Instruction word acquisition method for voice interaction, device, and storage medium

Abstract

Disclosed in embodiments of the present application are an instruction word acquisition method for voice interaction, a device, and a storage medium. The method comprises: an electronic device acquiring image information; comparing identification information of the image information with pre-stored identification information to obtain a first comparison result; and if the first comparison result is that there is first identification information the same as the identification information of the image information in the pre-stored identification information, determining entry information corresponding to the first identification information as a first instruction word corresponding to the image information, so as to carry out voice interaction on the basis of the first instruction word.

Description

A method, device and storage medium for acquiring command words for voice interaction

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202311171515.3 and application date September 11, 2023, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present invention relates to the field of computer technology, and in particular to a method, device and storage medium for acquiring instruction words for voice interaction. Background Art

[0004] See-and-Speak technology means that the user only needs to speak the text on the current screen, and the vehicle computer will recognize and execute the corresponding command. This requires the vehicle computer to pre-acquire the text on the current screen to obtain the voice command words used for interaction with the user. Optical character recognition (OCR) technology can extract text from images, but current OCR technology generally suffers from the problem of long recognition time. For example, extracting text from a 1920×720 resolution image takes approximately 600ms. Therefore, when the image page displayed on the electronic device changes frequently, recognizing and scanning the text in the image based on current OCR technology will lead to delayed scanning results. In other words, existing methods for extracting command words generally suffer from the disadvantages of long time consumption and low extraction efficiency.

[0005] Summary of the Invention

[0006] One purpose of the present application is to provide a method, device and storage medium for obtaining instruction words for voice interaction. The advantage is that the identification information of the image information is compared with the pre-stored identification information. When it is determined that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the pre-stored first identification information is directly determined as the first instruction word of the image information. The instruction word corresponding to the image information can be obtained without performing related recognition and scanning. This can reduce the time spent in obtaining instruction words for the same image, effectively improve the efficiency of obtaining instruction words, and thus improve the timeliness of voice interaction.

[0007] Another object of the present application is to provide a method, device and storage medium for obtaining instruction words for voice interaction. Its advantage is that by storing different entry information corresponding to different identification information, pre-stored entry information is obtained, so that when obtaining the entry information corresponding to the first identification information, it can be obtained by searching using the pre-stored entry information, which can reduce the time spent on obtaining instruction words.

[0008] Another object of the present application is to provide a method, device and storage medium for obtaining instruction words for voice interaction. The advantage is that the image information is only identified and processed to obtain instruction words when the comparison result of comparing the identification information of the image information with the pre-stored identification information is that the first identification information does not exist in the pre-stored identification information. This can effectively improve the efficiency of obtaining instruction words, thereby improving the timeliness of voice interaction.

[0009] Another object of the present application is to provide a method, device and storage medium for obtaining command words for voice interaction. The advantage is that after the image information is segmented, the segmented sub-image is compared with the pre-stored identification information, and the command word corresponding to the segmented sub-image is determined based on the comparison result, which can adapt to the situation where the regional content of the image changes.

[0010] An embodiment of the present application provides a method for obtaining instruction words for voice interaction, the method comprising:

[0011] Obtain image information;

[0012] performing a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result;

[0013] If the first comparison result is that the pre-stored identification information contains first identification information that is identical to the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information.

[0014] An embodiment of the present application provides an electronic device, which includes a processor and a memory storing instructions executable by the processor; when the instructions are executed by the processor, the instruction word acquisition method for voice interaction as described above is implemented.

[0015] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for acquiring instruction words for voice interaction as described above is implemented.

[0016] An embodiment of the present application provides a method, device and storage medium for obtaining instruction words for voice interaction, wherein the electronic device obtains image information; performs comparison processing based on the identification information of the image information and pre-stored identification information to obtain a first comparison result; if the first comparison result is that the pre-stored identification information contains first identification information that is identical to the identification information of the image information, then the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word. It can be seen from this that the present application stores the identification information corresponding to the image information whose entry has been obtained by setting pre-stored identification information, and then when obtaining the instruction word for any image information, the identification information of the image information and the pre-stored identification information can be used for comparison. When the comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is directly determined as the first instruction word corresponding to the image information, thereby completing the extraction of the instruction word for the image information, without having to perform relevant identification and scanning on the image information every time the instruction word extraction for the image information is performed. This can greatly reduce the time spent on obtaining the instruction word for the same picture, effectively improve the efficiency of obtaining the instruction word, and thus improve the timeliness of voice interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a schematic diagram of a first implementation flow of a method for acquiring instruction words for voice interaction proposed in an embodiment of the present application;

[0018] FIG2 is a schematic diagram illustrating an implementation of a method for acquiring instruction words for voice interaction proposed in an embodiment of the present application;

[0019] FIG3 is a second schematic diagram of the implementation flow of the method for acquiring instruction words for voice interaction proposed in an embodiment of the present application;

[0020] FIG4 is a third schematic diagram of an implementation flow of the method for acquiring instruction words for voice interaction proposed in an embodiment of the present application;

[0021] FIG5 is a fourth flowchart of the method for obtaining command words for voice interaction proposed in an embodiment of the present application;

[0022] FIG6 is a first schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0023] FIG7 is a second schematic diagram of the composition structure of the electronic device proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain the related applications and are not intended to limit the applications. It should also be noted that for ease of description, only the portions relevant to the related applications are shown in the drawings.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0026] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0027] Currently, accessibility services are based on the assistive features and services provided by Android, helping users more easily use their electronic devices. These features include speech synthesis, haptic feedback, gesture navigation, and trackball and directional key navigation. The in-car "see-it-now" technology is primarily based on the accessibility solution provided by the system. This solution requires modifying the description text within the source code, but it is not adaptable to image-based text, which cannot be modified.

[0028] OCR technology refers to the technology in which an electronic device (such as a scanner or digital camera) examines characters printed on paper and then uses character recognition methods to translate the shapes into computer text. For current OCR technology, its recognition accuracy has reached a high level and the technology is quite mature. Using OCR technology can solve the above-mentioned scenario problems and extract text.

