User information feedback processing method and device based on voice recognition and terminal

Abstract

The invention discloses a user information feedback processing method and device based on voice recognition and a terminal. The method comprises the following steps: acquiring voice information of a user; performing voice recognition on the voice information, and converting the voice information into text information; performing semantic analysis on the text information, performing intention recognition, and understanding user feedback content and intention; when the intention recognition result is feedback information of the current watching content, controlling to record the feedback information in real time, and classifying and storing the feedback information according to different categories; creating a unique identifier for each piece of feedback information, and recording feedback time, feedback content and user ID information; and controlling the feedback information to be fed back and displayed in real time, and uploading and feeding back the feedback information to the content providing server. According to the invention, user feedback is carried out through voice input, so that the method is more natural and convenient, and real-time interaction can be carried out under the condition that the watching experience is not interrupted; according to the invention, the user experience can be obviously improved, and valuable user data can be provided for content providers.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent terminals, and in particular to a method and device for processing user information feedback based on voice recognition, an intelligent terminal and a storage medium. Background Art

[0002] With the rapid development of smart TV technology, users' demands for TV content are becoming more and more diversified and personalized. Traditional user feedback methods, such as button feedback and remote control input, can no longer meet users' needs for convenience and real-time performance.

[0003] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in view of the problems and defects of the above-mentioned prior art, a user information feedback processing method, device, intelligent terminal and storage medium based on voice recognition are provided. The present invention not only makes user feedback through voice input more natural and convenient, but also enables real-time interaction without interrupting the viewing experience; the present invention can significantly improve the user experience and provide valuable user data for content providers.

[0005] The technical solutions adopted by the present invention to solve the problem are as follows: A method for processing user information feedback based on speech recognition, comprising: Get the user's voice information; Performing speech recognition on the speech information and converting it into text information; Perform semantic analysis on the text information to identify the intent and understand the user feedback content and intent; When the intention recognition result is feedback information on the currently viewed content, the feedback information is recorded in real time and stored in different categories; a unique identifier is created for each piece of feedback information, and the feedback time, feedback content, and user ID information are recorded; Control the real-time feedback display of the feedback information and upload the feedback to the content providing server.

[0006] The user information feedback processing method based on voice recognition, wherein the feedback information includes: evaluation, suggestions and / or questions on the currently viewed content.

[0007] The method for processing user information feedback based on voice recognition, wherein the step of obtaining the user's voice information comprises: Capture the user's voice signal through the microphone set on the smart terminal; Preprocess the acquired speech signal.

[0008] The method for processing user information feedback based on speech recognition, wherein the step of performing speech recognition on the speech information and converting it into text information comprises: The speech information is recognized and processed by a speech recognition engine using a deep neural network model, and converted into text information.

[0009] The method for processing user information feedback based on speech recognition, wherein the step of performing semantic analysis on the text information to identify the intent and understand the user feedback content and intent comprises: Perform semantic analysis on the converted text information to analyze the specific content and emotional tendency of user feedback; Through semantic analysis, intent recognition is performed to obtain the user's feedback content and intention. The method for processing user information feedback based on speech recognition, wherein when the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and classified and stored according to different categories; and a unique identifier is created for each piece of feedback information, and the steps of recording the feedback time, feedback content, and user ID information include: When the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and classified and stored according to different categories; wherein the classification content of the feedback information includes positive evaluation, negative feedback, suggestions and / or questions; Create a unique identifier for each feedback message, and record the feedback time, feedback content, and user ID information.

[0010] In the method for processing user information feedback based on speech recognition, the step of controlling the real-time feedback display of the feedback information and uploading the feedback to the content providing server comprises: Controlling the real-time display of the feedback information on the intelligent terminal interface and displaying corresponding interactive prompts; Uploading the feedback information to the content service provider via the Internet; The content provider performs in-depth analysis on the uploaded feedback information and optimizes the content strategy.

[0011] A user information feedback processing device based on speech recognition, wherein the device comprises: A voice acquisition module is used to acquire the user's voice information; A speech recognition module, used to perform speech recognition on the speech information and convert it into text information; A natural language processing module is used to perform semantic analysis on the text information, identify the intent, and understand the user feedback content and intent; A user feedback module, which is used to control the real-time recording of the feedback information and classify and store it according to different categories when the intention recognition result is feedback information on the currently viewed content; and to create a unique identifier for each piece of feedback information, and record the feedback time, feedback content, and user ID information; The feedback display and upload module is used to control the real-time feedback display of the feedback information and upload the feedback to the content providing server.

