Non-motor vehicle certification identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a non-motor vehicle certification identification method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and the field of financial science and technology. The method comprises the following steps: acquiring a vehicle certificate image of a non-motor vehicle; obtaining the vehicle type of the non-motor vehicle, and obtaining a target vehicle type; wherein the target vehicle category is used for indicating an area to which the non-motor vehicle belongs and the number of wheels; determining a target character recognition template according to the target vehicle category; performing field identification on the vehicle certification image according to the target character identification template to obtain a target identification field character; determining a target field reading rule according to the target vehicle category; and performing field reading on the target identification field character according to the target field reading rule to obtain target certification field attribute data. According to the embodiment of the invention, automatic identification of the vehicle certificate of the non-motor vehicle can be realized.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence technology and financial technology, and in particular to a non-motor vehicle certificate recognition method and device, electronic equipment, and storage medium. Background Art

[0002] Vehicle insurance requires the entry of vehicle certificates. The process of motor vehicle insurance includes a step of scanning the vehicle certificate, which is mainly completed by entering the certificate information through information recognition through a neural network model. However, there is no step of scanning the vehicle certificate in the process of non-motor vehicle insurance. At present, for non-motor vehicles, it is necessary to manually enter the relevant information of the vehicle certificate, such as model, license plate number, frame number, motor number, vehicle structure and other fields.

[0003] There are many types of non-motor vehicles, such as two-wheeled, three-wheeled, and four-wheeled vehicles. Different types of vehicle certificates have different formats. In addition, even if they are all two-wheeled, three-wheeled, or four-wheeled, the formats of non-motor vehicle certificates in different regions are generally different. Based on these factors, the existing technology cannot realize automatic recognition of non-motor vehicle certificates. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a non-motor vehicle certificate recognition method and device, electronic equipment, and storage medium, which can realize automatic recognition of the vehicle certificate of a non-motor vehicle.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a non-motor vehicle certificate recognition method, the method comprising:

[0006] Obtaining a vehicle certificate image of a non-motor vehicle;

[0007] Acquire the vehicle type of the non-motor vehicle to obtain a target vehicle category; wherein the target vehicle category is used to indicate the region to which the non-motor vehicle belongs and the number of wheels;

[0008] Determining a target character recognition template according to the target vehicle category;

[0009] Performing field recognition on the vehicle certificate image according to the target character recognition template to obtain target recognition field characters;

[0010] Determine a target field reading rule according to the target vehicle category;

[0011] The target identification field characters are read according to the target field reading rule to obtain the target certificate field attribute data.

[0012] In some embodiments, the target certificate field attribute data includes target license plate number field attribute data, the target field reading rule includes a license plate number reading rule, the license plate number reading rule includes a license plate number region reading sub-rule, a license plate number number reading sub-rule and a sub-rule reading order, the sub-rule reading order indicates the reading order of the license plate number region reading sub-rule and the license plate number number reading sub-rule;

[0013] The step of reading the target identification field characters according to the target field reading rule to obtain the target certificate data includes:

[0014] According to the sub-rule reading order, one of the license plate number region reading sub-rule and the license plate number serial number reading sub-rule is taken as the target sub-rule in turn;

[0015] According to the target sub-rule being the license plate number area reading sub-rule, the target recognition field characters are read to obtain the license plate number area field attribute data;

[0016] According to the target sub-rule being the license plate number reading sub-rule, the target recognition field characters are read to obtain the license plate number field attribute data;

[0017] Data splicing is performed based on the license plate number region field attribute data and the license plate number number field attribute data to obtain the target license plate number field attribute data.

[0018] In some embodiments, the license plate number regional reading sub-rule includes regional character reading templates for at least two levels of sub-regions and a reading order for the sub-regions at each level;

[0019] The target sub-rule is the license plate number area reading sub-rule, and the target recognition field characters are read to obtain the license plate number area field attribute data, including:

[0020] Perform field reading on the target recognition field characters according to the reading order of each level of the sub-region and the regional character reading template to obtain a sub-region reading field;

[0021] The sub-region read fields are spliced ​​according to the reading order of the sub-regions at each level to obtain the license plate number region field attribute data.

[0022] In some embodiments, after performing field reading on the target identification field characters according to the target field reading rule to obtain target certificate field attribute data, the method further includes:

[0023] Obtaining an initial insurance policy for the non-motor vehicle; wherein the initial insurance policy includes fields for filling in requirements;

[0024] Perform field name matching on the fill-in requirement field and each candidate field attribute data of the target certificate field attribute data to obtain a field name matching result;

[0025] If the field name matching result indicates that the filling requirement field matches the attribute data of the candidate field, then the filling requirement field is updated according to the attribute data of the candidate field to obtain the attribute data of the target filling field;

[0026] Update the initial insurance application form according to the target filled-in field attribute data to obtain a target insurance application form;

[0027] Insure the non-motor vehicle according to the target insurance policy.

