CN117541267A

CN117541267A - Supplier qualification information checking method and device

Info

Publication number: CN117541267A
Application number: CN202311507616.3A
Authority: CN
Inventors: 任学武; 高枫; 杨军; 石广华; 郝鹏飞; 成飞; 闫秀茂; 武强; 乔少波; 牛居寨; 王杰飞
Original assignee: Beijing Qianrunhe Technology Co ltd
Current assignee: Beijing Qianrunhe Technology Co ltd
Priority date: 2023-11-14
Filing date: 2023-11-14
Publication date: 2024-02-09

Abstract

The invention relates to a method and a device for checking qualification information of suppliers, wherein the method comprises the following steps: obtaining a file to be checked of a supplier, wherein the file to be checked at least comprises: vendor basic information, financial reports, contracts, invoices, etc.; service data; and identifying the file to be checked by using a trained identification model to obtain an identification result, wherein the trained identification model at least comprises: a form recognition model, a text recognition model, and an image recognition model; according to the identification result and the pre-configured checking rule, checking different checking scenes, wherein the checking scenes at least comprise: financial report verification, contract performance verification, inspection report verification, management system certificate verification, development design verification, production manufacturing verification, and test inspection verification. According to the method and the device for checking the supplier qualification information, the problem that the efficiency and the accuracy of checking the supplier qualification information in the related technology are low is solved, and the effect of improving the efficiency and the accuracy of checking the supplier qualification information is achieved.

Description

Supplier qualification information checking method and device

Technical Field

The present invention relates to the field of information processing technologies, and in particular, to a method and an apparatus for checking qualification information of a provider.

Background

At present, the checking work of the qualification information of the suppliers is usually carried out off-line, the suppliers voluntarily apply for participation in the checking, and the checking units uniformly check the qualification information of the suppliers. Every time of checking, a plurality of checking experts are required to complete the checking of hundreds of supplier qualification information in a plurality of working days, and electronic documents of all links of the qualification information, research and development design, production and manufacture, test detection, raw material group component management, after-sales service, productivity and the like are mainly checked, so that the problems of uneven quality, multiple file types, short checking period, heavy checking tasks and the like of submitted files of adjacent suppliers are met, and the problems are specifically expressed as follows:

(1) The supplier has more evidence materials and is stored offline

The evidence materials of the suppliers are all compressed and then sent to the checking expert through the network disc, the checking expert needs to download the data provided by each supplier in the network disc in the checking process, the evidence materials of the suppliers are more, and the arrangement modes of each supplier are different, so that the data are not easy to arrange and file.

(2) Expert checking workload is large, and manual checking is performed

In the checking process, the expert compares and checks the ECP2.0 report data of the supplier with the evidence materials provided by the supplier, and the checking expert needs to identify whether the qualification, the finance and the performance of the supplier meet the requirements in various files, and meanwhile needs to check whether the performance of the supplier is repeated, the invoice is true or false, and the like, so that the problems of short checking period, heavy checking task, and the like exist.

(3) The total amount of checking results is large, and the labor is repeated

After the checking work is finished, the checked data such as the basic information of the supplier, the report information of the supplier type and the like are pasted and copied from the ECP2.0 to the electronic form one by one for data summarization, and the problems that the repeated mechanical work is caused, the data are easy to be in serial in the pasting process and the like exist.

In summary, the existing provider qualification information verification has low efficiency and accuracy.

At present, no effective solution is proposed for the problem of low efficiency and accuracy of checking the qualification information of suppliers in the related art.

Disclosure of Invention

The present application aims to overcome the shortcomings in the prior art, and provides a method, a device, a computer device and a computer readable storage medium for checking vendor qualification information, so as to at least solve the problem of low efficiency and accuracy of vendor qualification information checking in the related art.

In order to achieve the above purpose, the technical scheme adopted by the application is as follows:

in a first aspect, an embodiment of the present application provides a method for checking vendor qualification information, including:

obtaining a file to be checked of a provider, wherein the file to be checked at least comprises: vendor basic information, financial reports, contracts, invoices, detection reports, management system certificates, qualification certificates, production process files, business data;

And identifying the file to be checked by using a trained identification model to obtain an identification result, wherein the trained identification model at least comprises: a form recognition model, a text recognition model, and an image recognition model;

and checking different checking scenes according to the identification result and a preset checking rule, wherein the checking scenes at least comprise: financial report verification, contract performance verification, inspection report verification, management system certificate verification, development design verification, production manufacturing verification, and test inspection verification.

