Artificial intelligence recognition system based on big data

Abstract

The invention belongs to the technical field of artificial intelligence recognition, and particularly relates to an artificial intelligence recognition system based on big data, which comprises a user module used for analyzing user personnel and corresponding personnel preferences according to the daily life of a user so as to recommend related contents according to the used personnel when a television is used; the sound acquisition module is used for acquiring the sound of the personnel so as to analyze the password of the personnel; and the field analysis module is used for analyzing the field of the content to be played according to the sound acquired by the sound acquisition module. According to the invention, when the television analyzes the password of the person by using the voice recognition technology, the identity of the person can be analyzed according to the data provided by the user module, and corresponding recommendation is carried out, so that accurate recommendation can be carried out on the person, and the recommendation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence recognition technology, and in particular to an artificial intelligence recognition system based on big data. Background Art

[0002] Artificial intelligence TV refers to a TV product equipped with artificial intelligence technology, which realizes intelligent control and management of home appliances through voice control, image recognition, natural language processing and other technologies. AI TV not only has the functions of traditional TV, but also can improve user experience through functions such as online video playback, application installation, smart home control, and personalized content recommendation.

[0003] At present, it is difficult to make corresponding recommendations based on the preferences of corresponding personnel in artificial intelligence televisions. Specifically, when personnel use artificial intelligence to make televisions play movies, existing artificial intelligence televisions cannot make recommendations based on personnel's preferences. There are limitations. Specifically, when people watch TV, they do not look for movies purposefully, but look for movies of their favorite type among many movies, which will reduce their desire to watch to a certain extent. In addition, it will also bring inconvenience to illiterate personnel, because these personnel will not look for movies after turning on the TV. Therefore, an artificial intelligence recognition system based on big data is invented. Summary of the invention

[0004] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0005] An artificial intelligence recognition system based on big data, comprising:

[0006] The user module is used to analyze user personnel and their corresponding personal preferences according to the user's daily life, so as to recommend relevant content according to the user when using the TV;

[0007] The voice collection module is used to collect the voice of the personnel so as to analyze the password of the personnel;

[0008] A domain analysis module is used to analyze the domain of the content to be played based on the sound collected by the sound collection module;

[0009] A judgment module, used to judge the preferred areas of personnel based on the data provided by the user module and the data analyzed by the sound collection module and the area analysis module;

[0010] A control module, used to control the television according to the data determined by the determination module, so that the television can recommend relevant content according to the preferences of the person;

[0011] The user module comprises:

[0012] A monitoring module, used to shoot the environment in front of the TV;

[0013] An appearance analysis module is used to analyze the appearance of a person based on the image captured by the monitoring module, so as to analyze the person's preferences based on their clothing, age and gender;

[0014] A voice analysis module is used to analyze the sounds in the content captured by the monitoring module so as to be able to analyze the preferences of people from their ordinary words;

[0015] The preference analysis module is used to analyze the preferences of the personnel based on the data analyzed by the appearance analysis module and the voice analysis module;

[0016] The identity generation module is used to register the identity of a person based on his / her facial features and voice, so as to distinguish between people;

[0017] A database for storing the preferences analyzed by the preference analysis module and the personal identities generated by the identity generation module;

[0018] Deletion module, used to delete information in the database;

[0019] The entry module is used to add new data to the database as needed, including preferences and identities.

[0020] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the appearance analysis module includes:

[0021] An image acquisition module, used to acquire images taken by the monitoring module;

[0022] The first analysis module is used to perform preference analysis based on the dressing style of the person in the image acquired by the image acquisition module.

[0023] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the appearance analysis module further includes:

[0024] A second analysis module is used to analyze the preferences of people according to their gender and age in the images acquired by the image acquisition module;

[0025] The first storage module is used to store the data analyzed by the first analysis module and the second analysis module so as to be able to transmit it to the preference analysis module at a later time.

