Vehicle document identification and analysis system and method

Abstract

The invention discloses a document recognition and analysis system and method for a vehicle. The system comprises an in-vehicle camera, an in-vehicle character recognition module, a character processing module and a vehicle machine interface. The in-vehicle camera is used for photographing the document file and transmitting an image to the in-vehicle character recognition module; the in-vehicle character recognition module is used for recognizing and extracting characters in the image and transmitting the characters to the character processing module; the character processing module is used for analyzing characters, obtaining character analysis results and transmitting the character analysis results to the vehicle machine interface; the vehicle-mounted machine interface is used for displaying the character analysis result. By means of the existing camera and the vehicle machine interface in the cabin, function decomposition and replacement of special equipment are achieved through embedding of the character recognition module and communication between the vehicle and the large model, in-vehicle document recognition is achieved, and the convenience and life of document recognition are improved.

Description

Technical Field

[0001] This application relates to the technical field of automobiles, and more specifically, to a document recognition and analysis system and method for vehicles. Background Art

[0002] Document recognition technology has currently been applied in the education and medical industries, but it is limited by proprietary equipment and fixed scenarios, and cannot be widely used in daily life, including in the automotive industry. Summary of the Invention

[0003] This application provides a document recognition and analysis system and method for vehicles. By leveraging the existing cameras and in-vehicle infotainment (IVI) interfaces in the cockpit, through the embedding of a text recognition module and the communication between the vehicle and a large model, the functions of dedicated equipment are decomposed and replaced, enabling in-vehicle document recognition and improving the convenience and applicability of document recognition in daily life.

[0004] This application provides a document recognition and analysis system for vehicles, including an in-vehicle camera, an in-vehicle text recognition module, a text processing module, and an IVI interface;

[0005] The in-vehicle camera is used to take pictures of document files and transmit the images to the in-vehicle text recognition module;

[0006] The in-vehicle text recognition module is used to recognize and extract the text in the images and transmit the text to the text processing module;

[0007] The text processing module is used to analyze the text, obtain the text analysis result, and transmit it to the IVI interface;

[0008] The IVI interface is used to display the text analysis result.

[0009] Preferably, the IVI interface is further used to display the images and receive the user's confirmation information for the images.

[0010] Preferably, the text processing module is a cloud-based large model.

[0011] Preferably, the text analysis result displayed on the IVI interface is audio information, picture information, or video information.

[0012] Preferably, the IVI interface is further used to receive the user's confirmation information for the text analysis result.

[0013] Preferably, the IVI interface is further used to send the text analysis result to a mobile terminal.

[0014] Preferably, the IVI interface includes a user recognition module, a display model determination module, and a display module;

[0015] The user recognition module is used to recognize user information through the in-vehicle camera;

[0016] The display model determination module is used to determine the corresponding display model according to user information;

[0017] The display module is used to display the text analysis result with the display model as the carrier.

[0018] This application also provides a method for document recognition and analysis of a vehicle, including:

[0019] Taking a photo of the document file with an in-vehicle camera to obtain an image;

[0020] Using the in-vehicle text recognition module to recognize the text in the image;

[0021] Analyzing the text to obtain a text analysis result;

[0022] Using the vehicle-mounted interface to display the text analysis result.

[0023] Preferably, the method for document recognition and analysis of a vehicle further includes:

[0024] Using the vehicle-mounted interface to display the image;

[0025] Using the vehicle-mounted interface to receive the user's confirmation information for the image;

[0026] If positive information for the image is received, then use the in-vehicle text recognition module to recognize the text in the image.

[0027] Preferably, the method for document recognition and analysis of a vehicle further includes:

[0028] Using the vehicle-mounted interface to receive the user's confirmation information for the text analysis result;

[0029] If negative information for the text analysis result is received, then re-execute the document recognition process.

[0030] Preferably, the method for document recognition and analysis of a vehicle further includes:

[0031] Using the vehicle-mounted interface to send the text analysis result to a mobile terminal.

[0032] Preferably, the text analysis result displayed on the vehicle-mounted interface is audio information, picture information or video information.

[0033] Preferably, the vehicle-mounted interface displays the text analysis result, specifically including:

[0034] Recognizing user information through the in-vehicle camera;

[0035] Confirming the corresponding display model according to the user information;

[0036] Displaying the text analysis result with the display model as the carrier.

[0037] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. Description of the Drawings

[0038] The drawings incorporated in and forming a part of this specification illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application.

[0039] Figure 1 Structural diagram of the vehicle document recognition and analysis system provided by the present application;

[0040] Figure 2 Flowchart of the vehicle document recognition and analysis method provided by the present application. Detailed Embodiments

[0041] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present application.

