Voice interaction method and device, electronic equipment and computer storage medium

Abstract

The invention provides a voice interaction method and device, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining voice instruction information sent by a user; determining user feature information of the user according to the voice instruction information; determining intention information corresponding to the voice instruction information according to the voice instruction information; and determining feedback content corresponding to the voice instruction information based on the user feature information and the intention information. According to the embodiment provided by the scheme, the personalization and accuracy of voice interaction can be improved.

Description

Technical Field

[0001] The present application relates to the field of voice assistant technology, and in particular to a voice interaction method, device, electronic device and computer storage medium. Background Art

[0002] In the related art, when different users interact with intelligent voice assistants through voice, intelligent voice assistants usually provide preset and fixed responses. This approach is difficult to meet the diverse needs of different users due to the lack of in-depth understanding and response capabilities of users' personalized needs. This lack of personalized interaction experience not only affects the user experience, but may also limit the application of intelligent voice assistants in more complex scenarios, such as personalized recommendations, emotional support, and personalized learning. Summary of the invention

[0003] The embodiments of the present application provide a voice interaction method, device, electronic device and computer storage medium, which can improve the personalization and accuracy of voice interaction. The above technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides a voice interaction method, the method comprising:

[0005] Obtain the voice command information issued by the user;

[0006] Determine user characteristic information of the user according to the voice command information;

[0007] Determine the intention information corresponding to the voice command information according to the voice command information;

[0008] The feedback content corresponding to the voice command information is determined based on the user feature information and the intention information.

[0009] In a possible implementation, the determining the user characteristic information of the user according to the voice command information includes:

[0010] Extracting features from the voice command information to obtain first feature information of the user corresponding to the voice command information;

[0011] Acquire second feature information corresponding to the user based on the first feature information, wherein the second feature information includes feature information obtained based on historical voice command information of the user;

[0012] The user characteristic information of the user is determined according to the first characteristic information and the second characteristic information.

[0013] In a possible implementation, determining the intention information corresponding to the voice command information according to the voice command information includes:

[0014] Recognize and process the voice command information to obtain text information corresponding to the voice command information;

[0015] The intention of the above text information is recognized through a preset intention recognition model to obtain the intention information corresponding to the above voice command information.

[0016] In a possible implementation, generating feedback content corresponding to the voice command information based on the user feature information and the intention information includes:

[0017] Determine the intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type;

[0018] The feedback content corresponding to the voice command information is determined according to the intention type and the user characteristic information.

[0019] In a possible implementation, the generating of feedback content corresponding to the voice command information according to the intention type and the user characteristic information includes:

[0020] In the case where the intention type is the content recommendation type, determining a plurality of to-be-determined recommended contents corresponding to the intention information based on the intention information;

[0021] Filtering the plurality of recommended contents to be determined according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information;

[0022] The at least one recommended content is determined as the feedback content corresponding to the voice instruction information.

[0023] In a possible implementation, the generating of feedback content corresponding to the voice command information according to the intention type and the user characteristic information includes:

[0024] In the case where the above-mentioned intention type is the above-mentioned question-answer dialogue type, determining the answer text corresponding to the above-mentioned intention information based on the above-mentioned intention information;

[0025] Determining a target timbre corresponding to the intention information according to the intention information, the target timbre being any one of a plurality of preset timbres;

[0026] Processing the answer text by the speech synthesis model corresponding to the target timbre to obtain speech answer information;

[0027] The voice answer information is determined as the feedback content corresponding to the voice command information.

[0028] In a possible implementation, determining the target timbre corresponding to the intention information according to the intention information includes:

[0029] Determining whether the intention information includes a specified timbre;

[0030] If yes, the specified timbre is used as the target timbre corresponding to the intention information;

[0031] If not, the target timbre corresponding to the intention information is determined according to a preset correspondence relationship and the user characteristic information; wherein the preset correspondence relationship is a correspondence relationship between characteristic information of multiple users and the multiple timbres.

[0032] In a second aspect, an embodiment of the present application provides a voice interaction device, the device comprising:

[0033] An acquisition module is used to acquire the voice command information issued by the user;

[0034] A first determining module, used to determine user characteristic information of the user according to the voice command information;

[0035] A second determination module is used to determine the intention information corresponding to the voice command information according to the voice command information;

[0036] The third determination module is used to determine the feedback content corresponding to the above-mentioned voice command information based on the above-mentioned user characteristic information and the above-mentioned intention information.

[0037] In a possible implementation, the first determining module includes:

[0038] A feature extraction unit, used to extract features from the voice command information to obtain first feature information of the user corresponding to the voice command information;

[0039] an acquisition unit, configured to acquire second feature information corresponding to the user based on the first feature information, wherein the second feature information includes feature information obtained based on historical voice command information of the user;

[0040] The first determining unit is used to determine the user characteristic information of the user according to the first characteristic information and the second characteristic information.

[0041] In a possible implementation, the second determining module includes:

[0042] A first recognition unit is used to recognize and process the voice command information to obtain text information corresponding to the voice command information;

[0043] The second recognition unit performs intent recognition on the above text information through a preset intention recognition model to obtain intent information corresponding to the above voice command information.

[0044] In a possible implementation, the third determining module includes:

[0045] A second determining unit is used to determine the intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type;

[0046] The third determination unit is used to determine the feedback content corresponding to the above-mentioned voice instruction information according to the above-mentioned intention type and the above-mentioned user characteristic information.

[0047] In a possible implementation, the third determining unit includes:

[0048] A first determining subunit is configured to determine, when the intention type is the content recommendation type, a plurality of to-be-determined recommended contents corresponding to the intention information based on the intention information;

[0049] A screening subunit, configured to screen the plurality of recommended contents to be determined according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information;

[0050] The second determining subunit is used to determine the at least one recommended content as the feedback content corresponding to the voice instruction information.

