A method for intelligent auditing of factory workshops

Abstract

The present invention relates to the field of information authentication, and in particular to a method for intelligent auditing of factory workshops. The method comprises: obtaining a workshop type and a first image set provided by a supplier; determining a first part set included in the workshop and first supplier information corresponding to the parts in the first part set according to the workshop type; segmenting the images in the first image set based on a neural network to obtain a part image set and a workshop object image set, wherein the workshop object image set includes workshop object images other than the parts in the workshop; determining the conformity of the workshop parts according to the part drawings in the part image set; determining other objects in the workshop according to the workshop object images, and determining the conformity of foreign objects in the automobile manufacturing workshop. This solves the problems of shortage of human resources caused by the need for on-site audits, as well as manual misjudgments and low efficiency.

Description

Technical Field

[0001] The present invention relates to the field of information authentication, and in particular to an intelligent audit method for a factory workshop. Background Art

[0002] With the development of economy and the upgrading of residents' material consumption level, more and more enterprises have begun to pay attention to the importance of various enterprise qualification certifications and apply for various qualification certifications. Correspondingly, the business volume of third-party certification agencies has also increased.

[0003] With the increase in business volume, the workload of certification body staff has increased dramatically. Some work that requires on-site audits has made the already tight human resources even more stretched.

[0004] In view of the above phenomenon, the present invention proposes an intelligent audit method for a factory workshop to audit the workshop. Summary of the invention

[0005] At least one aspect or advantage of the invention will be set forth in part in the following description, or may be obvious from the description, or may be learned by practice of the disclosed subject matter.

[0006] According to a first aspect of the present invention, a factory workshop intelligent audit method includes:

[0007] Get the workshop type and first image set provided by the supplier;

[0008] Determine, according to the workshop type, a first parts set included in the workshop and first supplier information corresponding to the parts in the first parts set;

[0009] Segmenting the images in the first image set based on a neural network to obtain a part image set and a workshop object image set, wherein the workshop object images included in the workshop object image set are images of other objects in the workshop except the parts;

[0010] Determine the conformity of parts in the workshop according to the part drawings in the part image collection;

[0011] Based on the images of objects in the workshop, other objects in the workshop are identified to determine the foreign body qualification of the automobile manufacturing workshop.

[0012] According to one embodiment of the present invention, the neural network is a fully convolutional neural network.

[0013] According to an embodiment of the present invention, determining the conformity of parts in a workshop according to the part drawings in the part image set includes:

[0014] Traverse the part image collection and obtain the part category corresponding to each part image.

[0015] Obtain a set of identified parts based on the part category corresponding to each part image;

[0016] Obtaining unidentified parts based on a difference between the first part set and the identified part set;

[0017] Determine in-shop part conformity based on unidentified parts.

[0018] According to one embodiment of the present invention, the identified parts are determined based on the intersection of the first part set and the identified part set;

[0019] Based on the part category corresponding to the identified part, optical character recognition is performed on the document submitted in the database to obtain second supplier information related to the part category;

[0020] Based on the second supplier information and the first supplier information corresponding to the part category, the compliance of the parts used in the automobile manufacturing workshop is determined.

[0021] According to one embodiment of the present invention, in response to any second supplier information corresponding to a part category not being included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of parts in the workshop; or in response to the second supplier information corresponding to the part category containing supplier information not included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of parts in the workshop.

[0022] According to one embodiment of the present invention, the step of determining the foreign matter qualification of the automobile manufacturing workshop includes:

[0023] According to other objects in the workshop, obtain their corresponding usage places from the database;

[0024] When the application places and workshops of other objects are not relevant, it is determined that the foreign matter qualification level of the automobile manufacturing workshop does not meet the requirements.

[0025] According to one embodiment of the present invention, the step of determining the foreign matter qualification of the automobile manufacturing workshop includes:

[0026] Determine the negative list of objects in the manufacturing shop according to the type of manufacturing shop;

[0027] According to the categories to which other objects in the workshop belong, when it is determined that other objects in the workshop belong to the negative object list, the foreign body qualification of the automobile manufacturing workshop does not meet the requirements.

[0028] According to one embodiment of the present invention, the category of foreign matter is determined based on the knowledge graph.

[0029] According to a second aspect of the present invention, an electronic device is characterized by comprising:

[0030] at least one processor;

[0031] at least one memory storing computer executable instructions,

[0032] Wherein, when the computer executable instructions are executed by the at least one processor, they prompt the at least one processor to execute the factory workshop intelligent audit method described in the first aspect.

