Certification application information review method
By using automated audit methods in the qualification certification process, the regional and time information in the image information is extracted and the information relevance is determined based on cluster analysis, the problem of low manual audit efficiency is solved, and efficient and accurate qualification audit is achieved.
Patent Information
- Application Number
- CN202411218656.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-02
AI Technical Summary
In the first step of the qualification certification process, subjective judgment leads to wrong judgments and reduced efficiency, and there is a time gap in manual acceptance, resulting in excessive burden on staff of third-party certification agencies.
Using a certification application information review method, the information correlation degree is determined by determining processing rules, extracting regional and time information in image information, clustering analysis based on historical audit data, and verifying the authenticity of information through application program interfaces to realize automated audit .
It effectively liberates the manual labor force, improves the efficiency and accuracy of qualification review, avoids manual subjective judgment, and realizes automated judgment.
Smart Images

Figure CN118761741B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information authentication, and in particular to a method for reviewing authentication application information. Background Art
[0002] With the continuous and steady development of various industries in recent years, more and more companies have begun to pay attention to the importance of various qualification certifications and apply for various qualification certifications. Correspondingly, the business volume of third-party certification agencies has also increased.
[0003] As the business volume increases, the workload of certification agency staff also increases dramatically. In the first step of the certification process, qualification review, misjudgments and reduced efficiency begin to appear due to subjective judgments, and there is a time gap in manual acceptance.
[0004] In response to the above problems, this application proposes a certification application information review method, which can automate part of the certification work to liberate labor and improve efficiency and accuracy. 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 method for reviewing authentication application information includes:
[0007] In response to the type of information to be classified and the first information to be authenticated submitted by the supplier, determining a first processing rule for processing the information to be classified;
[0008] Processing the first information to be authenticated using the first processing rule to obtain second information to be authenticated, wherein the second information includes geographical information and time information associated with the first information;
[0009] Obtaining classified authentication information associated with the first information based on the region information and time information associated with the first information, and determining a degree of association between the first information and the classified authentication information;
[0010] In response to the correlation of the classified authentication information being greater than a preset value, the first information to be authenticated is verified through an application program interface to determine the authenticity of the first information to be authenticated.
[0011] According to an embodiment of the present invention, the first information to be authenticated is image information, and the second information to be authenticated is extracted based on the image information and is obtained based on optical character recognition of the image information.
[0012] According to one embodiment of the present invention, the step of acquiring the second information to be authenticated includes:
[0013] Perform optical character recognition based on the image information to obtain the character string group and the position of the character string group in the image information;
[0014] According to the keyword list included in the first processing rule, determining whether the character string group includes all the keywords in the keyword list;
[0015] In response to the character string group including all the keywords in the keyword list, determining image features, geographical information, and time information of the image information;
[0016] The image features of the image information are text data, pixel width and pixel height of the text area of the image.
[0017] According to an embodiment of the present invention, historical audit data is obtained from a historical audit image database based on the geographical information and the time information, and the historical audit data includes data classified as positive samples and data classified as negative samples;
[0018] Obtain image features of positive sample data and negative sample data;
[0019] Cluster the image features of the positive sample data, the image features of the negative sample data and the image features to be reviewed, the number of clusters is 2, and obtain the cluster cluster to which the image features to be reviewed belong;
[0020] The positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs are obtained as the correlation between the first information and the classified authentication information.
[0021] According to an embodiment of the present invention, historical audit data is obtained from a historical audit image database based on the geographical information and the time information, and the historical audit data includes data classified as positive samples and data classified as negative samples;
[0022] Acquire second image features of the positive sample data and the negative sample data;
[0023] Clustering the second image features of the positive sample data, the second image features of the negative sample data, and the second image features to be reviewed, the number of clusters being 2, and obtaining the cluster cluster to which the image features to be reviewed belong;
[0024] Obtaining the positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs as the correlation between the first information and the classified authentication information;
[0025] The second image feature includes position information of keywords in the keyword list included in the first processing rule in the image and color histogram information of the image.
[0026] According to an embodiment of the present invention, the image features of the image information, the identifier of the first information to be authenticated and the image first information, the association data of the classified authentication information and / or the authenticity of the first information to be authenticated are saved in a database.
