CN117474479A - Material auditing method, device, computer equipment and storage medium - Google Patents

Material auditing method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN117474479A
CN117474479A CN202311417864.9A CN202311417864A CN117474479A CN 117474479 A CN117474479 A CN 117474479A CN 202311417864 A CN202311417864 A CN 202311417864A CN 117474479 A CN117474479 A CN 117474479A
Authority
CN
China
Prior art keywords
data
material data
checked
risk identification
result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311417864.9A
Other languages
Chinese (zh)
Inventor
马亿凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Life Insurance Company of China Ltd
Original Assignee
Ping An Life Insurance Company of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Life Insurance Company of China Ltd filed Critical Ping An Life Insurance Company of China Ltd
Priority to CN202311417864.9A priority Critical patent/CN117474479A/en
Publication of CN117474479A publication Critical patent/CN117474479A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of data analysis, and discloses a material auditing method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining material data to be audited, which are uploaded by a user, carrying out multi-level classification on the material data to be audited, obtaining a classification result, carrying out risk identification on the material data to be audited according to the classification result, obtaining a risk identification result of the material data to be audited, carrying out risk audit on the material data to be audited according to the risk identification result, and generating an audit result of the material data to be audited. According to the method and the device, the auditing material data are classified in multiple levels, and risk identification and risk auditing are carried out on the material data to be audited according to the classification result, so that the auditing result is generated, automatic auditing is realized, auditing efficiency and accuracy are improved, and potential risks and errors are reduced.

Description

Material auditing method, device, computer equipment and storage medium
Technical Field
The present invention relates to the field of data analysis, and in particular, to a method and apparatus for auditing materials, a computer device, and a storage medium.
Background
Various institutions (such as banking institutions, insurance institutions, stock institutions, investment institutions, etc.) in the current financial industry typically present detailed descriptions and clauses of their products through promotional materials. In order to ensure that the propaganda materials output by each institution meet the requirements of related laws and regulations and policies, the propaganda materials manufactured by all institutions can be printed through manual auditing, so that the problems of higher labor cost and lower auditing efficiency of material auditing are caused.
At present, the general technical proposal in the industry is to optimize the flow of material examination, carry out hierarchical management on the types of different materials, and lower the examination right to different levels in a hierarchical manner so as to shorten examination duration and improve efficiency. However, a great deal of manpower is still required to audit various materials, especially when short video contents are popular, audit personnel are required to completely browse the video contents to complete audit, and the time consumption is higher than that of other materials, so that the audit efficiency is lower.
Disclosure of Invention
Based on the above, it is necessary to provide a material auditing method, device, computer equipment and storage medium to solve the problems of higher cost and lower efficiency in the existing material auditing technology.
A method of material auditing, comprising:
acquiring material data to be checked uploaded by a user;
carrying out multi-level classification on the material data to be checked to obtain a classification result;
performing risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
A material auditing device, comprising:
the material to be checked data module is used for acquiring material to be checked data uploaded by a user;
the classification result module is used for carrying out multi-level classification on the material data to be checked to obtain a classification result;
the risk identification result module is used for carrying out risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and the auditing result module is used for conducting risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor implementing the material audit method described above when executing the computer readable instructions.
A computer readable storage medium storing a computer program which when executed by a processor implements the material audit method described above.
According to the material auditing method, the device, the computer equipment and the storage medium, the material data to be audited, which are uploaded by the user, are obtained, then the material data to be audited is subjected to multi-level classification to obtain the classification result, so that the risk identification of the material data to be audited is performed according to the classification result, the risk identification result of the material data to be audited is obtained, finally, the risk audit is performed on the material data to be audited according to the risk identification result, and the auditing result of the material data to be audited is generated.
According to the method and the device for checking the risk, the material data to be checked, which are uploaded by the user, are acquired, and then the material data to be checked is subjected to multi-level classification, so that the risk identification of the material data to be checked is carried out according to the classification result, the risk identification result of the material data to be checked is obtained, and finally, the risk checking of the material data to be checked is carried out according to the risk identification result, so that the checking result of the material data to be checked is generated, the automatic checking is realized, the checking efficiency and accuracy are improved, and the potential risk and the potential error are reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for auditing materials according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a material auditing apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a computer device in accordance with an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In one embodiment, as shown in FIG. 1, a method for auditing materials is provided, including the following steps S10-S40.