[0012] An intelligent terminal includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including the method for executing any one of the methods described above.

[0013] A computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any one of the methods described above.

[0014] Beneficial effects of the invention: The invention provides a method, device, intelligent terminal and storage medium for processing user information feedback based on voice recognition; real-time feedback of users on TV content is collected through voice recognition technology. The user's voice command can be automatically recognized, converted into text, and classified and stored according to the content type. Users can express their evaluation, suggestions or questions about the current viewing content through voice, and the system will record and feedback to the content provider in real time to optimize and improve the content quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flowchart of a method for processing user information feedback based on speech recognition provided in Example 1 of the present invention.

[0017] Figure 2 It is a flowchart of a method for processing user information feedback based on speech recognition provided in Example 2 of the present invention.

[0018] Figure 3 A principle block diagram of an embodiment of a user information feedback processing device based on speech recognition provided by the present invention.

[0019] Figure 4It is a block diagram of the internal structure principle of the intelligent terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] With the rapid development of smart TV technology, users' demands for TV content are becoming more diverse and personalized. Traditional user feedback methods, such as button feedback and remote control input, can no longer meet users' convenience and real-time needs. The advancement of speech recognition technology provides a new way to solve this problem. User feedback through voice input is not only more natural and convenient, but also enables real-time interaction without interrupting the viewing experience. This voice-based user feedback system has important application prospects and can significantly improve the user experience while providing valuable user data for content providers.

[0022] like Figure 1 As shown, a method for processing user information feedback based on speech recognition in Embodiment 1 of the present invention comprises the following steps: Step S100: obtaining the user's voice information; In the embodiment of the present invention, a smart TV is taken as an example for description. In specific implementation, the user's voice command can be captured by a built-in microphone or an external microphone on the smart TV.

[0023] Specifically, the user's voice signal can be captured by a microphone installed on the smart TV, and the acquired voice signal can be pre-processed, for example, the acquired voice signal can be filtered to remove noise and make the voice signal clearer.

[0024] Step S200: performing speech recognition on the speech information and converting it into text information; This step mainly performs speech recognition on the speech information, and is specifically implemented using a speech recognition engine (such as Google Speech-to-Text, Azure Speech Service, etc.) to convert the speech signal into text and ensure high-accuracy recognition.

[0025] Specifically, the present invention can use a speech recognition engine of a deep neural network model to recognize and process the speech information and convert it into text information.

[0026] Step S300: performing semantic analysis on the text information to identify the intent and understand the user feedback content and intent; In this step, the real needs and emotions of users are deeply understood, and the information they provide is analyzed to provide better responses and services.

[0027] The semantic analysis of the present invention refers to the use of natural language processing technology to parse the text and extract its inner meaning, including the analysis of vocabulary, syntactic structure and context in order to understand the emotions and information expressed.

[0028] Intention recognition in the embodiment of the present invention is to further confirm the specific intention of the user based on semantic analysis. For example, whether the information sent by the user is to seek help, express a complaint, or provide feedback on the product, intention recognition helps to identify these different needs.

[0029] Then, the user feedback content is understood. That is, by combining the above two steps, the present invention can grasp the information conveyed by the user, thereby identifying the user's actual feelings and needs. This is not limited to the literal meaning, but also includes the implicit emotions and attitudes.

[0030] For example, the text "I like this show" is parsed as a positive review, and "The picture is too dark" is parsed as negative feedback.

[0031] In this way, the present invention can more quickly and effectively understand the user's real feedback by accurately understanding the user's intention, so that it is convenient to identify the deficiencies in the product or service through analyzing the user feedback, make improvements, and improve the overall quality.

[0032] Furthermore, the step S300 specifically includes: S301, performing semantic analysis on the converted text information to analyze the specific content and emotional tendency of the user feedback; In the embodiment of this step, semantic analysis is first performed on the converted text information provided by the user. The purpose of semantic analysis is to identify the key content in the text, including keywords, phrases and context information, and to evaluate the emotional tendency conveyed by these contents. This step uses semantic analysis to deepen the user's feedback content from the surface phenomenon to its connotation, and judge whether the user is satisfied with the positive feedback or disappointed with the negative feedback.