[0051] In a possible implementation, the third determining unit includes:

[0052] A third determination subunit is used to determine an answer text corresponding to the intention information based on the intention information when the intention type is the question-answer dialogue type;

[0053] A fourth determination subunit is used to determine a target timbre corresponding to the intention information according to the intention information, wherein the target timbre is any one of a plurality of preset timbres;

[0054] A processing subunit, used for processing the answer text through the speech synthesis model corresponding to the target timbre to obtain speech answer information;

[0055] The fifth determining subunit is used to determine the above-mentioned voice answer information as the feedback content corresponding to the above-mentioned voice instruction information.

[0056] In a possible implementation manner, the fourth determining subunit is specifically configured to:

[0057] Determining whether the intention information includes a specified timbre;

[0058] If yes, the specified timbre is used as the target timbre corresponding to the intention information;

[0059] If not, the target timbre corresponding to the intention information is determined according to a preset correspondence relationship and the user characteristic information; wherein the preset correspondence relationship is a correspondence relationship between characteristic information of multiple users and the multiple timbres.

[0060] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory;

[0061] The above-mentioned memory stores a computer program, and the above-mentioned computer program is suitable for being loaded by the above-mentioned processor and executing the steps of the method provided by the first aspect of the embodiment of the present application or any possible implementation method of the first aspect.

[0062] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores multiple instructions, and the instructions are suitable for being loaded by a processor and executing the steps of the method provided by the first aspect of the embodiment of the present application or any possible implementation method of the first aspect.

[0063] The embodiments of the present application obtain voice command information issued by a user; determine user feature information of the user based on the voice command information; determine intent information corresponding to the voice command information based on the voice command information; and determine feedback content corresponding to the voice command information based on the user feature information and the intent information. The embodiments of the present application can combine the user feature information and the intent information to accurately understand the user's intent while generating more targeted and customized feedback content, thereby effectively improving the personalization and accuracy of voice interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of the structure of a voice interaction system provided by an exemplary embodiment of the present application;

[0066] Figure 2 A flowchart of a voice interaction method provided by an exemplary embodiment of the present application;

[0067] Figure 3 A schematic diagram of the structure of a terminal device provided for an exemplary embodiment of the present application;

[0068] Figure 4 A flowchart of a method for determining feedback content provided by an exemplary embodiment of the present application;

[0069] Figure 5 A flowchart of another feedback content determination method provided by an exemplary embodiment of the present application;

[0070] Figure 6 A schematic diagram of the structure of a voice interaction device provided by an exemplary embodiment of the present application;

[0071] Figure 7 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0073] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0074] Please refer to the following Figure 1 , which exemplarily shows a structural diagram of a voice interaction system provided in an embodiment of the present application. Figure 1 As shown, the system includes a terminal device 110 and a cloud device 120. The terminal device 110 and the cloud device 120 can be directly or indirectly connected via wired or wireless communication, which is not limited in the present application.

[0075] In some embodiments, the terminal device 110 can be a smart camera, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart appliance, etc., but is not limited thereto.

[0076] The cloud device 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), big data and artificial intelligence platforms.

[0077] The terminal device 110 may send a request to the cloud device 120 , and the cloud device 120 may process the request and return a response.

[0078] In some embodiments, the terminal device 110 is used to perform the following steps: obtain voice command information issued by a user; determine user characteristic information of the user based on the voice command information; determine intention information corresponding to the voice command information based on the voice command information; and determine feedback content corresponding to the voice command information based on the user characteristic information and the intention information.

[0079] Optionally, in some embodiments, a preset voice assistant may be installed in the terminal device, and the terminal device runs the preset voice assistant. The user may be a person who uses the terminal device to perform voice interaction with the preset voice assistant.

[0080] Optionally, the voice command information is information about a request or command sent by the user to the preset voice assistant through voice input, which is used to describe the user's intention, request or operation that the user wants to perform. For example, the voice command information can be "What's the weather like today?", "Tell a fairy tale", etc.

[0081] Optionally, a microphone is installed in the terminal device, and the microphone can be used to collect voice command information issued by the user.

[0082] Optionally, the terminal device 110 may send the voice command information to the cloud device 120, so that the cloud device 120 determines the user characteristic information of the user and the intention information corresponding to the voice command information, and determines the feedback content corresponding to the voice command information based on the user characteristic information and the intention information. Then, the terminal device 110 receives the feedback content sent by the cloud device 120.

[0083] In some embodiments, the cloud device 120 may also be used to perform the following steps: obtaining voice command information issued by a user; determining user characteristic information of the user based on the voice command information; determining intent information corresponding to the voice command information based on the voice command information; and determining feedback content corresponding to the voice command information based on the user characteristic information and the intent information.

[0084] An exemplary embodiment of the present application provides a voice interaction method. The voice interaction method can be applied to the above terminal device. For details, please refer to Figure 2 , which exemplarily shows a flow chart of a voice interaction method provided in an embodiment of the present application. Figure 2 As shown, the voice interaction method includes the following S21-S24:

[0085] S21. Acquire voice command information issued by the user.

[0086] In some embodiments, a preset voice assistant may be installed in the above-mentioned terminal device, and the terminal device runs the preset voice assistant. The user may be a person who uses the terminal device to perform voice interaction with the preset voice assistant.

[0087] In some embodiments, the above-mentioned voice command information is information about a request or command issued by a user to a preset voice assistant through voice input, which is used to describe the user's intention, request, or operation that the user wants to perform. Specifically, the voice command information can be continuous speech within a preset duration (such as 30 seconds). For example, the voice command information can be "What's the weather like today?", "Play a piece of music", etc.

[0088] In some embodiments, a microphone is installed in the terminal device, and the microphone can be used to collect voice command information issued by the user.

[0089] S22: Determine user characteristic information of the user according to the voice command information.

[0090] In some embodiments, the user characteristic information includes at least one of the following characteristics of the corresponding user: gender, age group, hobbies, life stage (such as students, professionals, housewives, etc.), geographic location, etc.

[0091] The voice command information may be identified to obtain characteristic information of the sound, and then determine the user characteristic information of the user.

[0092] S23. Determine the intention information corresponding to the voice command information according to the voice command information.