[0028] In some embodiments, after performing field name matching on the fill-in requirement field and each candidate field attribute data of the target certificate field attribute data to obtain a field name matching result, the method further includes:

[0029] If the field name matching result indicates that the filling requirement field does not match any of the candidate field attribute data, a first prompt message is generated according to the filling requirement field; wherein the first prompt message is used to prompt that the filling requirement field cannot be identified;

[0030] Receiving the target supplementary vehicle image of the non-motor vehicle; wherein the target supplementary vehicle image includes a vehicle area corresponding to the filling requirement field;

[0031] Performing image recognition on the target supplement vehicle image to obtain target supplement field attribute data;

[0032] The filling requirement field is updated according to the target supplementary field attribute data to obtain the target filling field attribute data.

[0033] In some embodiments, after performing field name matching on the fill-in requirement field and each candidate field attribute data of the target certificate field attribute data to obtain a field name matching result, the method further includes:

[0034] If the field name matching result indicates that each of the required filling fields does not match any of the candidate field attribute data, then the vehicle certificate image is subjected to failure cause detection to obtain certificate recognition failure cause data; wherein the certificate recognition failure cause data is used to characterize the cause of the certificate recognition failure;

[0035] Generate second prompt information according to the certificate recognition failure reason data; wherein, the second prompt information is used to prompt the reason for the certificate recognition failure.

[0036] In some embodiments, if the field name matching result indicates that each of the filling requirement fields does not match any of the candidate field attribute data, then after performing failure reason detection on the vehicle certificate image to obtain certificate recognition failure reason data, the method further includes:

[0037] If the certificate recognition failure reason data indicates that the clarity of the vehicle certificate image is less than a preset clarity threshold, a first image shooting guide is generated; the first image shooting guide is used to guide the shooting of a vehicle certificate image with a clarity greater than or equal to the clarity threshold;

[0038] If the certificate recognition failure reason data indicates that the size of the vehicle certificate image is smaller than a preset size threshold, a second image shooting guide is generated; the second image shooting guide is used to guide the shooting of a vehicle certificate image whose size is greater than or equal to the size threshold;

[0039] If the certificate recognition failure reason data indicates that the vehicle certificate image does not include the non-motor vehicle certificate, a third image shooting guide is generated; the third image shooting guide is used to guide the shooting of the vehicle certificate image including the non-motor vehicle certificate.

[0040] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a non-motor vehicle certificate recognition device, the device comprising:

[0041] A certificate acquisition module, used to acquire a vehicle certificate image of a non-motor vehicle;

[0042] A type determination module, used to obtain the vehicle type of the non-motor vehicle and obtain a target vehicle category; wherein the target vehicle category is used to indicate the region to which the non-motor vehicle belongs and the number of wheels;

[0043] A template determination module, used to determine a target character recognition template according to the target vehicle category;

[0044] A field recognition module, used for performing field recognition on the vehicle certificate image according to the target character recognition template to obtain target recognition field characters;

[0045] A rule determination module, used for determining a target field reading rule according to the target vehicle category;

[0046] The field reading module is used to read the target identification field characters according to the target field reading rule to obtain the target certificate field attribute data.

[0047] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the non-motor vehicle certificate identification method described in the first aspect when executing the computer program.

[0048] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the non-motor vehicle certificate identification method described in the first aspect above.

[0049] The non-motor vehicle certificate recognition method, non-motor vehicle certificate recognition device, electronic device and storage medium proposed in the present application, in addition to obtaining the vehicle certificate image, also need to obtain the target vehicle category. According to the target vehicle category, the target character recognition template and the target field reading rule can be determined. In this way, the target recognition field characters can be first identified according to the target character recognition template, also known as global recognition. Then, the target certificate field attribute data can be identified according to the target field reading rule, also known as local recognition. In summary, this embodiment can realize the automatic recognition of the vehicle certificate of a non-motor vehicle.

[0050] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a non-motor vehicle certificate recognition method provided in an embodiment of the present application;

[0052] Figure 2 yes Figure 1 Flowchart of step 106 in

[0053] Figure 3 yes Figure 2 Flowchart of step 202 in FIG.

[0054] Figure 4 is a flow chart of a non-motor vehicle certificate recognition method provided by another embodiment of the present application;

[0055] Figure 5 is a flow chart of a non-motor vehicle certificate recognition method provided by another embodiment of the present application;

[0056] Figure 6 is a flow chart of a non-motor vehicle certificate recognition method provided by another embodiment of the present application;

[0057] Figure 7 It is a module structure block diagram of a non-motor vehicle certificate recognition device provided in an embodiment of the present application;

[0058] Figure 8 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] First, some nouns involved in this application are analyzed:

[0063] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0064] Natural language processing (NLP): NLP uses computers to process, understand and apply human languages ​​(such as Chinese and English). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is often used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information image processing, information extraction and filtering, text classification and clustering, public opinion analysis and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0065] The number of non-motor vehicle policies of insurance companies has gradually increased. For example, the number of policies in some areas has reached 150,000 per year. Currently, the source of non-motor vehicle business models includes scattered orders, license plates, and vehicle inspections, which have high requirements for timeliness when issuing policies. For example, in the vehicle inspection scenario, it is usually necessary to check the vehicle on site and issue the policy on site, and customers have high requirements for the timeliness of issuing policies.