[0042] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way a limitation on the present application or its application or use.

[0043] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be considered as part of the specification.

[0044] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Accordingly, other examples of exemplary embodiments may have different values.

[0045] The present application provides a vehicle document recognition and analysis system and method. By means of the existing cameras and in-vehicle interfaces in the cockpit, through the embedding of the text recognition module and the communication between the vehicle and the large model, the function decomposition and replacement of dedicated devices are realized, and in-vehicle document recognition is achieved, improving the convenience and life-friendliness of document recognition.

[0046] As Figure 1 shown, the vehicle document recognition and analysis system provided by the present application includes an in-vehicle camera 110, an in-vehicle text recognition module 120, a text processing module 130, and an in-vehicle interface 140.

[0047] The in-vehicle camera 110 is used to take pictures of document files and transmit the images to the in-vehicle text recognition module.

[0048] As an example, the video signal captured by the codec chip in the camera is converted into a digital signal and transmitted to the codec chip in the in-vehicle computer for image recognition. The shooting, signal conversion, and image recognition of the in-vehicle camera for document files are existing facilities in the intelligent cockpit and belong to the prior art.

[0049] The document files include but are not limited to test papers, homework questions, physical examination reports, laboratory test reports, children's picture books, etc.

[0050] The in-vehicle text recognition module 120 is used to recognize and extract the text in the image and transmit the text to the text processing module.

[0051] As an example, the in-vehicle text recognition module 120 realizes the recognition and extraction of the text in the image through OCR (Optical Character Recognition) technology.

[0052] The text processing module 130 is used to analyze the text, obtain the text analysis result and transmit it to the in-vehicle computer interface.

[0053] The text processing module 130 is used to perform corresponding matching on the text, obtain the processing result corresponding to the text, and play an auxiliary role for the user in reading, analyzing, parsing, etc.

[0054] For example, for physical examination reports, laboratory test reports, etc., the text processing module 130 recognizes the abnormal detection items in the physical examination report and laboratory test report, and analyzes the abnormal detection items to obtain the analysis result of the physical examination report or laboratory test report, such as the predicted diseases, infection types, and targeted diet and life precautions, etc.

[0055] For test papers, homework questions, etc., the text processing module 130 corrects the test papers and homework questions and retrieves the answer teaching of the test papers and homework questions, etc.

[0056] For children's picture books, the text processing module 130 converts the text in the children's picture book into an audio or video format for story playback.

[0057] As an example, the text processing module is a cloud large model. The in-vehicle text recognition module 120 transmits the recognized result to the cloud large model in the form of an API interface. An encryption algorithm is required when uploading to the cloud large model to ensure information security.

[0058] The in-vehicle computer interface 140 is used to display the text analysis result.

[0059] As an example, the text analysis results displayed on the in-vehicle device interface are audio information (such as the analysis results of physical examination reports and laboratory test sheets, the teaching of answers to test papers and homework questions, and the story-playing audio of children's picture books, etc.), picture information (such as the marking results of test papers and homework questions, etc.) or video information (such as playing the analysis results of physical examination reports and laboratory test sheets, the teaching of answers to test papers and homework questions, and the story-playing video of children's picture books through the video APP in the in-vehicle device, etc.).

[0060] To increase the personalization and interestingness of the document recognition effect, preferably, the in-vehicle device interface includes a user recognition module 1401, a display model determination module 1402, and a display module 1403.

[0061] The user recognition module 1401 is used to recognize user information through the in-vehicle camera, such as estimating the user's age, recognizing the user's gender, obtaining the user's identity through face recognition, etc.

[0062] The display model determination module 1402 is used to determine the corresponding display model according to the user information. The display model has styles, tones, images, etc. adapted to the user information, which can be searched in real time through the network or the doll images preset in the in-vehicle device.

[0063] The display module 1403 is used to display the text analysis results with the display model as the carrier.

[0064] Preferably, the in-vehicle device interface 140 is also used to display images and receive the user's confirmation information for the images. The images of the documents collected by the camera are displayed to the user through the in-vehicle device interface 140, and the user checks the images to confirm whether the camera has captured the correct document file or whether the images are clear. If the shooting is incorrect or the images are not clear, the user can give negative information about the images through the in-vehicle device interface 140 (such as by clicking the "Retake" button), and re-execute the document recognition process of this application, that is, the in-vehicle camera re-shoots the document file. If the shooting is correct and the images are clear, the user can give positive information about the images through the in-vehicle device interface 140 (such as by clicking the "Confirm" button), and then transmit the images to the in-vehicle text recognition module 120.