[0093] In some embodiments, the voice command information can be recognized by voice recognition technology to obtain corresponding text information, and then the text information can be recognized by a preset intention model to obtain the intention information corresponding to the text information. The preset intention model is based on machine learning or deep learning, and the accuracy of intention recognition can be improved according to training data.

[0094] S24. Determine feedback content corresponding to the voice command information based on the user feature information and the intention information.

[0095] In some embodiments, based on the identified intent information, content matching the voice command information can be found from a preset database, and then personalized adjustments can be made to the content based on the user's user characteristic information, such as using different timbres, tones, language styles or content types, to obtain feedback content corresponding to the above voice command information. The feedback content not only matches the user's intent information, but is also personalized.

[0096] The embodiments of the present application obtain voice command information issued by a user; determine user feature information of the user based on the voice command information; determine intent information corresponding to the voice command information based on the voice command information; and determine feedback content corresponding to the voice command information based on the user feature information and the intent information. The embodiments of the present application can combine the user feature information and the intent information to accurately understand the user's intent while generating more targeted and customized feedback content, thereby effectively improving the personalization and accuracy of voice interaction.

[0097] Figure 3 A schematic diagram of a terminal device provided by an exemplary embodiment of the present application is shown in FIG. Figure 3 As shown, the terminal device can be a smart camera 300, which includes a camera 310, a dial button 320 and a night light 330. Among them, the camera 310, as the main image capture unit of the terminal device, can be composed of two cameras, namely a first camera 311 and a second camera 312. The dual camera system is generally used to improve image quality, depth perception, wide-angle view and other functions. The dial button 320 can be used for emergency calls or to establish a communication connection with other terminal devices (such as mobile phones). When the user needs to call for help or in an emergency, the preset number can be dialed by pressing the dial button 320. The night light 330 can be used to provide soft lighting at night to facilitate capturing clear images or videos under low light conditions. The brightness of the night light 330 may be adjustable to adapt to different scene requirements. In addition, the smart camera 300 may also include a speaker and a microphone, and the speaker is used to play sounds in multiple formats, such as the Moving Picture Experts Group Audio Layer 3 format.

[0098] In some embodiments, in S22, determining the user characteristic information of the user according to the voice command information includes S221-S223:

[0099] S221. Perform feature extraction on the voice command information to obtain first feature information of the user corresponding to the voice command information.

[0100] The first characteristic information is characteristic information of the corresponding user reflected by the current voice command information.

[0101] In some embodiments, before extracting features from the voice command information, the voice command information may be preprocessed to improve the signal quality of the voice command information and facilitate subsequent processing. For example, the voice command information may be denoised by using a filter to remove background noise to improve the quality of the voice signal; or the voice command information may be framed to divide the continuous voice signal into short time frames.

[0102] In some embodiments, the above-mentioned voice command information can be feature extracted by at least one of the following methods to obtain initial features corresponding to the voice command information: Mel-frequency cepstral coefficient, which extracts the spectral features of the audio signal by simulating the auditory characteristics of the human ear; spectrogram, which converts the voice signal into a spectrogram to analyze frequency and time changes; pitch and volume, which extracts the pitch and volume changes of the voice signal, which can reflect the speaker's emotions and state.

[0103] Furthermore, after obtaining the initial features corresponding to the voice command information, dimensionality reduction techniques (such as principal component analysis) can be used to reduce the dimensions of the initial features and retain important information, such as selecting features related to user characteristic information (such as life stage, gender, age group, hobbies, etc.) as the first characteristic information.

[0104] S222. Acquire second characteristic information corresponding to the user based on the first characteristic information, where the second characteristic information includes characteristic information obtained based on historical voice command information of the user.

[0105] In some embodiments, the second characteristic information may also include characteristic information preset by the user, for example, the user may preset gender, age, geographic location, etc.

[0106] In some embodiments, the second feature information may be stored in a preset feature database, which may include multiple feature information corresponding to multiple user identifiers, and the user identifiers correspond to the feature information one by one. The above user identifiers may represent the identity and / or name of the corresponding user, for example, in a family use scenario, the user identifiers may include any one or more of the following: father, mother, daughter, son, etc.

[0107] In some embodiments, in S222, obtaining the second feature information corresponding to the user based on the first feature information includes: determining feature information matching the first feature information from multiple feature information in a preset feature database, and determining the feature information as the second feature information corresponding to the user.

[0108] Specifically, when determining the feature information that matches the above-mentioned first feature information from multiple feature information in a preset feature database, the similarity score (such as Euclidean distance, cosine similarity, Manhattan distance, etc.) between each feature information in the multiple feature information and the above-mentioned first feature information can be calculated to obtain multiple similarity scores between the above-mentioned multiple feature information and the above-mentioned first feature information, and then the feature information corresponding to the largest similarity score is determined as the feature information that matches the above-mentioned first feature information, that is, the second feature information corresponding to the above-mentioned user.

[0109] S223: Determine user characteristic information of the user according to the first characteristic information and the second characteristic information.

[0110] In some embodiments, in S223, determining the user characteristic information of the user according to the first characteristic information and the second characteristic information includes: determining the first characteristic information and the second characteristic information as the user characteristic information of the user.

[0111] In other embodiments, in S223, the user characteristic information of the user is determined based on the first characteristic information and the second characteristic information, including: updating the second characteristic information based on the first characteristic information, and determining the updated second characteristic information as the user characteristic information of the user.

[0112] Specifically, the first feature information can be compared with the second feature information to identify the part that needs to be updated, and then the part that needs to be updated can be adjusted and replaced according to the first feature information to obtain user feature information, which reflects the user's latest status and preferences. In addition, the updated second feature information can also be stored in the feature database for subsequent query and analysis, and the real-time and accuracy of the user feature information is improved, thereby providing a more personalized user experience.

[0113] In some embodiments, the user's historical behavior characteristics may also be obtained from a preset characteristic database, and the historical behavior characteristics may also be used as user characteristic information.