[0027] According to an embodiment of the present invention, the credibility information of the first information to be authenticated is determined based on the image features of the image information stored in the database, the correlation data and / or the authenticity of the information to be authenticated.
[0028] According to one embodiment of the present invention, in response to the first information to be authenticated being true, obtaining qualification-related information returned by the application program interface;
[0029] The business-related description information in the qualification-related information is obtained based on the first processing rule, and the qualification review result of the supplier is determined based on the business-related description information.
[0030] According to the second aspect of the present invention, a server includes: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the certification application information review method of the first aspect.
[0031] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by a processor, they are used to implement the certification application information review method of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 A flowchart of a method for reviewing authentication application information is shown. DETAILED DESCRIPTION
[0033] 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.
[0034] 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.
[0035] According to one embodiment of the present invention, a method for reviewing authentication application information includes:
[0036] In response to the type of information to be classified and the first information to be authenticated submitted by the supplier, determining a first processing rule for processing the information to be classified;
[0037] Processing the first information to be authenticated using the first processing rule to obtain second information to be authenticated, wherein the second information includes geographical information and time information associated with the first information;
[0038] Obtaining classified authentication information associated with the first information based on the region information and time information associated with the first information, and determining a degree of association between the first information and the classified authentication information;
[0039] In response to the correlation of the classified authentication information being greater than a preset value, the first information to be authenticated is verified through an application program interface to determine the authenticity of the first information to be authenticated.
[0040] In this embodiment, a method for reviewing authentication application information is proposed. First, the type of information to be classified and the first information to be authenticated are obtained, and based on the two, a first processing rule for processing the information to be classified is confirmed. For example, if the supplier submits information of the type of business license, then the first information to be authenticated is the uploaded business license image, and the first processing rule is the rule for processing the type of business license.
[0041] Further, the first information to be authenticated is processed using the first processing rule to obtain the second information to be authenticated, and the second information to be authenticated is extracted from the first information to be authenticated and contains the geographical information and time information associated with the first information. Due to the different formats of the generation of regions and files, there will be differences in the formats of certificates or materials, so it is necessary to extract more specific information from the certificate for verification. For example, the format of business license certificates abroad is different from that in China. Foreign ones may be business licenses or registration certificates; and for China, there are also differences in the styles of qualification documents obtained by enterprises in different provinces and at different times, such as the business licenses in 2000 and 2020. However, the geographical information and time information therein generally have a relatively fixed format, and their characteristics are also relatively fixed, such as location or text style, so it is more in line with the requirements to extract the geographical information and time information associated with the first information in the first information to be authenticated for verification.
[0042] Furthermore, based on the geographical information and time information extracted from the second information to be authenticated, the classified authentication information associated with the first information in the historical audit image database is obtained to determine the correlation between the first information and the classified information. Specifically, the classified authentication information with similar image features and text features is searched in the database through the image features or text features of the geographical information and time information associated with the first information, and then the features of other dimensions of these information are associated with the features of other dimensions of the first information. If the feature vectors of each dimension are similar, it is considered that the first information and the authenticated information in the database are similar, and the correlation is high, and the possibility of the first information being qualified is relatively high. Otherwise, it indicates that there are defects in the material and it needs to be corrected.
[0043] Furthermore, if the correlation between the first information and the classified authentication information is greater than a preset value, the first information is considered to belong to the classification, and the corresponding program interface is used to verify the authenticity of the first information to be authenticated. Specifically, for the first information with a correlation greater than a preset value, the first information is classified into the classification of the associated classified authentication information, and then the corresponding program interface is used to verify the authenticity of the first information to be authenticated. The program interface here is a trusted third-party program interface, and the program interface is called for verification after the local verification is reliable. For example, if the correlation between the first information and the information of the business license category in the database is greater than a preset value, the first information is classified into the business license category, and then the program interface of the relevant department is used to verify the authenticity of the business license.
[0044] Furthermore, through the above method, the first step of qualification review in the certification process can be liberated from manual labor, and efficiency and accuracy can be improved on the basis of avoiding subjective human judgment. When manual acceptance time is inconvenient, automatic judgment can also be achieved.
[0045] According to an embodiment of the present invention, the first information to be authenticated is image information, and the second information to be authenticated is extracted based on the image information and is obtained based on optical character recognition of the image information.
