Image verification method and system, electronic equipment and storage medium

Abstract

The invention discloses an image verification method and system, electronic equipment and a storage medium. The method comprises the following steps: in response to a received information uploading request, obtaining a to-be-verified image of a to-be-verified object; the verification work order is analyzed, a target verification demand corresponding to the verification work order is determined, and the target verification demand is used for representing a condition demand for verifying the to-be-verified image; based on a target type and a target verification demand of the to-be-verified image, determining a target verification rule corresponding to the target type and the target verification demand from a plurality of pre-generated verification rules, the plurality of verification rules being generated by analyzing historical verification processes of a plurality of types of historical verification objects; historical verification requirements in different historical verification processes are different; and performing image verification on the to-be-verified image by using the target verification rule to obtain a verification result. According to the invention, the technical problem of low accuracy of image verification in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of image verification, and more specifically, to an image verification method, system, electronic device, and storage medium. Background Technology

[0002] With the rapid development of the service industry, the daily operations and maintenance of service providers are becoming increasingly complex. Verifying the qualifications of service providers is a crucial step in ensuring service quality. To ensure service quality, service providers need to regularly upload images of relevant merchants, such as storefront photos, scene photos, and equipment photos, for qualification verification.

[0003] However, related technologies often rely on manual review to verify uploaded images, but this lacks objectivity, and when faced with a massive number of images, manual review is difficult to maintain a high level of concentration and often suffers from visual fatigue, which may lead to missed detections or misjudgments. Therefore, the accuracy of image verification in related technologies is relatively low.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides an image verification method, system, electronic device, and storage medium to at least solve the technical problem of low accuracy in image verification in related technologies.

[0006] According to one aspect of the present invention, an image verification method is provided, comprising: in response to receiving an information upload request, acquiring an image of an object to be verified, wherein the information upload request is generated based on a verification work order after the object to be verified is created, and the verification work order is used to characterize a work order for verifying the qualifications of a service provider; parsing the verification work order to determine the target verification requirement corresponding to the verification work order, wherein the target verification requirement is used to characterize the conditional requirements for verifying the image to be verified; determining a target verification rule corresponding to the target type and target verification requirement from a plurality of pre-generated verification rules based on the target type and target verification requirement of the image to be verified, wherein the plurality of verification rules are generated by analyzing the historical verification processes of historical verification objects of multiple types, and the historical verification requirements are different in different historical verification processes; and performing image verification on the image to be verified using the target verification rule to obtain a verification result, wherein the verification result is used to characterize whether the image to be verified passes the verification.

[0007] Optionally, the above method further includes: determining multiple verification dimensions for verifying historical verification objects based on multiple types of historical verification objects; determining at least one verification condition corresponding to a verification dimension by semantic recognition of historical verification requirements for different verification dimensions; and obtaining multiple verification rules based on multiple verification dimensions and verification conditions.

[0008] Optionally, based on the target type and target verification requirements of the image to be verified, a target verification rule corresponding to the target type and target verification requirements is determined from a plurality of pre-generated verification rules: if the target type is a storefront photo, the target verification rule is determined to be whether the image to be verified includes the identification information corresponding to the target verification requirements; or, if the target type is a scene photo, the target verification rule is determined to be whether the image to be verified includes the scene information corresponding to the target verification requirements; or, if the target type is a device photo, the target verification rule is determined to be whether the image to be verified meets the requirement information corresponding to the target verification requirements.

[0009] Optionally, the target verification rules are used to perform image verification on the image to be verified to obtain the verification result, including: extracting image features from the image to be verified to obtain the image features of the image to be verified, and converting the image features into image vectors; converting the target verification rules into vectors to obtain rule vectors; and comparing the image vectors and rule vectors to obtain the verification result.

[0010] Optionally, the above method further includes: in response to the verification result that the image to be verified has failed the verification, determining the reason why the image to be verified has failed the verification; and adjusting the image to be verified based on the adjustment strategy corresponding to the reason.

[0011] Optionally, the above method further includes: in response to the verification result that the image to be verified has failed the verification, outputting a prompt message, wherein the prompt message is used to prompt the image to be verified to be re-uploaded; in response to receiving the newly re-uploaded verification image, performing image verification on the new verification image using the target verification rules to obtain a new verification result.

[0012] According to another aspect of the present invention, an image verification system is also provided, comprising: an acquisition module, configured to acquire an image of an object to be verified in response to receiving an information upload request, wherein the information upload request is generated based on a verification work order after the object to be verified is created, and the verification work order is used to characterize a work order for verifying the qualifications of a service provider; a parsing module, configured to parse the verification work order and determine the target verification requirement corresponding to the verification work order, wherein the target verification requirement is used to characterize the conditional requirements for verifying the image to be verified; a rule module, configured to determine a target verification rule corresponding to the target type and target verification requirement from a plurality of pre-generated verification rules based on the target type and target verification requirement of the image to be verified, wherein the plurality of verification rules are generated by analyzing the historical verification processes of historical verification objects of multiple types, and the historical verification requirements are different in different historical verification processes; and a verification module, configured to perform image verification on the image to be verified using the target verification rule to obtain a verification result, wherein the verification result is used to characterize whether the image to be verified passes the verification.