[0066] However, the related technology requires manual input of vehicle certificate related information for non-motor vehicles, such as model, license plate number, frame number, motor number, vehicle structure, etc. The related technology cannot realize automatic recognition of vehicle certificates for non-motor vehicles.

[0067] Based on this, the embodiments of the present application propose a non-motor vehicle certificate recognition method and device, electronic equipment, and storage medium, which can realize automatic recognition of the vehicle certificate of a non-motor vehicle.

[0068] The non-motor vehicle certificate recognition method provided in the embodiment of the present application can be applied to the terminal and the server side, and can also be software running on the server side. The server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the non-motor vehicle certificate recognition method, but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: server computers, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] The embodiments of the present application provide a non-motor vehicle certificate recognition method and a non-motor vehicle certificate recognition device, an electronic device, and a storage medium, which are specifically explained through the following embodiments. First, the non-motor vehicle certificate recognition method in the embodiments of the present application is described.

[0071] It should be noted that in each specific implementation method of the present application, when it comes to performing relevant processing based on the user's voice data or other data related to the user's identity or characteristics, the user's permission or consent must be obtained first, and the collection, use and processing of such data will comply with relevant laws, regulations and standards.

[0072] Reference Figure 1 , Figure 1 It is an optional flow chart of the non-motor vehicle certificate identification method provided in an embodiment of the present application, which may include but is not limited to steps 101 to 106.

[0073] Step 101, obtaining a vehicle certificate image of a non-motor vehicle;

[0074] Step 102, obtaining the vehicle type of the non-motor vehicle to obtain the target vehicle category;

[0075] Step 103, determining a target character recognition template according to the target vehicle category;

[0076] Step 104, performing field recognition on the vehicle certificate image according to the target character recognition template to obtain target recognition field characters;

[0077] Step 105, determining a target field reading rule according to the target vehicle category;

[0078] Step 106, read the target identification field characters according to the target field reading rule to obtain the target certificate field attribute data.

[0079] Steps 101 to 106 shown in the embodiment of the present application set corresponding character recognition templates and field reading rules for non-motor vehicles of different vehicle types in advance. During actual certificate recognition, in addition to obtaining the vehicle certificate image, it is also necessary to obtain the target vehicle category. According to the target vehicle category, the target character recognition template and target field reading rules are determined from the pre-set character recognition templates and field reading rules. In this way, the target recognition field characters can be first identified based on the target character recognition template, which is also called global recognition. Then, the target certificate field attribute data is identified based on the target field reading rules, which is also called local recognition. In summary, this embodiment can realize automatic recognition of vehicle certificates of non-motor vehicles.

[0080] In step 101 of some embodiments, a vehicle certificate image of a non-motor vehicle is obtained. A non-motor vehicle refers to a means of transportation that does not rely on a motor vehicle power system. Non-motor vehicles generally include the following categories: electric bicycles, electric tricycles, and electric four-wheel vehicles. A vehicle certificate image refers to an image containing the vehicle's certificate information. A vehicle's certificate is a document issued by the manufacturer or relevant agency that certifies that the vehicle complies with regional safety, environmental protection, and technical standards. The certificate generally contains the following information: (1) Basic vehicle information: including brand, model, production date, vehicle identification code (VIN), etc. (2) Manufacturer information: manufacturer's name, address, and contact information. (3) Qualification standards: industry standards that the vehicle complies with, such as safety standards, emission standards, etc. (4) Inspection results: the results of various inspections and tests that the vehicle has undergone.

[0081] In one embodiment, the vehicle certificate image can be obtained in the following ways: (1) an image acquisition unit (such as a camera) pre-deployed on the terminal is used to acquire an image of the non-motor vehicle certificate to obtain the vehicle certificate image. (2) the vehicle certificate image is uploaded through a file upload interface pre-deployed on the terminal.

[0082] In one example, the above process of obtaining the vehicle certificate image of a non-motor vehicle may include: (1) For non-motor vehicle products, add a "Scan vehicle certificate record" button icon. (2) The user first clicks the button, and calls to select a file to upload or take a photo according to the current record environment. (3) Select the certificate and obtain the upload token. (4) Carry the upload token, key and other information and upload it to the file storage platform. (5) Apply to download the source file. Based on the requested information, the file storage platform generates and calculates the signature string, compares it with the signature requested by the client, and performs authentication. (6) After the file is successfully downloaded, the vehicle certificate image is obtained.

