personalized recommended content aiming at the virtual trial according to the intention information and the historical transaction record.

Optionally, generating feedback content for the virtual trial according to the intention information and the attribute information includes: determining a target article which the target user desires to perform virtual trial according to the intention information; judging whether the target object is matched with the attribute information; and when the target object is not matched with the attribute information, generating feedback content aiming at the virtual trial.

In a second aspect, embodiments of the present application provide a virtual trial, which may include: the video acquisition module is used for acquiring video data containing a target user when the target user performs virtual trial of an article; the intention analysis module is used for carrying out intention analysis on audio data in the video data to obtain intention information of the target user; the image analysis module is used for carrying out image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user; and the feedback generation module is used for generating feedback contents aiming at the virtual trial according to the intention information and the attribute information.

Optionally, the feedback generation module includes: the similar acquisition unit is used for searching similar users of the same type as the target user from a database according to the attribute information; the record acquisition unit is used for acquiring the item transaction record of the similar user; and the first feedback unit is used for generating feedback contents aiming at the virtual trial according to the intention information and the item transaction record.

Optionally, the first feedback unit includes: the searching subunit is used for searching one or more transaction items matched with the intention information from the item transaction record; and the first recommending subunit is used for generating recommended content aiming at the virtual trial according to the one or more transaction items.

Optionally, the intention information includes a plurality of intentions, and the first feedback unit includes: an intent ordering subunit operable to obtain a priority ordering of the plurality of intents; the item matching subunit is used for searching one or more transaction items matched with the plurality of intentions from the item transaction records according to the priority ranking; and the second recommending subunit is used for generating recommended content aiming at the virtual trial according to the one or more transaction items, and the recommended content is displayed in the priority sequence.

Optionally, the similarity obtaining unit includes: the attribute acquisition subunit is used for acquiring the attribute record of each user in the database; the attribute matching subunit is used for matching the attribute information with the attribute record of each user; and the similarity determining subunit is used for determining one or more users with the similarity greater than a preset threshold from each user as similar users of the same type as the target user.

Optionally, the attribute information includes a plurality of feature information, the attribute record includes a plurality of feature records, and the attribute matching subunit may be specifically configured to: and when the feature information of a specified type in the feature information is successfully matched with the feature record corresponding to the specified type in the feature records of the current user, matching other feature information in the feature information with other feature records in the feature records, wherein the current user is any user in each user.

Optionally, the virtual trial further comprises: and the other user determining module is used for determining that the current user and the target user are different types of users when the feature information of the specified type in the feature information is unsuccessfully matched with the feature record corresponding to the specified type in the feature records of the current user.

Optionally, the attribute information includes emotional characteristics, and the feedback generation module includes: the preference determining unit is used for determining the preference degree value of the user to the current virtual trial article according to the emotional characteristics; and the preference recommending unit is used for generating feedback content aiming at the current virtual trial according to the intention information and the preference degree value.

Optionally, the preference recommending unit may be specifically configured to: and when the preference degree value is smaller than a first threshold value, generating first feedback content aiming at the current virtual trial, wherein the first feedback content is used for recommending other articles which are different from the articles on the current virtual trial.

Optionally, the virtual trial further comprises: and the second feedback module is used for generating second feedback content aiming at the current virtual trial when the preference degree value is larger than a second threshold, the second feedback content is used for recommending other articles of the same type as the articles on the current virtual trial, and the second threshold is larger than the first threshold.

Optionally, the attribute information includes identity information, and the feedback generation module may be specifically configured to: acquiring a historical transaction record of the target user according to the identity information; and generating personalized recommended content aiming at the virtual trial according to the intention information and the historical transaction record.

Optionally, the feedback generation module may be specifically configured to: determining a target article which the target user desires to perform virtual trial according to the intention information; judging whether the target object is matched with the attribute information; and when the target object is not matched with the attribute information, generating feedback content aiming at the virtual trial.

In a third aspect, an embodiment of the present application provides an electronic device, which may include: a memory; one or more processors coupled with the memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the method of the first aspect as described above.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having program code stored therein, where the program code is called by a processor to execute the method according to the first aspect.

The embodiment of the application provides a virtual trial method and device, electronic equipment and a storage medium, when a target user performs virtual trial of an article, the video data containing the target user is obtained, intention analysis is performed on audio data in the video data to obtain intention information of the target user, image analysis is performed on image data in the video data to obtain attribute information of the target user, the attribute information is used for representing characteristic information embodied outside the target user, and finally feedback content for the virtual trial is generated according to the intention information and the attribute information. Therefore, when the target user performs virtual trial of the object, the intention information and the attribute information of the user can be acquired according to the speaking video of the user, and virtual trial feedback matched with the intention information and the attribute information is generated, so that individuation and diversification of the trial feedback are realized, and the trial experience of the user is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments, not all embodiments, of the present application. All other embodiments and drawings obtained by a person skilled in the art based on the embodiments of the present application without any inventive step are within the scope of the present invention.

Fig. 1 shows a schematic diagram of an application environment suitable for the embodiment of the present application.

Fig. 2 shows a flowchart of a virtual trial method according to an embodiment of the present application.

Fig. 3 shows an interactive interface schematic diagram of a virtual trial method provided by the embodiment of the application.

Fig. 4 shows a flowchart of a virtual trial method according to another embodiment of the present application.

Fig. 5 shows a flowchart of the method of step S340 in fig. 4.

Fig. 6 is a flowchart illustrating a virtual trial method according to another embodiment of the present application.

Fig. 7 is a flowchart illustrating a virtual trial method according to still another embodiment of the present application.

Fig. 8 is a flowchart illustrating a virtual trial method according to still another embodiment of the present application.

Fig. 9 is a flowchart illustrating a virtual trial method according to yet another embodiment of the present application.

Fig. 10 is a flowchart illustrating a virtual trial method according to yet another embodiment of the present application.

Fig. 11 illustrates a block diagram of modules of a virtual trial provided by an embodiment of the present application;

fig. 12 is a block diagram illustrating a structure of an electronic device for executing a virtual trial method according to an embodiment of the present application;

fig. 13 is a block diagram illustrating modules of a computer-readable storage medium for executing a virtual trial method according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Currently, a user can choose to purchase an item offline or online by himself. Before purchasing the goods, the user usually has a strong willingness of trying the goods to observe whether the goods trying effect is satisfactory or not. However, when a user purchases the product online, the user cannot touch the real product, so that the product trial is difficult to realize, and although the user can purchase the product offline, for some products with complicated and troublesome trial processes, such as cosmetics, clothes and the like, the product needs to be tried continuously, that is, the process of trial and unloading is performed continuously. Not only spend a large amount of time, reduced user's experience of trying, moreover to cosmetics, also can have certain health or extravagant problem to trying constantly.