[0033] In this step, by analyzing the user's emotions and specific feedback, you can understand the user's needs and expectations. And timely identification of negative feedback can help companies take quick measures to improve service content.

[0034] S302: Perform intent recognition through semantic analysis to obtain the user's feedback content and intent. In the step of intention recognition, the present invention further clarifies the user's feedback content and intention based on the previous semantic analysis results. This step associates the user's emotional tendency with the specific behavioral intention and determines what the user hopes to achieve through feedback, such as complaints, suggestions for improvement, or information inquiries.

[0035] In this way, the present invention can more efficiently process user feedback, improve customer satisfaction, and enhance response efficiency by quickly identifying user intent.

[0036] Step S400: When the intention recognition result is feedback information on the currently viewed content, the feedback information is recorded in real time and stored according to different categories; a unique identifier is created for each piece of feedback information, and the feedback time, feedback content, and user ID information are recorded; In the embodiment of this step, when the intention recognition result after recognizing the user's voice information is feedback information on the currently viewed content, for example, if the text after the user's voice recognition is "I like this program", the intention recognition result is feedback information on the currently viewed content.

[0037] The feedback information is recorded in real time and stored according to different categories. That is, the present invention stores the analyzed user feedback according to different categories, including positive comments, negative feedback, suggestions, and questions. For example, the text "I like this program" is analyzed as a positive comment, and the positive comments are stored in a classified manner; while "this picture is too dark" is analyzed as a negative feedback, and the negative feedback is stored in a classified manner.

[0038] The present invention will create a unique identifier for each feedback, record the feedback time, feedback content, user ID and other information, so as to facilitate timely improvement.

[0039] In the embodiment of the present invention, the feedback information includes: evaluation, suggestions and / or questions on the currently viewed content.

[0040] Furthermore, the step S400 specifically includes: S401, when the intention recognition result is feedback information on the currently viewed content, controlling the real-time recording of the feedback information and classifying and storing the feedback information according to different categories; wherein the classification content of the feedback information includes positive evaluation, negative feedback, suggestions and / or questions; In this step, the feedback information is recorded in real time, that is, when the user feedback is confirmed to be related to the content they are watching through intention recognition, the present invention will automatically start recording the feedback. This recording is real-time, that is, the feedback of the user in the embodiment of the present invention will be captured instantly during the process of watching the content.

[0041] Regarding classified storage: the feedback information recorded by the present invention is classified according to its content, emotional tendency, feedback type, etc. For example, feedback can be divided into different categories such as "positive feedback", "negative feedback", "neutral feedback" and "suggestions for improvement". This classification helps subsequent data analysis and processing to be more efficient.

[0042] For example, when a user on a video streaming platform gives feedback after watching a movie: "The action scenes in this movie are very exciting, but the plot is not attractive enough," the embodiment of the present invention will record this feedback in real time and store it by category according to the content: Positive Feedback: The action scenes are exciting; Negative feedback: The storyline is not appealing; Suggested improvements: Enhance the storyline; By focusing on real-time recording and classified storage, the present invention can find in subsequent analysis that many users appreciate the action scenes of a certain type of movie, but lack interest in the storyline. This insight can prompt the platform to pay more attention to the development of the storyline in future content production and recommendation, or recommend other movies that better meet user needs. This not only increases user satisfaction, but also improves viewing time and overall user stickiness.

[0043] It can be seen that the embodiments of the present invention ensure that user feedback is not missed through real-time recording. This is particularly important in a rapidly changing user experience environment, because the user's emotions and thoughts may change rapidly depending on the content. And through classified storage, user feedback can be better organized and managed. In addition, after the feedback information is classified and stored, by analyzing different types of feedback, the user's preferences and dissatisfaction with the content can be quickly identified, thereby helping the platform to adjust the content strategy in a timely manner to improve user satisfaction.

[0044] S402: Create a unique identifier for each piece of feedback information, and record the feedback time, feedback content, and user ID information.