[0083] In step 102 of some embodiments, the vehicle type of the non-motor vehicle is obtained to obtain a target vehicle category. The target vehicle category is used to indicate the region to which the non-motor vehicle belongs and the number of wheels. For example, the region includes region A and region B, and the number of wheels includes 2, 3, and 4, then the target vehicle category includes any one of the following: 2 wheels in region A, 3 wheels in region A, 4 wheels in region A, 2 wheels in region B, 3 wheels in region B, and 4 wheels in region B.

[0084] In one embodiment, the target vehicle category can be obtained in the following manner: (1) obtaining the location information of the non-motor vehicle, and determining the region to which the non-motor vehicle belongs based on the location information; obtaining the appearance image of the non-motor vehicle, and performing wheel recognition on the appearance image to obtain the number of wheels of the non-motor vehicle; performing data splicing based on the region to which the non-motor vehicle belongs and the number of wheels of the non-motor vehicle to obtain the target vehicle category. (2) performing vehicle type recognition on the vehicle certificate image using a pre-trained target image classification model to obtain the target vehicle category.

[0085] In one embodiment, the target image classification model can be trained in the following manner: collect non-motor vehicle certificates of different vehicle types, set a corresponding category label for each certificate as an image category data set; train the initial image classification model according to the image category data set to obtain the target image classification model.

[0086] In step 103 of some embodiments, a target character recognition template is determined according to the target vehicle category. Different vehicle types correspond to different character recognition templates. The target character recognition template is a character recognition template corresponding to the target vehicle category. A recognition template generally refers to a pattern or model used in optical character recognition (OCR) technology to recognize and parse text characters in an image. The main functions and features of a character recognition template include: (1) Pattern matching: The template contains the shapes and features of various characters, which are used to compare with the characters in the input image to identify the corresponding text. (2) Feature extraction: During the character recognition process, the template can help extract key features of the characters, such as edges, corners, and contours, to improve recognition accuracy. (3) Classifier: The character recognition template can be used as part of a classifier to help the system determine which category the input character belongs to (e.g., letters, numbers, etc.). By using character recognition templates, the OCR system can convert text in an image into editable and searchable digital text, thereby improving the efficiency of information processing.

[0087] In one embodiment, step 103 specifically includes: searching a preset category template mapping library according to the target vehicle category to obtain a target character recognition template. The category template mapping library is used to indicate the mapping relationship between the vehicle type and the character recognition template.

[0088] In step 104 of some embodiments, field recognition is performed on the vehicle certificate image according to the target character recognition template to obtain the target recognition field characters. Fuzzy matching and renaming are performed during field recognition, and the field names are output uniformly. Specifically, the field characters recognized by OCR need to be compared with the field characters of the template to match the corresponding data, but the recognized field characters are often not 100% the same. The field characters may be incomplete or have different spellings. Matching needs to be achieved by approximate comparison of strings, such as using regular expressions and wildcards.

[0089] In step 105 of some embodiments, the target field reading rule is determined according to the target vehicle category. The formats of different regions are different, and the formats of different numbers of wheels are also different, resulting in different processes of reading field attribute data from the target identification field characters, that is, different field reading rules. The target field reading rule is a field reading rule corresponding to the target vehicle category. The target field reading rule includes license plate number reading rules and frame number reading rules, etc. The target field reading rule can be customized, such as custom configuration length and regular logic, which can greatly reduce the time of manual development. The configuration of aircraft vehicles with different numbers of wheels in different regions corresponds to different field reading rules.

[0090] In step 106 of some embodiments, the target identification field characters are read according to the target field reading rule to obtain the target certificate field attribute data. The target certificate field attribute data refers to the attribute value of the field of the non-motor vehicle certificate. The target certificate field attribute data includes the target license plate number field attribute data and the target frame number field attribute data.

[0091] The license plate number reading rule is required to obtain the target license plate number field attribute data. The license plate number reading rule includes the license plate number region reading sub-rule, the license plate number number reading sub-rule, and the sub-rule reading order. The sub-rule reading order indicates the reading order of the license plate number region reading sub-rule and the license plate number number reading sub-rule. For example, the sub-rule reading order can be the license plate number region reading sub-rule first, and then the license plate number number reading sub-rule. The sub-rule reading order can also be the license plate number number reading sub-rule first, and then the license plate number region reading sub-rule.