In some embodiments, for the financial report verification, the identifying the file to be verified by using the trained identification model, and obtaining the identification result includes:

identifying the financial report by using the form identification model according to the pre-configured business field and alias, the header alias, the identification page number range and the numerical fault tolerance range;

formatting the identified numerical data;

comparing the formatted numerical data with the service data;

and if the numerical data obtained after formatting and the business data are in the numerical fault tolerance range, determining that the identification is effective.

In some embodiments, the checking the contract performance check according to the identification result and a pre-configured check rule includes:

identifying key information in the contract by using the text identification model, wherein the key information comprises a contract buyer, a contract number, a provider name, a contract name, a project name and a contract amount;

extracting the content data of the form in the contract by using the form identification model, and comparing with the service data to determine whether the content data is consistent with the service data;

judging whether the contract buyer belongs to a preset supplier database or not;

acquiring the business information of the contract buyer, and comparing whether the business range of the contract buyer is consistent with the business information;

identifying data in the invoice by utilizing the image identification model, and comparing whether the invoice accords with the contract;

and judging whether the performance of the provider accords with a preset performance value or not based on the contract amount.

In some embodiments, checking the detection report check according to the identification result and a pre-configured check rule includes:

identifying the name of the supplier in the detection report by using the text identification model, and judging whether the supplier belongs to a preset supplier database or not;

Identifying the name and key parameters of the detection report by using the text identification model, and comparing whether the name and key parameters are consistent with the service data;

and judging whether the date of the detection report exceeds a preset time value or not and whether the mechanism is compliant or not.

In some embodiments, checking the management system certificate according to the identification result and a pre-configured checking rule includes:

identifying the name of the supplier in the management system certificate by using the text identification model, and judging whether the supplier belongs to a preset supplier database or not;

and identifying the date and the name in the management system certificate by using the text identification model, and comparing with the service data to determine whether the date and the name are consistent.

In some embodiments, checking the development design check according to the identification result and a pre-configured check rule includes:

identifying the name of the provider in the patent certificate by using the text identification model, and judging whether the provider belongs to a preset provider database or not;

identifying the name of the provider in the established standard by using the text identification model, and judging whether the provider belongs to a preset provider database or not;

judging whether the patent certificate, the standards participated in establishment and the product winning file contain target keywords or not;

And judging whether the used design software contains non-self-developed software or not.

In some of these embodiments, checking the production manufacturing check according to the identification result and a pre-configured check rule includes:

identifying the name of the supplier in the production process file by using the text identification model, and judging whether the supplier belongs to a preset supplier database or not;

determining the property rights of the production factory building, and if the factory building is leased, judging whether the leasing date exceeds the period;

and identifying equipment category information in the production process file by using the text identification model, and comparing the equipment category information with preset key equipment types.

In some embodiments, checking the test detection check according to the identification result and a pre-configured check rule includes:

judging whether the number of the test detection personnel is smaller than a preset number value;

comparing the property right conditions of the production factory building and the test place;

acquiring category information of test equipment, and comparing the category information with preset key equipment types;

and identifying the calibration date in the file calibration certificate by using the text model, and comparing with the calibration date in the service data to determine whether the calibration date is consistent with the calibration date.

In some of these embodiments, further comprising:

constructing a supplier qualification information base, wherein the supplier qualification information base adopts a database table structure, and the supplier qualification information base comprises: the system comprises a supplier table and a qualification table, wherein the supplier table is used for storing basic information of suppliers, and the qualification table is used for storing qualification information of the suppliers;

constructing a checking information base, wherein the checking information base adopts a database collection structure, and the checking information base comprises: the system comprises a checking expert set and a standard set, wherein the checking expert set is used for storing information of checking experts, and the standard set is used for storing information of checking standards.

In a second aspect, an embodiment of the present application provides a vendor qualification information checking apparatus, including:

the device comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is used for acquiring a file to be verified of a supplier, and the file to be verified at least comprises: vendor basic information, financial reports, contracts, invoices, detection reports, management system certificates, qualification certificates, production process files, business data;

the identifying unit is used for identifying the file to be checked by using a trained identifying model to obtain an identifying result, wherein the trained identifying model at least comprises: a form recognition model, a text recognition model, and an image recognition model;

And the checking unit is used for checking different checking scenes according to the identification result and a pre-configured checking rule, wherein the checking scenes at least comprise: financial report verification, contract performance verification, inspection report verification, management system certificate verification, development design verification, production manufacturing verification, and test inspection verification.

In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the vendor qualification information checking method according to the first aspect described above when executing the computer program.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a vendor qualification information checking method as described in the first aspect above.