S10, acquiring material data to be checked uploaded by a user.
It is understood that the material data to be reviewed may be different types of files, here including but not limited to text files, picture files, audio files, and video files.
The material auditing method can be applied to the financial related fields such as insurance, payment, banking, transaction and the like. Taking the insurance field as an example, acquiring the materials to be audited, which are uploaded by the user, through a material auditing platform.
S20, carrying out multi-level classification on the material data to be checked to obtain a classification result.
Understandably, the process of classifying the material data to be audited in multiple levels may be a process of automatically analyzing and understanding the material data to be audited by using a Natural Language Processing (NLP) through a preset classifier, and then classifying the material data into different categories, so as to facilitate the subsequent risk identification and audit process. The classification result may be a result of characterizing a data type of the material data to be inspected and a material type, where the data type includes, but is not limited to, text data, picture data, audio data, and video data, and the material type may be a product introduction, a claim case, and the like. Here, the preset classifier may employ a decision tree classifier.
Taking the insurance field as an example, classifying the material data to be checked of the insurance company according to a preset classifier to obtain the data type and the material type of the material data to be checked, and determining the data type and the material type of the material data to be checked as the classification result of the material data to be checked.
And S30, performing risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked.
Understandably, the risk identification may be a model for identifying a quality inspection point of a classification result through a preset risk identification model, so as to determine a quality inspection point score of material data to be inspected, where the quality inspection point may be a quality inspection point preset according to actual needs, the quality inspection point score may be a numerical value reflecting the risk degree of the quality inspection point, in this embodiment, the value range of the quality inspection point score may be 0 to 10, the higher the quality inspection point score is, the higher the risk is, and conversely, the lower the quality inspection point score is, the lower the risk is.
Taking the insurance field as an example, carrying out quality inspection point identification on classification results through a preset risk identification model, obtaining quality inspection points of the material data to be inspected and quality inspection point scores corresponding to the quality inspection points, and determining the quality inspection point scores corresponding to the quality inspection points of the material data to be inspected as the risk identification results of the material data to be inspected.
And S40, performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
Understandably, risk auditing can be an auditing mode of judging whether the material data to be audited has risks or not by judging the risk identification result according to a preset risk degree judging rule. In this embodiment, the preset risk degree determination rule may determine the risk degree according to whether the composite score of the quality inspection score of the material to be inspected is greater than a risk threshold, for example, if the risk threshold is 6 and the composite score is greater than or equal to 6, it is determined that the material to be inspected has risk; and if the comprehensive score is less than 6, judging that the material data to be checked is not at risk. The process of generating the auditing result of the material data to be audited may be a process of acquiring a material data processing mode associated with the risk auditing result according to the risk auditing result of the material data to be audited, so as to exercise different processing modes on the material data to be audited under different risk auditing results. For example, if the material data to be checked has risk, the manual checking is carried out, and if the material data to be checked has no risk, the checking is passed.
Taking the insurance field as an example, judging a risk identification result according to a preset risk degree judgment rule, and if the auditing result of the material data to be audited is that the risk exists, transferring the material data to be audited into manual auditing; if the auditing results of the material data to be audited are all that the risk does not exist, the material data to be audited passes the auditing.
According to the method, the device and the system, the material data to be audited, which are uploaded by the user, are acquired, and then the material data to be audited are subjected to multi-level classification, so that risk identification is carried out on the material data to be audited according to the classification result, the risk identification result of the material data to be audited is obtained, and finally, risk audit is carried out on the material data to be audited according to the risk identification result, so that the audit result of the material data to be audited is generated, automatic audit is realized, audit efficiency and audit accuracy are improved, and potential risks and errors are reduced.
Optionally, step S20, namely performing multi-level classification on the material data to be inspected to obtain a classification result, includes:
s201, acquiring a data format of the material data to be checked. It is understood that the data format may be a suffix name of the data file, e.g., txt, doc, ppt, png, wav, mp, mp4, wmv, etc.