[0092] In one embodiment, referring to Figure 2 , step 106 may include:

[0093] Step 201, according to the sub-rule reading order, one of the license plate number region reading sub-rule and the license plate number serial number reading sub-rule is taken as the target sub-rule in turn;

[0094] Step 202, according to the target sub-rule being the license plate number area reading sub-rule, field reading is performed on the target recognition field characters to obtain the license plate number area field attribute data;

[0095] Step 203, according to the target sub-rule being the license plate number reading sub-rule, the target recognition field characters are read to obtain the license plate number field attribute data;

[0096] Step 204, performing data splicing based on the license plate number region field attribute data and the license plate number field attribute data to obtain the target license plate number field attribute data.

[0097] For example, the license plate number rules for two-wheeled non-motor vehicles in area A are: XX area-digital number, and the license plate number rules for two-wheeled non-motor vehicles in area B are: digital number-XX area.

[0098] In one embodiment, step 202 specifically includes: according to the target sub-rule being the license plate number area reading sub-rule, field reading is performed on the first recognition field character in the target recognition field characters to obtain the license plate number area field attribute data. The first recognition field character refers to the field character in the target recognition field characters that has not been field read.

[0099] In one embodiment, step 203 specifically includes: according to the target sub-rule being a license plate number reading sub-rule, field reading is performed on the second recognition field character in the target recognition field character to obtain the license plate number field attribute data. The second recognition field character refers to the field character in the target recognition field character that has not been field read. The second recognition field character overlaps with the first recognition field character.

[0100] It is understandable that if step 202 is performed first and then step 203, the second recognition field character does not include the field character corresponding to the license plate number area field attribute data. If step 203 is performed first and then step 202, the first recognition field character does not include the field character corresponding to the license plate number field attribute data.

[0101] The benefit of the above-mentioned embodiment of steps 201 to 204 is that it fully takes into account the differences in license plate numbers in different regions and with different numbers of wheels, thereby improving the universality of obtaining the license plate number field attribute data.

[0102] The license plate number regional reading sub-rule includes at least two levels of regional character reading templates for sub-regions and the reading order of each level of sub-regions. Figure 3 , step 202 may include:

[0103] Step 301, performing field reading on target recognition field characters according to the reading order of each level of sub-regions and the regional character reading template to obtain the sub-region reading field;

[0104] Step 302, concatenate the sub-region read fields according to the reading order of each level of sub-regions to obtain the license plate number region field attribute data.

[0105] For example, the regional reading sub-rule of the license plate number of three-wheeled non-motor vehicles in area A is XX first-level sub-region-XX second-level sub-region. For another example, the regional reading sub-rule of the license plate number of three-wheeled non-motor vehicles in area B is XX first-level sub-region-XX second-level sub-region-XX third-level sub-region.

[0106] The benefit of the embodiment of the above steps 301 to 302 is that when reading the attribute data related to the license plate number region field, the differences in the number of sub-regions in the license plate number region and the order of sub-reading are fully considered, thereby improving the universality of obtaining the attribute data of the license plate number region field.

[0107] In one embodiment, referring to Figure 4 After step 106, the non-motor vehicle certificate recognition method provided in this embodiment may further include:

[0108] Step 401, obtaining an initial insurance policy for a non-motor vehicle, the initial insurance policy including filling in required fields;

[0109] Step 402, performing field name matching on each candidate field attribute data of the required field and the target certificate field attribute data to obtain a field name matching result;

[0110] Step 403, if the field name matching result indicates that the filling requirement field matches the candidate field attribute data, the filling requirement field is updated according to the candidate field attribute data to obtain the target filling field attribute data;

[0111] Step 404, updating the initial insurance application form according to the target filled-in field attribute data to obtain the target insurance application form;

[0112] Step 405, insuring the non-motor vehicle according to the target insurance policy.

[0113] In this embodiment, the initial insurance application form for non-motor vehicles is a type of insurance application form. The insurance application form is a part of the insurance contract and is a formal document filled out by the insured when applying for insurance from an insurance company. To insure a non-motor vehicle, it is necessary to fill in the relevant information of the non-motor vehicle, that is, the initial insurance application form includes filling in the required fields. According to whether the filled-in required fields match the attribute data of each candidate field, the target filled-in field attribute data can be updated, so that the target insurance application form can be updated, and then the non-motor vehicle can be insured according to the target insurance application form. Insurance refers to the process of an individual or organization applying to an insurance company to purchase insurance.

[0114] The benefit of the above-mentioned embodiment of steps 401 to 405 is that it can automatically insure non-motor vehicles, which not only saves labor costs but also improves the efficiency and timeliness of insurance.

[0115] In one embodiment, referring to Figure 5 After step 402, the non-motor vehicle certificate recognition method provided in this embodiment may further include:

[0116] Step 501, if the field name matching result indicates that the required field does not match the attribute data of any candidate field, then first prompt information is generated according to the required field;

[0117] Step 502, receiving a target supplementary vehicle image of a non-motor vehicle;

[0118] Step 503, performing image recognition on the target supplementary vehicle image to obtain target supplementary field attribute data;

[0119] Step 504, update the filling requirement fields according to the target supplementary field attribute data to obtain the target filling field attribute data.