[0029] However, although OCR technology can extract text, its recognition takes a long time. For example, it takes about 600ms to extract text from a 1920×720 resolution image. Therefore, when the image pages displayed on the electronic device frequently change, recognizing and scanning the text in the image based on the current OCR technology will lead to delayed scanning results, such as the problem that the user cannot respond after speaking. In other words, the existing command word acquisition methods for voice interaction generally have the defects of long time consumption and low extraction efficiency.

[0030] In order to solve the above problems, in an embodiment of the present application, an electronic device obtains image information; performs comparison processing based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result; if the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, then the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word, which can reduce the time spent in obtaining instruction words for the same picture, effectively improve the efficiency of obtaining instruction words, and thus improve the timeliness of voice interaction.

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0032] FIG1 is a schematic diagram of a first implementation flow of a method for acquiring instruction words for voice interaction proposed in an embodiment of the present application. As shown in FIG1 , in an embodiment of the present application, a method for an electronic device to implement image generation may include the following steps:

[0033] Step 101: Obtain image information.

[0034] In an embodiment of the present application, the electronic device may first acquire image information.

[0035] It should be noted that in the embodiments of the present application, the electronic device can be any device with communication and storage functions, and the electronic device can have the need to obtain image information. For example, the electronic device can be a smart lock, a tablet computer, a mobile phone, an e-reader, a remote control, a personal computer (PC), a laptop computer, a car-mounted electronic device, an Internet TV, a wearable electronic device, a personal digital assistant (PDA), a portable media player (PMP), a navigation device, and other electronic devices.

[0036] Furthermore, in an embodiment of the present application, the electronic device may include a screen for displaying image information, so that the electronic device can obtain image information based on the picture currently displayed on the screen. The image information may be the entire picture currently displayed on the screen, or a part of the picture; for example, the electronic device can perform a screenshot based on the picture currently displayed on the screen to obtain image information corresponding to the entire displayed picture, or obtain image information corresponding to a part of the displayed picture.

[0037] For example, in an embodiment of the present application, when the electronic device is an in-vehicle electronic device, the instruction word acquisition method for voice interaction in the present application can be applied to the following scenarios: Figure 2 is a schematic diagram of the implementation of the instruction word acquisition method for voice interaction proposed in an embodiment of the present application. As shown in Figure 2, it is a screenshot of a portion of the screen of the in-vehicle electronic device. It can be seen that the screenshot contains the entry "My Subscription". When the user wants to conduct voice interaction through the in-vehicle electronic device and wake up the function corresponding to "My Subscription", the in-vehicle electronic device needs to be able to extract the "My Subscription" instruction word in the screenshot, so that after the in-vehicle electronic device receives the voice information from the user, it can simulate the click operation according to the extracted "My Subscription" instruction word to complete the entire voice interaction process.

[0038] Furthermore, in an embodiment of the present application, the electronic device may obtain image information in response to a wake-up instruction to perform a subsequent comparison processing procedure.

[0039] It should be noted that, in an embodiment of the present application, the wake-up instruction may be an instruction for waking up an electronic device, turning it on, and starting to acquire image information. The type or issuance form of the wake-up instruction is not specifically limited in this application; for example, the wake-up instruction may be a voice instruction "Hello, XX". When the electronic device receives the voice instruction, it may respond to the voice instruction, perform the power-on process, and start acquiring the image information on the screen to execute the subsequent comparison processing process; for example, the electronic device may issue a wake-up instruction by receiving the operation information of a physical button. For example, a "power on" button is deployed on the electronic device. When the electronic device receives the operation information of the "power on" button, it can determine that the wake-up instruction has been received, thereby starting to acquire image information.

[0040] Step 102: Perform a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result.

[0041] In an embodiment of the present application, after acquiring the image information, the electronic device may perform a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result.

[0042] It should be noted that, in the embodiments of the present application, the identification information of the image information may be any cryptographic hash function value, or other information that can be used to identify the image information, and the present application does not make any specific limitation.

[0043] In an embodiment of the present application, the pre-stored identification information may include cryptographic hash function values ​​of different image information.

[0044] In some embodiments of the present application, the identification information of the image information may be generated based on the Message Digest Algorithm 5 (MD5) in a cryptographic hash function. That is, the identification information of the image information may be an MD5 value.

[0045] In some embodiments of the present application, the pre-stored identification information may also include MD5 values ​​of different images.

[0046] It should be noted that in the embodiments of the present application, MD5 is a hash function whose purpose is to compress input data of arbitrary length into an output of a fixed length (128 bits, usually represented by 32 hexadecimal characters); MD5 is usually used for data integrity and consistency verification, password verification and digital signature.

[0047] It should be noted that, in the embodiment of the present application, the pre-stored identification information is already stored identification information, and different identification information in the pre-stored identification information corresponds to different image information.

[0048] In some embodiments of the present application, some pre-acquired image information can be used to extract and cache identification information to obtain pre-stored identification information. During the execution process of instruction word acquisition, identification information in the pre-stored identification information can also be added and supplemented based on the specific circumstances of the first comparison result.

[0049] Furthermore, in an embodiment of the present application, the first comparison result may include two results, one result being that the first identification information identical to the identification information of the image information exists in the pre-stored identification information, and the other result being that the first identification information identical to the identification information of the image information does not exist in the pre-stored identification information.

[0050] It is understandable that, in the embodiment of the present application, before performing comparison processing based on the identification information of the image information and the pre-stored identification information, the identification information of the image information may be extracted first.

[0051] Exemplarily, in an embodiment of the present application, the identification information of the image information is A, and the pre-stored identification information includes A, B, and C. After comparing the identification information of the image information and the pre-stored identification information, the first comparison result obtained may be that there is first identification information A in the pre-stored identification information that is the same as the identification information of the image information.

[0052] Exemplarily, in an embodiment of the present application, the identification information of the image information is A, and the pre-stored identification information includes B, C, and D. After comparing the identification information of the image information and the pre-stored identification information, the first comparison result obtained may be that there is no first identification information in the pre-stored identification information that is the same as the identification information of the image information.

