Intelligent photo album system supporting home equipment control

Abstract

The invention discloses an intelligent photo album system supporting household equipment control, which comprises an intelligent photo album terminal, and is characterized in that the intelligent photo album terminal is in interactive connection with an intelligent photo album controller or a household equipment control server or household equipment; the intelligent photo album terminal comprises a voice input module, the output end of the voice input module is connected with the input end of a voice recognition module, and the output end of the voice recognition module is connected with the input end of a text output module. The text output module is in interactive connection with the intelligent photo album controller or the home equipment control server or the home equipment through the intelligent photo album APP. According to the application, noise in the input voice information can be removed in a multi-stage manner, and meanwhile, framing processing is performed on the voice information, so that the discrimination accuracy of the voice information is improved, and the user experience is improved. And the voice information is accurately converted into the control text information, so that the accuracy of inputting the control instruction is improved, the control instruction can be input in multiple modes, and the effect of controlling the home equipment is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent photo albums, and particularly relates to an intelligent photo album system supporting home device control. Background Art

[0002] An intelligent photo album system is a supporting device for photo album management. With the improvement of mobile phone pixels and the development of cloud resources, cloud photo albums have become a current technological hotspot, providing services such as intelligent analysis of image content, intelligent album generation, and intelligent search, making artificial intelligence technology accessible. With the continuous development of technology, people's requirements for intelligent photo album systems are also getting higher and higher.

[0003] As disclosed in an invention with the publication number CN115587198A, an intelligent photo album management system and an intelligent photo album management system content processing method, the system includes: a box with an interface; a processor and a memory are arranged in the box; an intelligent device to be managed for multimedia resources is connected to the box through the interface, so that the processor can automatically read corresponding data from the intelligent device and transmit it to the memory for storage and backup. Compared with the traditional electronic photo album that manually copies data, it is more convenient and faster. In addition, the processor is used to read multimedia data from the intelligent device in the first working mode and transmit the multimedia data to the memory for storage; or, the processor is used to read multimedia incremental data from the intelligent device in the second working mode and transmit the multimedia incremental data to the memory for storage, so that users can select the corresponding working mode according to actual needs, and the functions are more abundant.

[0004] When the above technical solution is used, it cannot perform noise reduction and frame splitting processing on the user's voice, which is likely to cause inaccurate input of voice control instructions and result in control failure. At the same time, it cannot control home devices in multiple modes, and the control operation of home devices is inconvenient. Therefore, we propose an intelligent photo album system supporting home device control. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent photo album system supporting home device control to solve the problems in the above background art that the existing technology cannot perform noise reduction and frame splitting processing on the user's voice, which is likely to cause inaccurate input of voice control instructions and result in control failure, and at the same time, it cannot control home devices in multiple modes, and the control operation of home devices is inconvenient.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An intelligent photo album system supporting home device control, including an intelligent photo album terminal, and the intelligent photo album terminal is interactively connected with an intelligent photo album controller or a home device control server or a home device;

[0007] The smart album terminal includes a voice input module, the output end of the voice input module is connected to the input end of the voice recognition module, the output end of the voice recognition module is connected to the input end of the text output module, and the text output module is interactively connected to the smart album controller or the home device control server or the home device through the smart album APP.

[0008] Preferably, the voice input module includes a microphone, which is connected to the voice recognition module and is used to collect user voice information.

[0009] Preferably, the speech recognition module is used to perform noise reduction processing on the collected speech information, perform text matching, and convert it into clear speech information.

[0010] Preferably, the text output module is used to convert voice information into dialogue text information.

[0011] Preferably, the smart album APP is used to transmit the conversation text information to the smart album controller or the home device control server or the home device for controlling the home device.

[0012] Preferably, the smart album terminal further includes a display and a speaker, wherein the display is used to display the dialogue text generated by the user voice conversion, and the speaker is used to voice broadcast the execution result.