[0120] Specifically, if the field name matching result indicates that the required filling field does not match any of the candidate field attribute data, it means that some required filling fields cannot be recognized. The first prompt information is used to prompt that the required filling field cannot be recognized. The target supplementary vehicle image includes a vehicle area corresponding to the required filling field.

[0121] The benefit of the above-mentioned embodiment of steps 501 to 504 is that even if the field name matching result is a mismatch, the target supplementary vehicle image can be improved to identify the target supplementary field attribute data, thereby obtaining the target filled field attribute data, thereby improving the success rate of data filling.

[0122] In one embodiment, referring to Figure 6 After step 402, the non-motor vehicle certificate recognition method provided in this embodiment may further include:

[0123] Step 601, if the field name matching result indicates that each required field does not match any candidate field attribute data, then the vehicle certificate image is detected for the failure reason to obtain certificate recognition failure reason data;

[0124] Step 602: Generate a second prompt message according to the certificate recognition failure reason data.

[0125] Specifically, if the field name matching result indicates that each required field does not match any of the candidate field attribute data, it means that the certificate recognition has failed. The vehicle certificate image can be input into a pre-trained cause detection model to detect the cause of failure, and obtain certificate recognition cause data. The certificate recognition failure cause data is used to characterize the cause of the failure of certificate recognition. The second prompt information is used to prompt the cause of the failure of certificate recognition. The certificate recognition failure cause data includes at least one of the following: the clarity of the vehicle certificate image is less than a preset clarity threshold; the size of the vehicle certificate image is less than a preset size threshold; the vehicle certificate image does not contain a non-motor vehicle certificate.

[0126] The benefit of the embodiment of the above-mentioned steps 601 to 602 is that after the certificate recognition fails, by generating a corresponding second prompt message, the user is informed of the reason for the recognition failure, which helps to improve the success rate of the next certificate recognition, avoid the user from repeating invalid recognition behaviors multiple times, and improve the user experience.

[0127] In one embodiment, after step 601, the non-motor vehicle certificate recognition method provided in this embodiment may further include:

[0128] If the certificate recognition failure reason data indicates that the clarity of the vehicle certificate image is less than a preset clarity threshold, a first image shooting guide is generated; the first image shooting guide is used to guide the shooting of a vehicle certificate image with a clarity greater than or equal to the clarity threshold;

[0129] If the certificate recognition failure reason data indicates that the size of the vehicle certificate image is smaller than a preset size threshold, a second image shooting guide is generated; the second image shooting guide is used to guide the shooting of a vehicle certificate image whose size is greater than or equal to the size threshold;

[0130] If the data on the reason for failure of certificate recognition indicates that the vehicle certificate image does not include a non-motor vehicle certificate, a third image shooting guide is generated; the third image shooting guide is used to guide the shooting of a vehicle certificate image including a non-motor vehicle certificate.

[0131] The image shooting guide is a suggestion and technique to help users obtain better image quality and effect during shooting. The image shooting guide may include at least one of the following: selecting appropriate light, selecting appropriate composition, stabilizing the camera, focusing accurately, paying attention to the background, selecting appropriate shooting angle, adjusting brightness, adjusting contrast, adjusting color, etc. The above image shooting guides can be customized to obtain the first image shooting guide, the second image shooting guide, and the third image shooting guide.

[0132] The benefit of the above embodiment is that it can guide the user to take a vehicle certificate image with better quality, thereby improving the success rate of certificate recognition.

[0133] In another embodiment, since there are many types of non-motor vehicles and their styles vary, the recognition success rate is not high. An entry for uploading photos after recognition fails is added, and attachments such as frame number photos, vehicle body appearance, etc. can be uploaded.

[0134] Based on the above embodiments, the following beneficial effects can be achieved: optimizing the non-motor vehicle recording process and adding a non-motor vehicle certificate recognition function, which helps to quickly issue insurance policies; improving the accuracy of data information extraction and analysis; and improving the customer's experience in issuing policies and the timeliness of insurance.

[0135] See also Figure 7 The embodiment of the present application also provides a non-motor vehicle certificate recognition device, which can implement the above-mentioned non-motor vehicle certificate recognition method. Figure 7 The module structure block diagram of the non-motor vehicle certificate recognition device provided in the embodiment of the present application includes: a certificate acquisition module 701, a type determination module 702, a template determination module 703, a field recognition module 704, a rule determination module 705 and a field reading module 706. The certificate acquisition module 701 is used to obtain the vehicle certificate image of the non-motor vehicle; the type determination module 702 is used to obtain the vehicle type of the non-motor vehicle and obtain the target vehicle category; wherein the target vehicle category is used to indicate the region and the number of wheels of the non-motor vehicle; the template determination module 703 is used to determine the target character recognition template according to the target vehicle category; the field recognition module 704 is used to perform field recognition on the vehicle certificate image according to the target character recognition template to obtain the target recognition field characters; the rule determination module 705 is used to determine the target field reading rules according to the target vehicle category; the field reading module 706 is used to perform field reading on the target recognition field characters according to the target field reading rules to obtain the target certificate field attribute data.