S202, classifying the material data to be checked in multiple levels according to the data format to obtain the classification result. It is understood that the process of classifying the material data to be audited in multiple levels may be a process of classifying the data format of the material data to be audited, for example, txt, doc, docx and the like are all classified as text data, ppt, pptx, jpg, png and the like are all classified as picture data, wav, mp3, aiff, aac and the like are all classified as audio data, and mp4, avi, mov, wmv and the like are all classified as video data.
Taking the insurance field as an example, identifying the file suffix name of the material data to be audited, obtaining the data format of the material data to be audited, classifying the data format of the material data to be audited in multiple levels,
according to the method and the device, the data format of the material data to be audited is obtained, the material data to be audited is classified in multiple levels according to the data format, and the classification result is obtained, so that the material to be audited is effectively classified, and the auditing efficiency and the auditing accuracy are improved. Meanwhile, the multi-level classification can provide more detailed classification results, and the requirements of different use scenes are better met.
Optionally, step S202, namely, classifying the material data to be inspected in multiple levels according to the data format, to obtain the classification result, includes:
and S203, judging whether the material data to be checked is text data or not according to the data format.
And S204, if the material data to be checked is non-text data, performing text extraction on the non-text data to obtain text materials corresponding to the non-text data. It is understood that the process of text extraction of non-text data may be a process of selecting a text extraction model corresponding to a data type according to the data type of the non-text data to extract text of the non-text data. Here, if the non-text data is picture data, text extraction is performed on the picture data using a Hidden Markov Model (HMM); if the non-text data is audio data, adopting a Convolutional Neural Network (CNN) to extract text from the audio data; if the non-text data is video data, video segmentation processing is firstly carried out on the video data to obtain video streams and audio streams, text extraction is carried out on the audio streams by adopting a Convolutional Neural Network (CNN), image picture processing is carried out on the video streams by extracting one frame every N seconds, a picture stream is obtained, and text extraction is carried out on the picture stream by adopting a Hidden Markov Model (HMM).
S205, classifying the material data to be checked into material types corresponding to the text materials. Understandably, the material type can be a product introduction, a claim case, etc. The process of obtaining the material types corresponding to the text material may be a process of performing vector word conversion on the text material, calculating euclidean distance between the vector word and a preset keyword, extracting the vector word as the recognition keyword if the euclidean distance is smaller than a preset distance threshold, obtaining a comprehensive score of each recognition keyword according to the matching degree between the recognition keyword and the preset keyword and the occurrence frequency of the recognition keyword, obtaining the material types associated with the preset keyword corresponding to the recognition keyword one by one according to a keyword-material association table, namely, selecting the material type associated with each recognition keyword as a target keyword with the highest comprehensive score, and determining the material type corresponding to the target keyword as the material type corresponding to the text material. Here, the keyword-material association table may be an association table in which preset keywords are associated with material types in a one-to-one correspondence, where the keyword-material association table includes a plurality of material types, each keyword is associated with a material type, and each material type is associated with at least one keyword.
S206, generating the classification result according to the material type and the material data to be checked.
Taking the insurance field as an example, judging whether the material data to be checked is text data according to the data format of the material data to be checked, if the material data to be checked is non-text data, extracting text from the non-text data to obtain text materials corresponding to the non-text data, wherein the identification keywords of the text materials are safe and good fortune and money loss, the preset keywords are safe and good fortune and money loss, the matching degree of the identification keywords 'safe and good fortune' and the preset keywords 'safe and good fortune' is 1, the comprehensive score of the identification keyword 'peace and happiness' is 10 points, the matching degree of the identification keyword 'benefit' and the preset keyword 'benefit' is 0.5, the comprehensive score of the identification keyword 'benefit' is 2 points, the identification keyword 'peace and happiness' is used as a target keyword, the material type corresponding to the preset keyword 'peace and happiness' is product introduction, the material type corresponding to the text material is product introduction, namely the material data to be checked is product introduction; if the material data to be checked is text data, directly extracting identification keywords and matching the identification keywords of the text data, determining target keywords, acquiring material types associated with the preset keywords according to the preset keywords corresponding to the target keywords, and generating classification results according to the material types and the material data to be checked.
According to the embodiment, whether the material data to be checked is text data or not is judged according to the data format, if the material data to be checked is non-text data, text extraction is carried out on the non-text data, text materials corresponding to the non-text data are obtained, the material data to be checked is classified into material types corresponding to the text materials, and a classification result is generated according to the material types and the material data to be checked. The method and the device have the advantages that through text extraction and classification, the material types can be judged more accurately, corresponding classification results are generated, auditing efficiency and auditing accuracy are improved, and requirements of different use scenes are met better.