[0013] Optionally, the system further includes: a feedback module, used to determine the reason why the image to be verified failed the verification in response to the verification result being that the image to be verified failed the verification; and to adjust the image to be verified based on the adjustment strategy corresponding to the reason.

[0014] Optionally, the system further includes a display module, used to output a prompt message in response to the verification result indicating that the image to be verified has failed verification, wherein the prompt message is used to prompt the user to re-upload the image to be verified.

[0015] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0018] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0019] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0020] In this embodiment of the invention, in response to receiving an information upload request, after obtaining the image of the object to be verified, the verification work order is parsed to determine the target verification requirement corresponding to the verification work order. The target verification requirement characterizes the conditional requirements for verifying the image to be verified. Based on the target type and target verification requirement of the image to be verified, a target verification rule corresponding to the target type and target verification requirement is determined from multiple pre-generated verification rules. This target verification rule is then used to perform image verification on the image to be verified, yielding a verification result. After receiving the information upload request corresponding to the verification work order, this application automatically obtains the image of the object to be verified to verify the service provider's qualifications. Specifically, the verification work order is first parsed to determine the conditional requirements for verifying the work order. Then, based on the target type and target verification requirement of the image to be verified, a suitable target verification rule is determined from multiple verification rules. Since multiple verification rules are generated through analysis of historical verification processes, the subjectivity of manual verification is avoided. Therefore, using the target verification rule to perform image verification on the image to be verified can yield accurate verification results, achieving the goal of ensuring the accuracy of image verification. This achieves the technical effect of improving the accuracy of image verification, thereby solving the technical problem of low accuracy in image verification in related technologies. Attached Figure Description

[0021] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0022] Figure 1 This is a flowchart of an image verification method according to an embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of an optional image verification method according to an embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of an image verification system according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0028] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0029] According to an embodiment of the present invention, an embodiment of an image verification method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 1 This is a flowchart of an image verification method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0031] Step S102: In response to receiving the information upload request, obtain the image of the object to be verified.

[0032] Among them, the information upload request is generated based on the verification work order after the object to be verified creates a verification work order. The verification work order is used to represent the work order for verifying the qualifications of the service provider.

[0033] The aforementioned information upload request can be an instruction initiated by the service provider to the intelligent visit quality inspection system after completing a merchant visit task, or it can be an instruction automatically generated by the system periodically. The purpose of the information upload request is to submit photos taken on-site along with relevant work order information, requesting the system to verify them. The information upload request can be triggered after the on-site inspection is completed. The service provider uploads photos via a smart terminal or professional software, and the system automatically receives and prepares for subsequent image recognition and verification. The information upload request not only includes the images to be verified but may also carry metadata related to the visit date, time, location, and task details, facilitating the system's understanding and execution of the correct verification process.

[0034] The aforementioned entities to be verified can refer to various service providers. In the field of intelligent on-site quality inspection, the entities to be verified are not limited to photos of merchants' storefronts, scenes, and equipment, but can also broadly refer to all service providers participating in the service quality supervision process. Here, service providers refer to entities or individuals that cooperate with the merchant service management platform and upload on-site photos for verification. By verifying the images of the entities to be verified, a unified and comprehensive quality control can be implemented to assess the compliance, execution capabilities, and operational standards of each service provider.

[0035] The images to be verified can be high-resolution photos taken on-site, designed to provide intuitive evidence to support the assessment of merchant service quality. These images may contain, but are not limited to, multi-dimensional information such as the merchant's environment, facilities, and personnel activities. These images form the basis for the system's verification process. Each image can be preprocessed, such as resizing, color correction, and contrast enhancement, to ensure that the image recognition model can analyze the image and accurately determine whether it conforms to the preset verification rules, effectively preventing verification errors caused by image quality issues.

[0036] Specifically, images to be verified refer to various photos captured during the site visit, such as storefront photos, scene photos, and equipment photos. These images carry rich visual information, reflecting the actual situation of the merchant's operation, environmental safety, equipment condition, and other aspects. These images are the core processing object of the intelligent site visit quality inspection system. Through image recognition technology, the system can automatically analyze and understand the content of each image and determine whether it meets pre-set quality standards and compliance requirements. For example, storefront photos need to clearly display the merchant's name and logo; scene photos should fully present the store layout and hygiene conditions; and equipment photos must accurately display the equipment model and operating status.