Compared with the prior art, the method for checking the qualification information of the suppliers provided by the embodiment of the application comprises the steps of obtaining the files to be checked of the suppliers, wherein the files to be checked at least comprise: vendor basic information, financial reports, contracts, invoices, detection reports, management system certificates, qualification certificates, production process files, business data; and identifying the file to be checked by using a trained identification model to obtain an identification result, wherein the trained identification model at least comprises: a form recognition model, a text recognition model, and an image recognition model; and checking different checking scenes according to the identification result and a preset checking rule, wherein the checking scenes at least comprise: financial report verification, contract performance verification, detection report verification, management system certificate verification, research and development design verification, production manufacturing verification and test detection verification, the problem that the efficiency and accuracy of supplier qualification information verification in the related technology are low is solved, and the effect of improving the efficiency and accuracy of supplier qualification information verification is achieved.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

fig. 1 is a block diagram of a mobile terminal according to an embodiment of the present application;

FIG. 2 is a flow chart of a vendor qualification information verification method according to an embodiment of the present application;

fig. 3 is a block diagram of a configuration of a provider qualification information checking apparatus according to an embodiment of the present application;

fig. 4 is a schematic hardware structure of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described and illustrated below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden on the person of ordinary skill in the art based on the embodiments provided herein, are intended to be within the scope of the present application.

It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the embodiments described herein can be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar terms herein do not denote a limitation of quantity, but rather denote the singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein refers to two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.

The embodiment provides a mobile terminal. Fig. 1 is a block diagram of a mobile terminal according to an embodiment of the present application. As shown in fig. 1, the mobile terminal includes: radio Frequency (RF) circuit 110, memory 120, input unit 130, display unit 140, sensor 150, audio circuit 160, wireless fidelity (wireless fidelity, wiFi) module 170, processor 180, and power supply 190. Those skilled in the art will appreciate that the mobile terminal structure shown in fig. 1 is not limiting of the mobile terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The following describes the components of the mobile terminal in detail with reference to fig. 1:

the RF circuit 110 may be used for receiving and transmitting signals during the process of receiving and transmitting information or communication, specifically, after receiving downlink information of the base station, the downlink information is processed by the processor 180; in addition, the data of the design uplink is sent to the base station. Typically, RF circuitry includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, simply referred to as an LNA), a duplexer, and the like. In addition, RF circuit 110 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to global system for mobile communications (Global System of Mobile communication, abbreviated GSM), general packet radio service (General Packet Radio Service, abbreviated GPRS), code division multiple access (Code Division Multiple Access, abbreviated CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, abbreviated WCDMA), long term evolution (Long Term Evolution, abbreviated LTE), email, short message service (Short Messaging Service, abbreviated SMS), and the like.

The memory 120 may be used to store software programs and modules, and the processor 180 performs various functional applications and data processing of the mobile terminal by executing the software programs and modules stored in the memory 120. The memory 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebooks, etc.) created according to the use of the mobile terminal, etc. In addition, memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The input unit 130 may be used to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the mobile terminal. In particular, the input unit 130 may include a touch panel 131 and other input devices 132. The touch panel 131, also referred to as a touch screen, may collect touch operations thereon or thereabout by a user (e.g., operations of the user on the touch panel 131 or thereabout by using any suitable object or accessory such as a finger, a stylus, etc.), and drive the corresponding connection device according to a predetermined program. Alternatively, the touch panel 131 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch azimuth of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 180, and can receive commands from the processor 180 and execute them. In addition, the touch panel 131 may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 130 may include other input devices 132 in addition to the touch panel 131. In particular, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, mouse, joystick, etc.

The display unit 140 may be used to display information input by a user or information provided to the user and various menus of the mobile terminal. The display unit 140 may include a display panel 141, and alternatively, the display panel 141 may be configured in the form of a liquid crystal display (Liquid Crystal Display, abbreviated as LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 131 may cover the display panel 141, and when the touch panel 131 detects a touch operation thereon or thereabout, the touch panel is transferred to the processor 180 to determine the type of the touch event, and then the processor 180 provides a corresponding visual output on the display panel 141 according to the type of the touch event. Although in fig. 1, the touch panel 131 and the display panel 141 implement the input and output functions of the mobile terminal as two independent components, in some embodiments, the touch panel 131 and the display panel 141 may be integrated to implement the input and output functions of the mobile terminal.

The mobile terminal may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 141 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 141 and/or the backlight when the mobile terminal moves to the ear. As one of the motion sensors, the accelerometer sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and direction when stationary, and can be used for recognizing the application of the gesture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that may also be configured with the mobile terminal are not described in detail herein.