Optionally, step S30, namely performing risk identification on the material data to be checked according to the classification result, to obtain a risk identification result of the material data to be checked, includes:
s301, inquiring quality inspection information corresponding to the classification result in a preset quality inspection library; the quality inspection information includes at least one quality inspection point. Understandably, the preset quality inspection library may be an information library which is associated with quality inspection information in a one-to-one correspondence manner according to preset data types in actual needs, wherein the quality inspection library contains a plurality of quality inspection information, each data type is associated with one quality inspection information, and each quality inspection information is associated with at least one data type. The quality inspection point can be a quality inspection point preset according to actual needs.
S302, carrying out risk identification on the material data to be inspected according to all the quality inspection points to obtain a risk identification result of the material data to be inspected. Understandably, the risk identification may be an action of respectively auditing all quality inspection points of the material data to be audited through a preset risk identification model to determine the score of the quality inspection points.
Taking the insurance field as an example, quality inspection information corresponding to the classification result is queried in a preset quality inspection library, for example, quality inspection points corresponding to text data and picture data are { quality inspection point 1, quality inspection point 2 and quality inspection point 3}, quality inspection points corresponding to audio data are { quality inspection point 2 and quality inspection point 3}, quality inspection points corresponding to video data are { quality inspection point 1 and quality inspection point 3}, all quality inspection points are acquired according to the quality inspection information, each quality inspection point is inspected respectively, quality inspection point score of each quality inspection point is determined, risk identification result of material data to be inspected is determined according to the quality inspection point score of each quality inspection point, risk assessment of the material data to be inspected is achieved, accuracy and efficiency of inspection can be improved through identification and marking of risks, and potential problems are helped to be found and processed rapidly.
Optionally, step S302, namely performing risk identification on the material data to be inspected according to all the quality inspection points, to obtain a risk identification result of the material data to be inspected, including:
and S303, matching keywords corresponding to each quality inspection point to the material data to be inspected through a text recognition model to obtain keyword information corresponding to all the quality inspection points. It is understood that the text recognition model may be a text extraction model preset according to actual needs for extracting text at the texture points. The keyword matching process corresponding to each quality inspection point may be a process of performing keyword matching on the text at each quality inspection point, and since each quality inspection point may have different preset keywords, keyword matching needs to be performed on each quality inspection point. The keyword information includes, but is not limited to, whether keyword information exists or not, and keyword matching degree information.
S304, calculating a risk identification result of the material data to be checked according to the keyword information.
Taking the insurance field as an example, text extraction is carried out on each quality inspection point of the material data to be inspected through a text recognition model, text information corresponding to each quality inspection point is obtained, keyword matching is carried out on the text information corresponding to each quality inspection point according to a preset keyword matching rule and a preset keyword of each quality inspection point, keyword information corresponding to all the quality inspection points is obtained, quality inspection point scores of each quality inspection point are calculated according to the keyword information, and risk recognition results of the material data to be inspected are determined according to the quality inspection point scores of each quality inspection point.
According to the embodiment, the keyword corresponding to each quality inspection point is matched with the material data to be inspected through the text recognition model, the keyword information corresponding to all the quality inspection points is obtained, the risk recognition result of the material data to be inspected is calculated according to the keyword information, the material data to be inspected is analyzed accurately and finely, the risk degree of the material data to be inspected can be judged better, potential problems can be found and processed in time, the inspection efficiency and the inspection accuracy are improved, the user rights and interests are protected, and the platform safety is maintained.
Optionally, step S302, namely performing risk identification on the material data to be checked according to the classification result, to obtain a risk identification result of the material data to be checked, further includes:
s305, if the classification result indicates that the material data to be checked is video data, video segmentation processing is carried out on the material data to be checked, and a video stream to be checked and an audio stream to be checked are obtained. It is understood that the video segmentation process may be the act of dividing video data into a video stream and an audio stream.
S306, inquiring a video stream quality inspection point corresponding to the video stream to be inspected and an audio stream quality inspection point corresponding to the audio stream to be inspected in the preset quality inspection library.