[0045] In a specific embodiment, regarding the creation of a unique identifier, the present invention can generate a unique identifier (ID) for each piece of feedback information. This ID can be a randomly generated string or number to ensure that each piece of feedback in the system is unique. The purpose of this is to accurately identify and reference each piece of feedback in subsequent data processing and query.

[0046] About recording feedback time: Record the specific timestamp of user feedback, including date and time. This information is very important for analyzing the timeliness and trend changes of feedback.

[0047] About recording feedback content: This is the actual feedback information provided by users, including their opinions, suggestions or emotional expressions. This content is the basis for subsequent analysis.

[0048] About recording user ID information: that is, recording the user ID of the feedback, which is the user's unique identification code in the system. This helps to track the user's feedback history, analyze user behavior, and provide personalized services.

[0049] For example, when a user leaves a feedback after watching a TV series: "The plot of this episode is very compact, I like it very much!", the present invention will create a unique identifier for this feedback, such as "FB123456", and record the following information: Unique identifier: FB123456; Feedback time: 14:30:00, February 18, 2025; Feedback: "The plot development of this episode is very compact, I like it very much!"; User ID: User789; In this way, the embodiment of the present invention can easily find this feedback in subsequent analysis, view other feedback records of the user, and analyze the emotional changes and preferences of the user in different time periods. This not only helps to improve the user experience, but also provides data support for content creation and platform optimization.

[0050] In this way, each piece of feedback information can be easily tracked and managed through a unique identifier to avoid data confusion and duplicate records. And recording the feedback time and user ID information makes data analysis more accurate, and the time trend of user feedback can be analyzed to understand the emotional changes of users in a specific time period. And by associating the user ID with the feedback content, the present invention can better understand the needs and preferences of users, and then provide more personalized recommendations and services. In addition, by recording the feedback time and user ID information, the present invention makes it easy to query the user's historical feedback later, helping the customer service or product team to better solve user problems.

[0051] Step S500: Control the real-time feedback display of the feedback information and upload the feedback to the content providing server.

[0052] That is, in the embodiment of the present invention, the user feedback can be displayed in real time on the TV interface, and corresponding interactive prompts can be displayed. For example, after the user publishes a positive evaluation, the interface displays "Thank you for your feedback!" and provides relevant suggestions.

[0053] In addition, the embodiment of the present invention can also upload the user feedback data to the server of the content provider through the Internet through the data transmission module, so that the content provider can conduct in-depth analysis based on the data and optimize the content strategy.

[0054] Furthermore, the step S500 specifically includes: S501, controlling the real-time display of the feedback information on the intelligent terminal interface and displaying corresponding interactive prompts; In the embodiment of the present invention, the user's feedback information will be displayed in real time on the TV interface, and corresponding interactive prompts can be displayed.

[0055] S502, uploading the feedback information to the content service provider via the Internet; In the embodiment of the present invention, the user feedback data may be uploaded to the server of the content provider via the Internet.

[0056] S503: The content provider server performs an in-depth analysis on the uploaded feedback information to optimize the content strategy.

[0057] In the embodiment of the present invention, the content provider service end can systematically analyze the collected user feedback through technical means (such as data analysis tools and natural language processing technology). This includes mining the user's emotional tendencies, main concerns, suggestions and complaints about the content to identify the user's overall satisfaction and reaction to specific content. The content that may be involved in the analysis includes text sentiment analysis, keyword extraction, frequency statistics, etc.

[0058] Then optimize the content strategy. Specifically, based on the results of feedback analysis, you can identify which types of content are popular with users and which types of content are insufficient, and then develop improvement plans. The optimized content strategy may cover content creation direction, type selection, program arrangement, marketing strategy, etc., to better meet user needs and expectations and improve user satisfaction.

[0059] For example, when an online video platform collects a large amount of user feedback, many users express their high praise for a certain type of educational video, but also mention that they hope to add more in-depth thematic content and interactive evaluation. The content provider service side conducts in-depth analysis of these feedbacks and finds that users watch educational videos for a significantly longer time than other categories, and the frequency of keywords such as "interaction" and "in-depth discussion" mentioned in the comments is relatively high.

[0060] Based on the analysis results, the embodiment of the present invention adopts the following optimization strategy: Increase in-depth content on topics: Create educational videos specifically for more complex issues to attract users who want to learn more deeply.