A speaker 161 in the audio circuit 160 and a microphone 162 may provide an audio interface between the user and the mobile terminal. The audio circuit 160 may transmit the received electrical signal converted from audio data to the speaker 161, and the electrical signal is converted into a sound signal by the speaker 161 to be output; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, receives the electrical signal from the audio circuit 160, converts the electrical signal into audio data, outputs the audio data to the processor 180 for processing, transmits the audio data to, for example, another mobile terminal via the RF circuit 110, or outputs the audio data to the memory 120 for further processing.

WiFi belongs to a short-distance wireless transmission technology, and a mobile terminal can help a user to send and receive emails, browse webpages, access streaming media and the like through the WiFi module 170, so that wireless broadband Internet access is provided for the user. Although fig. 1 shows a WiFi module 170, it will be understood that it does not belong to the necessary configuration of the mobile terminal, and may be omitted entirely or replaced with other short-range wireless transmission modules, such as Zigbee modules, WAPI modules, or the like, as desired within the scope of not changing the essence of the invention.

The processor 180 is a control center of the mobile terminal, connects various parts of the entire mobile terminal using various interfaces and lines, and performs various functions of the mobile terminal and processes data by running or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120, thereby performing overall monitoring of the mobile terminal. Optionally, the processor 180 may include one or more processing units; preferably, the processor 180 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 180.

The mobile terminal also includes a power supply 190 (e.g., a battery) for powering the various components, which may be logically connected to the processor 180 via a power management system so as to provide for the management of charge, discharge, and power consumption by the power management system.

Although not shown, the mobile terminal may further include a camera, a bluetooth module, etc., which will not be described herein.

In this embodiment, the processor 180 is configured to:

In some of these embodiments, the processor 180 is further configured to:

formatting the identified numerical data;

comparing the formatted numerical data with the service data;

In some of these embodiments, the processor 180 is further configured to:

The embodiment provides a supplier qualification information checking method. Fig. 2 is a flowchart of a vendor qualification information verification method according to an embodiment of the present application, as shown in fig. 2, the flowchart including the steps of:

step S201, obtaining a file to be checked of a provider, where the file to be checked at least includes: vendor basic information, financial reports, contracts, invoices, detection reports, management system certificates, qualification certificates, production process files, business data;

step S202, identifying the file to be checked by using a trained identification model to obtain an identification result, wherein the trained identification model at least comprises: a form recognition model, a text recognition model, and an image recognition model;

Step S203, checking different checking scenes according to the identification result and a pre-configured checking rule, where the checking scenes at least include: financial report verification, contract performance verification, inspection report verification, management system certificate verification, development design verification, production manufacturing verification, and test inspection verification.

Through the steps, the files to be checked of the suppliers are identified by using the trained identification model, different checking scenes are checked according to the identification result by using the preconfigured checking rule, and compared with the manual off-line checking in the prior art, the method and the device can solve the problem that the checking efficiency and accuracy of the qualification information of the suppliers are lower, and further achieve the effect of improving the checking efficiency and accuracy of the qualification information of the suppliers.

In some of these embodiments, based on the diversity of audit categories, embodiments of the present application may build audit catalog dynamic configurations: configuring a checking catalog to realize quick switching of checked products; configuring a license material catalog to realize classified management of the license materials of the suppliers; and configuring a data verification rule and a logic verification rule to realize data verification and logic verification. After the replacement of the checking product is satisfied, the quick configuration deployment of the checking tool can be realized by configuring the checking rule without developing codes.

In some of these embodiments, based on the non-tamperable technology of blockchains, the embodiments of the present application construct a store on the chain of evidence material: and realizing the required evidence materials for the supplier resource capacity check, carrying out on-chain storage in an encrypted mode, improving the data flow efficiency, breaking the data island, tracking each file change and data flow transfer in the checking period, and tracking the history track of the whole course check to form public transparent information, and finally realizing information sharing.

The embodiment of the application is based on an artificial intelligence technology, and the automatic compiling of the verification report is constructed: collecting core elements of materials such as financial reports, test reports, contract performance, invoices, personnel certificates, social security certificates and the like, constructing a general (form and text) model identification model and a special (invoice, enterprise certificate and personnel certificate) model identification model, and converting an image file of a provider into computer-readable structural information; and the structural information is intelligently identified and automatically compared by adopting an artificial intelligence technology. The intelligent checking of the supplier resource capability information is realized, and an expert is assisted to improve the checking working quality and efficiency.

Aiming at the file to be checked uploaded by the supplier, the embodiment of the application uses advanced recognition technology to perform different types of recognition, including form recognition, image recognition and general character recognition, and combines manual labeling to improve the recognition rate.