[0114] In the embodiment of the present application, by using the first characteristic information (characteristic information reflected by the current voice command) and the second characteristic information (characteristic information reflected by the historical voice command and the preset characteristic information), feedback content that better meets the personalized needs of the user can be provided. Not only can the user's real-time needs be responded to, but the service can also be optimized in combination with the user's long-term behavior data, such as recommending content suitable for the user or adjusting the voice interaction method, which effectively improves the accuracy and reliability of the feedback content.

[0115] In some embodiments, in S23, determining the intention information corresponding to the voice command information according to the voice command information includes S231-S232:

[0116] S231. Perform recognition processing on the voice command information to obtain text information corresponding to the voice command information.

[0117] In some embodiments, the ASR technology in the related art can be used to recognize and process the voice command information to obtain text information corresponding to the above voice command information.

[0118] In some embodiments, before the voice command information is recognized and processed, in order to improve the recognition effect, the collected voice command information can also be pre-processed, such as noise reduction, normalization, etc.; then the pre-processed voice command information is converted into a series of feature parameters, which can effectively represent the content of the speech; the extracted feature parameters are input into the relevant acoustic model and language model, and the most likely text sequence is generated through the decoding algorithm; and the decoded text is post-processed, such as spelling and grammar checking, punctuation addition, etc., to obtain a text with higher readability and accuracy as the text information corresponding to the above-mentioned voice command information.

[0119] In some embodiments, a voice activity detection (VAD) algorithm may also be used to detect whether the user is speaking. VAD is used to distinguish between background noise and voice activity, and further speech recognition processing is initiated only when valid voice activity is detected.

[0120] In some embodiments, voiceprint recognition can also be performed on the voice command information. Voiceprint recognition is a technology for identity verification based on individual voice characteristics. The identity of the speaker can be determined by analyzing and matching the voiceprint characteristics (such as frequency, pitch, sound waveform, etc.) in the audio data. The user's voiceprint data can be stored in the terminal device, and the uploaded voice command information can be compared with the stored voiceprint characteristics to perform identity verification or personalized services (such as personalized recommendations or automatic login).

[0121] S232: Perform intent recognition on the text information using a preset intent recognition model to obtain intent information corresponding to the voice command information.

[0122] In some embodiments, the above-mentioned intention recognition model can be a pre-trained model, which is used to analyze the input text information to understand the user's intention and obtain the intention information corresponding to the above-mentioned voice command information.

[0123] In an embodiment of the present application, by recognizing the voice command information input by the user through a pre-trained model, the intent information corresponding to the voice command information can be more accurately identified, thereby improving the efficiency and accuracy of intent information recognition.

[0124] In some embodiments, in S24, feedback content corresponding to the voice command information is generated based on the user feature information and the intention information, including S241-S242:

[0125] S241. Determine the intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type.

[0126] In some embodiments, the intent information may be identified based on the above-mentioned preset intent model to obtain the intent type of the intent information.

[0127] In some embodiments, the content recommendation type refers to the needs expressed by the user through voice, aiming to obtain recommendations for certain content. The preset voice assistant needs to analyze and determine the content that the user may be interested in based on the user's intention information, and provide corresponding recommendations.

[0128] For example, when the content of the voice command information issued by the user is "I want to listen to some relaxing music.", the intent information may be "play relaxing music", and the intent type of the intent information is the content recommendation type.

[0129] In some embodiments, the question-and-answer dialogue type refers to a dialogue form in which a user asks a question and a preset voice assistant gives a specific answer based on the question. This type of dialogue is aimed at solving the problem, and the user usually expects a clear and concise answer.

[0130] For example, when the content of the voice command information issued by the user is "How is the weather today?", the intention information may be "Ask about today's weather", and the intention type of the intention information is a question-and-answer dialogue type.

[0131] In some embodiments, the above-mentioned intent type may also be other types, and the specific intent type corresponding to the intent information may be flexibly set.

[0132] S242: Determine feedback content corresponding to the voice command information according to the intention type and the user characteristic information.

[0133] In some embodiments, suitable content may be selected from a preset recommended content library based on user feature information and intent information to generate personalized feedback content.

[0134] In the embodiment of the present application, by distinguishing different intent types, the voice assistant can understand the user's needs more accurately and select the most appropriate feedback form according to the intent type. For example, the content recommendation type will provide a variety of possible options, while the question-and-answer dialogue type will directly give a clear answer. This distinction can improve the user's experience.

[0135] In some embodiments, in S242, the feedback content corresponding to the voice command information is determined according to the intention type and the user characteristic information, including S2421-S2423:

[0136] S2421. When the above-mentioned intention type is the above-mentioned content recommendation type, determine a plurality of to-be-determined recommended contents corresponding to the above-mentioned intention information based on the above-mentioned intention information.

[0137] In some embodiments, a plurality of to-be-determined recommended contents corresponding to the above-mentioned intention information may be determined from a preset recommended content library based on the intention information.

[0138] Optionally, the determination of multiple to-be-determined recommended contents can be achieved through a recommendation algorithm in related technologies, such as: a collaborative filtering algorithm that recommends content based on the behavior of similar users; content-based recommendation that recommends similar new content based on the features of content that the user liked in the past; and hybrid recommendation that combines the features of collaborative filtering and content recommendation.

[0139] S2422: Filter the plurality of to-be-determined recommended contents according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information.

[0140] In some embodiments, in S2422, the plurality of recommended contents to be determined are screened according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information, including: generating screening conditions according to the user characteristic information, for example, only selecting content types that meet the user's interests; screening suitable content according to the user's age group; excluding content that the user previously disliked or had a low score, etc. The plurality of recommended contents to be determined are screened according to the screening conditions to exclude the content to be determined that meets the screening conditions, and at least one recommended content corresponding to the user characteristic information is obtained.

[0141] For example, when the user is a child, the user characteristic information may include the user's age group, such as 3-year-old children. A filtering condition may be generated based on the user characteristic information: recommended content that is not suitable for 3-year-old children. The above-mentioned multiple to-be-determined recommended contents may then be filtered based on the filtering condition to exclude the to-be-determined contents that meet the filtering condition, and obtain at least one recommended content corresponding to the above-mentioned user characteristic information, which is content suitable for 3-year-old children.