[0053] Step 103: If the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

[0054] In an embodiment of the present application, after the electronic device performs comparison processing based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result, if the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

[0055] It should be noted that, in the embodiment of the present application, the entry information corresponding to the first identification information can be obtained from pre-stored entry information.

[0056] It should also be noted that, in the embodiment of the present application, different entry information in the pre-stored entry information corresponds to different identification information.

[0057] In some embodiments of the present application, when the electronic device obtains the entry information corresponding to the first identification information, it can perform a search in the pre-stored entry information according to the first identification information to obtain the entry information corresponding to the first identification information.

[0058] Exemplarily, in an embodiment of the present application, the identification information of the image information is C, and the first comparison result is that there is first identification information in the pre-stored identification information that is the same as the identification information of the image information, that is, C. Then, the entry information corresponding to C can be searched in the pre-stored entry information, and the entry information corresponding to C can be determined as the first instruction word corresponding to the image information.

[0059] It can be understood that in an embodiment of the present application, when there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, directly determining the entry information corresponding to the first identification information as the first instruction word corresponding to the image information can reduce the time consumption of a related recognition and scanning, thereby greatly improving the efficiency of instruction word acquisition.

[0060] Furthermore, FIG3 is a second schematic diagram of an implementation flow of the method for acquiring instruction words for voice interaction proposed in an embodiment of the present application. As shown in FIG3 , in an embodiment of the present application, after the electronic device performs a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result, that is, after step 102, it may further include the following steps:

[0061] Step 104: If the first comparison result is that the first identification information does not exist in the pre-stored identification information, recognition processing is performed based on the image information to obtain a first instruction word.

[0062] In an embodiment of the present application, after the electronic device performs comparison processing based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, it performs recognition processing based on the image information to obtain a first instruction word.

[0063] It should be noted that in the embodiments of this application, recognition processing includes text recognition and control recognition. Text recognition is used to extract various texts in the image, such as "My Music," "My Subscription," and so on; control recognition is used to extract icon controls in the image, such as the air conditioning icon, window icon, various application APP icons, continue play icon, pause play icon, and so on. By performing recognition processing on the image information, the text and controls are identified, and a matching search is performed with the instruction library to obtain the instruction word corresponding to each text and each control, thereby obtaining the first instruction word.

[0064] It should be noted that in the embodiments of the present application, the present application does not perform recognition processing or scanning operations every time it is necessary to extract instruction words from an image. Instead, it only performs recognition processing on the image information to obtain the first instruction word of the image information when it is determined that the first identification information does not exist in the pre-stored identification information after comparison processing is performed based on the pre-stored identification information. This can greatly improve the efficiency of extracting instruction words from images and can quickly extract instruction words from images to achieve efficient voice interaction.

[0065] Furthermore, in an embodiment of the present application, an image recognition interface may be deployed in the electronic device to perform recognition processing on the image information and obtain a first instruction word of the image information; in addition, the image recognition interface may also be used to extract identification information of the image information.

[0066] In some embodiments of the present application, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, the electronic device can add the first instruction word to the pre-stored entry information after performing recognition processing based on the image information and obtaining the first instruction word.

[0067] For example, in an embodiment of the present application, the pre-stored entry information originally includes MD5 (identification information) A, B, C, D corresponding to the entry information a, b, c, d, respectively, and the MD5 of the image information is represented as E; after comparing the MD5 (identification information) of the image information with the pre-stored identification information, the first comparison result obtained is that there is no MD5 of E in the pre-stored identification information, then the image information can be identified and processed, and the first instruction word "My Music" is obtained, and the first instruction word "My Music" of the image information is added to the pre-stored entry information; wherein, the first instruction word "My Music" is stored according to the MD5 corresponding to E.

[0068] In some embodiments of the present application, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, the electronic device can also determine the identification information of the image information after performing recognition processing based on the image information and obtaining the first instruction word, and add the identification information of the image information to the pre-stored identification information.

[0069] For example, in an embodiment of the present application, the pre-stored entry information originally includes the entry information a, b, c, d corresponding to MD5 (identification information) A, B, C, and D, and the MD5 of the image information is represented as E; after comparing the MD5 (identification information) of the image information with the pre-stored identification information, the first comparison result obtained is that there is no MD5 of E in the pre-stored identification information, then after the image information is identified and the identification information is extracted, the MD5 of the image information can be added to the pre-stored identification information, so that the updated pre-stored identification information includes five different MD5s of A, B, C, D, and E.

[0070] Furthermore, in an embodiment of the present application, in addition to storing entry information that does not exist in the pre-stored entry information and storing identification information that does not exist in the pre-stored identification information during the process of acquiring the instruction word, the electronic device can also first acquire identification information and entry information for a portion of the image, thereby constructing pre-stored identification information and pre-stored entry information.

[0071] In some embodiments of the present application, the electronic device may first obtain preset image information; then determine the identification information corresponding to the preset image information and the entry information corresponding to the preset image information; and then obtain the pre-stored identification information based on the identification information corresponding to the preset image information; and obtain the pre-stored entry information based on the entry information corresponding to the preset image information.

[0072] It can be understood that, in the embodiment of the present application, the preset image information is used to construct the pre-stored identification information and the pre-stored entry information, and the number of the preset image information can be at least one.

[0073] Illustratively, in an embodiment of the present application, when the electronic device is an in-vehicle electronic device, image information (preset image information) corresponding to some interface content that may be displayed on the screen can be obtained in advance. For example, if the obtained preset image information includes words such as "music" and "navigation", the preset image information can be recognized and processed, and the obtained entry information such as "music" and "navigation" can be cached to obtain pre-stored entry information; at the same time, the MD5 of the preset image information can be extracted, and the MD5 can be cached to obtain pre-stored identification information.

[0074] Furthermore, Figure 4 is a third schematic diagram of the implementation process of the method for acquiring instruction words for voice interaction proposed in an embodiment of the present application. As shown in Figure 4, in an embodiment of the present application, after the electronic device acquires the image information, that is, after step 101, it can also execute the following steps 105 to 107; that is, after executing step 101, the electronic device can choose to execute one of the two processes of steps 102 to 103 or steps 105 to 107.