[0065] Based on the above, preferably, the in-vehicle device interface 140 is also used to receive the user's confirmation information for the text analysis results. If the text analysis results reach the expected effect, the user inputs positive information about the text analysis results through the in-vehicle device interface 140 (such as by clicking the "Satisfied" button) to end the process; otherwise, the user inputs negative information about the text analysis results through the in-vehicle device interface (such as by clicking the "Dissatisfied" button), and re-execute the document recognition process of this application, that is, the in-vehicle camera re-shoots the document file.

[0066] Preferably, the in-vehicle device interface 140 is further configured to send the text analysis result to the mobile terminal 150, facilitating the user to receive the document recognition result from multiple channels.

[0067] Based on the above, the present application further provides a method for document recognition and analysis of a vehicle. As Figure 2 shown, the document recognition and analysis method includes:

[0068] S210: Take a photo of the document file using the in-vehicle camera to obtain an image.

[0069] S240: Use the in-vehicle text recognition module to recognize the text in the image.

[0070] S250: Analyze the text to obtain a text analysis result.

[0071] S260: Use the in-vehicle device interface to display the text analysis result.

[0072] As an embodiment, the text analysis result displayed by the in-vehicle device interface is audio information, picture information or video information.

[0073] Preferably, the document recognition and analysis method further includes:

[0074] S220: Use the in-vehicle device interface to display the image.

[0075] S230: Use the in-vehicle device interface to receive the confirmation information of the user for the image. If the positive information of the image is received, execute S240, and use the in-vehicle text recognition module to recognize the text in the image; if the negative information of the image is received, return to S210 and re-execute the document recognition process.

[0076] Preferably, the document recognition and analysis method further includes:

[0077] S270: Use the in-vehicle device interface to receive the confirmation information of the user for the text analysis result. If the positive information of the text analysis result is received, end the process; if the negative information of the text analysis result is received, return to S210 and re-execute the document recognition process.

[0078] Preferably, the document recognition and analysis method further includes:

[0079] S280: If the positive information of the text analysis result is received, use the in-vehicle device interface to send the text analysis result to the mobile terminal, and then end the process.

[0080] Preferably, in S260, when the in-vehicle device interface displays the text analysis result, it specifically includes:

[0081] S2601: Identify the user information through the in-vehicle camera;

[0082] S2602: Confirm the corresponding display model according to the user information;

[0083] S2603: Use the display model as a carrier to display the text analysis results.

[0084] Although some specific embodiments of the present application have been described in detail through examples, those skilled in the art should understand that the above examples are only for illustration and not for limiting the scope of the present application. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. A document recognition and analysis system for a vehicle, characterized in that It includes an in-vehicle camera, an in-vehicle text recognition module, a text processing module, and a vehicle head unit interface; The in-vehicle camera is used to take pictures of document files and transmit the images to the in-vehicle text recognition module; The in-vehicle text recognition module is used to recognize and extract the text in the images and transmit the text to the text processing module; The text processing module is used to analyze the text, obtain a text analysis result and transmit it to the vehicle head unit interface; The vehicle head unit interface is used to display the text analysis result.

2. The document recognition and analysis system for a vehicle according to claim 1, wherein The vehicle head unit interface is also used to display the image and receive the user's confirmation information about the image.

3. The document recognition and analysis system for a vehicle according to claim 1, wherein, The text processing module is a cloud-based large model.

4. The document recognition and analysis system for a vehicle according to claim 1, characterized in that The text analysis result displayed by the vehicle head unit interface is audio information, picture information or video information.

5. The document recognition and analysis system for a vehicle according to claim 1, wherein The vehicle head unit interface is also used to receive the user's confirmation information about the text analysis result.

6. A method for document recognition and analysis of a vehicle, characterized in that It includes: Using the in-vehicle camera to take pictures of document files to obtain images; Using the in-vehicle text recognition module to recognize the text in the images; Analyzing the text to obtain a text analysis result; Using the vehicle head unit interface to display the text analysis result.

7. The method for document recognition and analysis of a vehicle according to claim 6, wherein It also includes: Using the vehicle head unit interface to display the image; Using the vehicle head unit interface to receive the user's confirmation information about the image; If a positive message about the image is received, use the in-vehicle text recognition module to recognize the text in the image.

8. The method for document recognition and analysis of a vehicle according to claim 6, wherein It also includes: Using the vehicle head unit interface to receive the user's confirmation information about the text analysis result; If a negative message about the text analysis result is received, re-execute the document recognition process.

9. The method for document recognition and analysis of a vehicle according to claim 6, characterized in that, It also includes: Using the vehicle head unit interface to send the text analysis result to the mobile terminal.

10. The method for document recognition and analysis of a vehicle according to claim 6, characterized in that The text analysis result displayed by the vehicle head unit interface is audio information, picture information or video information.

Images