[0142] S2423: Determine the at least one recommended content as feedback content corresponding to the voice command information.

[0143] In some embodiments, when there are multiple recommended contents, they can be prioritized according to relevance scores, user's historical behaviors, etc., and then the recommended content with the highest priority is determined as the feedback content corresponding to the above-mentioned voice instruction information.

[0144] In the embodiment of the present application, by analyzing the characteristic information of the user (such as interests, age, historical behavior, etc.) and generating screening conditions, personalized recommended content can be provided. In addition, the user's past behavior data, such as the content they like or have high ratings, can be used to screen out content that better meets the user's preferences. In this way, the recommended content can be continuously optimized to enhance the user's experience.

[0145] In some embodiments, in S242, the feedback content corresponding to the voice command information is generated according to the intention type and the user characteristic information, and further includes S2424-S2427:

[0146] S2424. When the above-mentioned intention type is the above-mentioned question-and-answer dialogue type, determine the answer text corresponding to the above-mentioned intention information based on the above-mentioned intention information.

[0147] In some embodiments, when the above-mentioned intent type is the above-mentioned question-and-answer dialogue type, relevant answers can be found from a preset knowledge base or external information source (such as a weather application programming interface, encyclopedia information, etc.) based on the above-mentioned intent information. After obtaining the answer, the answer can be converted into a text that is easy for the user to understand (i.e., the answer text) for feedback. For example, when the intent information is "query today's weather", the answer text can be generated based on the queried weather data: "Today's weather is sunny, with a maximum temperature of 25 degrees."

[0148] Among them, the preset knowledge base can contain common questions and their corresponding answers, and the content in the knowledge base is classified and indexed in advance to facilitate quick search.

[0149] In some embodiments, the answer text may also be integrated and optimized, for example, relevant context information may be integrated into the answer text to make it more complete.

[0150] S2425. Determine a target timbre corresponding to the intention information according to the intention information, where the target timbre is any one of a plurality of preset timbres.

[0151] In some embodiments, the above-mentioned multiple preset timbres can be stored in a preset timbres library, and the multiple timbres include but are not limited to: warm and friendly timbres, suitable for friendly conversations; formal and clear timbres, suitable for professional or formal occasions; lively and vivid timbres, suitable for entertainment or relaxed interactions; calm and peaceful timbres, suitable for providing advice or answering questions.

[0152] In some embodiments, a target timbre may be selected based on the intent information and user characteristics, and the selected target timbre may be applied when generating feedback content to ensure that the emotion and tone of speech synthesis are consistent with the user's intent. Figure 1 To.

[0153] S2426. Process the above answer text through the speech synthesis model corresponding to the above target timbre to obtain speech answer information.

[0154] Each of the multiple timbres may correspond to a speech synthesis model, and the speech synthesis model is used to generate speech information of the corresponding timbre.

[0155] In some embodiments, in S2426, the answer text is processed by the speech synthesis model corresponding to the target timbre to obtain speech answer information, including: inputting the answer text into the speech synthesis model corresponding to the target timbre, so as to pre-process the answer text by the speech synthesis model, for example, punctuation processing and word segmentation processing, etc.; generating corresponding speech answer information according to the pre-processed answer text by the speech synthesis model.

[0156] S2427: Determine the above-mentioned voice answer information as the feedback content corresponding to the above-mentioned voice command information.

[0157] In some embodiments, the voice answer information can also be post-processed, for example, volume adjustment, noise filtering, etc., and then the post-processed voice answer information is determined as the feedback content corresponding to the above-mentioned voice command information, and the feedback content is returned to the user in an appropriate manner (such as playing audio, sending audio stream, etc.).

[0158] In some embodiments, the intent type of the intent information may also be a device interaction type, where the device interaction type refers to a user instructing a terminal device to interact with other devices through voice to control other devices or receive information from other devices.

[0159] Among them, the terminal device is connected to other devices through a network. The other devices may be smart phones, smart cameras, smart wearable devices, etc. The other devices may include at least one of the following functions: ambient temperature detection, ambient humidity detection, user blood oxygen detection, user heart rate detection, night light on / off, voice playback, etc. The user can obtain information such as ambient temperature, humidity, user blood oxygen, user heart rate, etc. through voice command information, and can also control the night light on / off, voice playback volume adjustment, etc. through voice command information.

[0160] For example, when the content of the voice command information issued by the user is "What is the current temperature and humidity of the environment", the intention information can be "Query the temperature and humidity of the current environment". The intention type of the intention information is the device interaction type. The terminal device needs to obtain the current environment temperature and humidity from other devices (such as smart terminal devices, smart thermometers, and smart hygrometers) to generate feedback content corresponding to the above voice command information.

[0161] In the embodiments of the present application, the most suitable voice timbre is selected according to different intention information and user characteristic information, which improves the personalization of the timbre, and the personalized selection of the timbre can enhance the user experience. For example, using a "warm and friendly timbre" to provide weather information during speech synthesis will make the user feel comfortable and relaxed, while using a "formal and clear timbre" can increase authority and professionalism. This allows the voice assistant to not only give answers, but also convey emotions through voice, thereby narrowing the distance with the user.

[0162] In some embodiments, in S2425, determining the target timbre corresponding to the intention information according to the intention information includes:

[0163] Determine whether the intention information includes a specified timbre; if so, use the specified timbre as the target timbre corresponding to the intention information; if not, determine the target timbre corresponding to the intention information based on a preset correspondence and the user characteristic information; wherein the preset correspondence is a correspondence between characteristic information of multiple users and the multiple timbres.

[0164] For example, when the content of the user command information is "Let Dad tell me a story", the corresponding intent information may be "Dad tells a story", that is, the intent information includes a specified timbre, that is, the timbre of the user "Dad", and then the timbre may be used as the target timbre corresponding to the intent information, and the above answer text may be processed by a speech synthesis model corresponding to the target timbre to obtain voice answer information, and the above voice answer information may be determined as the feedback content corresponding to the above voice command information.