In order to improve the above problems, the inventor researches a difficult point of the prior article trial, and further comprehensively considers the article trial requirement of the actual scene, and proposes the virtual trial method, the virtual trial device, the electronic device and the storage medium in the embodiment of the application, so as to improve the trial experience of the user.

In order to better understand the virtual trial method, apparatus, electronic device, and storage medium provided in the embodiments of the present application, an application environment suitable for the embodiments of the present application is described below.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an application environment suitable for the embodiment of the present application. The virtual trial method provided by the embodiment of the present application can be applied to the polymorphic interaction system 100 shown in fig. 1. The polymorphic interaction system 100 includes a terminal device 101 and a server 102, the server 102 being communicatively coupled to the terminal device 101. The server 102 may be a conventional server or a cloud server, and is not limited herein.

The terminal device 101 may be various electronic devices having a display screen and supporting data input, including but not limited to AR (Augmented Reality) cosmetic mirrors, robots, smart phones, tablet computers, laptop portable computers, desktop computers, wearable electronic devices, and the like. Specifically, the data input may be based on a voice module provided on the terminal device 101 to input voice, a character input module to input characters, an image input module to input images, a video input module to input video, and the like, or may be based on a gesture recognition module provided on the terminal device 101, so that a user may implement an interaction manner such as gesture input.

Wherein, the terminal device 101 may be installed with a client application program, and the user may communicate with the server 102 based on the client application program (e.g. APP, wechat applet, etc.), specifically, the server 102 is installed with a corresponding server application program, and the user may register a user account at the server 102 based on the client application program and communicate with the server 102 based on the user account, for example, a user logs into a user account at a client application, and enters through the client application based on the user account, text information, voice information, image information or video information and the like can be input, and after the client application program receives the information input by the user, the information may be sent to the server 102 so that the server 102 may receive the information, process and store the information, and the server 102 may also receive the information and return a corresponding output information to the terminal device 101 according to the information.

In some embodiments, the client application may be used to provide customer service to the user, in order to communicate with the user. As one way, the client application may also interact with the user based on the virtual robot, i.e., the client application may receive information input by the user and respond to the information based on the virtual robot. In some embodiments, after acquiring the reply information corresponding to the information input by the user, the terminal device 101 may display the reply information on a display screen of the terminal device 101 or other image output device connected thereto. As a mode, while the reply information is displayed, the corresponding audio may also be played through the speaker of the terminal device 101 or other audio output devices connected thereto, and the text or graphic corresponding to the reply information may also be displayed on the display screen of the terminal device 101, so as to implement multi-state interaction with the user in multiple aspects of image, voice, text, and the like.

In some embodiments, the means for processing the information input by the user may also be disposed on the terminal device 101, so that the terminal device 101 can interact with the user without relying on establishing communication with the server 102, and in this case, the polymorphic interaction system 100 may only include the terminal device 101.

The above application environments are only examples for facilitating understanding, and it is to be understood that the embodiments of the present application are not limited to the above application environments.

The virtual trial method, apparatus, terminal device and storage medium provided in the embodiments of the present application are described in detail below with specific embodiments.

Referring to fig. 2, fig. 2 is a schematic flow chart of a virtual trial method according to an embodiment of the present application, where the virtual trial method according to the embodiment may be applied to an electronic device. The electronic device may be the terminal device having the display screen or other image output device, or the server. In a specific embodiment, the virtual trial method may be applied to the virtual trial 900 shown in fig. 11 and the terminal device 600 shown in fig. 12. As will be described in detail with respect to the flow shown in fig. 2, the virtual trial method may specifically include the following steps:

step S210: when a target user performs virtual trial of an article, video data containing the target user is acquired.

Augmented Reality (AR): the method is a technology for seamlessly integrating real world information and virtual world information, and is characterized in that entity information which is difficult to experience in a certain time and space range of the real world originally is overlapped after simulation through scientific technologies such as computers, virtual information is applied to the real world and is perceived by human senses, so that the sensory experience beyond reality is achieved. That is, the real environment and the virtual object are superimposed on the same picture or space in real time and exist simultaneously. The virtual trial (namely, the AR trial) can be understood as an accurate simulation technology for the use effect of the article by means of image recognition, the AR technology and the use effect of the article, and the effect of the user after using the article can be quickly simulated, so that the user can quickly and intuitively experience the actual use effect of the article.

In some embodiments, the interaction of the virtual trial can be realized through a touch screen, that is, an item which the user wants to try can be selected through screen clicking, and then the trial effect is displayed on the screen. However, the trial process is relatively fixed and rigid, and usually feedback on the trial of the user cannot be made (for example, articles preferred by the user cannot be recommended according to the face shape and trial feeling of the user), so that the trial experience of the user is reduced. Therefore, in the embodiment of the application, virtual trial can be realized through voice and video interaction, so that the trial experience of a user is improved.

Specifically, when the target user performs a virtual test on an article, the terminal device may obtain video data including the target user. The articles to be virtually tried out by the user may be cosmetics such as lipstick, eye shadow, blush, eyeliner, eyelash, foundation, etc., or clothing accessories such as hat, jacket, trousers, glasses, earrings, etc., and the articles to be tried out are not limited herein.

In some embodiments, virtual trialing may be implemented both online and offline. As an embodiment, when the terminal device is a mobile terminal (such as a mobile phone) equipped with an AR trial function, the user may select online purchase, and the user may perform virtual trial of an article based on the mobile terminal. As another embodiment, when the terminal device is an offline physical device with an AR trial function, such as an AR cosmetic mirror, a physical robot, or the like, the user may select offline purchase while the user may select interaction with the physical device for virtual trial of the item. The specific application scenario is not limited herein, and only virtual trial of the article is needed.

In some embodiments, the video data including the target user may be speaking video data of the target user, which is acquired by the terminal device in real time by using an audio acquisition device such as a microphone and an image acquisition device such as a camera when the target user performs a virtual test on an article, where the audio acquisition device and the image acquisition device may be external devices or may be integrated in the terminal device, and the audio acquisition device and the image acquisition device are not limited herein. Specifically, as a manner, when an application program for AR trial runs in the system foreground of the terminal device, each hardware module of the terminal device may be called to collect a speaking video of the user.