[0046] In this embodiment, the first information to be authenticated is image information, and the second information to be authenticated is information obtained through optical character recognition based on the image, including geographical information and time information associated with the first information.
[0047] Furthermore, optical character recognition (OCR) is a process of examining printed characters on paper or other media through an electronic device (such as a scanner or digital camera), determining their shapes by detecting dark and light patterns, and then translating the shapes into computer text using character recognition methods.
[0048] According to one embodiment of the present invention, the step of acquiring the second information to be authenticated includes:
[0049] Perform optical character recognition based on the image information to obtain the character string group and the position of the character string group in the image information;
[0050] According to the keyword list included in the first processing rule, determining whether the character string group includes all the keywords in the keyword list;
[0051] In response to the character string group including all the keywords in the keyword list, determining image features, geographical information, and time information of the image information;
[0052] The image features of the image information are text data, pixel width and pixel height of the text area of the image.
[0053] In this embodiment, the steps for obtaining the second information to be authenticated are described. First, optical character recognition is performed through OCR technology to obtain a string group and its position in the image; secondly, according to the keyword list preset in the first processing rule, it is determined whether the string group contains all the keywords therein; finally, if it does, the image features, geographical information and time information of the image information are determined through the information expressed by the string group.
[0054] Furthermore, the image features include features such as text data, pixel width and pixel height of the text area of the image. For example, the product quality certificate for steel quality provided by the supplier includes the pixel width and pixel height occupied by the "certificate of conformity" and the corresponding pattern, as well as the four words and the pattern itself.
[0055] Furthermore, for example, if the first information to be authenticated submitted is a product inspection report of a car tire, the keyword list set by the first rule includes keywords such as "inspection report", "product name", "specification model", "inspected unit", and "report date". By identifying that the second information to be authenticated contains the aforementioned keywords, the character string group after the keywords is extracted, and the corresponding information such as the name, model, supplier, origin, and time of the tire can be confirmed through the character string group.
[0056] According to an embodiment of the present invention, historical audit data is obtained from a historical audit image database based on the geographical information and the time information, and the historical audit data includes data classified as positive samples and data classified as negative samples;
[0057] Obtain image features of positive sample data and negative sample data;
[0058] Cluster the image features of the positive sample data, the image features of the negative sample data and the image features to be reviewed, the number of clusters is 2, and obtain the cluster cluster to which the image features to be reviewed belong;
[0059] The positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs are obtained as the correlation between the first information and the classified authentication information.
[0060] In this embodiment, historical audit data is obtained from a historical audit image database through geographical information and time information, and historical audit data with similar geographical information and time information in the historical database is matched. The historical audit data is divided into positive sample data and negative sample data. Image features of the positive sample data and negative sample data are obtained by calling associated data or re-extracting data. The image features of the positive sample data, the image features of the negative sample data and the image features to be audited are clustered, and the number of clusters is 2. The cluster clusters described by the image features to be audited are obtained, and the positive sample ratio and the negative sample ratio in the cluster cluster are used as the correlation between the first information and the classified authentication information.
[0061] Furthermore, the positive sample data is the historical sample data whose geographical information and time information are similar to the first information to be authenticated and are qualified, and the negative sample data is the historical sample data whose geographical information and time information are similar to the first information to be authenticated and are unqualified. In actual applications, the positive sample data is not necessarily qualified, and the negative sample data is not necessarily unqualified. Its qualification or not only depends on whether it meets the requirements of the system. There are many factors that affect its qualification, such as shooting angle, shooting quality, scanning clarity or others.
[0062] Furthermore, the image features of the positive sample data, the image features of the negative sample data and the image features to be reviewed are clustered, the number of clusters is 2, and the cluster to which the image features to be reviewed belong is obtained; the positive sample ratio and the negative sample ratio in the cluster to which the image features to be reviewed belong are obtained as the correlation between the first information and the classified authentication information. Specifically, the positive sample data, the negative sample data and the image to be reviewed with similar image features are clustered into two categories, each of which contains positive sample data and negative sample data, and the cluster containing the image to be reviewed is found, and the ratio of positive and negative samples in the cluster is obtained as the correlation between the first information and the classified authentication information.