[0026] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the first analysis module includes:

[0027] A clothing extraction module, used to extract clothing of a person from the image acquired by the image acquisition module;

[0028] The style analysis module is used to analyze the dressing style extracted by the dressing extraction module so as to analyze the preferences of people based on the dressing style.

[0029] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the second analysis module includes:

[0030] A face extraction module, used to extract the face of a person from the image acquired by the image acquisition module;

[0031] The age analysis module is used to perform age and gender analysis on the facial image extracted by the face extraction module, so as to analyze the preferences of the person according to age and gender.

[0032] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the speech analysis module includes:

[0033] A sound acquisition module is used to acquire the sound in the content captured by the monitoring module;

[0034] A language extraction module is used to extract the language from the sound acquired by the sound acquisition module to filter out background noise;

[0035] The timbre analysis module is used to perform timbre analysis based on the speech extracted by the language extraction module to analyze the person who matches the timbre.

[0036] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the speech analysis module further includes:

[0037] A text conversion module, used to convert the speech extracted by the language extraction module into text;

[0038] A sensitive word detection module, used to detect sensitive words on the text converted by the text conversion module;

[0039] The recording module is used to record the sensitive words involved so as to obtain the number of occurrences of the sensitive words.

[0040] As a preferred solution of the big data-based artificial intelligence recognition system described in the present invention, the speech analysis module further includes:

[0041] The scoring module is used to score the sensitive words involved according to the data recorded by the recording module, specifically, to score according to the number of occurrences of the sensitive words;

[0042] The second storage module is used to store the data scored by the scoring module so that it can be transmitted to the preference analysis module at a later time.

[0043] Compared with existing technologies:

[0044] By setting up a user module, it is possible to analyze user persons and their corresponding preferences based on their daily lives. Further, when the TV uses voice recognition technology to analyze a person's password, it is able to analyze the person's identity based on the data provided by the user module and make corresponding recommendations, thereby making accurate recommendations for the person, which not only improves the accuracy of the recommendation, but also brings convenience to the person's use. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0047] The present invention provides an artificial intelligence recognition system based on big data, please refer to Figure 1 ;

[0048] The system comprises: a user module, which is used to analyze the user and the corresponding preferences of the user according to the user's daily life, so as to recommend relevant content according to the user when the TV is used; a sound collection module, which is used to collect the voice of the user to analyze the password of the user; a domain analysis module, which is used to analyze the domain of the content to be played according to the sound collected by the sound collection module; a judgment module, which is used to judge the preference domain of the user according to the data provided by the user module and the data analyzed by the sound collection module and the domain analysis module; and a control module, which is used to control the TV according to the data judged by the judgment module, so as to enable the TV to recommend relevant content according to the preferences of the user.

[0049] The user module includes: a monitoring module, which is used to shoot the environment in front of the TV; an appearance analysis module, which is used to analyze the appearance of a person based on the image shot by the monitoring module, so as to analyze the preferences of the person from the person's clothing, age and gender; a voice analysis module, which is used to analyze the sound in the content shot by the monitoring module, so as to analyze the preferences of the person from ordinary words; a preference analysis module, which is used to finally analyze the preferences of the person based on the data analyzed by the appearance analysis module and the voice analysis module; an identity generation module, which is used to register the identity of the person based on the facial features and the tone of the person, so as to distinguish the person; a database, which is used to store the preferences analyzed by the preference analysis module and the identity of the person generated by the identity generation module; a deletion module, which is used to delete the information in the database; an entry module, which is used to add new data to the database according to needs, including preferences and identities.

[0050] The appearance analysis module includes: an image acquisition module for acquiring images taken by the monitoring module; a first analysis module for performing preference analysis based on the dressing style of the person in the images acquired by the image acquisition module; a second analysis module for performing preference analysis based on the gender and age of the person in the images acquired by the image acquisition module; and a first storage module for storing the data analyzed by the first analysis module and the second analysis module so that it can be transmitted to the preference analysis module at a later time.