The target user may be a user within a visual field of the image capturing device. In some embodiments, the terminal device may be provided with an image capturing device, and when there are a plurality of users in the field of view of the image capturing device, the user closest to the terminal device may be used as the target user.

Further, in some embodiments, the virtual trial may set a single-person mode and a multi-person mode, and the user may enter the operation interface of the virtual trial to select the mode. If the current mode is the single mode, the user closest to the terminal equipment can be taken as a target user; if the current mode is a multi-user mode, all users in the visual field may be the target users, which is not limited herein.

In some embodiments, the video data including the target user may be obtained by the target user when the target user enters the visual field of the image capturing apparatus, that is, the target user may not start the virtual trial of the article, but only wants to start the virtual trial of the article. In other embodiments, the video data including the target user may be obtained by the target user when the virtual trial function of the article is successfully triggered, that is, the target user may have started the virtual trial of the article.

Step S220: and performing intention analysis on the audio data in the video data to obtain intention information of the target user.

In some embodiments, when the target user performs a virtual trial of an item, the user may perform a voice interaction with the terminal device, for example, a dialog of the item to be tried, the item suitable for use, and the like. At this time, when the target user performs the virtual trial of the article, the terminal device may acquire the video data of the target user, so that the voice interaction content between the user and the terminal device may be acquired through the audio data in the video data.

The video is formed by combining an audio stream and a video image stream, and the video image stream is formed by splicing video images of one frame and another frame according to the time sequence. Thus, in some embodiments, the acquired video data may be decomposed by various existing video decomposition software to obtain a complete audio stream and video image sequence of the video data. Wherein the time stamp lengths of the complete audio stream and the sequence of video images are identical, which may be the same as the length of the video. The video image sequence may be understood as a set of consecutive video image frames that are generated in chronological order after a video is decomposed into a plurality of video images.

In some embodiments, after obtaining the complete audio stream of the video data, the intention analysis may be performed on the audio stream directly, or may be performed after performing interference removal on the complete audio stream. The step of performing interference elimination on the complete audio stream refers to acquiring audio segments of the complete audio stream except for the interference audio. The disturbing audio may be noise audio, background audio, silence audio, audio of other users, and other audio that is not related to the target user, and is not limited herein. For example, after a video of 30FPS of 1 minute length is decomposed into 1800 video images (1 minute × 60 seconds/minute × 30 frames/second) and 1 minute audio, a target audio clip of 30 seconds after disturbance is removed is extracted for intention analysis.

In some embodiments, when the sound of multiple users is included in the complete audio stream, the sound data of the user with the clearest sound or the largest volume may be selected from the complete audio stream, and used as the audio data of the target user who has a conversation with the terminal device, and the intention analysis is performed on the audio data.

In some embodiments, the intention analysis may be performed on the audio data, and the audio data may be subjected to speech-to-text processing to obtain text content corresponding to the audio data, and then the text content is processed by using a natural language processing technology to obtain intention information of the target user based on the text content, for example, intentions of the target user, such as a product that the target user wants to try, a product that the target user is suitable for, trial sharing, and the like. In which audio data can be converted from speech to text in a variety of ways.

As one approach, audio data may be converted to textual content through deep learning techniques. Specifically, audio data may be input into a trained speech recognition model to obtain text content corresponding to the audio data output by the speech recognition model. The speech recognition model can be obtained by training through a neural network based on audio information of a large number of real persons during speaking and training samples of text contents corresponding to the audio information in advance. The machine learning model used is not limited herein. For example, it may be a variation or a combination of RNN (Recurrent Neural Network) model, CNN (Convolutional Neural Networks) model, BiLSTM (Bi-directional long short-Term Memory) model.

Step S230: and performing image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user.

In some embodiments, after decomposing the acquired video data, a video image sequence of the video data, that is, image data in the video data, may be obtained. The terminal device may perform image analysis on the image data according to a computer vision technique to obtain attribute information of the target user. The attribute information may be used to characterize characteristic information embodied outside the target user. For example, the information may be skin information such as skin color and skin type, body structure information such as face shape, distribution of five sense organs, and body shape, and emotion information and identity information obtained by face recognition, which are not limited herein. For example, the wearing style and the wearing value range may be used.

In some embodiments, image analysis may be performed on the image data by a deep learning technique. As one way, a sequence of video images may be input into a trained image recognition model, resulting in an output from the image recognition model. Wherein the output result may include attribute information of a person in the image. Specifically, in some embodiments, the image recognition model may be obtained by training through a neural network in advance based on a human image sequence when a large number of real persons speak and a training sample of attribute information presented by the real persons. The training samples may include input samples and output samples, the input samples may include a character image sequence, and the output samples may be attribute information of a character in an image, so that the trained image recognition model may be used to output the attribute information of the character in the image according to the acquired video image sequence.

Step S240: and generating feedback content aiming at the virtual trial according to the intention information and the attribute information.

In some embodiments, after the terminal device obtains the intention information and the attribute information of the target user, the feedback content for virtual trial of the target user can be generated according to the intention information and the attribute information of the target user, so that personalized feedback of article trial is realized, and trial experience is improved. The feedback content may be, but is not limited to, a trial recommendation of the article, a trial evaluation score of the article, a trial correction of the article, and the like.

For example, when the attribute information is skin information, items that the user may purchase may be better recommended according to the skin condition of the target user. For example, when the attribute information is personal information of the target user, the user item may be personalized and recommended according to personal conditions, purchase records, and the like of the target user.

In some embodiments, when the user does not know what kind of article the user wants to try out specifically, the terminal device may perform intent analysis according to the received voice by inquiring the user's needs (i.e., voice interaction), for example, the user replies that the user wants to improve the skin quality, so as to obtain the article the user intends to improve the skin quality.

In some embodiments, the feedback content for the virtual trial is generated according to the intention information and the attribute information, which may be that firstly, a trial article that the target user wants to perform the virtual trial is determined according to the intention information, then, according to the attribute information of the skin, the body structure, the value view and the like of the target user, a target article suitable for the target user to use is determined from different colors, sizes or prices of the trial article, and then, the target article is recommended, that is, the recommendation feedback including the target article is generated. Therefore, products are recommended in a personalized mode according to the personal conditions of the users, and the trial experience of the users is improved.