[0033] According to a third aspect of the present invention, a computer program product is characterized in that:

[0034] The instructions in the computer program product are executed by at least one processor to perform the factory workshop intelligent audit method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a factory workshop intelligent audit method is shown. DETAILED DESCRIPTION

[0036] The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thus implement the present disclosure, rather than implying any limitation on the scope of the present disclosure.

[0037] As used herein, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "based at least in part on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment". The term "another embodiment" is to be interpreted as "at least one other embodiment". The orientation or position relationship indicated by the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "vertical", "horizontal", "lateral", "longitudinal" and the like is based on the orientation or position relationship shown in the accompanying drawings. These terms are mainly for better describing the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation. In addition, in addition to being used to indicate an orientation or position relationship, some of the above terms may also be used to indicate other meanings, such as the term "upper" may also be used to indicate a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the terms "install", "set", "provided with", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be an internal connection between two devices, elements or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. In addition, the terms "first", "second", etc. are mainly used to distinguish different devices, elements or components (the specific types and structures may be the same or different), and are not used to indicate or imply the relative importance and quantity of the indicated devices, elements or components. Unless otherwise specified, "plurality" means two or more.

[0038] The present invention mainly provides an intelligent method for the inspection and audit process of automobile factories, through which past audit experience can be applied to on-site inspections. The review of automobile factories generally includes whether the procedures, drawings, operating instructions and other documents are reasonable, as well as the actual implementation records of regulations. Since the actual audit content is large, it is not realistic to provide a universal way to solve common problems. The present invention only provides an intelligent solution for the parts involved in the on-site verification process through image recognition. It can solve the defects of the on-site factory inspection and verification process that need to combine multiple types of data, reduce the workload, so that part of the factory inspection process can be carried out on-site and remotely at the same time.

[0039] According to one embodiment of the present invention, a factory workshop intelligent audit method includes:

[0040] Get the workshop type and first image set provided by the supplier;

[0041] Determine, according to the workshop type, a first parts set included in the workshop and first supplier information corresponding to the parts in the first parts set;

[0042] Segmenting the images in the first image set based on a neural network to obtain a part image set and a workshop object image set, wherein the workshop object images included in the workshop object image set are images of other objects in the workshop except the parts;

[0043] Determine the conformity of parts in the workshop according to the part drawings in the part image collection;

[0044] Based on the images of objects in the workshop, other objects in the workshop are identified to determine the foreign body qualification of the automobile manufacturing workshop.

[0045] In this embodiment, a method for intelligent auditing of factory workshops is proposed. First, the workshop type and a first image set provided by a supplier are obtained, and a first parts set included in the workshop and its corresponding first supplier information are determined according to the workshop type. A neural network is used to perform image segmentation according to the first image set to obtain a parts image set and a workshop object image set. Then, the conformity of the parts in the workshop is obtained by comparing the parts drawings in the parts image set with the first parts set in the workshop. Other objects in the automobile manufacturing workshop are determined according to the object images in the workshop, and the conformity of foreign objects in the automobile manufacturing workshop is determined according to the other objects.

[0046] Furthermore, in the above text, the workshop type is determined according to the products produced by the workshop, such as a workshop for the production of parts such as gearboxes and universal joints, and a workshop for the installation of complete vehicles. It should be understood that different workshop types perform different functions, and the standards used for vehicle audits are also consistent. Therefore, different categories can be set in the database, and the content of the audit in the workshop can be determined according to the classification. Then, the target to be audited in the corresponding workshop is clarified, and the image of the object in the workshop is identified through image recognition to obtain the audit or inspection results. For example, when the audit object is the seat of the target vehicle, the identified target image includes the frame or the seat of the vehicle. For another example, if the identification target is vehicle-related information, the identification target may include the image of the frame.

[0047] Furthermore, to review whether the factory's manufacturing workshop is qualified, one is to verify whether the parts of the corresponding workshop type are qualified, and the other is to verify whether other objects in the workshop, that is, foreign objects, are qualified. The qualification of the parts is verified by verifying the image and part drawing of the parts and the supplier of the parts, and the qualification of foreign objects is verified by verifying whether other objects in the automobile manufacturing workshop except the parts are qualified. In this way, it can be verified whether the automobile manufacturing workshop can meet its industry standards or national standards.