[0051] The first analysis module includes: a clothing extraction module for extracting the clothing of a person from the image acquired by the image acquisition module; and a style analysis module for analyzing the clothing style extracted by the clothing extraction module so as to analyze the preferences of the person based on the clothing style.

[0052] The second analysis module includes: a face extraction module for extracting the face of a person from the image acquired by the image acquisition module; an age analysis module for performing age and gender analysis on the facial image extracted by the face extraction module, so as to analyze the preferences of the person based on age and gender.

[0053] The voice analysis module includes: a sound acquisition module, which is used to acquire the sound in the content captured by the monitoring module; a language extraction module, which is used to extract the language in the sound acquired by the sound acquisition module to filter out background noise; a timbre analysis module, which is used to perform timbre analysis based on the voice extracted by the language extraction module to analyze the person matching the timbre; a text conversion module, which is used to convert the voice extracted by the language extraction module into text; a sensitive word detection module, which is used to perform sensitive word detection on the text converted by the text conversion module; a recording module, which is used to record the sensitive words involved so as to be able to obtain the number of occurrences of the sensitive words; a scoring module, which is used to score the sensitive words involved according to the data recorded by the recording module, specifically scoring according to the number of occurrences of the sensitive words; a second storage module, which is used to store the data scored by the scoring module so that it can be transmitted to the preference analysis module at a later stage.

[0054] When used, the specific steps are as follows:

[0055] Step 1: The environment in front of the TV is photographed by the monitoring module. After the photographing, the image photographed by the monitoring module is acquired by the image acquisition module. After the acquisition, the clothing of the person is extracted from the image acquired by the image acquisition module by the clothing extraction module. After the extraction, the clothing style extracted by the clothing extraction module is analyzed by the style analysis module, so that the person's preference can be analyzed according to the clothing style. At the same time, the face of the person is extracted from the image acquired by the image acquisition module by the face extraction module. After the extraction, the age and gender of the face image extracted by the face extraction module are analyzed by the age analysis module, so that the person's preference can be analyzed according to the age and gender. After that, the data analyzed by the first analysis module and the second analysis module are stored by the first storage module, so that they can be transmitted to the preference analysis module at a later time.

[0056] Step 2: The sound in the content captured by the monitoring module is acquired through the sound acquisition module. After acquisition, the language in the sound acquired by the sound acquisition module is extracted through the language extraction module to filter the background noise. After extraction, the voice extracted by the language extraction module is analyzed by the voice analysis module to analyze the personnel matching the voice. At the same time, the voice extracted by the language extraction module is converted into text through the text conversion module. After conversion, the text converted by the text conversion module is detected for sensitive words (including but not limited to names) through the sensitive word detection module. After detection, the sensitive words involved are recorded through the recording module to obtain the number of occurrences of the sensitive words. After recording, the sensitive words involved are scored according to the data recorded by the recording module through the scoring module, specifically, the scoring is performed according to the number of occurrences of the sensitive words. After scoring, the data scored by the scoring module is stored through the second storage module so that it can be transmitted to the preference analysis module at a later time.

[0057] Step 3: The preference analysis module uses the data analyzed by the appearance analysis module and the voice analysis module to finally analyze the preferences of the person. After that, the identity generation module will register the identity of the person based on the facial features and voice of the person to achieve personnel differentiation. After differentiation, the preferences analyzed by the preference analysis module and the identity of the person generated by the identity generation module will be stored in the database;

[0058] Step 4: The voice of the person is collected through the sound collection module to analyze the password of the person. After the analysis, the field analysis module will analyze the field of the content to be played based on the sound collected by the sound collection module. After the analysis, the judgment module will judge the field of the person's preference based on the data provided by the user module and the data analyzed by the sound collection module and the field analysis module. After that, the control module will control the TV according to the data judged by the judgment module, so that the TV can recommend relevant content according to the person's preferences.