[0037] The aforementioned verification work order is an electronic document generated during merchant visits, recording visit information and images to be verified. Serving as a bridge between the service provider and the intelligent visit quality inspection system, the verification work order details the visit date, time, location, and services provided. More importantly, it includes all photos uploaded by the service provider for automatic system verification. The generation mechanism of the verification work order is often closely integrated with the service process, ensuring that each uploaded image is correctly categorized and processed, thereby accelerating the verification process and improving overall operational efficiency. Verification work orders can be used to verify service provider qualifications, including their permissions, eligibility, and service quality. Through verification work orders, a convenient mechanism for reviewing and maintaining service provider qualifications can be implemented.

[0038] In one optional embodiment, upon receiving an information upload request, the image to be verified for the corresponding object can be invoked via an application programming interface (API). The API enables efficient data exchange and function calls between different software applications. The object to be verified can upload its image in real time according to the information upload request for image verification. Invoking the image to be verified using the API can include, but is not limited to, encrypted image transmission to ensure data security. Simultaneously, parameters such as size limits and image formats can be pre-set to ensure the uploaded image meets the system's processing requirements. The API call enables fast and seamless transmission of the image to be verified.

[0039] In another alternative embodiment, files can be transferred over the Internet via a file transfer protocol. The service provider can upload the images to be verified to a server directory or cloud platform specified by the system using client software. This allows the system to automatically retrieve and obtain these files to acquire the images during the verification task, initiating subsequent image processing and recognition procedures. The file transfer protocol ensures file transfer quality across various operating systems and network environments.

[0040] Step S104: Parse the verification work order to determine the target verification requirement corresponding to the verification work order.

[0041] Among them, the target verification requirement is used to characterize the conditions required for verifying the image to be verified.

[0042] The aforementioned target verification requirements refer to the conditions set for conducting qualification audits, service inspections, or compliance assessments of service providers in specific contexts. Target verification requirements reflect the expected image types, content, quality, and special requirements for the verification work order, aiming to ensure that the information provided by the service provider meets predetermined audit standards or service requirements. Target verification requirements may include, but are not limited to, quality requirements, such as image clarity, resolution, and lighting conditions, ensuring that image quality meets the needs of identification and analysis; and content requirements, such as specifying specific elements or scenes that must be included in the image. For example, for storefront photos, the merchant name and address must be included; for equipment photos, the equipment model and status must be clearly shown. Additionally, target verification requirements may include additional verification conditions set based on the context of a specific service or event. Target verification requirements provide clear guidance, offering clear image upload and audit guidelines for service providers and auditors, reducing misunderstandings and subjective judgments. Target verification requirements can also ensure data quality by setting specific quality and content standards, ensuring that uploaded images accurately reflect the entity's status, providing a reliable basis for subsequent analysis and decision-making.

[0043] In one alternative embodiment, natural language processing (NLP) and deep learning technologies can be combined to automatically parse the descriptive text of verification work orders, extract key information, and determine verification requirements. NLP technologies can understand the semantics of text and identify keywords and phrases such as "storefront photo" and "equipment status," while deep learning algorithms, especially recurrent neural networks or transformer models, can capture the contextual relationships in the text and more accurately understand the complexity of the requirements. Specifically, part-of-speech tagging can be performed on the verification work orders to identify key entities and attributes in the text. The relationships between keywords can be analyzed using deep learning models to understand the intent and requirements of the verification work orders. Then, the parsed semantic information is transformed into specific verification requirements, such as image type and checkpoints.

[0044] In another alternative embodiment, historical work order processing cases stored in a case library can be utilized, including work order descriptions, parsed verification requirements, and processing results. When a verification work order arrives, similar cases are retrieved from the case library to determine the target verification requirement based on the historical verification requirement. A case library can be constructed by collecting and organizing historical work order cases, including descriptions, parsed verification requirements, and review results.

[0045] Step S106: Based on the target type and target verification requirements of the image to be verified, determine the target verification rule corresponding to the target type and target verification requirements from a number of pre-generated verification rules.

[0046] Among them, multiple verification rules are generated by analyzing the historical verification process of multiple types of historical verification objects, and the historical verification requirements are different in different historical verification processes.

[0047] The aforementioned verification rules can be a set of standards developed based on multiple dimensions such as merchant type, service items, and security standards. These rules guide the image recognition module in correctly determining whether the image to be verified conforms to specifications. The verification rules can be detailed enough to specify the exact requirements for each storefront photo, scene photo, and equipment photo, such as size, clarity, and content completeness. They also include criteria for recognizing specific objects within the image. These verification rules ensure that the verification results are both objective and comprehensive, facilitating accurate quality inspection tasks.

[0048] Specifically, the generation of multiple verification rules can be based on in-depth analysis of the historical verification processes of various types of historical verification objects. Since the requirements differ across different historical verification processes, different verification rules can be generated for different needs. First, identify and classify the types of verification objects in historical work orders. This may include merchants from different industries, with different service content, or in different scenarios. For example, restaurants and retail stores may have different verification standards, and new service providers and long-term service providers with established track records may have different qualification reviews. For each type of historical verification object, collect the requirements from specific verification work orders, including image content requirements, quality standards, and the presence of specific elements. Analyze the collected historical requirements to understand which rules have proven effective in actual verification processes and which rules are prone to disputes or inconsistencies. Simultaneously, identify common problems in historical verifications, such as unclear images and missing key information.