[0048] Furthermore, different types of manufacturing workshops have different parts. For example, if the workshop type is an automobile manufacturing workshop, then the first set of parts is the parts in the automobile manufacturing workshop, such as the crank-connecting rod mechanism and valve mechanism of the engine accessories, the transmission shaft and wheel hub of the transmission system accessories, the brake pads and vacuum booster of the brake system accessories, the tires and axles of the driving system accessories, and the lamps and motors of the electrical accessories. The correctness of the parts is verified by verifying whether their images are consistent with the part drawings.

[0049] Furthermore, in some processes in the manufacturing workshop, certain specifications and grades are required for some parts, and for some parts, specific suppliers or domestic suppliers are specified. The supplier information is verified to determine whether the specific parts meet the requirements. For example, in an automobile manufacturing workshop, if the tires are specified to be supplied by a specific company, the supplier information of the tires needs to be verified. For example, if the brake pads are specified to be FF grade, there is a corresponding supplier in the database that can produce FF grade brake pads. If the detected supplier is not in the database, the brake pads do not meet the standards.

[0050] Furthermore, the qualification of foreign matter is also an important indicator of a manufacturing workshop. For example, in an automobile manufacturing workshop, if there are foreign matter such as metal shavings, dust, and oil stains, it may cause pollution and damage to automobile parts. For example, if metal shavings are mixed into the circuit structure, it is likely to affect the performance of the circuit. If oil stains adhere to the surface of parts, it will also affect their performance and life. Therefore, in this application, the qualification of foreign matter in the workshop is judged by reviewing other objects in the manufacturing workshop except parts.

[0051] According to one embodiment of the present invention, the neural network is a fully convolutional neural network.

[0052] In this embodiment, it is shown that the neural network used to separate images in this application is a fully convolutional neural network.

[0053] Furthermore, the Fully Convolutional Network (FCN) is a deep learning model widely used in the field of computer vision, which is particularly suitable for image semantic segmentation tasks. It has the characteristics of dense prediction, arbitrary size input, combination of local and global information, and skip connection.

[0054] Furthermore, FCN is a network structure that replaces the fully connected layer in the traditional convolutional neural network with a convolutional layer. This design allows FCN to accept inputs of any size and output feature maps of the same size as the input, thereby achieving pixel-level understanding and segmentation of the image. The core operations of FCN include convolution, pooling, and upsampling (or transposed convolution). Through these operations, FCN can extract the features of the image and gradually restore the size of the feature map, ultimately achieving pixel-level prediction.

[0055] According to an embodiment of the present invention, determining the conformity of parts in a workshop according to the part drawings in the part image set includes:

[0056] Traverse the part image collection and obtain the part category corresponding to each part image.

[0057] Obtain a set of identified parts based on the part category corresponding to each part image;

[0058] Obtaining unidentified parts based on a difference between the first part set and the identified part set;

[0059] Determine in-shop part conformity based on unidentified parts.

[0060] In this embodiment, the specific process of determining the conformity of parts in a workshop according to the part drawings in the part image set is shown. First, the part image set is traversed, the parts corresponding to each part image are classified, and the identified part set is obtained based on the part category corresponding to each part image; secondly, the unidentified part set is obtained according to the difference set of the first part set and the identified part set; finally, the conformity of the parts in the workshop is determined according to the unidentified parts.

[0061] Furthermore, the first image set provided by the supplier cannot guarantee complete identification of all parts. For example, some very small parts in the automobile manufacturing workshop, such as spark plugs and fuses, may not be identified. In this case, it is necessary to review other parts information provided by the supplier.

[0062] Furthermore, the conformity of parts in the workshop is determined based on unidentified parts, and corresponding thresholds are set for the conformity according to different types of workshops and different categories of parts. For example, in an automobile manufacturing workshop, parts with obvious features and easy to identify, such as drive shafts, steering knuckles, steering wheel radiators, and motors, can be set with a higher conformity to ensure their quality and integrity. Parts such as switches, water pipes, and wires that are used in multiple systems but are difficult to distinguish should be set with a relatively low conformity for compliance judgment.

[0063] According to one embodiment of the present invention, the identified parts are determined based on the intersection of the first part set and the identified part set;

[0064] Based on the part category corresponding to the identified part, optical character recognition is performed on the document submitted in the database to obtain second supplier information related to the part category;

[0065] Based on the second supplier information and the first supplier information corresponding to the part category, the compliance of the parts used in the automobile manufacturing workshop is determined.

[0066] According to one embodiment of the present invention, in response to any second supplier information corresponding to a part category not being included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of parts in the workshop; or in response to the second supplier information corresponding to the part category containing supplier information not included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of parts in the workshop.

