Vehicle-mounted multimedia content pushing method and device, medium and electronic equipment
User intentions are obtained through voice input conversion and semantic recognition, feature vectors are generated based on user attribute information, and multimedia content is matched for pushing, which solves the problem that existing systems cannot adapt to complex scenarios and lack real-time, and achieves higher push accuracy and user experience.
Patent Information
- Application Number
- CN202411427749.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2025-03-11
AI Technical Summary
The existing vehicle multimedia content recommendation system cannot adapt to complex scenarios and lacks real-time performance, resulting in poor accuracy and user experience of push results.
Convert voice input into text information, semantic recognition is performed to obtain user intention and slot information, and user feature vectors are generated based on user attribute information, and selected multimedia content is matched for pushing.
It improves the accuracy of multimedia content push, improves user experience, can better adapt to complex scenarios and provide real-time recommendations.
Smart Images
Figure CN119597940A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing technology, and in particular, relates to a method, device, medium and electronic device for pushing vehicle-mounted multimedia content. Background Art
[0002] With the rapid development of intelligent in-vehicle systems, users' personalized demand for in-vehicle multimedia content is growing. In the current technical solutions, the in-vehicle multimedia content recommendation system mainly relies on the user's historical behavior data, analyzes user preferences through simple algorithms, and then recommends corresponding multimedia content. However, the above method cannot adapt to complex scenarios and lacks real-time performance, resulting in poor accuracy of push results and user experience. Therefore, how to improve the accuracy of multimedia content push and ensure user experience has become a technical problem that needs to be solved urgently. Summary of the invention
[0003] The embodiments of the present application provide a method, device, medium and electronic device for pushing in-vehicle multimedia content, which can improve the accuracy of multimedia content push at least to a certain extent and ensure user experience.
[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0005] According to one aspect of an embodiment of the present application, a method for pushing in-vehicle multimedia content is provided, comprising:
[0006] Convert the target user's voice input to obtain corresponding text information;
[0007] Perform semantic recognition according to the text information to obtain the user intention of the target user and the corresponding slot information;
[0008] In the case where the user intention is a target type, obtaining corresponding multiple candidate multimedia contents and content feature vectors corresponding to each candidate multimedia content according to the slot information;
[0009] Generate a corresponding user feature vector according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle location information;
[0010] At least one target multimedia content is determined from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and is pushed.
[0011] In some embodiments of the present application, based on the above scheme, generating a corresponding user feature vector according to the attribute information of the target user includes:
[0012] Determining user preference information of the target user according to a preference preset record of the target user and / or an operation record during multimedia content playback;
[0013] Performing emotion recognition according to the voice input to obtain user emotion information of the target user;
[0014] Obtain the current vehicle's driving environment information and vehicle location information;
[0015] A user feature vector corresponding to the target user is generated according to the user preference information, the user emotion information, the driving environment information and the vehicle position information.
[0016] In some embodiments of the present application, based on the aforementioned solution, determining the user preference information of the target user according to the preset preference record of the target user and / or the operation record during the multimedia content playback includes:
[0017] Determining user preference information of the target user according to the preset preference record of the target user;
[0018] The user preference information is updated according to the operation record of the target user during multimedia content playback within a previous predetermined time period.
[0019] In some embodiments of the present application, based on the above scheme, generating a user feature vector corresponding to the target user according to the user preference information, the user emotion information, the driving environment information and the vehicle location information includes:
[0020] Perform encoding processing according to the user preference information, the user emotion information, the driving environment information and the vehicle position information to generate a corresponding initial user feature vector;
[0021] Performing dimension reduction processing on the initial user feature vector to obtain a target user feature vector corresponding to the target user.
[0022] In some embodiments of the present application, based on the aforementioned solution, the driving environment information includes one or more of temperature, humidity, light intensity and weather.
[0023] In some embodiments of the present application, based on the above solution, at least one target multimedia content is determined from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and pushed, including:
[0024] Calculating the similarity between the user feature vector and each of the preset feature vectors;
[0025] Determining at least one target multimedia content from the candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents;
[0026] Push at least one of the target multimedia contents.
[0027] In some embodiments of the present application, based on the above scheme, determining at least one target multimedia content from a plurality of candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents includes:
[0028] According to the descending order of the similarities, a predetermined number of candidate multimedia contents arranged in front of the candidate multimedia contents are determined as target multimedia contents;
[0029] or
[0030] The candidate multimedia content whose similarity is greater than a predetermined threshold is determined as the target multimedia content.