[0165] To give another example, when the content of the voice command information is "Tell a story about a little rabbit", the corresponding intent information may be "Tell a story about a little rabbit". The intent information does not include a specified timbre, so the target timbre corresponding to the above intent information can be determined according to the user characteristic information of the user according to a preset correspondence. For example, if the user is a child, the user characteristic information may include features indicating that the user is a child, and then the timbre corresponding to the child can be queried in the above preset correspondence, such as the timbre of a related cartoon character.

[0166] For another example, when the content of the voice command information is "tell a story", the corresponding intention information may be "tell a story". The intention information does not include a specified timbre, so the target timbre corresponding to the above intention information can be determined according to the user characteristic information of the user according to a preset correspondence.

[0167] In the embodiment of the present application, by judging whether the intention information includes a specified timbre and selecting the target timbre according to the user characteristics and the preset timbre correspondence, it is possible to accurately identify and use the timbre for feedback when the user specifies a specific timbre, so that the user can obtain a personalized experience consistent with his or her expectations. If the user does not explicitly specify the timbre, the most appropriate timbre can be selected according to the user characteristics (such as age, gender, and interests). This flexible timbre adjustment mechanism greatly improves the intelligence and humanization of the voice assistant.

[0168] Furthermore, the above feedback content is explained below in conjunction with specific processes. Figure 4 A flowchart of a method for determining feedback content provided by an exemplary embodiment of the present application is shown in FIG. Figure 4 As shown, in the case where the above-mentioned intention type is a content recommendation type, the feedback content determination method includes S401-S406:

[0169] S401. Determine an answer text corresponding to the intention information based on the intention information.

[0170] S402: Determine whether the intention information includes a designated timbre. If not, execute S403, and then execute S405; if yes, execute S404, and then execute S405.

[0171] S403: Determine the target timbre corresponding to the intention information according to the preset corresponding relationship and the user characteristic information.

[0172] S404: Use the designated timbre as the target timbre corresponding to the intention information.

[0173] S405. Process the answer text through a speech synthesis model corresponding to the target timbre to obtain speech answer information.

[0174] S406: Determine the voice answer information as feedback content corresponding to the voice instruction information.

[0175] The specific process of the feedback content determination method has been described in the above content and will not be repeated here.

[0176] Figure 5 A flowchart of another feedback content determination method provided by an exemplary embodiment of the present application is as follows: Figure 5 As shown, in the case where the above-mentioned intention type is a content recommendation type, the feedback content determination method includes S501-S503:

[0177] S501: Determine, based on the intent information, a plurality of to-be-determined recommended contents corresponding to the intent information.

[0178] S502: Filter multiple recommended contents to be determined according to user characteristic information to obtain at least one recommended content corresponding to the user characteristic information.

[0179] S503: Determine at least one recommended content as feedback content corresponding to the voice instruction information.

[0180] The specific process of the feedback content determination method has been described in the above content and will not be repeated here.

[0181] In some embodiments, before executing S21, obtaining the voice command information issued by the user, the method further includes S201-S204:

[0182] S201: Receive a voice wake-up signal sent by the user.

[0183] In some embodiments, when the preset voice assistant is in an unaware state, it can be detected that the user sends a voice wake-up signal, wherein the voice wake-up signal is a wake-up signal sent by the user to attempt to wake up the preset voice assistant.

[0184] S202: Determine whether the voice wake-up signal matches the wake-up word of the preset voice assistant; if so, execute S203.

[0185] The wake-up word of the preset voice assistant is a specific word or phrase used to wake up the preset voice assistant. The wake-up word can be customized by the user, for example, the wake-up signal can be "Xiaobao Xiaobao", "Xiaobei Xiaobei", etc.

[0186] In some embodiments, the wake-up word of the preset voice assistant may be one or more, and different wake-up words may wake up different digital people, where the digital people refer to virtual assistants or virtual agents created based on artificial intelligence technology in the preset voice assistant. Different wake-up words may wake up different digital characters, indicating that each wake-up word corresponds to a specific virtual assistant or function, and these assistants may perform different tasks or provide different services.

[0187] In other embodiments, when there are multiple wake-up words for the above-mentioned preset voice assistant, different wake-up words can wake up different modes. For example, the wake-up word "Xiaobao Xiaobao" can be used to wake up the normal mode. In the normal mode, the preset voice assistant can communicate with the user in a preset normal tone; the wake-up word "Xiaobei Xiaobei" can be used to wake up the early education machine mode. In the early education machine mode, the preset voice assistant can communicate with the user in a child's voice to enlighten the user's language ability, for example, it can play nursery rhymes and stories suitable for children.

[0188] S203: Determine the state of the preset voice assistant as a wake-up state.

[0189] In some embodiments, when the above-mentioned voice wake-up signal does not match the wake-up word of the preset voice assistant, the preset voice assistant remains in an unaware state.

[0190] S204: When the preset voice assistant is in the wake-up state, detecting whether the user issues the voice command information.

[0191] Further, after detecting that the user issues a voice command message, the above-mentioned step S21 of acquiring the voice command message issued by the user is executed.

[0192] In some embodiments, the wake-up function of the preset voice assistant can be implemented by a speech recognition algorithm run by a central processing unit (CPU) of the terminal device. The CPU can continuously detect the audio input signal from the microphone and detect a specific wake-up word or command word by running a lightweight speech recognition algorithm.

[0193] In other embodiments, the wake-up function of the preset voice assistant can also be implemented through a related voice chip, which is a hardware specially designed to process voice signals, and has a built-in low-power voice recognition algorithm for detecting specific wake-up words. The voice chip can continuously detect voice input in an extremely low-power state, and only when the voice chip detects the wake-up word will it wake up the main processor (CPU) and enter the full-speed working state to handle the subsequent complex tasks (such as natural language understanding and answer generation).