[0067] In this embodiment, the identified parts are determined by the intersection of the first parts set and the identified parts set, and then the documents submitted to the database are subjected to character group extraction based on the categories corresponding to the identified parts to obtain the second supplier information, and the compliance of the parts used in the automobile manufacturing workshop is determined based on the second supplier information corresponding to the part category and the first supplier information.

[0068] Furthermore, Optical Character Recognition (OCR) is a technology that scans and recognizes text on paper documents and converts them into a computer-editable text format. Through OCR technology, the supplier information of the parts corresponding to the submitted documents in the database can be extracted for comparison with the first supplier information to verify its compliance.

[0069] Furthermore, for the identified parts, it is necessary to compare their suppliers to ensure the quality and reliability of the parts. Optical recognition is performed based on the documents in the database, and the information of the identified parts and their suppliers is associated and compared with the first supplier information associated with the part.

[0070] Furthermore, if any second supplier information corresponding to a part category is not included in the first supplier information, then the part category is considered to not meet the compliance of parts in the workshop. That is, if any second supplier information corresponding to a part category extracted from a document submitted to the database is not included in the first supplier information, then the part category is not compliant. For example, in an automobile manufacturing workshop, the identified transmission parts include three first supplier information A, B, and C, and the second supplier information corresponding to the transmission parts extracted from the document submitted to the database is A, B, C, and D. Then the second supplier information D is not included in the first supplier information, and the transmission parts are not compliant.

[0071] Furthermore, if the second supplier information extracted from the document submitted to the database contains supplier information that does not exist in the first supplier information, then the part category is not compliant. For example, if the identified transmission parts contain the first supplier information of A, B, C, and D, and the second supplier information corresponding to the transmission parts extracted from the document submitted to the database is A, B, and C, then D is not included in the second supplier information, and the transmission parts are not compliant.

[0072] According to one embodiment of the present invention, the step of determining the foreign matter qualification of the automobile manufacturing workshop includes:

[0073] According to other objects in the workshop, obtain their corresponding usage places from the database;

[0074] When the application places and workshops of other objects are not relevant, it is determined that the foreign matter qualification level of the automobile manufacturing workshop does not meet the requirements.

[0075] In this embodiment, the steps for determining the foreign matter qualification of an automobile manufacturing workshop are shown. Based on other objects, their corresponding places of use are obtained from a database. If the application places of other objects are not related to the workshop, it is considered that the foreign matter qualification does not meet the requirements.

[0076] Furthermore, for example, if a potted plant appears in a car manufacturing workshop, it is obviously not satisfied; for example, if a small bucket full of water appears in the car manufacturing workshop, and the database shows that the bucket is used in the washroom, then the foreign matter qualification does not meet the requirements; for example, if there is a chip in the car manufacturing workshop, but the database shows that the use scenario of this type of chip is in the electronic chip assembly room, then the foreign matter qualification does not meet the requirements.

[0077] According to one embodiment of the present invention, the step of determining the foreign matter qualification of the automobile manufacturing workshop includes:

[0078] Determine the negative list of objects in the manufacturing shop according to the type of manufacturing shop;

[0079] According to the categories to which other objects in the workshop belong, when it is determined that other objects in the workshop belong to the negative object list, the foreign body qualification of the automobile manufacturing workshop does not meet the requirements.

[0080] According to one embodiment of the present invention, the category of foreign matter is determined based on the knowledge graph.

[0081] In this embodiment, the negative object list is determined according to the type of the manufacturing workshop. If there are other objects in the manufacturing workshop whose categories belong to the negative object list, the foreign object qualification does not meet the requirements.

[0082] Furthermore, the Knowledge Graph is a structured semantic knowledge base that describes concepts and their relationships in the physical world in a symbolic form. Its basic components are the "entity-relationship-entity" triples, as well as entities and their related attribute-value pairs. Entities are connected to each other through relationships, forming a network-like knowledge structure with the characteristics of visualization and dynamic update. The use of the Knowledge Graph can meet the needs of the manufacturing workshop for the judgment of the category of foreign objects.

[0083] Furthermore, the negative object list is determined according to the type of workshop, and includes foreign objects that will have a negative impact on the product manufacturing in that type of workshop. For example, in an automobile manufacturing workshop, metal chips, metal powder, dust, limiters, oil stains, paper scraps, plastic bags, rags, living insects, dead insects, etc. will all have a negative impact to a certain extent, so they are included in the negative object list. If other object categories in the manufacturing workshop belong to these categories, the foreign object qualification does not meet the requirements.