[0031] According to one aspect of an embodiment of the present application, a device for pushing in-vehicle multimedia content is provided, including:
[0032] A conversion module, used to convert the target user's voice input to obtain corresponding text information;
[0033] A semantic module, used to perform semantic recognition based on the text information to obtain the user intention of the target user and the corresponding slot information;
[0034] A query module, configured to obtain, when the user intention is a target type, a number of corresponding candidate multimedia contents and a content feature vector corresponding to each of the candidate multimedia contents according to the slot information;
[0035] A generating module, configured to generate a corresponding user feature vector according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle position information of the target user;
[0036] The processing module is used to determine at least one target multimedia content from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors, and push the target multimedia content.
[0037] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for pushing vehicle-mounted multimedia content as described in the above embodiment is implemented.
[0038] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for pushing in-vehicle multimedia content as described in the above embodiments.
[0039] According to one aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for pushing in-vehicle multimedia content provided in the above embodiments.
[0040] In the technical solutions provided in some embodiments of the present application, the voice input of the target user is converted to obtain the corresponding text information, and semantic recognition is performed based on the text information to obtain the user intention of the target user and its corresponding slot information. When the user intention is a target type, the corresponding several candidate multimedia contents, i.e., the content feature vector corresponding to each candidate multimedia content, are obtained based on the slot information. Then, the corresponding user feature vector is generated based on the attribute information of the target user, and the attribute information includes the user preference information, user emotion information, driving environment information and vehicle location information of the target user. Then, based on the user feature vector and each content feature vector, at least one target multimedia content is determined from several candidate multimedia contents and pushed. Thus, by extracting the attribute information of the user to generate the corresponding user feature vector, and then pushing the multimedia content based on the user feature vector, the accuracy of multimedia content push can be improved and the user experience can be guaranteed.
[0041] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0043] Figure 1 A schematic diagram showing a process of a method for pushing in-vehicle multimedia content according to an embodiment of the present application is shown;
[0044] Figure 2A block diagram of a device for pushing in-vehicle multimedia content according to an embodiment of the present application is shown;
[0045] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0047] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0048] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0049] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0050] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.
[0051] Figure 1A flow chart of a method for pushing in-vehicle multimedia content according to an embodiment of the present application is shown. The method can be applied to a terminal device or a server, wherein the terminal device can include but is not limited to one or more of an in-vehicle terminal, a smart phone, a tablet computer, a portable computer, and a desktop computer; the server can be a physical server or a cloud server.
[0052] Please refer to Figure 1 The method for pushing in-vehicle multimedia content at least includes steps S110 to S150, which are described in detail as follows (the method is described below by taking the application of the method to an in-vehicle terminal as an example):
[0053] In step S110, the target user's voice input is converted to obtain corresponding text information. In this embodiment, the vehicle terminal can receive the target user's voice input through a voice receiving device (such as a microphone) configured by itself. It should be noted that the target user can be any one of all the people in the current vehicle, such as the driver or a passenger.
[0054] After receiving the voice input of the target user, the vehicle-mounted terminal can convert the voice input to obtain the corresponding text information. In one example, the vehicle-mounted terminal can first pre-process the voice input, and the pre-processing includes but is not limited to pre-emphasis, endpoint detection, noise suppression, etc., so as to eliminate the background noise in the voice input and improve the quality of the voice input. Then, the pre-processed voice input is converted into a corresponding feature vector, which can reflect the inherent characteristics of the voice input, such as spectral features or inverse spectrum features. The feature vector is then input into the trained acoustic model and language model for voice-to-text conversion to obtain the corresponding text information. It should be noted that other existing speech recognition technologies can also be used to convert voice input, and this application does not specifically limit this.
[0055] In step S120, semantic recognition is performed based on the text information to obtain the user intention of the target user and the corresponding slot information.
[0056] The user intent may be a purpose or need expressed by the target user through voice input, which may be used to guide the vehicle-mounted terminal on how to respond to the target user's request. In one example, those skilled in the art may pre-classify the user intent into multiple categories, such as search, purchase, command, play, navigation, etc.
[0057] In the field of natural language processing and dialogue systems, slots can be variables or attributes that need to be filled in the dialogue. They can be used to capture specific information related to the user's intent. These attributes can be entities (such as names, places), categories (such as food types, music genres), or specific values (such as quantity, price). Therefore, slots are a key part of understanding user requests and performing tasks.