[0059] Step 5: After storing the preferences analyzed by the preference analysis module and the personal identity generated by the identity generation module in the database, the personnel can delete the information in the database using the deletion module through a computer or other terminal, and can also use the entry module to add new data to the database as needed, so that the preferences and identities of the personnel can be manually entered and adjusted; thereby, the flexibility of use of the system can be improved.

[0060] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. An artificial intelligence recognition system based on big data, characterized in that: include: The user module is used to analyze user personnel and their corresponding personal preferences according to the user's daily life, so as to recommend relevant content according to the user when using the TV; The voice collection module is used to collect the voice of the personnel so as to analyze the password of the personnel; A domain analysis module is used to analyze the domain of the content to be played based on the sound collected by the sound collection module; A judgment module, used to judge the preferred areas of personnel based on the data provided by the user module and the data analyzed by the sound collection module and the area analysis module; A control module, used to control the television according to the data determined by the determination module, so that the television can recommend relevant content according to the preferences of the person; The user module comprises: A monitoring module, used to shoot the environment in front of the TV; An appearance analysis module is used to analyze the appearance of a person based on the image captured by the monitoring module, so as to analyze the person's preferences based on their clothing, age and gender; A voice analysis module is used to analyze the sounds in the content captured by the monitoring module so as to be able to analyze the preferences of people from their ordinary words; The preference analysis module is used to analyze the preferences of the personnel based on the data analyzed by the appearance analysis module and the voice analysis module; The identity generation module is used to register the identity of a person based on his / her facial features and voice, so as to distinguish between people; A database for storing the preferences analyzed by the preference analysis module and the personal identities generated by the identity generation module; Deletion module, used to delete information in the database; The entry module is used to add new data to the database as needed, including preferences and identities.

2. The artificial intelligence recognition system based on big data according to claim 1, characterized in that: The appearance analysis module comprises: An image acquisition module, used to acquire images taken by the monitoring module; The first analysis module is used to perform preference analysis based on the dressing style of the person in the image acquired by the image acquisition module.

3. The artificial intelligence recognition system based on big data according to claim 2 is characterized in that: The appearance analysis module also includes: A second analysis module is used to analyze the preferences of people according to their gender and age in the images acquired by the image acquisition module; The first storage module is used to store the data analyzed by the first analysis module and the second analysis module so as to be able to transmit it to the preference analysis module at a later time.

4. The artificial intelligence recognition system based on big data according to claim 3 is characterized in that: The first analysis module comprises: A clothing extraction module, used to extract clothing of a person from the image acquired by the image acquisition module; The style analysis module is used to analyze the dressing style extracted by the dressing extraction module so as to analyze the preferences of people based on the dressing style.

5. The artificial intelligence recognition system based on big data according to claim 4 is characterized in that: The second analysis module comprises: A face extraction module, used to extract the face of a person from the image acquired by the image acquisition module; The age analysis module is used to perform age and gender analysis on the facial image extracted by the face extraction module, so as to analyze the preferences of the person according to age and gender.

6. The artificial intelligence recognition system based on big data according to claim 1, characterized in that: The speech analysis module comprises: A sound acquisition module is used to acquire the sound in the content captured by the monitoring module; A language extraction module is used to extract the language from the sound acquired by the sound acquisition module to filter out background noise; The timbre analysis module is used to perform timbre analysis based on the speech extracted by the language extraction module to analyze the person who matches the timbre.

7. The artificial intelligence recognition system based on big data according to claim 6, characterized in that: The speech analysis module also includes: A text conversion module, used to convert the speech extracted by the language extraction module into text; A sensitive word detection module, used to detect sensitive words on the text converted by the text conversion module; The recording module is used to record the sensitive words involved so as to obtain the number of occurrences of the sensitive words.

8. The artificial intelligence recognition system based on big data according to claim 7, characterized in that: The speech analysis module also includes: The scoring module is used to score the sensitive words involved according to the data recorded by the recording module, specifically, to score according to the number of occurrences of the sensitive words; The second storage module is used to store the data scored by the scoring module so that it can be transmitted to the preference analysis module at a later time.

Images