In other embodiments, feedback content for virtual trial is generated according to the intention information and the attribute information, or whether a target user wants to know whether a trial article is suitable for the target user is determined according to the intention information, then fitness analysis is performed according to the attribute information of the skin, the body structure, the value view and the like of the target user, and then analysis feedback is generated based on the analysis result. Therefore, the user can determine which trial articles are suitable for the user according to the analysis feedback, and the trial experience of the user is improved. The fitness can be understood as the matching degree of the trial article on the user, and the higher the fitness is, the more the trial article fits the target user. Thereby realizing accurate recommendation of the articles.

Of course, the generation of the feedback content for the virtual trial based on the intention information and the attribute information is only an example, and a specific feedback content generation method is not limited herein.

For example, in a specific application scenario, as shown in fig. 3, a user may open an application client (e.g., a wechat applet or an independent APP) through a terminal device to enter a virtual trial interactive interface, and at the same time, the terminal device may collect a speaking video of the user by calling each hardware module such as a camera and a microphone, and then display the speaking video in the interactive interface. The terminal device may then perform intent analysis and image analysis on the speaking video to generate feedback content for the speaking video, such as feedback of "recommended item" and "similar item" (the item list displayed in the bottom of fig. 3 is the feedback content). In some scenarios, feedback audio may also be played simultaneously, such as "suggest/not suggest to use XX articles.

In some embodiments, in a state where the terminal device establishes a communication connection with the server, when the terminal device obtains video data including a target user, the video data may also be sent to the server, the server performs intention analysis and image analysis on the video data, and then the server determines intention information and attribute information of the target user and generates feedback content for virtual trial. And outputting the feedback content to the terminal equipment, and acquiring, playing and displaying by the terminal equipment.

It can be understood that, in this embodiment, each step may be performed locally by the terminal device, may also be performed in the server, and may also be performed by the terminal device and the server separately, and according to different actual application scenarios, tasks may be allocated according to requirements, so as to implement an optimized virtual robot customer service experience, which is not limited herein.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial of an article, the video data containing the target user is obtained, intention analysis is performed on the audio data in the video data to obtain intention information of the target user, image analysis is performed on the image data in the video data to obtain attribute information of the target user, the attribute information is used for representing characteristic information embodied outside the target user, and finally feedback content for the virtual trial is generated according to the intention information and the attribute information. Therefore, when the target user performs virtual trial of the object, the user does not need to independently input through a screen, accurate virtual trial recommendation or feedback can be obtained directly according to the speaking video of the user, individuation and diversification of trial feedback are achieved, and trial experience of the user is improved. And because virtual probation need not the actual use article to can save the user and try and unload the time that spent to different article, improve user's efficiency of trying.

Referring to fig. 4, fig. 4 is a schematic flowchart illustrating a virtual trial method according to another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 4, the virtual trial method may specifically include: step S310 to step S360.

In the embodiment of the present application, reference may be made to the related descriptions in the steps S210 to S230 in the steps S310 to S330, and details are not repeated here.

Step S340: and searching similar users of the same type as the target user from a database according to the attribute information.

In some embodiments, after the terminal device obtains the attribute information of the target user through the image data in the video data, the terminal device may search a user similar to the target user from the database according to the attribute information, so as to perform item recommendation according to the transaction items of the users of the same type.

In some embodiments, similar users of the same type as the target user may be determined by obtaining the similarity of each user to the target user. Specifically, referring to fig. 5, step S340 may include:

step S341: and acquiring the attribute record of each user in the database.

Step S342: and matching the attribute information with the attribute record of each user.

Step S343: determining similarity of the target user and each user based on the matching result.

Step S344: and determining one or more users with the similarity larger than a preset threshold value from each user as similar users of the same type as the target user.

In some embodiments, when each user performs a virtual trial of an article, all data (such as attribute information of the user, a purchase record, and the like) acquired by identification in the trial process may be recorded and stored in the database. Therefore, the terminal equipment can search users with similar attribute information from the database according to the attribute information of the target user.

Specifically, the terminal device may obtain an attribute record (i.e., recorded attribute information) of each user in the database, match the attribute information of the target user with the attribute record of each user, determine a similarity between the target user and each user based on a matching result, and determine one or more users with the similarity greater than a preset threshold from the similarity as similar users of the same type as the target user. The preset threshold value can be stored in the terminal device in advance, and can be reasonably adjusted and set according to a specific scene, for example, the preset threshold value is set to be 90%. Further, in some embodiments, when there are fewer or even no similar users acquired according to the current preset threshold, the current preset threshold may be reduced, and the reduction degree may be fixed or adjusted by the user, which is not limited herein.

In some embodiments, when the attribute information includes one or more feature information and the attribute record includes one or more feature records, the matching of the attribute information of the target user with the attribute record of each user may be a one-to-one comparison of features of the same type. The feature information may be skin feature information such as skin color and skin texture, or body structure feature information such as facial form, distribution of five sense organs, and body shape. And determining the similarity between the target user and each user based on the matching result, wherein the similarity can be the proportion occupied by the successful matching of the same type of characteristics after one-to-one comparison of the same type of characteristics, and the similarity between the target user and each user can be determined according to the proportion. It is understood that the more features in the attribute information that successfully match, the higher the degree of similarity.

In some embodiments, when the attribute information includes one or more feature information, and the attribute record includes one or more feature records, the matching of the attribute information of the target user with the attribute record of each user may be preferentially performed, and then it is determined whether to perform matching of other feature information, so that operation operations may be reduced, trial feedback efficiency is improved, and the rationality and accuracy of trial articles are ensured.

Specifically, when matching between feature information of a specified type in the plurality of feature information and a feature record corresponding to the specified type in the plurality of feature records of the current user is successful, matching other feature information in the plurality of feature information with other feature records in the plurality of feature records, wherein the current user is any user in each user. The specific type of feature information can be understood as key feature information to be considered when the article is tried out.

For example, when trying to apply cosmetics, the key characteristic information of the user may be skin characteristic information, and when the skin characteristic information of two persons do not match (one black and one white), the cosmetics applied by one person may be highly unsuitable for the other person. For another example, when trying to wear clothes, the key feature information of the user may be the shape feature information, and when the shape feature information of two persons does not match (one is fat and one is thin), the clothes worn by one person may be too large to fit the other person.

It can be understood that when matching between the feature information of the specified type in the plurality of feature information and the feature records corresponding to the specified type in the plurality of feature records of the current user is unsuccessful, that is, the key feature information is not matched, it can be directly determined that the current user and the target user are different types of users, and the trial articles of the current user are likely not suitable for the target user. And when the feature information of the specified type in the plurality of feature information is successfully matched with the feature record corresponding to the specified type in the plurality of feature records of the current user, namely the key feature information is successfully matched, matching of other feature information can be carried out. Then, similarity is obtained.