[0061] Introduce interactive assessment sessions: Add interactive questions and answers or quizzes to educational videos to enhance user engagement and learning outcomes.

[0062] Through such strategic adjustments, the platform can effectively meet user needs, not only improving the user viewing experience, but also attracting new users to participate.

[0063] It can be seen that the present invention can directly improve the quality and relevance of content by deeply understanding user feedback, thereby improving user satisfaction and loyalty. And by quantitatively analyzing user feedback, more accurate and targeted decisions can be made, reducing the risks brought by subjective judgment. Moreover, timely analysis of user needs and feedback can enable content provider services to quickly adjust content strategies, adapt to market changes and changes in user preferences, and maintain competitiveness.

[0064] The present invention is further described in detail below through another specific application embodiment. Figure 2 As shown, a user information feedback processing method based on speech recognition in this specific application embodiment includes the following steps: S10, the user starts to send a voice message, and then goes to step S11; S11, the microphone captures the user's voice; and then proceeds to step S12; The user interacts with the microphone through voice, and the user's voice input is captured by the microphone to generate a voice signal; the voice signal captured by the microphone is transmitted to the voice input module; S12, the voice input module obtains the generated voice signal; and proceeds to step S13; S13, the speech recognition module converts the speech signal into text; and proceeds to step S14; The speech recognition module converts the speech signal into text and passes it to the natural language processing module; S14, the natural speech processing module performs semantic analysis on the converted text, performs intent recognition, and enters step S15 after classification processing; The natural language processing module parses the text content and passes it to the user feedback management module; S15, the user feedback management module stores the processed feedback into a database by category; and proceeds to steps S16, S17, and S18; The user feedback management module stores and categorizes the parsed feedback; S16, the real-time feedback display module displays the user feedback on the TV interface; S17, the data transmission module uploads the feedback data to the content provider server; S18. The content provider server performs in-depth analysis based on these data and optimizes content strategy.

[0065] As can be seen from the above, the voice-based user feedback in the specific embodiment of the present invention can greatly improve the user experience and provide valuable data support for content providers, thereby promoting further optimization of television content and services.

[0066] Exemplary Devices like Figure 3 As shown, an embodiment of the present invention provides a user information feedback processing device based on speech recognition, the device comprising: The voice acquisition module 310 is used to acquire the user's voice information; A speech recognition module 320 is used to perform speech recognition on the speech information and convert it into text information; A natural language processing module 330 is used to perform semantic analysis on the text information to identify the intent and understand the user feedback content and intent; The user feedback module 340 is used to control the real-time recording of the feedback information and classify and store it according to different categories when the intention recognition result is feedback information on the currently viewed content; and to create a unique identifier for each piece of feedback information, and record the feedback time, feedback content, and user ID information; The feedback display and upload module 350 is used to control the real-time feedback display of the feedback information and upload the feedback to the content providing server, as described above.

[0067] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 4 As shown. The intelligent terminal includes a processor, a memory, a network interface, a display screen, and a database connected through a system bus. Among them, the processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a user information feedback processing method based on voice recognition is implemented. The database of the intelligent terminal is used to store a user information feedback processing program based on voice recognition.

[0068] Those skilled in the art will understand that Figure 4 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the smart terminal to which the scheme of the present invention is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0069] In one embodiment, a smart terminal is provided, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations: Get the user's voice information; Performing speech recognition on the speech information and converting it into text information; Perform semantic analysis on the text information to identify the intent and understand the user feedback content and intent; When the intention recognition result is feedback information on the currently viewed content, the feedback information is recorded in real time and stored in different categories; a unique identifier is created for each piece of feedback information, and the feedback time, feedback content, and user ID information are recorded; Controlling the real-time feedback display of the feedback information and uploading the feedback to the content providing server, as described above.

[0070] The feedback information includes: comments, suggestions and / or questions about the currently viewed content.

[0071] The step of obtaining the user's voice information includes: Capture the user's voice signal through the microphone set on the smart terminal; The acquired speech signal is preprocessed as described above.

[0072] The step of performing speech recognition on the speech information and converting the speech information into text information comprises: The speech information is recognized and processed by a speech recognition engine using a deep neural network model, and converted into text information, as described above.