[0075] It should be noted that, in the embodiment of the present application, the method of steps 102 to 103 is actually to directly extract instruction words from the image information. Therefore, when there are fewer text or icon controls in the image information, the electronic device can obtain the instruction words corresponding to the image information by executing the method of steps 102 to 103; and the method of steps 105 to 107 is more suitable for situations where there are more text or icon controls in the image information, or when the image information undergoes regional content changes.

[0076] Step 105: Segment the image information to obtain segmented sub-images.

[0077] In an embodiment of the present application, after acquiring image information, the electronic device may segment the image information to obtain segmented sub-images.

[0078] It should be noted that in the embodiments of the present application, in order to cope with regional content changes in the image, the present application can also segment the image information, thereby executing instruction word acquisition based on each segmented sub-image, which can further improve the efficiency of instruction word acquisition.

[0079] In some embodiments of the present application, the situation where the regional content of image information changes may be that only part of the screen content is different from that of the previous image information; thus, by segmenting the image information and then acquiring instruction words for the changed part of the sub-image based on the segmented sub-images, the time consumption of acquiring instruction words can be effectively reduced.

[0080] In some embodiments of the present application, when there are many text or icon controls in the image information, the image information is segmented to obtain segmented sub-images, and then the respective instruction words are extracted based on the segmented sub-images. Compared with directly extracting the instruction words from the entire image information, this method is less time-consuming and more efficient.

[0081] Furthermore, in the embodiments of the present application, the specific segmentation method for segmenting the image information and the number of segments are not limited in the present application.

[0082] Illustratively, in an embodiment of the present application, the electronic device may segment an image information obtained by screenshot processing into blocks, for example, dividing the image information into 4 or 8 parts, thereby obtaining 4 or 8 segmented sub-images.

[0083] Step 106 : performing a comparison process based on the identification information corresponding to the segmented sub-image and the pre-stored identification information to obtain a second comparison result.

[0084] In an embodiment of the present application, after the electronic device segments the image information to obtain segmented sub-images, it can perform a comparison process based on the identification information corresponding to the segmented sub-images and pre-stored identification information to obtain a second comparison result.

[0085] Furthermore, in an embodiment of the present application, the pre-stored identification information can also be used to store identification information corresponding to the segmented sub-images. For example, in addition to the identification information corresponding to the complete image information G, H, and I, the pre-stored identification information can also include identification information corresponding to the segmented sub-images G1, G2, G3, H1, H2, H3, I1, I2, I3, and I4, wherein G1, G2, and G3 are three segmented sub-images obtained after segmentation based on the complete image information G, H1, H2, and H3 are three segmented sub-images obtained after segmentation based on the complete image information H, and I1, I2, I3, and I4 are four segmented sub-images obtained after segmentation based on the complete image information I.

[0086] Furthermore, in an embodiment of the present application, the identification information corresponding to each segmented sub-image may be compared with the pre-stored identification information to obtain a second comparison result.

[0087] It can be understood that in the embodiments of the present application, by comparing the identification information corresponding to a segmented sub-image with the pre-stored identification information, a second comparison result corresponding to the segmented sub-image can be obtained. That is to say, after performing comparison processing on multiple segmented sub-images, multiple second comparison results corresponding to each of the multiple segmented sub-images can be obtained.

[0088] In some embodiments of the present application, the second comparison result may include two situations, one is that there is no second identification information in the pre-stored identification information that is identical to the identification information corresponding to the segmented sub-image, and the other is that there is second identification information in the pre-stored identification information that is identical to the identification information corresponding to the segmented sub-image.

[0089] Exemplarily, in an embodiment of the present application, the image information A is segmented to obtain four segmented sub-images A1, A2, A3, and A4, and the identification information a1, a2, a3, and a4 corresponding to each of A1, A2, A3, and A4 are obtained respectively. Then, a1, a2, a3, and a4 are compared with the pre-stored identification information respectively. If the pre-stored identification information includes a1, a2, and a3, when a1 is compared with the pre-stored identification information, the corresponding second comparison result is that the same second identification information a1 exists in the pre-stored identification information; when a2 is compared with the pre-stored identification information, the corresponding second comparison result is that the same second identification information a2 exists in the pre-stored identification information; when a3 is compared with the pre-stored identification information, the corresponding second comparison result is that the same second identification information a3 exists in the pre-stored identification information; and when a4 is compared with the pre-stored identification information, the corresponding second comparison result is that the same second identification information a4 does not exist in the pre-stored identification information.

[0090] Step 107: Determine the second instruction word corresponding to the segmented sub-image according to the second comparison result.

[0091] In an embodiment of the present application, after the electronic device performs a comparison process based on the identification information corresponding to the segmented sub-image and the pre-stored identification information and obtains a second comparison result, it can determine the second instruction word corresponding to the segmented sub-image based on the second comparison result.

[0092] In some embodiments of the present application, when the electronic device determines the second instruction word corresponding to the segmented sub-image based on the second comparison result, if the second comparison result is that the second identification information that is identical to the identification information corresponding to the segmented sub-image does not exist in the pre-stored identification information, then recognition processing is performed based on the segmented sub-image to obtain the second instruction word; if the second comparison result is that the second identification information exists in the pre-stored identification information, then the entry information corresponding to the second identification information is determined as the second instruction word corresponding to the segmented sub-image.

[0093] In an embodiment of the present application, the electronic device may perform recognition processing through an image recognition interface to obtain the first instruction word or the second instruction word.

[0094] It can be understood that in an embodiment of the present application, if there is no second identification information in the pre-stored identification information that is identical to the identification information corresponding to the segmented sub-image, recognition processing is performed based on the segmented sub-image to obtain the second instruction word. Since the recognition processing is performed on regional content, it takes less time than the recognition processing of the entire image. Therefore, the present application can more effectively improve the recognition speed when responding to regional content changes, thereby improving the efficiency of obtaining instruction words.