[0063] Furthermore, clustering is an unsupervised learning method in the field of data mining and machine learning, which is used to divide the samples in the data set into several groups or clusters, so that the similarity between samples in the same cluster is high, while the similarity between samples in different clusters is low.
[0064] According to an embodiment of the present invention, historical audit data is obtained from a historical audit image database based on the geographical information and the time information, and the historical audit data includes data classified as positive samples and data classified as negative samples;
[0065] Acquire second image features of the positive sample data and the negative sample data;
[0066] Clustering the second image features of the positive sample data, the second image features of the negative sample data, and the second image features to be reviewed, the number of clusters being 2, and obtaining the cluster cluster to which the image features to be reviewed belong;
[0067] Obtaining the positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs as the correlation between the first information and the classified authentication information;
[0068] The second image feature includes position information of keywords in the keyword list included in the first processing rule in the image and color histogram information of the image.
[0069] In this embodiment, historical audit data is obtained based on geographical information and time information, that is, historical data in the historical data that is close to the first information to be authenticated is obtained, and the historical audit data is divided into positive sample data and negative sample data, and their second image features are respectively obtained and clustered with the second image features to be audited to obtain the clustering cluster described by the second image features to be audited, and the positive sample ratio and negative sample ratio in the clustering cluster to which the second image features belong are used as the correlation between the first information and the classified authentication information.
[0070] Furthermore, the second image feature includes the location information of the keyword list in the image. For example, if the "residence" and "business scope" in the business license are respectively located in the middle right and middle left sections of the entire image, then this location feature is the location information of the business license.
[0071] Furthermore, the second image feature includes color histogram information, which describes the proportion of different colors in the entire image without caring about the spatial position of each color. It is a statistical representation of the color distribution in the image. For example, the color distribution characteristics in a product certificate are different from those in an enterprise management certification. Generally speaking, the color distribution characteristics of different certificates are different.
[0072] Furthermore, by obtaining historical data that is close to the first information to be authenticated in the historical data and dividing it into positive sample data and negative sample data, the image features of the positive sample data, the image features of the negative sample data and the second image features to be reviewed are clustered, and divided into two categories according to the similarity of the features. Each cluster contains positive sample data and negative sample data, and the cluster described by the second image features to be reviewed is obtained, and the proportion of positive samples and the proportion of negative samples therein are used as the correlation between the first information and the classified authentication information.
[0073] According to an embodiment of the present invention, the image features of the image information, the identifier of the first information to be authenticated and the image first information, the association data of the classified authentication information and / or the authenticity of the first information to be authenticated are saved in a database.
[0074] According to an embodiment of the present invention, the credibility information of the first information to be authenticated is determined based on the image features of the image information stored in the database, the correlation data and / or the authenticity of the information to be authenticated.
[0075] According to one embodiment of the present invention, in response to the first information to be authenticated being true, obtaining qualification-related information returned by the application program interface;
[0076] The business-related description information in the qualification-related information is obtained based on the first processing rule, and the qualification review result of the supplier is determined based on the business-related description information.
[0077] In this embodiment, the image features of the image information, the identifier of the first information to be authenticated and the image first information, the correlation data of the classified authentication information and / or the authenticity of the first information to be authenticated are maintained in the database, and the credibility information of the first information to be authenticated is confirmed through these information.
[0078] Furthermore, since the verification rules of the system require the authenticity of the certificate or material, the authenticity of the information stored in the database has been verified. Therefore, when the characteristics of each dimension of the first information to be authenticated are similar to the characteristics in the historical data, the first information to be authenticated is considered to be more credible.
[0079] Furthermore, if the first information to be authenticated is credible, obtain the qualification-related information returned by the application interface, extract the business-related description information in the qualification-related information through the first processing rule, that is, the preset keywords, and give the business-related description information to determine the supplier's qualification review result.
[0080] Furthermore, the application program interface is a credible interface, for example: identity information is verified through the query interface of the relevant department, business license is verified through the query interface of the industrial and commercial department, and certificate of qualification is verified through the query interface of the inspection department, etc. Therefore, the qualification-related information returned through the interface is also credible, and the business-related description information in the qualification-related information is obtained through preset keywords, and the qualification review result of the supplier is determined based on the information, that is, the returned information is compared with the information provided by the supplier for features. If the features are similar, the qualification review is passed, otherwise it is not passed.