For table recognition, a table recognition model based on deep learning is adopted, and the structure, row and column information and cell content of the table can be automatically detected and extracted through training and optimizing the model. Firstly, image preprocessing is carried out on the uploaded check file, and the steps of denoising, contrast enhancement, image enhancement and the like are included to optimize the image quality. Then, by using the form recognition model, we can accurately extract the data in the form and perform the structuring process to facilitate the subsequent data comparison and analysis.

For image (e.g., invoice) recognition, recognition models specific to the invoice have been developed using deep learning and OCR techniques. The definition and contrast of the invoice can be improved by preprocessing and optimizing the uploaded invoice image. The key fields of the invoice, such as the invoice number, date, amount, etc., can then be automatically extracted using a trained invoice recognition model. In order to further improve the recognition rate, a manual marking method is combined to manually correct and correct some complicated or difficult-to-accurately-recognized invoices, so that the accuracy and the integrity of a final recognition result are ensured.

In addition, the embodiments of the present application also use generic word recognition techniques to process non-tabular and non-invoice portions of the audit file. The universal text recognition model is capable of recognizing and extracting text content in an image, including paragraphs, titles, labels, and the like. By identifying and extracting the text, the overall understanding and data extraction of the check file can be further perfected.

The advanced identification technologies are comprehensively used, and the identification rate of uploading check files to suppliers can be effectively improved by combining a manual labeling method. The comprehensive method can process different types of files, extract various key information, ensure high quality and accuracy, and continuously optimize and improve the recognition algorithm so as to adapt to check files with different scenes and complexity, and ensure optimal recognition performance and user experience.

Based on the identification technology, specialized application can be performed in different verification scenes.

formatting the identified numerical data;

comparing the formatted numerical data with the service data;

By configuring parameters such as service field, service field alias for file identification, header alias, identification page number range, and numerical fault tolerance range, high-precision identification and comparison of financial table data can be realized.

Before file identification, the business fields to be identified, such as the total amount of assets of the audit report, are configured according to specific business requirements, and aliases, such as the total amount of assets, the total amount of liability owners equity, etc., are configured for these fields. This is done to ensure that the target data can be accurately matched and extracted, especially in cases where different naming and expression patterns may exist in the file. Optionally, the embodiment of the application can calculate the semantic similarity of aliases of different service fields, integrate aliases with semantic similarity higher than a predetermined threshold value, and achieve the purpose of accurately extracting and matching target data.

Meanwhile, the embodiment of the application also configures the header aliases needing to be identified, such as the end-of-term balance, and the like, and can accurately position and extract header information corresponding to the target data in the financial form.

In the identification process, the embodiment of the application limits the range of the file page numbers to be identified, for example, from page 3 to page 12, so that the identification operation can be ensured to be carried out in the appointed range, and the identification efficiency and accuracy are improved.

For the identification of the numerical data, the embodiment of the application performs formatting processing, and the identified numerical data is reserved with two decimal places and rounded, so that the data format can be unified, and the consistency of subsequent comparison and analysis is ensured.

In the embodiment of the application, when the numerical comparison is performed, the business field is compared with the corresponding field in the acquired financial form data. If the business value and the acquired financial form value are within a preset fault tolerance range, namely, within plus or minus ten thousand ranges, errors are allowed, the identification is judged to be successful, otherwise, if the business value and the acquired financial form value are beyond the fault tolerance range, the identification is marked as failure.

Through the above configuration and processing steps, the embodiments of the present application are able to perform recognition of financial form data in a professional manner. Relevant parameters are configured according to service requirements, an identification range is limited and numerical comparison after data formatting is carried out through accurate field alias and header alias matching, a high-accuracy identification result is realized, and the processing flow can provide a reliable data base for analysis and decision of financial data and ensure accuracy and reliability.

It should be noted that, first, text recognition is performed on the contract attachment front page by using OCR technology, and key information such as a contract buyer, a contract number, a provider name, a contract name, a project name, an engineering name, etc. is extracted.

Secondly, a form analysis technology is adopted to conduct form identification and analysis on the same page, various contents are extracted and compared with service data, and data consistency is ensured.

Meanwhile, by combining a provider database, whether the contract buyer belongs to the provider in the checking range is judged by utilizing an image recognition technology, and effectiveness verification of performance is improved.

In addition, the business information of both parties of the contract is obtained by calling the business information interface, and whether the business scope is consistent is checked by utilizing the image recognition technology, so that the effectiveness of the performance is further judged.

And aiming at the invoice corresponding to the contract, carrying out identification and verification by utilizing an image identification technology, comparing four elements of the invoice with contract information, checking whether the detail list contains business data checked at the time, and ensuring consistency of buyers.