[0084] Another embodiment of the present invention discloses an electronic device, comprising:

[0085] at least one processor;

[0086] at least one memory storing computer executable instructions,

[0087] Among them, when the computer executable instructions are executed by the at least one processor, they prompt the at least one processor to execute the above-mentioned factory workshop intelligent audit method.

[0088] Another embodiment of the present invention discloses a computer program product, wherein instructions in the computer program product are executed by at least one processor to execute the above-mentioned factory workshop intelligent audit method.

[0089] The beneficial effect of the present invention is that through the above-mentioned factory workshop intelligent audit method, the situation where staff need to go to the site for audit can be effectively solved, saving a lot of labor costs and manpower costs. In addition, it can make up for the misjudgment and reduced efficiency caused by manual subjective judgment, and to a certain extent is not restricted by time and space.

[0090] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] In the 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 modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 modules, which can be electrical, mechanical or other forms.

[0093] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0094] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0095] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0096] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0097] It should be understood that the size of the sequence number of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. For the purpose of example and description, the foregoing description of the implementation of the present disclosure has been given. The foregoing description is not exhaustive and is not intended to limit the present disclosure to the exact form disclosed. Various deformations and modifications may exist according to the above teachings, or various deformations and modifications may be obtained from the practice of the present disclosure. These embodiments are selected and described to illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can use the present disclosure in various embodiments and various modifications suitable for the specific purpose conceived.

Claims

1. A factory workshop intelligent audit method, characterized in that: include: Get the workshop type and first image set provided by the supplier; Determine, according to the workshop type, a first parts set included in the workshop and first supplier information corresponding to the parts in the first parts set; Segmenting the images in the first image set based on a neural network to obtain a part image set and a workshop object image set, wherein the workshop object images included in the workshop object image set are images of other objects in the workshop except the parts; Determine the conformity of parts in the workshop according to the part drawings in the part image collection; Determine other objects in the workshop based on the images of objects in the workshop and determine the foreign matter qualification of the automobile manufacturing workshop; Determining the conformity of parts in a workshop according to the part drawings in the part image set includes: Traverse the part image collection and obtain the part category corresponding to each part image. Obtain a set of identified parts based on the part category corresponding to each part image; Obtaining unidentified parts based on a difference between the first part set and the identified part set; Determine part conformity within the shop floor based on unidentified parts; Determining the identified parts based on the intersection of the first part set and the identified part set; Based on the part category corresponding to the identified part, optical character recognition is performed on the document submitted in the database to obtain second supplier information related to the part category; Determine compliance of the parts used in the automobile manufacturing workshop based on the second supplier information and the first supplier information corresponding to the part category; In response to any second supplier information corresponding to the part category not being included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of the parts in the workshop; or in response to the second supplier information corresponding to the part category containing supplier information not included in the first supplier information, it is determined that the corresponding part category does not meet the conformity of the parts in the workshop.

2. A factory workshop intelligent audit method as claimed in claim 1, characterized in that: The neural network is a fully convolutional neural network.

3. A factory workshop intelligent audit method as claimed in claim 1, characterized in that: The step of determining the foreign matter qualification of the automobile manufacturing workshop comprises: According to other objects in the workshop, obtain their corresponding usage places from the database; When the application places and workshops of other objects are not relevant, it is determined that the foreign matter qualification level of the automobile manufacturing workshop does not meet the requirements.

4. A factory workshop intelligent audit method as claimed in claim 1, characterized in that: The step of determining the foreign matter qualification of the automobile manufacturing workshop comprises: Determine the negative list of objects in the manufacturing shop according to the type of manufacturing shop; According to the categories to which other objects in the workshop belong, when it is determined that other objects in the workshop belong to the negative object list, the foreign body qualification of the automobile manufacturing workshop does not meet the requirements.

5. A factory workshop intelligent audit method as claimed in claim 4, characterized in that: Determine the category of foreign objects based on the knowledge graph.

6. An electronic device, characterized in that: The invention is characterized by comprising: at least one processor; at least one memory storing computer executable instructions, Wherein, when the computer executable instructions are executed by the at least one processor, the at least one processor is prompted to execute a factory workshop intelligent audit method as claimed in any one of claims 1 to 5.

7. A computer program product, characterized in that The instructions in the computer program product are executed by at least one processor to perform the factory workshop intelligent audit method according to any one of claims 1 to 5.

Images