[0194] In an embodiment of the present application, when the preset smart assistant is in an unaware state, there is no need for continuous high-intensity voice processing and analysis, and only the voice wake-up signal needs to be detected, which reduces unnecessary resource consumption and saves computing and battery energy consumption; in the unaware state, the preset voice assistant does not perform recognition or processing of voice command information, and therefore does not record or analyze the user's daily conversations. Only when the voice wake-up signal is detected to match the preset wake-up word, it enters the awakening state and starts further operations, which helps to protect user privacy and avoid the risk of unintentional recording or data leakage; in addition, by supporting multiple wake-up words, a more flexible configuration can be achieved to adapt to the preferences and language habits of different users. This diversified wake-up word configuration also helps to personalize the user experience.

[0195] Please refer to the following Figure 6 , which is a structural diagram of a voice interaction device provided by an exemplary embodiment of the present application. Figure 6 As shown, the above-mentioned voice interaction device 600 includes:

[0196] The acquisition module 601 is used to acquire the voice command information issued by the user;

[0197] A first determining module 602, configured to determine user characteristic information of the user according to the voice command information;

[0198] A second determination module 603 is used to determine the intention information corresponding to the voice command information according to the voice command information;

[0199] The third determination module 604 is used to determine the feedback content corresponding to the voice instruction information based on the user characteristic information and the intention information.

[0200] In a possible implementation, the first determining module 602 includes:

[0201] A feature extraction unit, used to extract features from the voice command information to obtain first feature information of the user corresponding to the voice command information;

[0202] an acquisition unit, configured to acquire second feature information corresponding to the user based on the first feature information, wherein the second feature information includes feature information obtained based on historical voice command information of the user;

[0203] The first determining unit is used to determine the user characteristic information of the user according to the first characteristic information and the second characteristic information.

[0204] In a possible implementation, the second determining module 603 includes:

[0205] A first recognition unit is used to recognize and process the voice command information to obtain text information corresponding to the voice command information;

[0206] The second recognition unit performs intent recognition on the above text information through a preset intention recognition model to obtain intent information corresponding to the above voice command information.

[0207] In a possible implementation, the third determining module 604 includes:

[0208] A second determining unit is used to determine the intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type;

[0209] The third determination unit is used to determine the feedback content corresponding to the above-mentioned voice instruction information according to the above-mentioned intention type and the above-mentioned user characteristic information.

[0210] In a possible implementation, the third determining unit includes:

[0211] A first determining subunit is configured to determine, when the intention type is the content recommendation type, a plurality of to-be-determined recommended contents corresponding to the intention information based on the intention information;

[0212] A screening subunit, configured to screen the plurality of recommended contents to be determined according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information;

[0213] The second determining subunit is used to determine the at least one recommended content as the feedback content corresponding to the voice instruction information.

[0214] In a possible implementation, the third determining unit includes:

[0215] A third determination subunit is used to determine an answer text corresponding to the intention information based on the intention information when the intention type is the question-answer dialogue type;

[0216] A fourth determination subunit is used to determine a target timbre corresponding to the intention information according to the intention information, wherein the target timbre is any one of a plurality of preset timbres;

[0217] A processing subunit, used for processing the answer text through the speech synthesis model corresponding to the target timbre to obtain speech answer information;

[0218] The fifth determining subunit is used to determine the above-mentioned voice answer information as the feedback content corresponding to the above-mentioned voice instruction information.

[0219] In a possible implementation manner, the fourth determining subunit is specifically configured to:

[0220] Determining whether the intention information includes a specified timbre;

[0221] If yes, the specified timbre is used as the target timbre corresponding to the intention information;

[0222] If not, the target timbre corresponding to the intention information is determined according to a preset correspondence relationship and the user characteristic information; wherein the preset correspondence relationship is a correspondence relationship between characteristic information of multiple users and the multiple timbres.

[0223] The division of the modules in the above-mentioned voice interaction device 600 is only for illustration. In other embodiments, the voice interaction device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned voice interaction device. The implementation of each module in the voice interaction device provided in the embodiment of this specification can be in the form of a computer program. The computer program can be run on a terminal or a server. The program modules constituted by the computer program can be stored in the memory of the terminal or the server. When the computer program is executed by the processor, all or part of the steps of the voice interaction method described in the embodiment of this specification are implemented.

[0224] See next Figure 7 , which is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 7 As shown, the electronic device 700 may include: a processor 710 and a memory 720 , and may also include a user interface 730 , a network interface 740 and a communication bus 750 .

[0225] Among them, the processor 710 may include one or more processing cores. The processor 710 uses various interfaces and lines to connect various parts of the entire electronic device 700, and executes various functions and processes data of the electronic device 700 by running or executing instructions, programs, code sets or instruction sets stored in the memory 720, and calling data stored in the memory 720. Optionally, the processor 710 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 710 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes operating systems and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 710, and it can be implemented separately through a chip.

[0226] Among them, the memory 720 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 720 includes a non-transitory computer-readable storage medium. The memory 720 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 720 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a receiving function, a control function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 720 may also be optionally at least one storage device located away from the aforementioned processor 710. As Figure 7 As shown, the memory 720 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0227] Optionally, the communication bus 750 is used to realize the connection and communication between these components. The user interface 730 may include a display screen (Display), a camera (Camera), and may also include a standard wired interface and a wireless interface; the network interface 740 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface).

[0228] exist Figure 7 In the electronic device 700 shown, the processor 710 may be used to call program instructions stored in the memory 720 and specifically perform the following operations:

[0229] Obtain the voice command information issued by the user;

[0230] Determine user characteristic information of the user according to the voice command information;

[0231] Determine the intention information corresponding to the voice command information according to the voice command information;

[0232] The feedback content corresponding to the voice command information is determined based on the user feature information and the intention information.

[0233] In a possible implementation, the determining the user characteristic information of the user according to the voice command information includes:

[0234] Extracting features from the voice command information to obtain first feature information of the user corresponding to the voice command information;

[0235] Acquire second feature information corresponding to the user based on the first feature information, wherein the second feature information includes feature information obtained based on historical voice command information of the user;

[0236] The user characteristic information of the user is determined according to the first characteristic information and the second characteristic information.