[0013] Preferably, the specific recognition process of the speech recognition module is:

[0014] The user's voice information is preprocessed, and then the frequency domain of the preprocessed voice information is converted and the energy is obtained. Then, the preprocessed voice information is processed by Mel filtering, and the difference inverse spectrum features of the preprocessed voice information are extracted. Then, the difference inverse spectrum features are calculated, and the voice information is denoised by the subtraction method. Finally, the noise in the voice information is filtered out by the filter module.

[0015] Preferably, the specific output process of the text output module is:

[0016] After the noise reduction, the voice information is parsed to obtain the voice command text; then the voice command text result is segmented, the keywords are extracted, and the keywords are filtered for synonyms to obtain a standardized expression. Finally, the standardized expression is analyzed for intent, the best matching intent of the user's voice command is obtained, and the most accurate voice text information is obtained.

[0017] Preferably, the smart photo album APP is embedded in the smart photo album terminal for manual operation by the user.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] (1) During the voice input process of this application, it can perform multi-level noise removal on the voice information in the input voice, and at the same time perform frame segmentation on the voice information, improving the discrimination accuracy of the voice information and accurately converting the voice information into control text information, thereby improving the accuracy of the input control instructions.

[0020] (2) This application can control home appliances by means of voice input or manual input of control instructions, and can adopt multi-mode input of control instructions, improving the control effect of home appliances. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the system structure of the first embodiment in the present invention;

[0022] Figure 2 It is a schematic diagram of the system structure of the second embodiment in the present invention;

[0023] Figure 3 It is a schematic diagram of the system structure of the third embodiment in the present invention;

[0024] Figure 4 It is a schematic diagram of the system structure of the fourth embodiment in the present invention;

[0025] Figure 5 It is a schematic diagram of the system structure of the fifth embodiment in the present invention;

[0026] Figure 6 It is a schematic diagram of the system structure of the sixth embodiment in the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] Embodiment 1

[0029] Please refer to Figure 1 , the present invention provides a technical solution: an intelligent photo album system supporting home appliance control, including an intelligent photo album terminal; the intelligent photo album terminal includes a voice input module, the output end of the voice input module is connected to the input end of the voice recognition module, the output end of the voice recognition module is connected to the input end of the text output module, the text output module is connected to the intelligent photo album controller through the intelligent photo album APP, the intelligent photo album controller is connected to the home appliance control server in an interactive manner, and the home appliance controller is connected to the home appliances in an interactive manner.

[0030] The voice input module includes a microphone, which is connected to the speech recognition module and is used to collect user voice information.

[0031] The speech recognition module is used to perform noise reduction processing on the collected voice information, perform text matching, and convert it into clear voice information.

[0032] The noise reduction processing of the speech recognition module for voice information is specifically as follows:

[0033] 1. Preprocess the user voice information;

[0034] 1.1. Perform pre-emphasis on the voice information;

[0035] Pre-emphasis is to make the spectrum of the voice signal more flat by compensating for high-frequency voices,

[0036] and thus can eliminate the friction effect of the vocal cords and lips to a certain extent during the voice generation process.

[0037] The input signal s(n) is first subjected to high-pass filtering to obtain:

[0038] H(z) = 1 - a*(z - 1);

[0039] In the formula, H(z) is the z-domain filter function; a is a constant; z is the z-domain independent variable;

[0040] The signal after pre-emphasis is s2(n), and its time-domain expression is:

[0041] s2(n) = s(n) - a*s(n - 1)

[0042] 1.2. Frame the voice information;

[0043] The voice signal has the characteristic of short-time stationarity and can be framed to reduce the processing difficulty. Usually, a frame of signal has N sampling points (usually taking 256), and the duration is about 26 ms.

[0044] And a part of the overlapping area is set between two frames. Assuming there are M sampling points, its value is generally about 1 / 3 of N. Generally, the sampling frequency of the voice signal is 8 kHz. It can be known that the duration corresponding to one frame after framing is 32 ms.

[0045] 1.3. Window the voice information;

[0046] After framing, each frame of the voice signal is convolved with a window function to reduce the influence of spectral leakage. Assuming the framed voice signal is s3(n), n = 0, 1,..., N - 1, N is the number of frames, and the Hamming window W(n) is used;

[0047] W(n,a) = (1 - a) - a * cos[2πN / (N - )];

[0048] Where; the value range of n is [0, N - 1]; the convolved signal is:

[0049] s′(n) = s(n) * W(n).