[0058] In this embodiment, the vehicle terminal can deeply analyze text information through natural language understanding technology (including part-of-speech tagging, named entity recognition, dependency syntax analysis, etc.), understand sentence structure and identify key information, and then apply machine learning or deep learning models, such as Transformer-based BERT, to deeply understand the contextual meaning of the text information, and then use intent classification and slot filling technology to map the text to predefined intent categories and extract related entity information to achieve a comprehensive understanding of the target user's voice input.
[0059] Please continue to refer to Figure 1 In step S130, when the user intention is a target type, a number of corresponding candidate multimedia contents and a content feature vector corresponding to each of the candidate multimedia contents are obtained according to the slot information.
[0060] In this embodiment, after determining the user intention of the target user and its corresponding slot information, the vehicle terminal can first determine whether the user intention is of the target type, such as playing audio, video, etc. In the case where the user intention is of the target type, the vehicle terminal can search for multiple corresponding alternative multimedia content in the multimedia content database. For example, if the target user's voice input is "play relaxing music", the corresponding user intention is to play music, and the corresponding slot information is "relaxing", the vehicle terminal can search from the multimedia content database and determine the music that is pre-classified as "relaxing" as the alternative multimedia content.
[0061] Those skilled in the art can generate a corresponding content feature vector for each multimedia content in the multimedia content database in advance. In one example, multiple attribute information of each multimedia content can be obtained in advance. Taking music as an example, the attribute information of the music genre, artist, and emotional state of the audience corresponding to the music can be obtained in advance, and then the corresponding content feature vector can be generated according to the multiple attribute information. For example, each attribute information can be converted into a corresponding vector form, and then multiple vectors can be processed by splicing or weighted averaging to obtain a content feature vector corresponding to the multimedia content.
[0062] After generating a corresponding content feature vector for each multimedia content, the multimedia content and its corresponding content feature vector may be associated and stored, so that the vehicle terminal can obtain the content feature vector of the candidate multimedia content after determining the candidate multimedia content.
[0063] In step S140, a corresponding user feature vector is generated according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle position information.
[0064] In this embodiment, the vehicle terminal can obtain the attribute information of the target user, which may include user preference information, user emotion information, driving environment information and vehicle location information. Among them, the user preference information may be the target user's preference for multimedia content, such as music genre, artist or podcast theme, etc.; the user emotion information may be the target user's emotional state at the current moment, such as happiness, sadness, anger, etc.; the driving environment information may be relevant information about the current vehicle environment. In one example, the driving environment information may include but is not limited to one or more of the temperature, humidity, light and weather conditions of the vehicle environment; the vehicle location information may be the precise geographic location of the current vehicle.
[0065] After obtaining the above attribute information, the vehicle terminal can generate a corresponding user feature vector based on the above multiple attribute information for subsequent multimedia content push. In one example, the vehicle terminal can convert each attribute information into a vector form, and concatenate or weighted average multiple vectors to generate a user feature vector corresponding to the target user.
[0066] In step S150, at least one target multimedia content is determined from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and is pushed.
[0067] In this embodiment, after determining the user feature vector of the target user, the vehicle terminal can match the user feature vector with the content feature vectors of each candidate multimedia content, and determine at least one target multimedia content from the plurality of candidate multimedia content according to the matching result, and push the at least one target multimedia content. It should be understood that the higher the matching degree corresponding to the multimedia content, the higher its ranking should be when pushed.
[0068] Therefore, based on Figure 1In the embodiment shown, the target user's voice input is converted to obtain the corresponding text information, and semantic recognition is performed based on the text information to obtain the target user's user intention and its corresponding slot information. When the user intention is a target type, the corresponding several candidate multimedia contents, i.e., the content feature vector corresponding to each candidate multimedia content, are obtained based on the slot information. Then, the corresponding user feature vector is generated based on the target user's attribute information, and the attribute information includes the target user's user preference information, user emotion information, driving environment information, and vehicle location information. Then, based on the user feature vector and each content feature vector, at least one target multimedia content is determined from several candidate multimedia contents and pushed. Thus, by extracting the user's attribute information to generate the corresponding user feature vector, and then pushing the multimedia content based on the user feature vector, the accuracy of multimedia content push can be improved and the user experience can be guaranteed.
[0069] In some embodiments of the present application, generating a corresponding user feature vector according to the attribute information of the target user includes:
[0070] Determining user preference information of the target user according to a preference preset record of the target user and / or an operation record during multimedia content playback;
[0071] Performing emotion recognition according to the voice input to obtain user emotion information of the target user;
[0072] Obtain the current vehicle's driving environment information and vehicle location information;
[0073] A user feature vector corresponding to the target user is generated according to the user preference information, the user emotion information, the driving environment information and the vehicle position information.