[0081] Another embodiment of the present invention discloses a server, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the above-mentioned certification application information review method.
[0082] Another embodiment of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the above-mentioned certification application information review method.
[0083] The beneficial effect of the present invention is that through the above-mentioned certification application information review method, the qualification review work of the first step in the certification process is liberated from manual labor, and the efficiency and accuracy can be improved on the basis of avoiding manual subjective judgment. At the same time, when the manual acceptance time is inconvenient, automatic judgment can also be achieved.
[0084] 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.
[0085] 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.
[0086] 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.
[0087] 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.
[0088] 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.
[0089] 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.
[0090] 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.
[0091] 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. The certification application information review method is characterized by: include: In response to the type of information to be classified and the first information to be authenticated submitted by the supplier, determining a first processing rule for processing the information to be classified; Processing the first information to be authenticated using the first processing rule to obtain second information to be authenticated, wherein the second information to be authenticated includes geographical information and time information associated with the first information; Obtaining classified authentication information associated with the first information based on the region information and time information associated with the first information, and determining a degree of association between the first information and the classified authentication information; In response to the correlation of the classified authentication information being greater than a preset value, verifying the first information to be authenticated through an application program interface to determine the authenticity of the first information to be authenticated; The determining the correlation between the first information and the classified authentication information includes: Obtaining historical audit data from a historical audit image database based on the region information and the time information, wherein the historical audit data includes data classified as positive samples and data classified as negative samples; Obtain image features of positive sample data and negative sample data; Cluster the image features of the positive sample data, the image features of the negative sample data and the image features to be reviewed, the number of clusters is 2, and obtain the cluster cluster to which the image features to be reviewed belong; Obtaining the positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs as the correlation between the first information and the classified authentication information; or Obtaining historical audit data from a historical audit image database based on the region information and the time information, wherein the historical audit data includes data classified as positive samples and data classified as negative samples; Acquire second image features of the positive sample data and the negative sample data; Clustering the second image features of the positive sample data, the second image features of the negative sample data, and the second image features to be reviewed, the number of clusters being 2, and obtaining the cluster cluster to which the image features to be reviewed belong; Obtaining the positive sample ratio and the negative sample ratio in the cluster to which the image feature to be reviewed belongs as the correlation between the first information and the classified authentication information; The second image feature includes position information of keywords in the keyword list included in the first processing rule in the image and color histogram information of the image.
2. The certification application information review method according to claim 1, characterized in that: The first information to be authenticated is image information, and the second information to be authenticated is extracted based on the image information and is obtained based on optical character recognition of the image information.
3. The certification application information review method according to claim 2, characterized in that: The step of obtaining the second information to be authenticated includes: Perform optical character recognition based on the image information to obtain the character string group and the position of the character string group in the image information; According to the keyword list included in the first processing rule, determining whether the character string group includes all the keywords in the keyword list; In response to the character string group including all the keywords in the keyword list, determining image features, geographical information, and time information of the image information; The image features of the image information are text data, pixel width and pixel height of the text area of the image.
4. The certification application information review method according to claim 3, characterized in that: The image features of the image information, the identifier of the first information to be authenticated and the image first information, the correlation data of the classified authentication information and / or the authenticity of the first information to be authenticated are stored in a database.
5. The certification application information review method according to claim 4, characterized in that: The credibility information of the first information to be authenticated is determined based on the image features of the image information stored in the database, the correlation data and / or the authenticity of the information to be authenticated.
6. The certification application information review method according to claim 1, characterized in that: In response to the first information to be authenticated being true, obtaining qualification-related information returned by the application program interface; The business-related description information in the qualification-related information is obtained based on the first processing rule, and the qualification review result of the supplier is determined based on the business-related description information.
7. A server, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the certification application information review method as described in any one of claims 1-6.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the certification application information review method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Automobile accessory picture intelligent auditing method
CN110414929A
Image recognition method based on big data
CN113033585A
Information auditing method and device based on artificial intelligence, terminal equipment and medium
CN113743902A
Supplier qualification auditing method, equipment and medium
CN117196646A
Enterprise information auditing method and system based on image recognition and big data
CN117523569A