Step S350: and acquiring the item transaction record of the similar user.

In some embodiments, when acquiring a similar user of the same type as the target user, the terminal device may acquire an item transaction record of the similar user. The item transaction record can embody information with item recommendation reference, such as item preference, brand preference, value view and the like of similar users.

Step S360: and generating feedback content aiming at the virtual trial according to the intention information and the item transaction record.

In some embodiments, after obtaining the intention information of the target user, the terminal device may perform feedback of virtual trial according to the article transaction record of similar users of the same type as the target user. In one mode, when the intention information of the target user indicates that the cosmetics are to be tried, one or more cosmetics matched with the highest price intention can be selected from the commodity transaction record according to the highest price intention which can be borne by the target user for trial recommendation. Therefore, corresponding trial recommendation is carried out according to the purchasing conditions of the users of the same type, and the commodity recommendation is accurate and personalized, and meanwhile, the commodity transaction success rate is improved.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial on an article, the intention information and the attribute information of the target user can be obtained by acquiring the video data containing the target user and performing intention analysis and image analysis on the video data, the attribute information is used for representing the characteristic information embodied outside the target user, then similar users of the same type as the target user are searched from the database according to the attribute information, and article transaction records of the similar users are acquired, so that feedback content for the virtual trial is generated according to the intention information of the target user and the article transaction records of the similar users. Therefore, after the intention information and the attribute information of the target user are determined according to the speaking video of the user, accurate virtual trial recommendation or feedback can be obtained through the article transaction records of the users of the same type, individuation and diversification of the trial feedback are achieved, and the trial experience of the user is improved.

Referring to fig. 6, fig. 6 is a schematic flowchart illustrating a virtual trial method according to another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 6, the virtual trial method may specifically include: step S410 to step S470.

In the embodiment of the present application, reference may be made to the related descriptions in the steps S310 to S350 in the steps S410 to S450, and details are not repeated here.

Step S460: and searching one or more transaction items matched with the intention information from the item transaction record.

Step S470: and generating recommended content aiming at the virtual trial according to the one or more transaction items.

In some embodiments, after acquiring the intention information of the target user, the terminal device may search one or more transaction items matching the intention information from item transaction records of similar users of the same type as the target user. Recommended content for the virtual trial is then generated based on the one or more transactional items.

In some embodiments, when the intent information includes an item that the user wants to try, the terminal device may look up one or more transaction items matching the item that the user wants to try from item transaction records of similar users. For example, when the user wants to try out the lipstick, the terminal device can recommend the product from the lipstick purchase records of the users of the same type.

Further, when the intention information includes the highest price that can be accepted, after one or more transaction items that match the items that the user wants to try are found, it may be determined whether the one or more transaction items exceed the highest price that can be accepted by the target user. If yes, brand information of one or more transaction items can be determined, and items matched with the intention information are searched from the brand information to be recommended. If not, the one or more transaction items can be directly recommended.

For example, the user wants to try the lipstick on trial, the terminal device may search the transaction records of the lipstick 1, the lipstick 2 and the lipstick 3 from the article transaction records of the users of the same type, and if it is determined that the price of the lipstick 1, the lipstick 2 and the lipstick 3 exceeds the price which can be borne by the user, the terminal device may obtain the brand information a of the lipstick 1, the lipstick 2 and the lipstick 3, and obtain the lipstick which does not exceed the price which can be borne by the user from all lipstick products in the brand information a for recommendation.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial on an article, the video data containing the target user is obtained, intention analysis and image analysis are performed on the video data, intention information and attribute information of the target user can be obtained, the attribute information is used for representing characteristic information embodied outside the target user, similar users of the same type as the target user are searched for from a database according to the attribute information, article transaction records of the similar users are obtained, one or more transaction articles matched with the intention information of the target user are searched for from the article transaction records, and recommended content for the virtual trial is generated according to the one or more transaction articles. Therefore, after the intention information and the attribute information of the target user are determined according to the speaking video of the user, accurate virtual trial recommendation or feedback can be obtained through the article transaction records of the users of the same type, individuation and diversification of the trial feedback are achieved, and the trial experience of the user is improved.

Referring to fig. 7, fig. 7 is a schematic flowchart illustrating a virtual trial method according to still another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 7, the virtual trial method may specifically include: step S510 to step S580.

In the embodiment of the present application, reference may be made to the related descriptions in the steps S310 to S350 in the steps S510 to S550, and details are not repeated here.

Step S560: and acquiring the priority ranking of a plurality of intentions in the intention information.

In some embodiments, when the intention information of the target user identified by the terminal device includes a plurality of intentions, the intention information may be prioritized according to importance levels of the plurality of intentions to recommend the item according to the priority, so as to ensure that the trial item viewed by the user at the first time is most interesting or suitable. For example, when the intent information of the target user includes item type, brand, etc. multi-dimensional intent, the prioritization may be item type > subject price > brand.

Step S570: and according to the priority ranking, searching one or more transaction items matched with the plurality of intentions from the item transaction record.

In some embodiments, after obtaining the priority ranking of the multiple intentions, the terminal device may sequentially search and filter one or more transaction items matching the multiple intentions from item transaction records of similar users according to the priorities.

As one mode, when the priority ranking includes three priorities, the terminal device may perform item search from item transaction records of similar users according to an intention of first higher priority, obtain a round of item list, and then perform search again from the obtained round of item list according to an intention of second priority, obtain a round of item list. And finally, searching again from the obtained two-round item list according to the intention with low priority to obtain a final item searching result, wherein the result is one or more transaction items matched with the intention information.

Step S580: generating recommended content for the virtual trial based on the one or more transactional items, the recommended content being displayed in the prioritization.

In some embodiments, when one or more transaction articles matched with the intention information of the target user are acquired, the terminal device may generate recommended content for the virtual trial according to the one or more transaction articles, and the recommended content is displayed in a priority ranking of the plurality of intentions. Therefore, the user can be ensured to look up accurate and reasonable recommendation of trial articles in the first time.

According to the virtual trial method, after the attribute information and the intentions of the target user are determined according to the speaking video of the user, one or more transaction articles matched with the intentions can be searched from article transaction records of users of the same type according to the priority sequence of the intentions, the priority display of virtual trial recommendation or feedback is realized, the accurate and reasonable trial article recommendation can be found by the user in the first time, the individuation and diversification of the trial feedback are realized, and the trial experience of the user is improved.