[0050] 2. Convert the frequency domain of the pre - processed speech information and calculate the energy;

[0051] 2.1. For the signal after frame - dividing and windowing, its frequency domain is obtained through fast Fourier transform;

[0052] 2.2. Solve the spectral energy of the speech signal after Fourier transform.

[0053] 3. Perform Mel filtering on the pre - processed speech information;

[0054] 3.1. Pass the above spectral line energy through a set of triangular filter banks to smooth the spectrum, eliminate the influence of harmonics, highlight the formants of speech, and at the same time reduce the data volume;

[0055] 3.2. Calculate the logarithmic energy output by each filter bank;

[0056] 3.3. After performing discrete cosine transform on the above logarithmic energy, the Mel cepstral parameters of order L can be obtained.

[0057] 4. Extract differential cepstrum features from the pre - processed speech information;

[0058] 5. Calculate the differential cepstrum features;

[0059] 6. Denoise the speech information through spectral subtraction;

[0060] 6.1. Use spectral subtraction for speech denoising. First, according to the endpoints of each speech segment found in the previous stage, eliminate the noise segment and update the noise floor level, eliminate the influence of noise on the speech segment, and then perform smoothing;

[0061] 6.2. In subsequent calculations, approximately replace the phase spectrum of the noisy speech before spectral subtraction with the phase spectrum of the speech after spectral subtraction, and then the time - domain speech signal after denoising can be calculated.

[0062] 7. Then filter out the noise in the speech information through the filter module.

[0063] The text output module is used to convert the speech information into dialogue text information.

[0064] The text output module parses the voice information after noise reduction to obtain the voice command text; then performs word segmentation on the voice command text result, extracts keywords, and filters synonyms of the keywords to obtain a standardized expression. Finally, intention analysis is performed on the standardized expression to obtain the best matching intention of the user's voice command and the most accurate voice text information.

[0065] The intelligent photo album APP is used to transmit the conversation text information to the intelligent photo album controller or the home device control server or the home device for controlling the home device.

[0066] The intelligent photo album terminal further includes a display and a speaker. The display is used to display the conversation text generated by the user's voice conversion, and the speaker is used to voice broadcast the execution result.

[0067] The specific system control method of this embodiment is as follows:

[0068] Step 1: First, the microphone collects the user's voice information;

[0069] Step 2: The voice recognition module in the intelligent photo album APP processes the voice information, then converts the voice information into conversation text through the text output module, and displays the conversation text information through the display screen;

[0070] Step 3: The intelligent photo album APP sends the conversation text to the intelligent photo album server. If the intelligent photo album server determines that the user instruction needs to control the furniture device, it issues a control instruction to the home device control server;

[0071] Step 4: The home device control server sends the specific instruction to the corresponding home device to implement the operation;

[0072] Step 5: The home device control server feeds back the home device control result to the intelligent photo album server, and the intelligent photo album server feeds back the home device control result to the intelligent photo album APP;

[0073] Step 6: The intelligent photo album APP conveys the control result to the display and the speaker. The display shows the home device control result, and the speaker voice broadcasts the home device control result.

[0074] Embodiment 2

[0075] Please refer to Figure 2, the present invention provides a technical solution: an intelligent photo album system supporting home device control, including an intelligent photo album terminal; the intelligent photo album terminal includes a voice input module, the output end of the voice input module is connected to the input end of the voice recognition module, the output end of the voice recognition module is connected to the input end of the text output module, and the text output module is directly connected to the home device control server through the intelligent photo album APP, and the home device controller is connected to the home device for interaction.

[0076] The voice input module includes a microphone, and the microphone is connected to the voice recognition module for collecting user voice information.

[0077] The voice recognition module is used to perform noise reduction processing on the collected voice information, perform text matching, and convert it into clear voice information.