[0049] In one alternative embodiment, a machine learning classifier (such as a support vector machine, random forest, neural network, etc.) can be used to identify and match the association between the target type and target verification requirements of the image to be verified and pre-generated verification rules. The classifier extracts features, such as keywords, verification frequency, and historical work order results, from the target type and target verification requirements of the image to be verified, and outputs matching target verification rules from multiple verification rules. The machine learning classifier can be trained using historical verification requirements and corresponding verification rules.

[0050] In another alternative embodiment, a knowledge graph can be constructed, modeling the relationships between target types, target verification requirements, and verification rules as nodes and edges on a graph. A query engine is then used to retrieve rules from the knowledge graph that match the target type and target verification requirements. Specifically, a knowledge graph containing verification object types, verification requirements, and verification rules can be established. Thus, using the target type and target verification requirements as query conditions, the graph query engine can retrieve relevant target verification rules based on the query conditions.

[0051] Step S108: Perform image verification on the image to be verified using the target verification rules to obtain the verification result.

[0052] The verification result is used to characterize whether the image to be verified passes the verification.

[0053] The aforementioned verification results can be conclusive findings obtained after verifying the images corresponding to the verification work order. The verification results not only clarify whether the images meet the specifications but also provide a detailed analysis of the reasons for non-compliance, such as "unclear storefront photos," "missing important equipment in scene photos," and "equipment photos not showing operational status," providing service providers with immediate feedback to upload accurate images. Furthermore, the verification results can be recorded for subsequent data analysis and model adjustments to improve learning and adaptability to future verification tasks, continuously enhancing the accuracy and efficiency of verification.

[0054] In one optional embodiment, a rule engine can be used for image verification. The rule engine determines whether the image to be verified meets the target verification rules based on preset judgment rules.

[0055] In another alternative embodiment, an image recognition model can be used to automatically analyze image features and match them with target verification rules. The image recognition model detects elements in the image to be verified, automatically verifying each element according to the target verification rules to obtain the verification result.

[0056] In this embodiment of the invention, in response to receiving an information upload request, after obtaining the image of the object to be verified, the verification work order is parsed to determine the target verification requirement corresponding to the verification work order. Based on the target type and target verification requirement of the image to be verified, a target verification rule corresponding to the target type and target verification requirement is determined from multiple pre-generated verification rules, so as to utilize the target verification rule to verify the image. After receiving the information upload request corresponding to the verification work order, this application automatically obtains the image of the object to be verified to verify the service provider's qualifications. Specifically, the verification work order is first parsed to determine the conditions for verifying the verification work order. Then, according to the target type and target verification requirement of the image to be verified, a suitable target verification rule is determined from multiple verification rules. Since multiple verification rules are generated by analyzing historical verification processes, the subjectivity of manual verification is avoided. Therefore, by using the target verification rule to verify the image, accurate verification results can be obtained, achieving the goal of ensuring the accuracy of image verification. This achieves the technical effect of improving the accuracy of image verification, thereby solving the technical problem of low accuracy in image verification in related technologies.

[0057] Optionally, the above method further includes: determining multiple verification dimensions for verifying historical verification objects based on multiple types of historical verification objects; determining at least one verification condition corresponding to a verification dimension by semantic recognition of historical verification requirements for different verification dimensions; and obtaining multiple verification rules based on multiple verification dimensions and verification conditions.

[0058] In one alternative embodiment, since different verification objects may involve different dimensions—for example, verification of a merchant's storefront photo might focus on "signage clarity" and "business hours display," while equipment photo verification might focus on "equipment model identification" and "equipment operating status"—this method can flexibly adapt to the verification needs of different objects. By identifying and defining the key attributes and characteristics of the verification object, and decomposing the type of the verification object into multiple dimensions, verification standards can be set more meticulously, ensuring the comprehensiveness and relevance of the verification.

[0059] Then, different verification conditions are determined for different dimensions. Specifically, semantic recognition can transform abstract verification requirements into concrete and measurable conditions, such as "the merchant name is clearly visible in the storefront photo" or "the QR code in the equipment photo is identifiable." Through automated semantic recognition, the work of manually interpreting and setting verification conditions can be significantly reduced, improving the automation level of the verification process. Semantic recognition helps to understand the logic and intent behind each verification dimension more deeply, thereby generating more accurate verification conditions.

[0060] This allows for the comprehensive verification of dimensions and conditions, resulting in executable verification rules. The generated rules provide clear criteria for image verification. The generation of these rules ensures consistency in the verification process, avoiding inconsistencies in results caused by differences in human judgment. Furthermore, the verification rules can be dynamically adjusted based on changes in historical verification data, ensuring their adaptability and timeliness, and promptly responding to changes in work order requirements.