Referring to fig. 8, fig. 8 is a schematic flowchart illustrating a virtual trial method according to still another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 8, the virtual trial method may specifically include: step S610 to step S650.

In the embodiment of the present application, reference may be made to the related descriptions in the steps S210 to S230 in the steps S610 to S630, and details are not repeated here.

Step S640: and determining the preference degree value of the target user to the current virtual trial article according to the emotional characteristics in the attribute information.

In some embodiments, the attribute information that the terminal device identifies to the target user also includes emotional characteristics. Wherein the emotional characteristics can be used for representing the emotion of the person in the image. In some embodiments, the emotion characterized by the emotional characteristics may include positive emotions such as happy, excited, happy, satisfied, relaxed, calm, and the like, and may also include negative emotions such as tired, boring, frown, depressed depression, anger, tension, and the like, without limitation.

In some embodiments, the terminal device may determine the preference degree value of the target user for the current virtual trial item according to the emotional characteristics of the target user. Wherein, the higher the preference degree value is, the more the user likes the trial article. As one mode, the terminal device may determine the preference degree value according to a correspondence table between preset emotional characteristics and the preference degree value. Therefore, when the terminal equipment acquires the emotional characteristics of the target user, the corresponding preference degree value can be inquired according to the corresponding relation table.

Step S650: and generating feedback content aiming at the current virtual trial according to the intention information and the preference degree value.

In some embodiments, the terminal device may generate the feedback content for the current virtual trial according to the intention information and the preference degree value of the target user for the current virtual trial. Wherein, when the preference degree values are different, the feedback contents may be different.

As one mode, when the degree of preference value of the target user for the item on the current virtual trial is smaller than the first threshold, the target user may be considered to be dissatisfied with the item, and the terminal device may generate first feedback content for the current virtual trial, where the first feedback content is used to recommend another item that is different from the item on the current virtual trial.

As another way, when the preference degree value of the target user for the item on the current virtual trial is greater than a second threshold, the target user may be considered to be very satisfied with the item, and the terminal device may generate second feedback content for the current virtual trial, where the second feedback content is used to recommend another item of the same type as the item on the current virtual trial, and the second threshold is greater than the first threshold. The first threshold and the second threshold can be stored in the terminal device in advance, and can be set reasonably according to a specific scene, and the setting is not limited here, and only the second threshold is larger than the first threshold. For example, the first threshold may be 60% and the second threshold may be as good as 80%.

For example, in some application scenarios, when a user tries a certain article and then shows an unpleasant expression, according to the preference degree value corresponding to the expression, it may be determined that the user is not satisfied with the article, and another article may be recommended. If the user exposes a happy expression, the fact that the user likes the item very much is described according to the preference degree value corresponding to the expression, and the terminal device can interact with the user to strengthen the purchasing intention of the user.

In some embodiments, the difference of the voice intonation may also reflect the user's preference for trial products. Therefore, the terminal device can perform language analysis on the audio data to obtain the voice intonation of the audio data. And then determining the preference degree value of the user for the trial product according to the language tone.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial on an article, the intention information and the attribute information of the target user can be obtained by acquiring the video data containing the target user and performing intention analysis and image analysis on the video data, the attribute information is used for representing the characteristic information embodied outside the target user, then the preference degree value of the target user on the article currently subjected to virtual trial is determined according to the emotional characteristics in the attribute information, and the feedback content for the current virtual trial is generated according to the intention information and the preference degree value. Therefore, after the attribute information and the intentions of the target user are determined according to the speaking video of the user, the preference degree value of the target user to the current virtual trial article can be determined according to the emotional characteristics of the target user, and the virtual trial recommendation or feedback is correspondingly generated according to the preference degree value, so that the individuation and diversification of the trial feedback are realized, and the trial experience of the user is improved.

Referring to fig. 9, fig. 9 is a schematic flowchart illustrating a virtual trial method according to yet another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 9, the virtual trial method may specifically include: step S710 to step S750.

In the embodiment of the present application, reference may be made to the related descriptions in the steps S210 to S230 in the steps S710 to S730, and details are not repeated here.

Step S740: and acquiring the historical transaction record of the target user according to the identity information in the attribute information.

Step S750: and generating personalized recommended content aiming at the virtual trial according to the intention information and the historical transaction record.

In some application scenarios, some articles may be purchased with high frequency by users, such as cosmetics like facial masks, lipsticks, foundations, etc., so in some embodiments, the terminal device may also recommend trial articles personalized according to personal information such as personal condition, purchase record, etc. of the users.

Specifically, when the attribute information of the target user identified by the terminal device includes the identity information of the target user, the historical transaction record of the target user may be obtained according to the identity information, and the personalized recommended content for the virtual trial may be generated according to the intention information and the historical transaction record. The identity information of the target user can be account information of a user logging in the client, or can be identity card information, and the identity information is not limited and only needs to be referred to a transaction record. Therefore, the recommendation of the articles is realized according to the historical transaction records of the user, and the manual query and selection of the user are avoided.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial on an article, the intention information and the attribute information of the target user can be obtained by acquiring the video data containing the target user and performing intention analysis and image analysis on the video data, the attribute information is used for representing the characteristic information embodied outside the target user, then the historical transaction record of the target user is acquired according to the identity information in the attribute information, and the personalized recommendation content for the virtual trial is generated according to the intention information and the historical transaction record. Therefore, after the attribute information and the intentions of the target user are determined according to the speaking video of the user, virtual trial recommendation or feedback can be correspondingly generated according to the historical transaction record of the target user, so that article recommendation according to the historical transaction record of the user is realized, and manual query and selection of the user are avoided.

Referring to fig. 10, fig. 10 is a schematic flow chart illustrating a virtual trial method according to still another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 10, the virtual trial method may specifically include: step S810 to step S860.

In the embodiment of the present application, reference may be made to the related descriptions in steps S210 to S230 in steps S810 to S830, and details are not repeated here.

Step S840: and determining a target article which the target user desires to perform virtual trial according to the intention information.

Step S850: and judging whether the target object is matched with the attribute information.

Step S860: and when the target object is not matched with the attribute information, generating feedback content aiming at the virtual trial.

In some application scenarios, the user may not be aware of the item that fits himself, resulting in a less than ideal virtual trial effect for the item that wants to be tried. Therefore, in some embodiments, the terminal device may also perform analysis and correction on the virtual trial of the target user. Specifically, when acquiring the intention information of the target user, the terminal device may determine a target article that the target user desires to perform virtual trial. And then analyzing and judging whether the target object is matched with the attribute information of the target user. When the target object does not match the attribute information, the terminal device may generate feedback content for the virtual trial.