[0078] The specific system control method of this embodiment is as follows:

[0079] Step 1: First, the microphone collects the user's voice information;

[0080] Step 2: The voice recognition module in the intelligent photo album APP processes the voice information, then converts the voice information into a dialogue text through the text output module, and displays the dialogue text information through the display screen;

[0081] Step 3: If the intelligent photo album APP determines that the user instruction needs to control the furniture device, it sends a control instruction to the home device control server;

[0082] Step 4: The home device control server sends the specific instruction to the corresponding home device to implement the operation;

[0083] Step 5: The home device control server feeds back the home device control result to the intelligent photo album APP;

[0084] Step 6: The intelligent photo album APP conveys the control result to the display and the speaker. The display shows the home device control result, and the speaker broadcasts the home device control result by voice.

[0085] Embodiment III

[0086] Please refer to Figure 3 , an intelligent photo album system supporting home device control, including an intelligent photo album terminal; the intelligent photo album terminal includes a voice input module, the output end of the voice input module is connected to the input end of the voice recognition module, the output end of the voice recognition module is connected to the input end of the text output module, and the text output module is directly connected to the home device for interaction through the intelligent photo album APP.

[0087] The voice input module includes a microphone, and the microphone is connected to the voice recognition module for collecting user voice information.

[0088] The voice recognition module is used to perform noise reduction processing on the collected voice information, perform text matching, and convert it into clear voice information.

[0089] The specific system control method of this embodiment is as follows:

[0090] Step 1: First, the microphone collects the user's voice information;

[0091] Step 2: The voice recognition module in the intelligent photo album APP processes the voice information, then converts the voice information into a dialogue text through the text output module, and displays the dialogue text information through the display screen;

[0092] Step 3: If the intelligent photo album APP determines that the user instruction needs to control the furniture device, it issues a control instruction to the corresponding home device to achieve the operation;

[0093] Step 4: The home device feeds back the home device control result to the intelligent photo album APP;

[0094] Step 5: The intelligent photo album APP transmits the control result to the display and the speaker. The display shows the home device control result, and the speaker announces the home device control result by voice.

[0095] Compared with the second embodiment, in this embodiment, the intelligent photo album APP can be connected to the home device and control the home device, eliminating the judgment step of the intelligent photo album server and the home device control server. The intelligent photo album APP integrates the home device management and control ability, and the control is more accurate and efficient.

[0096] Embodiment Four

[0097] Please refer to Figure 4 , an intelligent photo album system supporting home device control, including an intelligent photo album terminal; the intelligent photo album terminal includes an intelligent photo album APP, and the intelligent photo album APP is also interactively connected to an intelligent photo album controller, and the intelligent photo album controller is interactively connected to a home device control server, and the home device controller is interactively connected to the home device.

[0098] The intelligent photo album APP is used to transmit the user operation instruction to the intelligent photo album controller for controlling the home device.

[0099] The intelligent photo album terminal further includes a display, and the display is used to display the device control result.

[0100] The specific system control method of this embodiment is as follows:

[0101] Step 1: The user manually inputs a control instruction through the intelligent photo album APP;

[0102] Step 2: The intelligent photo album APP sends the user operation instruction to the intelligent photo album server;

[0103] Step 3: If the intelligent photo album server determines that the user instruction needs to control the furniture device, it sends a control instruction to the home device control server;

[0104] Step 4: The home device control server sends the specific instruction to the corresponding home device to implement the operation;

[0105] Step 5: The home device control server feeds back the home device control result to the intelligent photo album server, and the intelligent photo album server feeds back the home device control result to the intelligent photo album APP;

[0106] Step 6: The intelligent photo album APP conveys the control result to the display, and the display shows the home device control result.

[0107] In this embodiment, the user can manually click the operation method, and the intelligent photo album APP realizes the control of the home device through the intelligent photo album server.

[0108] Embodiment Five

[0109] Please refer to Figure 5 , an intelligent photo album system supporting home device control, including an intelligent photo album terminal; the intelligent photo album terminal includes an intelligent photo album APP, the intelligent photo album APP is interconnected with the home device control server, and the home device controller is interconnected with the home device.

[0110] The intelligent photo album APP is used to transmit the user operation instruction to the intelligent photo album controller to control the home device.