[0095] Furthermore, in an embodiment of the present application, when the entry information corresponding to the second identification information is determined as the second instruction word corresponding to the segmented sub-image, a search process can also be performed in the pre-stored entry information to obtain the entry information corresponding to the second identification information.

[0096] In some embodiments of the present application, a search process may be performed in pre-stored entry information according to the second identification information to obtain the entry information corresponding to the second identification information.

[0097] Furthermore, in an embodiment of the present application, the pre-stored entry information includes entry information obtained based on complete image information and / or entry information corresponding to segmented image information.

[0098] It should be noted that in the embodiment of the present application, when acquiring the second instruction word for the segmented sub-image, the same method as the first instruction word for acquiring the image information is adopted. The only difference is that the target of the instruction word is replaced by the segmented sub-image.

[0099] Exemplarily, in an embodiment of the present application, after the image information is segmented, two segmented sub-images are obtained, and MD5 (identification information) is extracted from the two segmented sub-images. Then, the MD5 of one of the segmented sub-images is compared with the pre-stored MD5 (pre-stored identification information), and it is determined that the second comparison result is that there is no MD5 corresponding to the segmented sub-image in the pre-stored MD5, then the segmented sub-image is identified and processed to obtain the second instruction word of the segmented sub-image; when the MD5 of the other segmented sub-image is compared with the pre-stored MD5, the second comparison result obtained is that there is an MD5 identical to it in the pre-stored MD5, then the entry information corresponding to the MD5 is directly searched out in the pre-stored entry information as the second instruction word of this segmented sub-image.

[0100] Furthermore, in an embodiment of the present application, after acquiring the entry information based on all segmented sub-images, the entry information corresponding to the complete image information composed of all segmented sub-images can be obtained.

[0101] Furthermore, in an embodiment of the present application, whether the first instruction word corresponding to the image information is obtained or the second instruction word corresponding to the segmented sub-image is obtained, the electronic device can transmit the first instruction word and / or the second instruction word to the voice engine to prepare for scenarios such as voice interaction.

[0102] The embodiment of the present application provides a method for obtaining command words for voice interaction, wherein an electronic device obtains image information; compares the identification information of the image information with pre-stored identification information to obtain a first comparison result; if the first comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is determined as the first command word corresponding to the image information, so as to perform voice interaction based on the first command word. As can be seen from this, the present application stores the identification information corresponding to the image information whose entry has been obtained by setting pre-stored identification information, and then when obtaining command words for any image information, the identification information of the image information can be first compared with the pre-stored identification information. When the comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is directly determined as the first command word corresponding to the image information, thereby completing the extraction of command words for the image information, without having to perform relevant recognition and scanning on the image information each time when extracting command words for the image information, which can greatly reduce the time spent on obtaining command words for the same image, effectively improve the efficiency of command word acquisition, and thus improve the timeliness of voice interaction.

[0103] Based on the above embodiments, in another embodiment of the present application, exemplarily, the electronic device is a vehicle-mounted electronic device, i.e., a vehicle computer, which has an electronic screen and can be turned on by receiving the user's wake-up voice information (wake-up command), and synchronously starts to acquire instruction words for the image information displayed on the electronic screen, so that after receiving the user's voice interaction information, it can respond based on the acquired instruction words, such as simulating click operations, etc., to complete the interaction process with the user.

[0104] Furthermore, in an embodiment of the present application, when the on-board electronic device obtains the instruction word for the image information displayed on the electronic screen, it can extract the identification information of the image information, use the identification information of the image information to compare with the pre-stored identification information, obtain a first comparison result, and thereby determine the first instruction word for the image information based on the first comparison result.

[0105] It should be noted that, in the embodiment of the present application, the pre-stored identification information is already stored identification information, and different identification information in the pre-stored identification information corresponds to different image information.

[0106] Illustratively, in an embodiment of the present application, the pre-stored identification information may be pre-stored MD5, and these pre-stored MD5 may be embodied in the form of a queue, for example, may form an MD5 queue.

[0107] Furthermore, in an embodiment of the present application, the first comparison result may include two results, one result being that the first identification information identical to the identification information of the image information exists in the pre-stored identification information, and the other result being that the first identification information identical to the identification information of the image information does not exist in the pre-stored identification information.

[0108] Furthermore, in an embodiment of the present application, when the on-board electronic device determines the first instruction word of the image information based on the first comparison result, if the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, then the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information; if the first comparison result is that the first identification information does not exist in the pre-stored identification information, then recognition processing is performed based on the image information to obtain the first instruction word.

[0109] Furthermore, in an embodiment of the present application, different entry information in the pre-stored entry information corresponds to different identification information.

[0110] In some embodiments of the present application, when obtaining the entry information corresponding to the first identification information, the in-vehicle electronic device can perform a search in the pre-stored entry information according to the first identification information to obtain the entry information corresponding to the first identification information.

[0111] It can be understood that in the embodiments of the present application, recognition processing or scanning operations are not performed every time there is a need to extract instruction words from an image. Instead, only when comparison processing is performed based on pre-stored identification information and it is determined that the first identification information does not exist in the pre-stored identification information, is recognition processing performed on the image information to obtain the first instruction word of the image information, that is, the first instruction word. This can greatly improve the efficiency of extracting instruction words from images, and can quickly extract instruction words from images, thereby achieving efficient voice interaction.

[0112] Furthermore, in an embodiment of the present application, an image recognition interface may be deployed in the electronic device to perform recognition processing on the image information and obtain a first instruction word of the image information; in addition, the image recognition interface may also be used to extract identification information of the image information.

[0113] In some embodiments of the present application, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, the on-board electronic device can add the first instruction word to the pre-stored entry information after performing recognition processing based on the image information and obtaining the first instruction word; and determine the identification information of the image information, and add the identification information of the image information to the pre-stored identification information.

[0114] Furthermore, in an embodiment of the present application, in addition to storing entry information that does not exist in the pre-stored entry information and storing identification information that does not exist in the pre-stored identification information during the process of acquiring the instruction word, the electronic device can also first acquire identification information and entry information for a portion of the image, thereby constructing pre-stored identification information and pre-stored entry information.