[0061] Optionally, based on the target type and target verification requirements of the image to be verified, a target verification rule corresponding to the target type and target verification requirements is determined from a plurality of pre-generated verification rules, including: when the target type is a storefront photo, determining whether the image to be verified includes the identification information corresponding to the target verification requirements; or, when the target type is a scene photo, determining whether the image to be verified includes the scene information corresponding to the target verification requirements; or, when the target type is a device photo, determining whether the image to be verified meets the requirement information corresponding to the target verification requirements.

[0062] In one alternative embodiment, for certain industries, the display of storefront signage may be an industry standard requirement. This verification rule helps ensure that businesses comply with relevant regulations. It ensures that the storefront signage meets the verification requirements regarding clarity and completeness. For example, the signage information may include the business name and location.

[0063] In another optional embodiment, if the target type is a scene photo, it can be verified whether the scene photo accurately reflects the scene layout and elements specified in the verification requirements. Target verification rules can ensure that the scene photo covers scene information, such as store layout, hygiene conditions, staffing, and whether equipment is included. Verifying scene information helps confirm whether the merchant has set up or operated in accordance with service regulations or standards.

[0064] In another alternative embodiment, the security status of equipment is a crucial consideration for many services. This target verification rule helps identify security vulnerabilities and ensures merchants comply with security standards. If the target type is a device photograph, it can determine whether the device in the image to be verified is in a normal state, meeting the equipment status requirements in the verification process. These requirements can reflect the specific needs for the equipment, such as clearly displaying the device model and status. In this case, timely detection of equipment malfunctions or improper maintenance can ensure the normal operation and lifespan of the equipment.

[0065] Optionally, the target verification rules are used to perform image verification on the image to be verified to obtain the verification result, including: extracting image features from the image to be verified to obtain the image features of the image to be verified, and converting the image features into image vectors; converting the target verification rules into vectors to obtain rule vectors; and comparing the image vectors and rule vectors to obtain the verification result.

[0066] In one optional embodiment, to achieve image verification, features representing the content and structure of the image to be verified can be extracted, and these features can be converted into numerical vector representations for verification purposes. Image feature vectorization transforms the complex visual information of an image into a set of numerical features, facilitating subsequent calculations and comparisons. Vector representation of image features allows them to be compared with regular vectors in the same mathematical space, providing a foundation for intelligent verification. Image feature extraction can employ methods such as convolutional neural networks or deep residual networks to perform multi-level feature extraction on the image, including color, texture, shape, and object recognition.

[0067] Furthermore, transforming the target verification rules into a vector form that can be mathematically manipulated with image feature vectors enables direct comparison between the rules and image features. Rule vectorization converts non-quantized verification rules into quantized vector representations, facilitating comparison with the image to be verified. Rule vectors can be defined using natural language processing techniques or knowledge graphs.

[0068] Therefore, the comparison result between the rule vector and the image vector directly reflects whether the image meets the target verification rules, thus realizing an automated verification process. For example, by comparing the similarity or distance between the image vector and the rule vector, it is determined whether the image to be verified conforms to the target verification rules, thereby obtaining the verification result. This step automates image verification, avoiding the subjectivity and inefficiency of manual verification. Vector comparison can accurately identify the degree of matching between the image and the rules.

[0069] Optionally, the above method further includes: in response to the verification result that the image to be verified has failed the verification, determining the reason why the image to be verified has failed the verification; and adjusting the image to be verified based on the adjustment strategy corresponding to the reason.

[0070] In one optional embodiment, if the verification result indicates that the image fails verification, further analysis can be conducted to determine the specific reason for the failure, such as image blurriness, missing key information, or improper angle. This step is crucial because it helps service providers or operators accurately understand the problem, avoid repeating errors, and improve the efficiency and success rate of reshooting or modifying images. Targeted adjustment strategies are adopted based on the reasons for verification failure, aiming to pass verification upon re-upload. Based on the determined reasons for verification failure, the system recommends or guides service providers to adopt corresponding adjustment strategies, such as reshooting, enhancing image clarity, or supplementing missing information. Through this guided feedback, the system can facilitate service providers in quickly correcting problems, improving image quality and the efficiency of the verification process, avoiding unnecessary duplication of work, and enhancing the user experience.

[0071] Optionally, the above method further includes: in response to the verification result that the image to be verified has failed the verification, outputting a prompt message, wherein the prompt message is used to prompt the image to be verified to be re-uploaded; in response to receiving the newly re-uploaded verification image, performing image verification on the new verification image using the target verification rules to obtain a new verification result.