[0111] The intelligent photo album terminal further includes a display, and the display is used to show the device control result.

[0112] The specific system control method of this embodiment is as follows:

[0113] Step 1: The user manually inputs a control instruction through the intelligent photo album APP;

[0114] Step 2: The intelligent photo album APP sends the user operation instruction to the home device control server;

[0115] Step 3: The home device control server sends the specific instruction to the corresponding home device to implement the operation;

[0116] Step 4: The home device control server feeds back the home device control result to the intelligent photo album APP;

[0117] Step 5: The intelligent photo album APP conveys the control result to the display, and the display shows the home device control result.

[0118] Embodiment Six

[0119] Please refer to Figure 6 , an intelligent photo album system supporting home device control, including an intelligent photo album terminal; the intelligent photo album terminal includes an intelligent photo album APP, and the intelligent photo album APP is interactively connected to home devices.

[0120] The intelligent photo album APP is used to transmit user operation instructions to the intelligent photo album controller to control home devices.

[0121] The intelligent photo album terminal further includes a display, and the display is used to display the device control result.

[0122] The specific system control method of this embodiment is as follows:

[0123] Step 1: The user manually inputs a control instruction through the intelligent photo album APP;

[0124] Step 2: The intelligent photo album APP sends the user operation instruction to the corresponding home device to implement the operation;

[0125] Step 3: The home device feeds back the home device control result to the intelligent photo album APP;

[0126] Step 4: The intelligent photo album APP conveys the control result to the display, and the display shows the home device control result.

[0127] The home devices in this application include intelligent devices such as air conditioners, refrigerators, floor heating, curtains, windows, floor sweeping robots, washing machines, speakers, TVs, fans, lights, etc.

[0128] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent photo album system supporting home device control, characterized in that: It includes a smart photo album terminal, which is interactively connected to a smart photo album controller, a home device control server, or a home device; The smart photo album terminal includes a voice input module, the output end of the voice input module is connected to the input end of the voice recognition module, the output end of the voice recognition module is connected to the input end of the text output module, and the text output module is interactively connected to a smart photo album controller, a home device control server, or a home device through a smart photo album APP.

2. The intelligent photo album system supporting home device control according to claim 1, wherein: The voice input module includes a microphone, and the microphone is connected to the voice recognition module for collecting user voice information.

3. The intelligent photo album system for supporting home device control according to claim 1, characterized in that: The voice recognition module is used to perform noise reduction processing on the collected voice information, perform text matching, and convert it into clear voice information.

4. The intelligent photo album system for supporting home device control according to claim 1, characterized in that: The text output module is used to convert voice information into dialogue text information.

5. The intelligent photo album system for supporting home device control according to claim 1, characterized in that: The smart photo album APP is used to transmit the dialogue text information to a smart photo album controller, a home device control server, or a home device for controlling the home device.

6. The intelligent photo album system supporting home device control according to claim 1, wherein: The smart photo album terminal further includes a display and a speaker. The display is used to display the dialogue text generated by the conversion of the user's voice, and the speaker is used to voice broadcast the execution result.

7. An intelligent photo album system supporting home device control according to claim 1 or 3, characterized in that: The specific recognition process of the voice recognition module is as follows: Preprocess the user voice information, then convert the frequency domain of the preprocessed voice information and calculate the energy, then perform Mel filtering on the preprocessed voice information, extract the differential cepstrum features of the preprocessed voice information, then calculate the differential cepstrum features, perform noise reduction on the voice information through the spectral subtraction method, and finally filter out the noise in the voice information through the filter module.

8. An intelligent photo album system supporting home device control according to claim 1 or 4, characterized in that: The specific output process of the text output module is as follows: Parse the voice information after noise reduction to obtain the voice command text; then perform word segmentation on the voice command text result, extract the keywords, and perform synonym filtering on the keywords to obtain a standardized expression. Finally, perform intention analysis on the standardized expression to obtain the best matching intention of the user voice command and obtain the most accurate voice text information.

9. The intelligent photo album system for supporting home device control according to claim 1, wherein: The smart photo album APP is embedded in the smart photo album terminal for manual operation by the user.

Images