[0074] In this embodiment, the user can pre-edit the preferences for multimedia content in the vehicle terminal, and the vehicle terminal can receive the user's editing information to generate a corresponding preference preset record. In addition, when the user uses the vehicle terminal, the vehicle terminal can also record the user's operation records when playing multimedia content, such as pause, switch, favorite, etc.
[0075] When it is necessary to obtain the user preference information of the target user, the vehicle terminal can determine the user preference information of the target user based on the preference preset record and / or the operation record during the multimedia content playback. In one example, to ensure the accuracy of the determined user preference information, the vehicle terminal can determine the identity information of the target user based on the voice input, thereby obtaining the preference preset record corresponding to the identity information to determine the user preference information. For example, the vehicle terminal can determine whether there is a preference preset record corresponding to the voice print based on the voice input voice print, and if so, the corresponding preference preset record can be obtained.
[0076] It is worth noting that the vehicle-mounted terminal can determine the user preference information corresponding to the target user only based on the preference preset record, or it can determine the corresponding user preference information only based on the user's operation information when playing multimedia content. It can also comprehensively consider the two to determine the corresponding user preference information.
[0077] In some embodiments of the present application, determining the user preference information of the target user according to the preset preference record of the target user and / or the operation record during the multimedia content playback includes:
[0078] Determining user preference information of the target user according to the preset preference record of the target user;
[0079] The user preference information is updated according to the operation record of the target user during multimedia content playback within a previous predetermined time period.
[0080] In this embodiment, the vehicle-mounted terminal can first determine the corresponding user preference information based on the preset preference record of the target user, and then, based on the user preference information, update the predetermined user preference information based on the operation record of the target user when playing multimedia content within the previous predetermined time period, so as to be able to update the corresponding user preference information in real time as the preferences of the target user change, thereby ensuring the accuracy of the user preference information.
[0081] The predetermined time period may be preset by those skilled in the art based on prior experience, for example, the predetermined time period may be 7 days, 15 days, 30 days, etc. The above numbers are only illustrative examples and are not particularly limited thereto.
[0082] When it is necessary to obtain user emotional information, the vehicle terminal can perform emotion recognition based on the target user's voice input and determine the target user's user emotional information by analyzing the tone, rhythm, and intensity of the voice input. In addition, the vehicle terminal can also assist in inferring the target user's emotional state by analyzing the target user's facial expression and the tone of text information.
[0083] When it is necessary to obtain driving environment information, the vehicle terminal can obtain it through the sensor network integrated with the outside of the vehicle, such as temperature sensors, humidity sensors, light sensors and weather monitoring equipment. In addition, the vehicle terminal can also communicate with surrounding devices to obtain driving environment information, such as traffic lights, road signs, base stations, etc. If necessary, the vehicle terminal can also request driving environment information from other vehicle devices through a short-range wireless communication network.
[0084] When the vehicle location information is needed, the on-board terminal can determine the current vehicle location information through the vehicle's GPS and map services. When the GPS signal is unstable or unavailable, V2X network and other technologies can be used to assist in positioning.
[0085] After acquiring the above information, the vehicle-mounted terminal may generate a corresponding user feature vector according to the above information for subsequent push of multimedia content.
[0086] In some embodiments of the present application, generating a user feature vector corresponding to the target user according to the user preference information, the user emotion information, the driving environment information and the vehicle location information includes:
[0087] Perform encoding processing according to the user preference information, the user emotion information, the driving environment information and the vehicle position information to generate a corresponding initial user feature vector;
[0088] Performing dimension reduction processing on the initial user feature vector to obtain a target user feature vector corresponding to the target user.
[0089] In this embodiment, after obtaining user preference information, user emotion information, driving environment information and vehicle location information, the vehicle terminal can encode each type of information to obtain a vector representation corresponding to each type of information. Then, each vector representation is concatenated to obtain a corresponding initial user feature vector.
[0090] Then, the vehicle terminal can perform dimensionality reduction processing on the initial user feature vector, for example, using principal component analysis or t-SNE and other dimensionality reduction techniques to reduce the dimension of the initial user feature vector and retain the most important information to obtain the target user feature vector. In this way, the data dimension and the required storage space can be reduced, and redundant features and noise error factors can be eliminated.