And finally, comparing the actual supply amount, the actual quantity and the average price of the product performance by combining the image recognition technology and the business data to judge whether the performance meets a preset limit value.

The accuracy and efficiency of contract performance verification can be improved based on the optimization, and the effectiveness of performance data is ensured.

It should be noted that, the detection report application based on image recognition involves a plurality of association steps.

First, by means of text recognition, the attachment home page can be recognized and checked to see if there is a vendor name to determine if the detection report belongs to the vendor.

Secondly, the detection report name of the home page is identified and compared with the service data to ensure the consistency of the detection report name. Next, other pages are polled, text information therein is identified, and keywords (e.g., rated current, short-term withstand current, power frequency voltage test, etc.) are found. And comparing the extracted parameters with corresponding parameters in the service data to judge whether the parameters are consistent with the corresponding parameters.

In addition, it is judged whether the date of issuance of the inspection report exceeds 8 years, and it is checked whether a performance verification test is performed to ensure the reliability of the report. It is also desirable to determine whether the issuing authority of the detection report is compliant and verify whether the validity period of the report is valid.

Through the association steps, the image recognition-based detection report application can automatically check the report suppliers, report name consistency, key parameter matching, date and performance verification, compliance and validity of the issuing organization, and improve the efficiency and accuracy of detection report processing.

It should be noted that, the management system certificate application based on image recognition involves the following key steps:

first, the attachment home page is identified by means of text recognition, and whether the content of the attachment home page contains a provider name is queried to judge whether the certificate belongs to the provider.

Next, the first two pages are identified, and the information of the certification date, the certificate name, the validity period, and the like of the certification certificate of the management system is extracted and compared with the service data to verify the consistency of the certification certificate.

Text information in the certificate can be extracted through an image recognition technology, and the text information comprises key information such as a certification date, a certificate name, a validity period, and the like. And then, comparing the extracted information with corresponding data in the service data to ensure the consistency of the extracted information and the corresponding data.

These steps can help to quickly identify vendor names in the certificate and verify the consistency of key information of the certificate with the business data to ensure the accuracy and validity of the management system certificate.

It should be noted that, the development and design application based on image recognition includes the following key steps:

First, a patent front page is identified by means of text identification, and whether the content of the patent front page contains keywords such as a provider name, a patent type, a patent owner, a patent number, a high-voltage switch cabinet and the like is inquired.

Next, a list of criteria to participate in the formulation is identified by text recognition techniques and a query is made as to whether the first page content contains a vendor name to determine whether the vendor is involved in formulating the criteria. In terms of business data, it is judged whether an issuing authority is provincial in the case of winning a prize of a product, and whether the winning name contains keywords such as credit, reputation, business, etc. is checked. Further, it is checked whether the product patent name in the service data contains keywords such as a high-voltage switch cabinet.

In addition, it is determined whether the design software used contains software that is not developed autonomously, such as CAD, or the like. Finally, the patentee of the product patent checks whether the provider contains the provider to verify whether the provider has the relevant patent.

Through the association steps, the research and development design application based on image recognition can automatically recognize patent related information, standard establishment participation, winning information, product patent names, design software use conditions and patentee information, so that accuracy and reliability in the research and development design process are improved.

It should be noted that, first, the first page of the attachment of the production process file is identified by means of text recognition, and whether the content of the first page contains the name of the provider is queried to determine whether the process file belongs to the provider.

And secondly, judging the property right condition of the production factory according to the business data. If the factory building is leased, whether the leasing period is larger than a preset limit value or not needs to be checked.

In addition, for the main production equipment, it is necessary to ensure that the production equipment category contains key equipment types such as a numerical control bending machine, a numerical control punching machine, a numerical control plate shearing machine and the like. And extracting the equipment category information in the process file through a text recognition technology, and comparing the equipment category information with a preset key equipment type to verify whether the equipment category information meets the requirement.

Through these key steps, the image recognition-based manufacturing verification application can automatically recognize vendor names in process files, verify the property conditions of the manufacturing plants and check key equipment types in the manufacturing equipment, thereby improving the accuracy and reliability of the manufacturing verification.

It should be noted that, first, through the business data, it is judged whether the number of the high voltage test detecting personnel is less than two, this can be verified by comparing the personnel information in the business data.

If the production facility is leased and the test site is owned, then the piece of business data may be suspected of being counterfeited, which may be checked by comparing the property status of the production facility and the test site.

For test equipment, it is necessary to ensure that the equipment category contains critical equipment types such as insulation resistance testers, gas leak detectors, micro water detectors, and the like. And extracting category information of the test equipment through a text recognition technology, and comparing the category information with a preset key equipment type to verify whether the category information meets the requirements.