[0115] In some embodiments of the present application, the electronic device may first obtain preset image information; then determine the identification information corresponding to the preset image information and the entry information corresponding to the preset image information; and then obtain the pre-stored identification information based on the identification information corresponding to the preset image information; and obtain the pre-stored entry information based on the entry information corresponding to the preset image information.

[0116] In some embodiments of the present application, when pre-stored identification information and pre-stored entry information are constructed using preset image information, identification information corresponding to the preset image information and entry information corresponding to the preset image information can be obtained according to the image recognition interface in the vehicle-mounted electronic device.

[0117] Furthermore, in an embodiment of the present application, the image information can be segmented first, and then the above-mentioned method of obtaining command words can be executed based on the segmented sub-images. This can adapt to the situation where regional content on the screen of the vehicle-mounted electronic device changes, and is more conducive to effectively improving the efficiency of obtaining command words, thereby improving the timeliness of voice interaction.

[0118] In an embodiment of the present application, after the image information is segmented into a plurality of segmented sub-images, the identification information corresponding to each segmented sub-image may be compared with the pre-stored identification information to obtain a second comparison result.

[0119] In some embodiments of the present application, the second comparison result may include two situations, one is that there is no second identification information in the pre-stored identification information that is identical to the identification information corresponding to the segmented sub-image, and the other is that there is second identification information in the pre-stored identification information that is identical to the identification information corresponding to the segmented sub-image.

[0120] In some embodiments of the present application, when the electronic device determines the second instruction word corresponding to the segmented sub-image based on the second comparison result, if the second comparison result is that the second identification information that is identical to the identification information corresponding to the segmented sub-image does not exist in the pre-stored identification information, then recognition processing is performed based on the segmented sub-image to obtain the second instruction word; if the second comparison result is that the second identification information exists in the pre-stored identification information, then the entry information corresponding to the second identification information is determined as the second instruction word corresponding to the segmented sub-image.

[0121] Furthermore, in an embodiment of the present application, when the entry information corresponding to the second identification information is determined as the second instruction word corresponding to the segmented sub-image, a search process can also be performed in the pre-stored entry information to obtain the entry information corresponding to the second identification information.

[0122] For example, in an embodiment of the present application, the electronic device is an in-vehicle electronic device. FIG5 is a fourth flow chart of the implementation process of the method for acquiring command words for voice interaction proposed in an embodiment of the present application. As shown in FIG5 , the in-vehicle electronic device can first capture the screen image to obtain image information (step 201), then segment the image information to obtain segmented sub-images (step 202), and then extract MD5 based on the segmented sub-images (step 203), and determine whether there is an MD5 of the segmented sub-image in the pre-stored MD5 (step 204). If there is an MD5 of the segmented sub-image in the pre-stored MD5, then the pre-stored entry information is extracted. The entry information corresponding to MD5 is extracted (step 205), so that the entry information corresponding to MD5 can be determined as the second instruction word; if the pre-stored MD5 does not include the MD5 of the segmented sub-image, the segmented sub-image is identified and processed to obtain the second instruction word (step 206), and the second instruction word and MD5 corresponding to the segmented sub-image are cached (step 207); wherein, when the second instruction word and MD5 corresponding to the segmented sub-image are cached, the second instruction word corresponding to the segmented sub-image can be stored in the pre-stored entry information, and the MD5 corresponding to the segmented sub-image can be stored in the pre-stored identification information.

[0123] Furthermore, in an embodiment of the present application, after obtaining the second instruction word based on all the segmented sub-images, the instruction word corresponding to the complete image information composed of all the segmented sub-images can be obtained, and then the instruction word can be transmitted to the voice engine in the on-board electronic equipment, providing an implementation basis for subsequent voice interaction scenarios.

[0124] Furthermore, in the embodiments of the present application, through experimental comparison, the time consumed by using the method for acquiring command words for voice interaction in the present application to acquire command words for two identical pictures is reduced by 80% compared to using the relevant existing technology to perform text recognition on two identical pictures; and after dividing the picture into 8 sub-images and then executing the above-mentioned method for acquiring command words, the time consumed can be reduced by 40% to 80%; it can be seen that the method for acquiring command words for voice interaction proposed in the present application can effectively reduce the time consumed in extracting command words from images and improve the efficiency of acquiring command words.

[0125] In an embodiment of the present application, the above-mentioned method for acquiring instruction words for voice interaction can be applied to the use scenario of human-computer interaction. In this scenario, the vehicle can be provided with a sound system to realize functions such as voice dialogue and voice interaction.

[0126] In some embodiments of the present application, the vehicle's sound system may include a panel sound module, which may be any one of a piezoelectric sound module, an electromagnetic induction sound module, and a speaker; the panel sound module may be arranged in the vehicle's door interior panel, armrest box, seat headrest, etc.

[0127] In some embodiments of the present application, the piezoelectric sound module may include a piezoelectric ceramic speaker; the piezoelectric ceramic speaker may include an electrode sheet, a piezoelectric ceramic, a vibration plate, and a vibration gasket.

[0128] In some embodiments of the present application, the electrode sheet may be configured to receive an excitation voltage from a driving circuit; the electrode sheet may be a pair of positive and negative electrode sheets.

[0129] In some embodiments of the present application, the piezoelectric ceramic is configured to produce transverse or longitudinal extension or contraction under the action of an excitation voltage received through an electrode sheet; wherein the excitation voltage can be a high-frequency square wave with alternating polarity, so the piezoelectric ceramic will produce mechanical deformation, i.e., extension or contraction, under the action of the square wave with alternating polarity; in addition, the piezoelectric ceramic can be a transversely or longitudinally polarized piezoelectric ceramic, thereby producing transverse or longitudinal mechanical deformation under the action of the excitation voltage.

[0130] In some embodiments of the present application, a vibration plate can be bonded to a piezoelectric ceramic and vibrate as the piezoelectric ceramic expands or contracts. In this way, the piezoelectric ceramic speaker converts the input excitation voltage into vibration, thereby emitting speech. The vibration plate can also be bonded to a component such as a door panel to drive the component to vibrate. The larger the area of ​​the component such as the door panel driven by the piezoelectric ceramic speaker, the stronger the low-frequency response of the vibration and the weaker the high-frequency response.