[0136] In one embodiment, the non-motor vehicle certificate recognition device also includes: an insurance module, which is used to: obtain an initial insurance application form for the non-motor vehicle; wherein the initial insurance application form includes a filling requirement field; performing field name matching on the filling requirement field and each candidate field attribute data of the target certificate field attribute data to obtain a field name matching result; if the field name matching result indicates that the filling requirement field matches the candidate field attribute data, then updating the filling requirement field according to the candidate field attribute data to obtain the target filling field attribute data; updating the initial insurance application according to the target filling field attribute data to obtain the target insurance application; and insuring the non-motor vehicle according to the target insurance application.

[0137] In one embodiment, the above-mentioned insurance module is also used for: if the field name matching result indicates that the filling requirement field does not match any candidate field attribute data, then a first prompt message is generated based on the filling requirement field; wherein the first prompt message is used to prompt that the filling requirement field cannot be recognized; receiving a target supplementary vehicle image of a non-motor vehicle; wherein the target supplementary vehicle image includes a vehicle area corresponding to the filling requirement field; performing image recognition on the target supplementary vehicle image to obtain target supplementary field attribute data; updating the filling requirement field according to the target supplementary field attribute data to obtain target filling field attribute data.

[0138] In one embodiment, the above-mentioned insurance module is also used for: if the field name matching result indicates that each required field does not match any candidate field attribute data, then the failure reason detection is performed on the vehicle certificate image to obtain the certificate recognition failure reason data; wherein the certificate recognition failure reason data is used to characterize the cause of the certificate recognition failure; generate a second prompt information according to the certificate recognition failure reason data; wherein the second prompt information is used to prompt the cause of the certificate recognition failure.

[0139] In one embodiment, the above-mentioned insurance module is also used for: if the data of the reason for failure of certificate recognition indicates that the clarity of the vehicle certificate image is less than a preset clarity threshold, then generating a first image shooting guide; the first image shooting guide is used to guide the shooting of a vehicle certificate image with a clarity greater than or equal to the clarity threshold; if the data of the reason for failure of certificate recognition indicates that the size of the vehicle certificate image is less than a preset size threshold, then generating a second image shooting guide; the second image shooting guide is used to guide the shooting of a vehicle certificate image with a size greater than or equal to the size threshold; if the data of the reason for failure of certificate recognition indicates that the vehicle certificate image does not include a certificate of a non-motor vehicle, then generating a third image shooting guide; the third image shooting guide is used to guide the shooting of a vehicle certificate image including a certificate of a non-motor vehicle.

[0140] It should be noted that the specific implementation of the non-motor vehicle certificate recognition device is basically the same as the specific implementation example of the non-motor vehicle certificate recognition method mentioned above, and will not be repeated here.

[0141] The embodiment of the present application also provides an electronic device, which includes: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned non-motor vehicle certificate recognition method. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0142] See also Figure 8 , Figure 8 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0143] The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0144] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 802, and the processor 801 calls and executes the non-motor vehicle certificate recognition method of the embodiment of this application;

[0145] Input / output interface 803, used to implement information input and output;

[0146] The communication interface 804 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0147] A bus 805 that transmits information between the various components of the device (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0148] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0149] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned non-motor vehicle certificate identification method.

[0150] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0151] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0152] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0153] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0155] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0156] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0157] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present application 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 unit may be implemented in the form of hardware or in the form of software functional units.

[0160] If the integrated unit is implemented in the form of a software functional unit and 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 the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0161] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying a non-motor vehicle certificate, characterized in that: The method comprises: Obtaining a vehicle certificate image of a non-motor vehicle; Acquire the vehicle type of the non-motor vehicle to obtain a target vehicle category; wherein the target vehicle category is used to indicate the region to which the non-motor vehicle belongs and the number of wheels; Determining a target character recognition template according to the target vehicle category; Performing field recognition on the vehicle certificate image according to the target character recognition template to obtain target recognition field characters; Determine a target field reading rule according to the target vehicle category; The target identification field characters are read according to the target field reading rule to obtain the target certificate field attribute data.