[0072] The aforementioned prompts can be notifications sent to service providers or operators when an image fails verification, detailing the reasons for the failure and suggested corrective measures. Prompts are a crucial link in communication between the system and the user, guiding users on how to adjust or improve the image to meet verification standards. Prompts may include, but are not limited to: Specific error descriptions: pointing out problems in the image, such as "the merchant name in the storefront photo is unclear" or "the equipment photo lacks a model label." Correction suggestions: providing guidance on resolving these issues, such as "please retake the storefront photo in sunlight" or "ensure the equipment photo includes the label." Text prompts: clearly instructing users to re-upload the verification image, sometimes including a re-upload deadline and important notes. Prompts help users clearly identify areas for adjustment, saving time and resources. By providing specific errors and correction suggestions, users can react quickly, shortening the image adjustment cycle and accelerating the verification process. Prompts enhance user trust and satisfaction with the system; even if verification fails, users can perceive the system's professionalism and interactivity.

[0073] In one optional embodiment, when an image fails verification, a prompt message can be generated, clearly informing the service provider of the verification result and pointing out the problem, encouraging the service provider to make timely corrections. This mechanism ensures the transparency and interactivity of the verification process, helping service providers quickly identify problems and take action, reducing processing time and improving the overall efficiency of verification. Therefore, when a newly uploaded verification image is received, it can be verified based on the new image and the target verification rules to determine whether it passes verification. The re-uploaded image is then analyzed again using the target verification rules to determine if it conforms to them. This process provides a closed-loop verification mechanism, ensuring continuous improvement in image quality and the complete execution of the verification process. The new verification result reflects the adjusted state of the image. If the verification passes, it indicates that the problem has been resolved, and the service provider can continue to the next step; if it still fails, the system will provide feedback again until the image meets all verification requirements. This step provides clear feedback on verification failures and, through dynamic rule generation and re-verification processes, ensures the consistency of the verification process and the accuracy of the results, effectively promoting the improvement of image quality and service processes.

[0074] The technical solution proposed in this application is described below with reference to an optional embodiment. This application proposes a merchant intelligent verification method based on Artificial Intelligence (AI) image recognition. This method automatically analyzes the content of photos using AI image recognition technology to determine whether the photos meet the specifications, thereby replacing manual verification and improving verification efficiency and accuracy. It adopts multi-dimensional verification standards, such as combining merchant type, work order requirements, and other multi-dimensional information to set intelligent verification rules, ensuring the comprehensiveness and accuracy of the verification results. Furthermore, it can achieve real-time feedback, providing real-time feedback on verification results and self-adjusting based on actual usage to continuously improve the accuracy of verification.

[0075] Specifically, this method employs a convolutional neural network as its core algorithm, trained with a large amount of labeled data to accurately identify content in photos. The verification rule engine sets multi-dimensional verification rules based on merchant type, work order requirements, etc. For example: storefront photos include the merchant name and address; scene photos include key equipment and operators; equipment photos clearly show the equipment model and status, and can recognize QR codes in photos, etc. Real-time feedback mechanism: the system provides real-time feedback on verification results via API, allowing service providers to receive immediate feedback after uploading photos, improving work efficiency.

[0076] Therefore, this method can improve verification efficiency by automating photo verification through AI image recognition technology, significantly reducing the workload of manual review and increasing efficiency. It also improves verification accuracy, as AI image recognition can accurately judge photo content, avoiding misjudgments caused by subjectivity and fatigue in manual verification. Real-time feedback is provided, allowing service providers to adjust and re-upload photos promptly, speeding up work order processing. Furthermore, by continuously adjusting verification rules through machine learning algorithms, it can adapt to constantly changing service needs, improving the system's accuracy and adaptability.

[0077] The specific workflow of this method is as follows: Image Acquisition: After completing the work order, the service provider uploads photo attachments through the system. Image Preprocessing: The system formats the uploaded photos, including operations such as cropping, scaling, and enhancement. Image Recognition: The AI ​​image recognition module analyzes the content of the preprocessed photos to determine whether they meet the specifications. The specific steps are as follows: using a convolutional neural network to extract features from the photos; judging whether the photo content meets the requirements according to the rules set by the verification rule engine; for photos that do not meet the requirements, identifying specific problems (such as unclear storefront photos, missing key elements in scene photos, etc.). Result Feedback: The system provides real-time feedback of the verification results to the service provider. If the photo does not meet the specifications, it prompts the user to re-upload; if it meets the specifications, it records that the verification has passed. Data Storage and Improvement: The verification results and photo data are stored in the system, and the verification rules are continuously adjusted through machine learning algorithms to improve the accuracy and adaptability of the system.

[0078] like Figure 2 The image shown illustrates an optional merchant image verification process. This process includes the following: A service creates and assigns a work order to a service provider. After processing the work order, the service provider submits the processing result (e.g., taking a photo and uploading it). The background processes and recognizes the image, then determines whether the verification is successful. If verification is successful, the process ends; otherwise, it returns the submitted work order result to the service provider for further background image processing and recognition until verification is successful.