It is understood that, generally, the item is purchased only when it is suitable for itself, and therefore, in some embodiments, determining whether the target item matches the attribute information of the target user may be by analyzing and integrating the attribute information of all users who purchase the target item to obtain the reference attribute information applicable to the target item, and then matching the attribute information of the target user with the reference attribute information. When the attribute information of the target user is matched with the reference attribute information, the target object can be considered to be matched with the attribute information of the target user, namely the target object is suitable for the target user, and the terminal equipment can perform normal virtual trial effect display. When the attribute information of the target user is not matched with the reference attribute information, the target object can be considered to be not matched with the attribute information of the target user, namely the target object is not suitable for the target user, and the terminal equipment can generate feedback content of virtual trial so as to prompt that the target object is not suitable for trial use by the target user. In some embodiments, the feedback content generated by the terminal device may further include recommendation content for recommending a suitable trial item for the target user.

According to the virtual trial method provided by the embodiment of the application, when a target user performs virtual trial of an article, the intention information and the attribute information of the target user can be obtained by acquiring the video data containing the target user and performing intention analysis and image analysis on the video data, the attribute information is used for representing the characteristic information embodied outside the target user, then the target article which the target user desires to perform virtual trial is determined according to the intention information, whether the target article is matched with the attribute information of the target user is judged, and when the target article is not matched with the attribute information, feedback content for the virtual trial is generated. Therefore, after the attribute information and the intentions of the target user are determined according to the speaking video of the user, the virtual trial of the target user can be analyzed and corrected according to the intention information and the attribute information of the target user, the virtual trial effect is guaranteed, and the trial experience of the user is improved.

It should be understood that, although the steps in the flow charts of fig. 2, 4-10 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 4-10 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.

Referring to fig. 11, fig. 11 is a block diagram illustrating a module of a virtual trial apparatus according to an embodiment of the present application. As will be explained below with respect to the block diagram of modules shown in fig. 11, virtual trial 900 includes: a video acquisition module 910, an intent analysis module 920, an image analysis module 930, and a feedback generation module 940, wherein:

a video obtaining module 910, configured to obtain video data including a target user when the target user performs virtual trying on an article;

an intention analysis module 920, configured to perform intention analysis on the audio data in the video data to obtain intention information of the target user;

an image analysis module 930, configured to perform image analysis on image data in the video data to obtain attribute information of the target user, where the attribute information is used to represent feature information embodied outside the target user;

a feedback generating module 940, configured to generate feedback content for the virtual trial according to the intention information and the attribute information.

In some embodiments, the feedback generation module 940 may include: the similar acquisition unit is used for searching similar users of the same type as the target user from a database according to the attribute information; the record acquisition unit is used for acquiring the item transaction record of the similar user; and the first feedback unit is used for generating feedback contents aiming at the virtual trial according to the intention information and the item transaction record.

Further, in some embodiments, the first feedback unit may include: the searching subunit is used for searching one or more transaction items matched with the intention information from the item transaction record; and the first recommending subunit is used for generating recommended content aiming at the virtual trial according to the one or more transaction items.

In some embodiments, when the intention information includes a plurality of intentions, the first feedback unit may also include: an intent ordering subunit operable to obtain a priority ordering of the plurality of intents; the item matching subunit is used for searching one or more transaction items matched with the plurality of intentions from the item transaction records according to the priority ranking; and the second recommending subunit is used for generating recommended content aiming at the virtual trial according to the one or more transaction items, and the recommended content is displayed in the priority sequence.

In some embodiments, the similar acquiring unit may include: the attribute acquisition subunit is used for acquiring the attribute record of each user in the database; the attribute matching subunit is used for matching the attribute information with the attribute record of each user; and the similarity determining subunit is used for determining one or more users with the similarity greater than a preset threshold from each user as similar users of the same type as the target user.

In some embodiments, the attribute information includes a plurality of feature information, and when the attribute record includes a plurality of feature records, the attribute matching subunit may be specifically configured to: and when the feature information of a specified type in the feature information is successfully matched with the feature record corresponding to the specified type in the feature records of the current user, matching other feature information in the feature information with other feature records in the feature records, wherein the current user is any user in each user.

In some embodiments, the virtual trial 900 may further include: and the other user determining module is used for determining that the current user and the target user are different types of users when the feature information of the specified type in the feature information is unsuccessfully matched with the feature record corresponding to the specified type in the feature records of the current user.

In some embodiments, when the attribute information includes an emotional characteristic, the feedback generation module 940 may also include: the preference determining unit is used for determining the preference degree value of the user to the current virtual trial article according to the emotional characteristics; and the preference recommending unit is used for generating feedback content aiming at the current virtual trial according to the intention information and the preference degree value.

In some embodiments, the preference recommending unit may be specifically configured to: and when the preference degree value is smaller than a first threshold value, generating first feedback content aiming at the current virtual trial, wherein the first feedback content is used for recommending other articles which are different from the articles on the current virtual trial.

In some embodiments, the virtual trial may further comprise: and the second feedback module is used for generating second feedback content aiming at the current virtual trial when the preference degree value is larger than a second threshold, the second feedback content is used for recommending other articles of the same type as the articles on the current virtual trial, and the second threshold is larger than the first threshold.

In some embodiments, when the attribute information includes identity information, the feedback generation module 940 may be specifically configured to: acquiring a historical transaction record of the target user according to the identity information; and generating personalized recommended content aiming at the virtual trial according to the intention information and the historical transaction record.

In some embodiments, the feedback generation module 940 may also be specifically configured to: determining a target article which the target user desires to perform virtual trial according to the intention information; judging whether the target object is matched with the attribute information; and when the target object is not matched with the attribute information, generating feedback content aiming at the virtual trial.

The virtual trial device provided by the embodiment of the application is used for realizing the corresponding virtual trial method in the foregoing method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.

As will be clearly understood by those skilled in the art, the virtual trial apparatus provided in the embodiment of the present application can implement each process in the foregoing method embodiment, and for convenience and brevity of description, the specific working processes of the apparatus and the module described above may refer to corresponding processes in the foregoing method embodiment, and are not described herein again.