2. The method according to claim 1, characterized in that The target certificate field attribute data includes target license plate number field attribute data, the target field reading rule includes a license plate number reading rule, the license plate number reading rule includes a license plate number region reading sub-rule, a license plate number number reading sub-rule and a sub-rule reading order, the sub-rule reading order indicates the reading order of the license plate number region reading sub-rule and the license plate number number reading sub-rule; The step of reading the target identification field characters according to the target field reading rule to obtain the target certificate data includes: According to the sub-rule reading order, one of the license plate number region reading sub-rule and the license plate number serial number reading sub-rule is taken as the target sub-rule in turn; According to the target sub-rule being the license plate number area reading sub-rule, the target recognition field characters are read to obtain the license plate number area field attribute data; According to the target sub-rule being the license plate number reading sub-rule, the target recognition field characters are read to obtain the license plate number field attribute data; Data splicing is performed based on the license plate number region field attribute data and the license plate number number field attribute data to obtain the target license plate number field attribute data.

3. The method according to claim 2, characterized in that The license plate number regional reading sub-rule includes regional character reading templates for at least two levels of sub-regions and a reading order for the sub-regions at each level; The target sub-rule is the license plate number area reading sub-rule, and the target recognition field characters are read to obtain the license plate number area field attribute data, including: Perform field reading on the target recognition field characters according to the reading order of each level of the sub-region and the regional character reading template to obtain a sub-region reading field; The sub-region read fields are spliced ​​according to the reading order of the sub-regions at each level to obtain the license plate number region field attribute data.

4. The method according to any one of claims 1 to 3, characterized in that: After the target identification field characters are read according to the target field reading rule to obtain the target certificate field attribute data, the method further includes: Obtaining an initial insurance policy for the non-motor vehicle; wherein the initial insurance policy includes fields for filling in requirements; Perform field name matching on the fill-in requirement field and each candidate field attribute data of the target certificate field attribute data to obtain a field name matching result; If the field name matching result indicates that the filling requirement field matches the attribute data of the candidate field, then the filling requirement field is updated according to the attribute data of the candidate field to obtain the attribute data of the target filling field; Update the initial insurance application form according to the target filled-in field attribute data to obtain a target insurance application form; Insure the non-motor vehicle according to the target insurance policy.

5. The method according to claim 4, characterized in that After matching the fill-in requirement field with the candidate field attribute data of the target certificate field attribute data by field name to obtain the field name matching result, the method further includes: If the field name matching result indicates that the filling requirement field does not match any of the candidate field attribute data, a first prompt message is generated according to the filling requirement field; wherein the first prompt message is used to prompt that the filling requirement field cannot be identified; Receiving the target supplementary vehicle image of the non-motor vehicle; wherein the target supplementary vehicle image includes a vehicle area corresponding to the filling requirement field; Performing image recognition on the target supplement vehicle image to obtain target supplement field attribute data; The filling requirement field is updated according to the target supplementary field attribute data to obtain the target filling field attribute data.

6. The method according to claim 4, characterized in that After matching the fill-in requirement field with the candidate field attribute data of the target certificate field attribute data by field name to obtain the field name matching result, the method further includes: If the field name matching result indicates that each of the required filling fields does not match any of the candidate field attribute data, then the vehicle certificate image is subjected to failure cause detection to obtain certificate recognition failure cause data; wherein the certificate recognition failure cause data is used to characterize the cause of the certificate recognition failure; Generate second prompt information according to the certificate recognition failure reason data; wherein, the second prompt information is used to prompt the reason for the certificate recognition failure.

7. The method according to claim 6, characterized in that If the field name matching result indicates that each of the required filling fields does not match any of the candidate field attribute data, then the vehicle certificate image is subjected to failure reason detection to obtain certificate recognition failure reason data, the method further includes: If the certificate recognition failure reason data indicates that the clarity of the vehicle certificate image is less than a preset clarity threshold, a first image shooting guide is generated; the first image shooting guide is used to guide the shooting of a vehicle certificate image with a clarity greater than or equal to the clarity threshold; If the certificate recognition failure reason data indicates that the size of the vehicle certificate image is smaller than a preset size threshold, a second image shooting guide is generated; the second image shooting guide is used to guide the shooting of a vehicle certificate image whose size is greater than or equal to the size threshold; If the certificate recognition failure reason data indicates that the vehicle certificate image does not include the non-motor vehicle certificate, a third image shooting guide is generated; the third image shooting guide is used to guide the shooting of the vehicle certificate image including the non-motor vehicle certificate.

8. A non-motor vehicle certificate recognition device, characterized in that: The device comprises: A certificate acquisition module, used to acquire a vehicle certificate image of a non-motor vehicle; A type determination module, used to obtain the vehicle type of the non-motor vehicle and obtain a target vehicle category; wherein the target vehicle category is used to indicate the region to which the non-motor vehicle belongs and the number of wheels; A template determination module, used to determine a target character recognition template according to the target vehicle category; A field recognition module, used for performing field recognition on the vehicle certificate image according to the target character recognition template to obtain target recognition field characters; A rule determination module, used for determining a target field reading rule according to the target vehicle category; The field reading module is used to read the target identification field characters according to the target field reading rule to obtain the target certificate field attribute data.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images