[0073] The step of performing semantic analysis on the text information to identify the intent and understand the user feedback content and intent includes: Perform semantic analysis on the converted text information to analyze the specific content and emotional tendency of user feedback; Through semantic analysis, intent recognition is performed to obtain the user's feedback content and intention. Among them, when the intention recognition result is feedback information on the currently viewed content, the steps of controlling the real-time recording of the feedback information and classifying and storing the feedback information according to different categories; and creating a unique identifier for each piece of feedback information, and recording the feedback time, feedback content, and user ID information include: When the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and classified and stored according to different categories; wherein the classification content of the feedback information includes positive evaluation, negative feedback, suggestions and / or questions; A unique identifier is created for each feedback message, and the feedback time, feedback content, and user ID information are recorded, as described above.

[0074] The step of controlling the real-time feedback display of the feedback information and uploading the feedback to the content providing server includes: Controlling the real-time display of the feedback information on the intelligent terminal interface and displaying corresponding interactive prompts; Uploading the feedback information to the content service provider via the Internet; The content provider performs an in-depth analysis on the uploaded feedback information and optimizes the content strategy, as described above.

[0075] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0076] In summary, the present invention provides a method, device, intelligent terminal and storage medium for processing user information feedback based on voice recognition, which collects real-time user feedback on TV content through voice recognition technology. It can automatically recognize the user's voice command, convert it into text, and classify and store it according to the content type. The user can express his evaluation, suggestions or questions about the current viewing content by voice, and the system will record and feedback to the content provider in real time to optimize and improve the content quality.

Claims

1. A method for processing user information feedback based on speech recognition, characterized in that: include: Get the user's voice information; Performing speech recognition on the speech information and converting it into text information; Perform semantic analysis on the text information to identify the intent and understand the user feedback content and intent; When the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and stored in different categories; And create a unique identifier for each feedback message, record the feedback time, feedback content, and user ID information; Control the real-time feedback display of the feedback information and upload the feedback to the content providing server.

2. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: The feedback information includes: evaluation, suggestions and / or questions about the currently viewed content.

3. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: The step of obtaining the user's voice information comprises: Capture the user's voice signal through the microphone set on the smart terminal; Preprocess the acquired speech signal.

4. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: The step of performing speech recognition on the speech information and converting it into text information comprises: The speech information is recognized and processed by a speech recognition engine using a deep neural network model, and converted into text information.

5. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: The step of performing semantic analysis on the text information to identify the intent and understand the user feedback content and intent includes: Perform semantic analysis on the converted text information to analyze the specific content and emotional tendency of user feedback; Through semantic analysis, intent recognition is performed to obtain the user's feedback content and intention.

6. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: When the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and stored in different categories; The steps of creating a unique identifier for each feedback message and recording the feedback time, feedback content, and user ID information include: When the intention recognition result is feedback information on the currently viewed content, the feedback information is controlled to be recorded in real time and classified and stored according to different categories; wherein the classification content of the feedback information includes positive evaluation, negative feedback, suggestions and / or questions; Create a unique identifier for each feedback message, and record the feedback time, feedback content, and user ID information.

7. The method for processing user information feedback based on speech recognition according to claim 1, characterized in that: The step of controlling the real-time feedback display of the feedback information and uploading the feedback to the content providing server includes: Controlling the real-time display of the feedback information on the intelligent terminal interface and displaying corresponding interactive prompts; Uploading the feedback information to the content service provider via the Internet; The content provider performs in-depth analysis on the uploaded feedback information and optimizes the content strategy.

8. A user information feedback processing device based on speech recognition, characterized in that: The device comprises: A voice acquisition module is used to acquire the user's voice information; A speech recognition module, used to perform speech recognition on the speech information and convert it into text information; A natural language processing module is used to perform semantic analysis on the text information, identify the intent, and understand the user feedback content and intent; A user feedback module, which is used to control the real-time recording of the feedback information and classify and store it according to different categories when the intention recognition result is feedback information on the currently viewed content; and to create a unique identifier for each piece of feedback information, and record the feedback time, feedback content, and user ID information; The feedback display and upload module is used to control the real-time feedback display of the feedback information and upload the feedback to the content providing server.

9. An intelligent terminal, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include being used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method as described in any one of claims 1 to 7.

Images