[0091] It should be noted that when encoding each type of information, its possible value range and type (such as categorical features or continuous features) can be defined in advance. For categorical features, one-hot encoding or label encoding can be used to convert them into numerical form, while for continuous features, they can be standardized or normalized to have a uniform scale.
[0092] In some embodiments of the present application, determining at least one target multimedia content from a plurality of candidate multimedia contents and pushing the content according to the user feature vector and each of the content feature vectors includes:
[0093] Calculating the similarity between the user feature vector and each of the preset feature vectors;
[0094] Determining at least one target multimedia content from the candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents;
[0095] Push at least one of the target multimedia contents.
[0096] In this embodiment, after determining the user feature vector of the target user, the vehicle terminal can calculate the similarity between the user feature vector and the content feature vector of each candidate multimedia content, such as Euclidean distance or cosine similarity. According to the similarity corresponding to each candidate multimedia content, the vehicle terminal can determine at least one target multimedia content from a number of candidate multimedia contents for push.
[0097] In one example, determining at least one target multimedia content from a plurality of candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents includes:
[0098] According to the descending order of the similarities, a predetermined number of candidate multimedia contents arranged in front of the candidate multimedia contents are determined as target multimedia contents;
[0099] or
[0100] The candidate multimedia content whose similarity is greater than a predetermined threshold is determined as the target multimedia content.
[0101] That is, the vehicle terminal can sort the similarities corresponding to the candidate multimedia contents in descending order, and determine a predetermined number of candidate multimedia contents arranged in front as target multimedia contents to ensure that the pushed target multimedia contents can better meet the current status of the target user.
[0102] Alternatively, the vehicle-mounted terminal can determine the alternative multimedia content whose similarity is greater than a predetermined threshold as the target multimedia content, wherein the predetermined threshold may be pre-set by technical personnel in this field based on prior experience. If the similarity is greater than the predetermined threshold, it can ensure the relevance of the pushed multimedia content to the current state of the target user, thereby ensuring the user experience.
[0103] In one example, when pushing at least one target multimedia content, the vehicle terminal can display the target multimedia content in the form of a list for the target user to select. In some cases, such as when playing music, the vehicle terminal can also directly play the first ranked target multimedia content according to the sorting order of the target multimedia content (i.e., the order of corresponding similarity from large to small).
[0104] The following describes an embodiment of the device of the present application, which can be used to execute the method for pushing in-vehicle multimedia content in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for pushing in-vehicle multimedia content in the above embodiment of the present application.
[0105] Figure 2 A block diagram of a device for pushing in-vehicle multimedia content according to an embodiment of the present application is shown.
[0106] Reference Figure 2 As shown, according to an embodiment of the present application, a device for pushing in-vehicle multimedia content includes:
[0107] A conversion module, used to convert the target user's voice input to obtain corresponding text information;
[0108] A semantic module, used to perform semantic recognition based on the text information to obtain the user intention of the target user and the corresponding slot information;
[0109] A query module, configured to obtain, when the user intention is a target type, a number of corresponding candidate multimedia contents and a content feature vector corresponding to each of the candidate multimedia contents according to the slot information;
[0110] A generating module, used to generate a corresponding user feature vector according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle location information;
[0111] The processing module is used to determine at least one target multimedia content from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors, and push the target multimedia content.
[0112] In some embodiments of the present application, generating a corresponding user feature vector according to the attribute information of the target user includes:
[0113] Determining user preference information of the target user according to a preference preset record of the target user and / or an operation record during multimedia content playback;
[0114] Performing emotion recognition according to the voice input to obtain user emotion information of the target user;
[0115] Obtain the current vehicle's driving environment information and vehicle location information;
[0116] A user feature vector corresponding to the target user is generated according to the user preference information, the user emotion information, the driving environment information and the vehicle position information.
[0117] In some embodiments of the present application, determining the user preference information of the target user according to the preset preference record of the target user and / or the operation record during the multimedia content playback includes:
[0118] Determining user preference information of the target user according to the preset preference record of the target user;
[0119] The user preference information is updated according to the operation record of the target user during multimedia content playback within a previous predetermined time period.
[0120] In some embodiments of the present application, generating a user feature vector corresponding to the target user according to the user preference information, the user emotion information, the driving environment information and the vehicle location information includes:
[0121] Perform encoding processing according to the user preference information, the user emotion information, the driving environment information and the vehicle position information to generate a corresponding initial user feature vector;
[0122] Performing dimension reduction processing on the initial user feature vector to obtain a target user feature vector corresponding to the target user.