[0079] This method can be applied to a verification system that includes the following modules: Image acquisition module: receives photo attachments uploaded by the service provider. Image preprocessing module: formats the uploaded photos, including cropping, scaling, and enhancement operations, to improve the accuracy of image recognition. AI image recognition module: performs content analysis on the preprocessed photos based on deep learning algorithms to determine whether the photos meet the specifications. Verification rule engine: sets verification rules based on merchant type, work order requirements, etc., providing a basis for the AI ​​image recognition module's judgment. Result feedback module: provides real-time feedback of verification results to the service provider and prompts for re-uploading photos when necessary. Data storage and improvement module: stores verification results and photo data, and continuously adjusts the verification rules through machine learning algorithms.

[0080] According to an embodiment of the present invention, a system embodiment of an image verification system is provided. It should be noted that the device can be used to execute the above-described image verification method. The specific implementation scheme and application scenario of this embodiment are the same as those of the above embodiments, and will not be repeated here.

[0081] Figure 3 This is a schematic diagram of an image verification system according to an embodiment of this application, such as... Figure 3 As shown, the device includes the following:

[0082] The acquisition module 32 is used to acquire the image of the object to be verified in response to the received information upload request. The information upload request is generated based on the verification work order after the verification work order is created for the object to be verified. The verification work order is used to represent the work order for verifying the qualifications of the service provider.

[0083] The parsing module 34 is used to parse the verification work order and determine the target verification requirements corresponding to the verification work order. The target verification requirements are used to characterize the conditions required to verify the image to be verified.

[0084] The rule module 36 is used to determine the target verification rule corresponding to the target type and target verification requirements from a number of pre-generated verification rules based on the target type and target verification requirements of the image to be verified. The multiple verification rules are generated by analyzing the historical verification process of multiple types of historical verification objects, and the historical verification requirements are different in different historical verification processes.

[0085] The verification module 38 is used to perform image verification on the image to be verified using the target verification rules and obtain the verification result, wherein the verification result is used to characterize whether the image to be verified passes the verification.

[0086] The image verification system in this embodiment includes an acquisition module, a parsing module, a rule module, and a verification module. It can dynamically generate verification rules adapted to different work orders and objects, thereby improving the accuracy and flexibility of image verification. The verification module utilizes an image recognition model, enabling the image verification system to automatically identify image content and determine whether it conforms to preset verification rules. This automates image verification, reduces the workload of manual verification, and improves verification efficiency.

[0087] Optionally, the system further includes: a feedback module, used to determine the reason why the image to be verified failed the verification in response to the verification result being that the image to be verified failed the verification; and to adjust the image to be verified based on the adjustment strategy corresponding to the reason.

[0088] In one optional embodiment, by integrating a feedback module, the system responds to the verification results output by the verification module. Specifically, when an image fails verification, the system can accurately determine the specific reasons for the image's failure and formulate corresponding adjustment strategies based on these reasons. These adjustment strategies cover various aspects of the image to be verified, aiming to guide service providers or the system itself on how to effectively adjust the image to meet the specifications of work order management. This mechanism not only improves the transparency of the verification process but also promotes the improvement of service provider skills and reduces unnecessary rework through targeted feedback and suggestions.

[0089] Optionally, the system further includes a display module, used to output a prompt message in response to the verification result indicating that the image to be verified has failed verification, wherein the prompt message is used to prompt the user to re-upload the image to be verified.

[0090] In one optional embodiment, by integrating a display module, a prompt message can be generated and displayed when an image to be verified fails the verification rules. This functionality ensures that service providers can instantly understand the feedback results of photo verification. When a photo does not meet the specifications, the prompt message clearly indicates that the image to be verified needs to be re-uploaded, avoiding delays in work order processing caused by verification lag. Simultaneously, the image verification system can automatically adjust the image recognition model and verification strategy based on real-time feedback results and historical data to adapt to constantly changing verification requirements, improving the system's verification accuracy and efficiency. Through this mechanism, service providers can quickly obtain verification results after uploading photos and take timely adjustment measures, thereby accelerating the overall processing speed of work orders and enhancing the system's adaptability and reliability in complex service scenarios. Of course, the specific design of the display module can be diversified, such as through pop-ups, message pushes, etc., to meet the usage needs of different scenarios.

[0091] Optionally, the system further includes: a generation module, used to determine multiple verification dimensions for verifying historical verification objects based on multiple types of historical verification objects; for different verification dimensions, determine at least one verification condition corresponding to the verification dimension by semantic recognition of historical verification requirements; and obtain multiple verification rules based on multiple verification dimensions and verification conditions.

[0092] Optionally, the rules module is also used to determine whether the target verification rule is whether the image to be verified includes the identification information corresponding to the target verification requirement when the target type is a storefront photo; or, whether the target verification rule is whether the image to be verified includes the scene information corresponding to the target verification requirement when the target type is a scene photo; or, whether the target verification rule is whether the image to be verified meets the requirement information corresponding to the target verification requirement when the target type is a device photo.