In addition, whether the uploaded file calibration certificate exists in the service data is checked. And identifying the calibration date in the calibration certificate by means of text identification, and comparing the calibration date with the corresponding date in the service data to confirm the consistency of the calibration date.

The number of high-voltage test detection personnel, property conditions, test equipment types and the validity and consistency of the calibration certificate can be automatically verified through the test detection and verification application based on image recognition, and the accuracy and reliability of test detection and verification are improved.

In some embodiments, the data analysis of vendor qualification information and verification knowledge is performed by using a FineBI analysis tool, which specifically includes:

1. data integration and summarization:

and extracting and converting the supplier qualification information and the data source of the checking knowledge, and importing the data into a data warehouse. A star model data model is built in a data warehouse to support data association and querying. And establishing a hierarchy and association of data through a main key-external key relation between tables by using a relational data model.

2. Report and dashboard design:

report and dashboard creation using the FineBI tool. In the FineBI tool, dimensions and metrics are defined according to the data model and data correlation is performed. The visual function provided by the FineBI tool is utilized to display summarized data of provider qualification information and check knowledge in the form of a histogram, a line graph, a pie chart and the like.

3. Data analysis and exploration:

the summarized data is deeply analyzed and explored by utilizing the data analysis function provided by the FineBI tool. Using trend analysis, comparison analysis, correlation analysis, etc., the relationship and trend between vendor qualification information and audit knowledge is revealed. The interactive control provided by the FineBI tool is used for supporting the user to carry out multidimensional slicing and screening on the data.

Through the implementation process, the data integration, report design and data analysis of the supplier qualification information and the checking knowledge are supported, accurate and comprehensive data support is provided for the checking expert group, and deep data analysis and decision making are facilitated.

In some embodiments, the embodiments of the present application construct a vendor qualification information base and a verification information base by using a big data analysis technology, which specifically include:

1. Data cleaning:

preprocessing the original supplier qualification information data through a data cleaning technology, including data deduplication, data format conversion, missing value processing and other operations, so as to ensure the accuracy and consistency of the data.

2. Data mapping and labeling:

and correlating and classifying the supplier qualification information from different data sources by using a data mapping and labeling method. By establishing the mapping rules, matching and association of similar fields in different data sources, such as vendor names, certificate types and the like, are realized. Meanwhile, marking standards are defined, and supplier data are classified and marked, such as industry classification, geographical position and other information.

3. Constructing a supplier qualification information base:

a relational database management system (RDBMS) was selected as the data storage technology using a relational model (Entity-Relationship Model) as the data model. The database table structure is designed to include a vendor table (Supplier) and a Qualification table (Qualification). The vendor table stores basic information of vendors such as vendor ID, name, address, etc.; the qualification table stores qualification information of the provider, such as certificate type, certificate number, validity period, etc. And performing data insertion, updating and query operations by using database query languages such as SQL (structured query language) so as to realize storage, management and access of vendor qualification information.

4. Constructing a checking information base:

a Document Model (Document Model) is adopted as a data Model, and a Document database (NoSQL) is selected as a data storage technology. The database collection structure is designed to comprise a check Expert collection (Expert) and a Standard collection (Standard). The checking expert set stores information of checking experts, such as expert IDs, names, fields and the like; the standard set stores information of check standards such as standard IDs, names, descriptions, and the like. Data insertion, updating and query operations are performed using a database operating language to enable storage, management and retrieval of verification knowledge.

Through the implementation process of the technology, a supplier qualification information base is constructed by using a big data analysis technology through data cleaning, data mapping and data labeling, and data support is provided for checking similar suppliers in subsequent batches; constructing a checking information base to provide business support for checking other kinds of goods; and applying a BI analysis tool to provide technical support for checking expert group summarized data.

It should be noted that the steps illustrated in the above-described flow or flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.

The present embodiment provides a provider qualification information checking device, which is used to implement the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the terms "module," "unit," "sub-unit," and the like may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 3 is a block diagram of a vendor qualification information checking apparatus according to an embodiment of the present application, as shown in fig. 3, including:

an obtaining unit 31, configured to obtain a file to be checked of a vendor, where the file to be checked at least includes: vendor basic information, financial reports, contracts, invoices, detection reports, management system certificates, qualification certificates, production process files, business data;

the identifying unit 32 is configured to identify the file to be checked by using a trained identifying model, so as to obtain an identifying result, where the trained identifying model at least includes: a form recognition model, a text recognition model, and an image recognition model;

And a checking unit 33, configured to check different checking scenarios according to the identification result and a pre-configured checking rule, where the checking scenarios at least include: financial report verification, contract performance verification, inspection report verification, management system certificate verification, development design verification, production manufacturing verification, and test inspection verification.