[0123] In some embodiments of the present application, the driving environment information includes one or more of temperature, humidity, light intensity and weather.
[0124] In some embodiments of the present application, based on the above solution, at least one target multimedia content is determined from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and pushed, including:
[0125] Calculating the similarity between the user feature vector and each of the preset feature vectors;
[0126] Determining at least one target multimedia content from the candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents;
[0127] Push at least one of the target multimedia contents.
[0128] In some embodiments of the present application, determining at least one target multimedia content from a plurality of candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents includes:
[0129] According to the descending order of the similarities, a predetermined number of candidate multimedia contents arranged in front of the candidate multimedia contents are determined as target multimedia contents;
[0130] or
[0131] The candidate multimedia content whose similarity is greater than a predetermined threshold is determined as the target multimedia content.
[0132] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.
[0133] It should be noted that Figure 3 The computer system of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0134] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0135] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0136] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.
[0137] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0138] The flowchart and block diagram in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0139] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0140] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.
[0141] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0142] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.
[0143] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0144] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for pushing in-vehicle multimedia content, characterized in that: include: Convert the target user's voice input to obtain corresponding text information; Perform semantic recognition according to the text information to obtain the user intention of the target user and the corresponding slot information; In the case where the user intention is a target type, obtaining corresponding multiple candidate multimedia contents and content feature vectors corresponding to each candidate multimedia content according to the slot information; Generate a corresponding user feature vector according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle location information; At least one target multimedia content is determined from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and is pushed.
2. The method according to claim 1, characterized in that Generate a corresponding user feature vector according to the attribute information of the target user, including: Determining user preference information of the target user according to a preference preset record of the target user and / or an operation record during multimedia content playback; Performing emotion recognition according to the voice input to obtain user emotion information of the target user; Obtain the current vehicle's driving environment information and vehicle location information; A user feature vector corresponding to the target user is generated according to the user preference information, the user emotion information, the driving environment information and the vehicle position information.
3. The method according to claim 2, characterized in that Determining user preference information of the target user according to the preset preference record of the target user and / or the operation record during multimedia content playback includes: Determining user preference information of the target user according to the preset preference record of the target user; The user preference information is updated according to the operation record of the target user during multimedia content playback within a previous predetermined time period.
4. The method according to claim 2, characterized in that: Generating a user feature vector corresponding to the target user according to the user preference information, the user emotion information, the driving environment information and the vehicle location information, including: Perform encoding processing according to the user preference information, the user emotion information, the driving environment information and the vehicle position information to generate a corresponding initial user feature vector; Performing dimension reduction processing on the initial user feature vector to obtain a target user feature vector corresponding to the target user.
5. The method according to any one of claims 1 to 4, characterized in that The driving environment information includes one or more of temperature, humidity, light intensity and weather.
6. The method according to any one of claims 1 to 4, characterized in that Determining at least one target multimedia content from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors and pushing the target multimedia content comprises: Calculating the similarity between the user feature vector and each of the preset feature vectors; Determining at least one target multimedia content from the candidate multimedia contents according to the similarities corresponding to the candidate multimedia contents; Push at least one of the target multimedia contents.
7. The method according to claim 6, characterized in that Determining at least one target multimedia content from the candidate multimedia content according to the similarities corresponding to the candidate multimedia content includes: According to the descending order of the similarities, a predetermined number of candidate multimedia contents arranged in front of the candidate multimedia contents are determined as target multimedia contents; or The candidate multimedia content whose similarity is greater than a predetermined threshold is determined as the target multimedia content.
8. A device for pushing multimedia content in a vehicle, characterized in that: include: A conversion module, used to convert the target user's voice input to obtain corresponding text information; A semantic module, used to perform semantic recognition based on the text information to obtain the user intention of the target user and the corresponding slot information; A query module, configured to obtain, when the user intention is a target type, a number of corresponding candidate multimedia contents and a content feature vector corresponding to each of the candidate multimedia contents according to the slot information; A generating module, used to generate a corresponding user feature vector according to the attribute information of the target user, wherein the attribute information includes user preference information, user emotion information, driving environment information and vehicle location information; The processing module is used to determine at least one target multimedia content from a plurality of candidate multimedia contents according to the user feature vector and each of the content feature vectors, and push the target multimedia content.
9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for pushing vehicle-mounted multimedia content according to any one of claims 1 to 7 is implemented.
10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the method for pushing in-vehicle multimedia content as described in any one of claims 1 to 7.