In the several embodiments provided in the present application, the coupling or direct coupling or communication connection between the modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be in an electrical, mechanical or other form.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

Referring to fig. 12, a block diagram of an electronic device 600 according to an embodiment of the present disclosure is shown. The electronic device 600 may be a terminal device capable of running an application, such as a smart phone, a tablet computer, and an electronic book. The electronic device 600 in the present application may include one or more of the following components: a processor 610, a memory 620, and one or more applications, wherein the one or more applications may be stored in the memory 620 and configured to be executed by the one or more processors 610, the one or more programs configured to perform the methods as described in the aforementioned method embodiments.

The processor 610 may include one or more processing cores. The processor 610 interfaces with various components throughout the electronic device 600 using various interfaces and circuitry to perform various functions of the electronic device 600 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 620 and invoking data stored in the memory 620. Alternatively, the processor 610 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable gate Array (FPGA), and Programmable Logic Array (PLA). The processor 610 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 610, but may be implemented by a communication chip.

The Memory 620 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 620 may be used to store instructions, programs, code sets, or instruction sets. The memory 620 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created during use by the electronic device 600 (e.g., phone books, audio-visual data, chat log data), and so forth.

Further, the terminal device 100 may further include a foldable Display screen, and the Display screen may be a Liquid Crystal Display (LCD), an Organic Light-emitting diode (OLED), or the like. The display screen is used to display information entered by the user, information provided to the user, and various graphical user interfaces that may be composed of graphics, text, icons, numbers, video, and any combination thereof.

Those skilled in the art will appreciate that the structure shown in fig. 12 is a block diagram of only a portion of the structure associated with the present application, and does not constitute a limitation on the terminal device to which the present application is applied, and a particular terminal device may include more or less components than those shown in fig. 12, or combine certain components, or have a different arrangement of components.

Referring to fig. 13, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 1100 has stored therein a program code 1110, the program code 1110 being invokable by the processor for performing the method described in the above-described method embodiments.

The computer-readable storage medium 1100 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 1100 includes a non-transitory computer-readable storage medium. The computer readable storage medium 1100 has storage space for program code 1110 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 1110 may be compressed, for example, in a suitable form.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a smart gateway, a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

While the present embodiments have been described with reference to the accompanying drawings, the present embodiments are not limited to the above embodiments, which are merely illustrative and not restrictive, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention.

Claims

1. A virtual trial method, the method comprising:

when a target user performs virtual trial of an article, acquiring video data containing the target user;

performing intention analysis on audio data in the video data to obtain intention information of the target user;

performing image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user;

and generating feedback content aiming at the virtual trial according to the intention information and the attribute information.

2. The method according to claim 1, wherein the generating feedback content for the virtual trial according to the intention information and the attribute information comprises:

searching similar users of the same type as the target user from a database according to the attribute information;

acquiring an article transaction record of the similar user;

and generating feedback content aiming at the virtual trial according to the intention information and the item transaction record.

3. The method of claim 2, wherein generating feedback content for the virtual trial based on the intent information and the item transaction record comprises:

searching one or more transaction items matched with the intention information from the item transaction record;

and generating recommended content aiming at the virtual trial according to the one or more transaction items.

4. The method of claim 2, wherein the intent information includes a plurality of intentions, and wherein generating feedback for the virtual trial based on the intent information and the item transaction record comprises:

obtaining a prioritization of the plurality of intents;

according to the priority ranking, one or more transaction items matched with the intentions are searched from the item transaction records;

generating recommended content for the virtual trial based on the one or more transactional items, the recommended content being displayed in the prioritization.

5. The method of claim 2, wherein the searching for similar users of the same type as the target user from a database according to the attribute information comprises:

acquiring an attribute record of each user in a database;

matching the attribute information with the attribute record of each user;

determining similarity of the target user and each user based on matching results;

and determining one or more users with the similarity larger than a preset threshold value from each user as similar users of the same type as the target user.

6. The method of claim 5, wherein the attribute information comprises a plurality of feature information, wherein the attribute record comprises a plurality of feature records, and wherein matching the attribute information with the attribute record of each user comprises:

and when the feature information of a specified type in the feature information is successfully matched with the feature record corresponding to the specified type in the feature records of the current user, matching other feature information in the feature information with other feature records in the feature records, wherein the current user is any user in each user.

7. The method of claim 6, further comprising:

and when the feature information of the specified type in the feature information is unsuccessfully matched with the feature record corresponding to the specified type in the feature records of the current user, determining that the current user and the target user are different types of users.

8. The method according to any one of claims 1-7, wherein the attribute information includes an emotional characteristic, and wherein generating the feedback content for the virtual trial according to the intention information and the attribute information includes:

determining the preference degree value of the user to the current virtual trial article according to the emotional characteristics;

and generating feedback content aiming at the current virtual trial according to the intention information and the preference degree value.

9. The method of claim 8, wherein generating feedback content for the current virtual trial based on the intent information and the like degree value comprises:

and when the preference degree value is smaller than a first threshold value, generating first feedback content aiming at the current virtual trial, wherein the first feedback content is used for recommending other articles which are different from the articles on the current virtual trial.

10. The method of claim 9, wherein generating feedback content for the current virtual trial based on the intent information and the like degree value comprises:

and when the preference degree value is larger than a second threshold value, generating second feedback content aiming at the current virtual trial, wherein the second feedback content is used for recommending other articles of the same type as the articles on the current virtual trial, and the second threshold value is larger than the first threshold value.

11. The method according to any one of claims 1 to 10, wherein the attribute information includes identity information, and the generating feedback content for the virtual trial according to the intention information and the attribute information includes:

acquiring a historical transaction record of the target user according to the identity information;

and generating personalized recommended content aiming at the virtual trial according to the intention information and the historical transaction record.

12. The method according to any one of claims 1-10, wherein the generating feedback content for the virtual trial according to the intention information and the attribute information comprises:

determining a target article which the target user desires to perform virtual trial according to the intention information;

judging whether the target object is matched with the attribute information;

and when the target object is not matched with the attribute information, generating feedback content aiming at the virtual trial.

13. A virtual trial apparatus, the apparatus comprising:

the video acquisition module is used for acquiring video data containing a target user when the target user performs virtual trial of an article;

the intention analysis module is used for carrying out intention analysis on audio data in the video data to obtain intention information of the target user;

the image analysis module is used for carrying out image analysis on image data in the video data to obtain attribute information of the target user, wherein the attribute information is used for representing characteristic information embodied outside the target user;

and the feedback generation module is used for generating feedback contents aiming at the virtual trial according to the intention information and the attribute information.

14. An electronic device, comprising:

one or more processors;

a memory;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-12.

15. A computer-readable storage medium, having stored thereon program code that can be invoked by a processor to perform the method according to any one of claims 1 to 12.