S307, according to the video stream quality inspection, performing first risk identification on the text information and the picture information in the video stream to be checked, and obtaining a first risk identification result.
And S308, carrying out second risk identification on the audio information in the audio stream to be checked according to the audio stream quality inspection point to obtain a second risk identification result.
S309, generating the risk identification result according to the first risk identification result and the second risk identification result.
Taking the insurance field as an example, if the classification result indicates that the material data to be inspected is video data, performing video segmentation on the material data to be inspected to obtain a video stream to be inspected and an audio stream to be inspected, inquiring a video stream quality inspection point corresponding to the video stream to be inspected and an audio stream quality inspection point corresponding to the audio stream to be inspected in a preset quality inspection library, performing first risk identification on text information and picture information in the video stream to be inspected according to the video stream quality inspection point, respectively obtaining quality inspection point scores of the text information and quality inspection point scores of the picture information (wherein the quality inspection point of the text information and the quality inspection point of the picture information are obtained according to the video stream quality inspection point), performing second risk identification on the audio information in the audio stream according to the audio stream quality inspection point, respectively obtaining quality inspection point scores of the text information weight, the picture information weight and the quality inspection point scores of the text information, and the picture information, respectively comparing the text information weight and the quality inspection point scores of the audio information and the preset quality inspection point scores with the audio information, and comprehensively judging that the integrated result is smaller than the integrated risk score is formed by comprehensively judging that the integrated risk score is smaller than the integrated risk score of the integrated material data; if the composite score of the text information, the composite score of the picture information and the composite score of the audio information are not in accordance with the preset composite score threshold (namely, at least one of the composite score of the text information, the composite score of the picture information and the composite score of the audio information is larger than or equal to the preset composite score threshold), the material data to be checked is considered to be not checked, a result that the material data to be checked has risks is generated, and the manual checking is carried out.
According to the embodiment, when the classification result indicates that the material data to be audited is video data, video segmentation processing is carried out on the material data to be audited to obtain a video stream to be audited and an audio stream to be audited, video fluid quality checkpoints corresponding to the video stream to be audited and audio fluid quality checkpoints corresponding to the audio stream to be audited are searched in a preset quality check library, first risk identification is carried out on text information and picture information in the video stream to be audited according to the video fluid quality checkpoints to obtain a first risk identification result, second risk identification is carried out on audio information in the audio stream to be audited according to the audio fluid quality checkpoints to obtain a second risk identification result, and a risk identification result is generated according to the first risk identification result and the second risk identification result. The method and the device realize finer and accurate risk identification on the video data, and conduct special risk identification on different types of information, so that the auditing accuracy and auditing efficiency are improved. Meanwhile, the generated risk identification result can help the platform to discover potential risk problems in time, protect user rights and interests and maintain the safety of the platform.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, a material auditing device is provided, where the material auditing device corresponds to the material auditing method in the above embodiment one by one. As shown in fig. 3, the material auditing apparatus includes a material data module to be audited 10, a classification result module 20, a risk identification result module 30, and an auditing result module 40. The functional modules are described in detail as follows:
the material data to be checked module 10 is used for acquiring material data to be checked uploaded by a user;
the classification result module 20 is configured to perform multi-level classification on the material data to be checked to obtain a classification result;
the risk identification result module 30 is configured to perform risk identification on the material data to be inspected according to the classification result, so as to obtain a risk identification result of the material data to be inspected;
and the auditing result module 40 is used for performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
Optionally, the classification result module 20 includes:
the data format unit is used for acquiring the data format of the material data to be checked;
and the classification result unit is used for carrying out multi-level classification on the material data to be checked according to the data format to obtain the classification result.
Optionally, the classification result module 20 further includes:
the judging unit is used for judging whether the material data to be checked is text data or not according to the data format;
the text material unit is used for extracting text from the non-text data if the material data to be checked is the non-text data, and obtaining text materials corresponding to the non-text data;
the material classification unit is used for classifying the material data to be checked into material types corresponding to the text materials;
and the classification result unit is used for generating the classification result according to the material type and the material data to be checked.
Optionally, the risk identification result module 30 includes:
the quality inspection information unit is used for inquiring quality inspection information corresponding to the classification result in a preset quality inspection library; the quality inspection information comprises at least one quality inspection point;
and the risk identification result unit is used for carrying out risk identification on the material data to be inspected according to all the quality inspection points to obtain a risk identification result of the material data to be inspected.