[0131] In some embodiments of the present application, a vibration gasket can be positioned between a vibration plate and a device such as a door panel. This gasket can be used to adjust the frequency response of the vibration generated by the vibration plate. For example, if the low-frequency response of the vibration needs to be enhanced, the area of ​​the gasket can be increased; if the low-frequency response needs to be reduced, the area of ​​the gasket can be decreased. By utilizing the panel sound module, the vehicle's sound field is expanded.

[0132] The embodiment of the present application provides a method for obtaining command words for voice interaction, wherein an electronic device obtains image information; compares the identification information of the image information with pre-stored identification information to obtain a first comparison result; if the first comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is determined as the first command word corresponding to the image information, so as to perform voice interaction based on the first command word. As can be seen from this, the present application stores the identification information corresponding to the image information whose entry has been obtained by setting pre-stored identification information, and then when obtaining command words for any image information, the identification information of the image information can be first compared with the pre-stored identification information. When the comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is directly determined as the first command word corresponding to the image information, thereby completing the extraction of command words for the image information, without having to perform recognition and scanning on the image information each time when extracting command words for the image information, which can greatly reduce the time spent on obtaining command words for the same image, effectively improve the efficiency of command word acquisition, and thus improve the timeliness of voice interaction.

[0133] Based on the above embodiment, in another embodiment of the present application, Figure 6 is a schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application. As shown in Figure 6, the electronic device 10 proposed in the embodiment of the present application may include: an acquisition unit 11, a comparison unit 12, a determination unit 13, a storage unit 14 and a segmentation unit 15.

[0134] The acquiring unit 11 is configured to acquire image information.

[0135] The comparison unit 12 is configured to perform a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result.

[0136] The determination unit 13 is configured to determine the entry information corresponding to the first identification information as the first instruction word corresponding to the image information if the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, so as to perform voice interaction based on the first instruction word.

[0137] Furthermore, the determining unit 13 is further configured to perform a search process in pre-stored entry information according to the first identification information to obtain entry information corresponding to the first identification information; wherein different entry information in the pre-stored entry information corresponds to different identification information.

[0138] Furthermore, the determination unit 13 is also configured to perform comparison processing based on the identification information of the image information and the pre-stored identification information in the comparison unit 12, and after obtaining the first comparison result, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, perform recognition processing based on the image information to obtain the first instruction word.

[0139] The storage unit 14 is configured to, if the first comparison result is that the first identification information does not exist in the pre-stored identification information, then perform recognition processing in the determination unit 13 based on the image information, and after obtaining the first instruction word, add the first instruction word to the pre-stored entry information.

[0140] Furthermore, the storage unit 14 is further configured to determine identification information of the image information and add the identification information of the image information to the pre-stored identification information.

[0141] Furthermore, the acquisition unit 11 is further configured to acquire preset image information.

[0142] Furthermore, the determination unit 13 is also configured to determine the identification information corresponding to the preset image information and the entry information corresponding to the preset image information; and obtain the pre-stored identification information based on the identification information corresponding to the preset image information; and obtain the pre-stored entry information based on the entry information corresponding to the preset image information.

[0143] The segmentation unit 15 is configured to segment the image information after the acquisition unit 11 acquires the image information, to obtain segmented sub-images.

[0144] Furthermore, the comparison unit 12 is further configured to perform a comparison process based on the identification information corresponding to the segmented sub-image and the pre-stored identification information to obtain a second comparison result.

[0145] Furthermore, the determining unit 13 is further configured to determine a second instruction word corresponding to the segmented sub-image according to the second comparison result.

[0146] Furthermore, the determination unit 13 is also configured to, if the second comparison result is that the second identification information identical to the identification information corresponding to the segmented sub-image does not exist in the pre-stored identification information, perform recognition processing based on the segmented sub-image to obtain the second instruction word; and if the second comparison result is that the second identification information exists in the pre-stored identification information, determine the entry information corresponding to the second identification information as the second instruction word corresponding to the segmented sub-image.

[0147] Furthermore, the determining unit 13 is further configured to perform a search process in pre-stored entry information according to the second identification information to obtain the entry information corresponding to the second identification information.

[0148] Furthermore, the pre-stored entry information includes entry information obtained based on complete image information and / or entry information corresponding to segmented image information.

[0149] Furthermore, the determining unit 13 is further configured to perform the recognition process through an image recognition interface to obtain the first instruction word or the second instruction word.

[0150] Furthermore, the acquisition unit 11 is further configured to acquire the image information in response to a wake-up instruction to execute the comparison processing flow.

[0151] Furthermore, the identification information of the image information is an MD5 value; and the pre-stored identification information includes MD5 values ​​of different images.

[0152] Furthermore, the determination unit 13 is also configured to perform the voice interaction based on the vehicle's sound system and the first instruction word; wherein the vehicle's sound system includes a panel sound module; the panel sound module is any one of a piezoelectric sound module, an electromagnetic induction sound module and a speaker.

[0153] In the embodiment of the present application, further, Figure 7 is a second schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application. As shown in Figure 7, the electronic device 10 proposed in the embodiment of the present application may also include a processor 16 and a memory 17 storing executable instructions of the processor 16; further, the electronic device 10 may also include a communication interface 18, and a bus 19 for connecting the processor 16, the memory 17 and the communication interface 18.

[0154] In an embodiment of the present application, the processor 16 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor function may also be other, and the embodiment of the present application is not specifically limited. The electronic device 10 may further include a memory 17, which may be connected to the processor 16, wherein the memory 17 is used to store executable program code, the program code including computer operating instructions, and the memory 17 may include a high-speed RAM memory, and may also include a non-volatile memory, for example, at least two disk memories.

[0155] In the embodiment of the present application, the bus 19 is configured to connect the communication interface 18 , the processor 16 , and the memory 17 , and to facilitate mutual communication between these devices.