[0093] Optionally, the verification module is also used to extract image features from the image to be verified, obtain the image features of the image to be verified, and convert the image features into image vectors; convert the target verification rules into vectors to obtain rule vectors; and compare the image vectors and rule vectors to obtain the verification results.

[0094] Optionally, the verification module is also configured to, in response to the verification result that the image to be verified has failed verification, output a prompt message, wherein the prompt message is used to prompt the image to be verified to be re-uploaded; in response to receiving the re-uploaded new verification image, generate a model by combining the new verification image and the verification work order input rules, determine a new verification rule for verifying the new verification image; and perform image verification on the new verification image based on the new verification rule and the image recognition model to obtain a new verification result.

[0095] Embodiments of this application also provide an electronic device, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention during runtime.

[0096] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0097] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0098] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of the present invention.

[0099] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention.

[0100] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0104] If the integrated unit is implemented as 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 invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0105] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An image verification method characterized by, include: In response to receiving an information upload request, the image of the object to be verified is obtained, wherein the information upload request is a request generated based on the verification work order after the verification work order is created for the object to be verified, and the verification work order is used to represent a work order for verifying the qualifications of the service provider; The verification work order is parsed to determine the target verification requirement corresponding to the verification work order, wherein the target verification requirement is used to characterize the conditional requirements for verifying the image to be verified. Based on the target type of the image to be verified and the target verification requirements, a target verification rule corresponding to the target type and the target verification requirements is determined from a plurality of pre-generated verification rules. The plurality of verification rules are generated by analyzing the historical verification process of multiple types of historical verification objects, and the historical verification requirements are different in different historical verification processes. The image to be verified is verified using the target verification rules to obtain a verification result, wherein the verification result is used to characterize whether the image to be verified passes the verification.

2. The method of claim 1, wherein, The method further includes: Based on the multiple types of the historical verification objects, multiple verification dimensions are determined for verifying the historical verification objects. For different verification dimensions, at least one verification condition corresponding to the verification dimension is determined by semantic recognition of the historical verification requirements. Based on the multiple verification dimensions and the verification conditions, the multiple verification rules are obtained.

3. The method of claim 1, wherein, Based on the target type of the image to be verified and the target verification requirements, a target verification rule corresponding to the target type and the verification requirements is determined from a plurality of pre-generated verification rules, including: When the target type is a storefront photo, the target verification rule is determined to be whether the image to be verified includes the identification information corresponding to the target verification requirement; Alternatively, if the target type is a scene photo, the target verification rule is determined to be whether the image to be verified includes the scene information corresponding to the target verification requirement; Alternatively, if the target type is a device photo, the target verification rule is determined to be whether the image to be verified meets the requirement information corresponding to the target verification requirement.

4. The method of claim 1, wherein, The image to be verified is verified using the target verification rules to obtain the verification result, including: Image features are extracted from the image to be verified to obtain the image features of the image to be verified, and the image features are converted into image vectors; The target verification rules are transformed into a vector to obtain a rule vector; The image vector and the rule vector are compared to obtain the verification result.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to the verification result indicating that the image to be verified has failed the verification, the reason why the image to be verified has failed the verification is determined; Based on the adjustment strategy corresponding to the aforementioned reasons, the image to be verified is adjusted.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to the verification result that the image to be verified has failed the verification, a prompt message is output, wherein the prompt message is used to prompt the image to be verified to be re-uploaded; In response to receiving a newly uploaded verification image, the new verification image is verified using the target verification rules to obtain a new verification result.

7. An image verification system, characterized in that, include: The acquisition module is used to acquire the image of the object to be verified in response to receiving an information upload request. The information upload request is generated based on the verification work order after the object to be verified is created. The verification work order is used to represent a work order for verifying the qualifications of the service provider. The parsing module is used to parse the verification work order and determine the target verification requirement corresponding to the verification work order, wherein the target verification requirement is used to characterize the conditional requirements for verifying the image to be verified. The rule module is used to determine the target verification rule corresponding to the target type and the target verification requirement from a plurality of pre-generated verification rules based on the target type of the image to be verified and the target verification requirement. The plurality of verification rules are generated by analyzing the historical verification process of multiple types of historical verification objects, and the historical verification requirements are different in different historical verification processes. The verification module is used to perform image verification on the image to be verified using the target verification rules, and obtain a verification result, wherein the verification result is used to characterize whether the image to be verified passes the verification.

8. The system according to claim 7, characterized in that, The system also includes: The feedback module is used to determine the reason why the image to be verified failed the verification in response to the verification result that the image to be verified failed the verification; and to adjust the image to be verified based on the adjustment strategy corresponding to the reason.

9. The system according to claim 8, characterized in that, The system also includes: The display module is used to output a prompt message in response to the verification result indicating that the image to be verified has failed the verification, wherein the prompt message is used to prompt the image to be verified to be re-uploaded.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 6.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 6.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images