[0237] In a possible implementation, determining the intention information corresponding to the voice command information according to the voice command information includes:

[0238] Recognize and process the voice command information to obtain text information corresponding to the voice command information;

[0239] The intention of the above text information is recognized through a preset intention recognition model to obtain the intention information corresponding to the above voice command information.

[0240] In a possible implementation, generating feedback content corresponding to the voice command information based on the user feature information and the intention information includes:

[0241] Determine the intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type;

[0242] The feedback content corresponding to the voice command information is determined according to the intention type and the user characteristic information.

[0243] In a possible implementation, the generating of feedback content corresponding to the voice command information according to the intention type and the user characteristic information includes:

[0244] In the case where the intention type is the content recommendation type, determining a plurality of to-be-determined recommended contents corresponding to the intention information based on the intention information;

[0245] Filtering the plurality of recommended contents to be determined according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information;

[0246] The at least one recommended content is determined as the feedback content corresponding to the voice instruction information.

[0247] In a possible implementation, the generating of feedback content corresponding to the voice command information according to the intention type and the user characteristic information includes:

[0248] In the case where the above-mentioned intention type is the above-mentioned question-answer dialogue type, determining the answer text corresponding to the above-mentioned intention information based on the above-mentioned intention information;

[0249] Determining a target timbre corresponding to the intention information according to the intention information, the target timbre being any one of a plurality of preset timbres;

[0250] Processing the answer text by the speech synthesis model corresponding to the target timbre to obtain speech answer information;

[0251] The voice answer information is determined as the feedback content corresponding to the voice command information.

[0252] In a possible implementation, determining the target timbre corresponding to the intention information according to the intention information includes:

[0253] Determining whether the intention information includes a specified timbre;

[0254] If yes, the specified timbre is used as the target timbre corresponding to the intention information;

[0255] If not, the target timbre corresponding to the intention information is determined according to a preset correspondence relationship and the user characteristic information; wherein the preset correspondence relationship is a correspondence relationship between characteristic information of multiple users and the multiple timbres.

[0256] The embodiment of the present application also provides a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in the above embodiment. If the components of the above voice interaction device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium.

[0257] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The above-mentioned computer program product includes one or more computer instructions. When the above-mentioned computer program instructions are loaded and executed on a computer, the above-mentioned process or function according to the embodiment of the present application is generated in whole or in part. The above-mentioned computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium or transmitted by the above-mentioned computer-readable storage medium. The above-mentioned computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The above-mentioned computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The above-mentioned available media can be magnetic media (for example, floppy disks, hard disks, tapes), optical media (for example, digital versatile discs (DVD)), or semiconductor media (for example, solid state disks (SSD)), etc.

[0258] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0259] The above-mentioned embodiments are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the protection scope determined by the claims of the present application.

Claims

1. A voice interaction method, characterized in that: include: Obtain the voice command information issued by the user; Determining user characteristic information of the user according to the voice command information; Determining, according to the voice command information, the intention information corresponding to the voice command information; Determine feedback content corresponding to the voice instruction information based on the user feature information and the intention information.

2. The method according to claim 1, characterized in that The determining the user characteristic information of the user according to the voice command information includes: Extracting features from the voice command information to obtain first feature information of a user corresponding to the voice command information; Acquire second feature information corresponding to the user based on the first feature information, where the second feature information includes feature information obtained based on historical voice command information of the user; The user characteristic information of the user is determined according to the first characteristic information and the second characteristic information.

3. The method according to claim 1, characterized in that The determining, according to the voice command information, the intention information corresponding to the voice command information includes: Recognize and process the voice command information to obtain text information corresponding to the voice command information; The text information is subjected to intent recognition through a preset intent recognition model to obtain intent information corresponding to the voice command information.

4. The method according to claim 1, characterized in that Generating feedback content corresponding to the voice command information based on the user feature information and the intention information includes: Determine an intent type of the intent information, where the intent type is a content recommendation type or a question-and-answer dialogue type; Determine feedback content corresponding to the voice instruction information according to the intention type and the user characteristic information.

5. The method according to claim 4, characterized in that The generating feedback content corresponding to the voice instruction information according to the intention type and the user characteristic information includes: In a case where the intention type is the content recommendation type, determining, based on the intention information, a plurality of to-be-determined recommended contents corresponding to the intention information; Filtering the plurality of recommended contents to be determined according to the user characteristic information to obtain at least one recommended content corresponding to the user characteristic information; The at least one recommended content is determined as feedback content corresponding to the voice instruction information.

6. The method according to claim 4, characterized in that The generating feedback content corresponding to the voice instruction information according to the intention type and the user characteristic information includes: In a case where the intention type is the question-answer dialogue type, determining an answer text corresponding to the intention information based on the intention information; Determining a target timbre corresponding to the intention information according to the intention information, wherein the target timbre is any one of a plurality of preset timbres; Processing the answer text by a speech synthesis model corresponding to the target timbre to obtain speech answer information; The voice answer information is determined as feedback content corresponding to the voice instruction information.

7. The method according to claim 6, characterized in that Determining a target timbre corresponding to the intention information according to the intention information includes: Determining whether the intention information includes a specified timbre; If yes, taking the specified timbre as the target timbre corresponding to the intention information; If not, the target timbre corresponding to the intention information is determined according to a preset correspondence relationship and the user characteristic information; wherein the preset correspondence relationship is a correspondence relationship between characteristic information of multiple users and the multiple timbres.

8. A voice interaction device, characterized in that: include: An acquisition module is used to acquire the voice command information issued by the user; A first determining module, used to determine user characteristic information of the user according to the voice instruction information; A second determination module, used to determine the intention information corresponding to the voice instruction information according to the voice instruction information; The third determination module is used to determine the feedback content corresponding to the voice instruction information based on the user characteristic information and the intention information.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the steps of the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the steps of the method according to any one of claims 1 to 7.

Images