[0156] In the embodiment of the present application, the memory 17 is configured to store instructions and data.

[0157] Furthermore, in an embodiment of the present application, the above-mentioned processor 16 is configured to obtain image information; perform comparison processing based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result; if the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, then the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

[0158] In practical applications, the memory 17 may be a volatile memory, such as a random-access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 16.

[0159] In addition, the functional modules in this embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or software functional modules.

[0160] If the integrated unit is implemented as a software functional module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, or the portion that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method of this embodiment. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0161] The embodiment of the present application provides an electronic device, which obtains image information; performs a comparison process based on the identification information of the image information and pre-stored identification information to obtain a first comparison result; if the first comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word. As can be seen from this, the present application stores the identification information corresponding to the image information whose entry has been obtained by setting pre-stored identification information, and then when obtaining the instruction word for any image information, the identification information of the image information can be first compared with the pre-stored identification information. When the comparison result is that the pre-stored identification information contains the same first identification information as the identification information of the image information, the entry information corresponding to the first identification information is directly determined as the first instruction word corresponding to the image information, thereby completing the instruction word extraction of the image information, without having to perform relevant recognition and scanning on the image information each time the instruction word extraction of the image information is performed, which can greatly reduce the time spent on obtaining the instruction word for the same image, effectively improve the efficiency of instruction word acquisition, and thus improve the timeliness of voice interaction.

[0162] Specifically, the program instructions corresponding to the method for obtaining a command word for voice interaction in this embodiment can be stored on a storage medium such as a CD, a hard disk, or a USB flash drive. When the program instructions corresponding to the method for obtaining a command word for voice interaction in the storage medium are read or executed by an electronic device, the following steps are included:

[0163] Obtain image information;

[0164] performing a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result;

[0165] If the first comparison result is that there is first identification information in the pre-stored identification information that is identical to the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

[0166] An embodiment of the present application provides a chip, which includes a programmable logic circuit and / or program instructions. When the chip is running, the method for obtaining instruction words for voice interaction described above is implemented, specifically including the following steps:

[0167] Obtain image information;

[0168] performing a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result;

[0169] If the first comparison result is that the pre-stored identification information contains first identification information that is identical to the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

[0170] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0171] The present application is described with reference to the implementation flow diagram and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each flow and / or box in the flow diagram and / or block diagram and the combination of the flow and / or box in the flow diagram and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow diagram or multiple flows and / or one block or multiple blocks of the block diagram.

[0172] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in implementing one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0173] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0174] The above description is merely a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application.

Claims

1. A method for acquiring command words for voice interaction, the method comprising: Get image information; Performing a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result; If the first comparison result is that there is first identification information in the pre-stored identification information that is the same as the identification information of the image information, the entry information corresponding to the first identification information is determined as the first instruction word corresponding to the image information, so as to perform voice interaction based on the first instruction word.

2. The method according to claim 1, wherein: The method further comprises: Searching is performed in pre-stored entry information according to the first identification information to obtain entry information corresponding to the first identification information; wherein different entry information in the pre-stored entry information corresponds to different identification information.

3. The method according to claim 2, wherein: After performing a comparison process based on the identification information of the image information and the pre-stored identification information to obtain a first comparison result, the method further includes: If the first comparison result is that the first identification information does not exist in the pre-stored identification information, recognition processing is performed based on the image information to obtain the first instruction word.

4. The method according to claim 3, wherein: If the first comparison result is that the first identification information does not exist in the pre-stored identification information, then performing recognition processing according to the image information, after obtaining the first instruction word, the method further includes: The first instruction word is added to the pre-stored entry information.

5. The method according to claim 4, wherein: The method further comprises: Determine identification information of the image information, and add the identification information of the image information to the pre-stored identification information.

6. The method according to claim 4 or 5, wherein: The method further comprises: Get preset image information; Determine identification information corresponding to the preset image information and entry information corresponding to the preset image information; Obtaining the pre-stored identification information according to the identification information corresponding to the preset image information; The pre-stored entry information is obtained according to the entry information corresponding to the preset image information.

7. The method according to claim 1, wherein: After acquiring the image information, the method further includes: Performing segmentation processing on the image information to obtain segmented sub-images; Performing a comparison process based on the identification information corresponding to the segmented sub-image and the pre-stored identification information to obtain a second comparison result; A second instruction word corresponding to the segmented sub-image is determined according to the second comparison result.

8. The method according to claim 7, wherein: The determining, according to the second comparison result, a second instruction word corresponding to the segmented sub-image comprises: If the second comparison result is that the second identification information identical to the identification information corresponding to the segmented sub-image does not exist in the pre-stored identification information, performing recognition processing according to the segmented sub-image to obtain the second instruction word; If the second comparison result is that the second identification information exists in the pre-stored identification information, the entry information corresponding to the second identification information is determined as the second instruction word corresponding to the segmented sub-image.

9. The method according to claim 8, wherein: The method further comprises: A search process is performed in pre-stored entry information according to the second identification information to obtain the entry information corresponding to the second identification information.

10. The method according to claim 9, wherein: The pre-stored entry information includes entry information obtained based on complete image information and / or entry information corresponding to segmented image information.

11. The method according to claim 3 or 8, wherein: The method further comprises: The recognition process is performed through an image recognition interface to obtain the first instruction word or the second instruction word.

12. The method according to claim 1 or 7, wherein: The method further comprises: In response to the wake-up instruction, the image information is acquired to execute the comparison processing flow.

13. The method according to any one of claims 1 to 5, wherein: The identification information of the image information is an MD5 value; The pre-stored identification information includes MD5 values ​​of different images.

14. The method according to claim 1, wherein: The method further comprises: The voice interaction is performed based on the vehicle's sound system and the first command word; wherein the vehicle's sound system includes a panel sound module; the panel sound module is any one of a piezoelectric sound module, an electromagnetic induction sound module and a speaker.

15. An electronic device, comprising a processor and a memory storing instructions executable by the processor; when the instructions are executed by the processor, the method according to any one of claims 1 to 14 is implemented.

16. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 14 is implemented.

Images