In some of these embodiments, for the financial report check, the identification unit 32 is configured to:

formatting the identified numerical data;

comparing the formatted numerical data with the service data;

In some of these embodiments, the checking unit 33 is configured to:

In some of these embodiments, the apparatus further comprises:

the first construction unit is configured to construct a vendor qualification information base, where the vendor qualification information base adopts a database table structure, and the vendor qualification information base includes: the system comprises a supplier table and a qualification table, wherein the supplier table is used for storing basic information of suppliers, and the qualification table is used for storing qualification information of the suppliers;

the second construction unit is used for constructing a checking information base, wherein the checking information base adopts a database collection structure, and the checking information base comprises: the system comprises a checking expert set and a standard set, wherein the checking expert set is used for storing information of checking experts, and the standard set is used for storing information of checking standards.

The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.

Embodiments provide a computer device. The provider qualification information checking method in combination with the embodiment of the application can be realized by computer equipment. Fig. 4 is a schematic hardware structure of a computer device according to an embodiment of the present application.

The computer device may include a processor 41 and a memory 42 storing computer program instructions.

In particular, the processor 41 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.

Memory 42 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 42 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, solid state Drive (Solid State Drive, SSD), flash memory, optical Disk, magneto-optical Disk, tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. The memory 42 may include removable or non-removable (or fixed) media, where appropriate. The memory 42 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 42 is a Non-Volatile (Non-Volatile) memory. In a particular embodiment, the Memory 42 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (Electrically Alterable Read-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory FPMDRAM), extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory SDRAM), or the like, as appropriate.

Memory 42 may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by processor 41.

The processor 41 implements any of the supplier qualification information checking methods of the above embodiments by reading and executing the computer program instructions stored in the memory 42.

In some of these embodiments, the computer device may also include a communication interface 43 and a bus 40. As shown in fig. 4, the processor 41, the memory 42, and the communication interface 43 are connected to each other through the bus 40 and perform communication with each other.

The communication interface 43 is used to enable communication between various modules, devices, units and/or units in embodiments of the application. The communication interface 43 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.

Bus 40 includes hardware, software, or both, that couple components of the computer device to one another. Bus 40 includes, but is not limited to, at least one of: data Bus (Data Bus), address Bus (Address Bus), control Bus (Control Bus), expansion Bus (Expansion Bus), local Bus (Local Bus). By way of example, and not limitation, bus 40 may include a graphics acceleration interface (Accelerated Graphics Port), AGP or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture), EISA) Bus, front Side Bus (FSB), hyperTransport (HT) interconnect, industry standard architecture (Industry Standard Architecture), ISA) Bus, infiniBand (InfiniBand) interconnect, low Pin Count (LPC) Bus, memory Bus, micro channel architecture (Micro Channel Architecture), MCA Bus, peripheral component interconnect (Peripheral Component Interconnect), PCI-Express (PCI-X) Bus, serial advanced technology attachment (Serial Advanced Technology Attachment, SATA) Bus, video electronics standards association local (Video Electronics Standards Association Local Bus, VLB) Bus, or other suitable Bus, or a combination of two or more of these. Bus 40 may include one or more buses, where appropriate. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

In addition, in combination with the provider qualification information checking method in the above embodiment, the embodiment of the application may be implemented by providing a computer readable storage medium. The computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the provider qualification information checking methods of the above embodiments.

The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A vendor qualification information verification method, comprising:

2. The method of claim 1, wherein for the financial report verification, the identifying the document to be verified using the trained identification model, the obtaining the identification result comprises:

Formatting the identified numerical data;

comparing the formatted numerical data with the service data;

3. The method of claim 1, wherein the verifying the contract performance verification based on the recognition result and a pre-configured verification rule comprises:

4. The method of claim 1, wherein checking the detection report check based on the identification result and a pre-configured check rule comprises:

5. The method of claim 1, wherein checking the management system certificate check based on the identification result and a pre-configured check rule comprises:

6. The method of claim 1, wherein checking the development design check based on the recognition result and a pre-configured check rule comprises:

7. The method of claim 1, wherein checking the production manufacturing check based on the identification result and a pre-configured check rule comprises:

8. The method of claim 1, wherein checking the trial detection check based on the recognition result and a pre-configured check rule comprises:

9. The method according to any one of claims 1 to 8, further comprising:

10. A vendor qualification information checking apparatus, comprising:

11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 9 when executing the computer program.

12. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1 to 9.