Optionally, the risk identification result module 30 further includes:
the keyword information unit is used for matching keywords corresponding to each quality inspection point on the material data to be inspected through a text recognition model to obtain keyword information corresponding to all the quality inspection points;
and the risk identification result unit is used for calculating a risk identification result of the material data to be checked according to the keyword information.
Optionally, the risk identification result module 30 further includes:
the video segmentation unit is used for carrying out video segmentation processing on the material data to be checked if the classification result indicates that the material data to be checked is video data, so as to obtain a video stream to be checked and an audio stream to be checked;
the quality inspection point inquiring unit is used for inquiring a video stream quality inspection point corresponding to the video stream to be inspected and an audio stream quality inspection point corresponding to the audio stream to be inspected in the preset quality inspection library;
the first risk identification result unit is used for carrying out first risk identification on the text information and the picture information in the video stream to be checked according to the video stream quality inspection point to obtain a first risk identification result;
the second risk identification result unit is used for carrying out second risk identification on the audio information in the audio stream to be checked according to the audio fluid detection point to obtain a second risk identification result;
and the risk identification result unit is used for generating the risk identification result according to the first risk identification result and the second risk identification result.
For specific limitations of the material auditing apparatus, reference may be made to the above limitations of the material auditing method, and no further description is given here. All or part of the modules in the material auditing device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The non-volatile storage medium stores an operating system and computer readable instructions. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a readable storage medium. The network interface of the computer device is for communicating with an external server via a network connection. The computer readable instructions when executed by a processor implement a method of material auditing. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In one embodiment, a computer device is provided that includes a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, when executing the computer readable instructions, performing the steps of:
acquiring material data to be checked uploaded by a user;
carrying out multi-level classification on the material data to be checked to obtain a classification result;
performing risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
In one embodiment, a computer readable storage medium having computer readable instructions stored thereon is provided, the readable storage medium provided by the present embodiment including a non-volatile readable storage medium and a volatile readable storage medium. The readable storage medium has stored thereon computer readable instructions which when executed by one or more processors perform the steps of:
acquiring material data to be checked uploaded by a user;
carrying out multi-level classification on the material data to be checked to obtain a classification result;
performing risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by instructing the associated hardware by computer readable instructions stored on a non-volatile readable storage medium or a volatile readable storage medium, which when executed may comprise the above described embodiment methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (10)

1. A method for auditing materials, comprising:
acquiring material data to be checked uploaded by a user;
carrying out multi-level classification on the material data to be checked to obtain a classification result;
performing risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and performing risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
2. The material auditing method according to claim 1, wherein the step of classifying the material data to be audited in multiple levels to obtain classification results includes:
acquiring a data format of the material data to be checked;
and classifying the material data to be checked in multiple levels according to the data format to obtain the classification result.
3. The material auditing method of claim 2, wherein the multi-level classification of the material data to be audited according to the data format, to obtain the classification result, comprises:
judging whether the material data to be checked is text data or not according to the data format;
if the material data to be checked is non-text data, text extraction is carried out on the non-text data to obtain text materials corresponding to the non-text data;
classifying the material data to be checked into material types corresponding to the text materials;
and generating the classification result according to the material type and the material data to be checked.
4. The material auditing method according to claim 1, wherein the performing risk identification on the material data to be audited according to the classification result, to obtain a risk identification result of the material data to be audited, includes:
inquiring quality inspection information corresponding to the classification result in a preset quality inspection library; the quality inspection information comprises at least one quality inspection point;
and carrying out risk identification on the material data to be inspected according to all the quality inspection points to obtain a risk identification result of the material data to be inspected.
5. The material auditing method according to claim 4, wherein the performing risk identification on the material data to be audited according to all the quality inspection points to obtain a risk identification result of the material data to be audited includes:
matching keywords corresponding to each quality inspection point on the material data to be inspected through a text recognition model to obtain keyword information corresponding to all the quality inspection points;
and calculating a risk identification result of the material data to be checked according to the keyword information.
6. The material auditing method according to claim 4, wherein the performing risk identification on the material data to be audited according to the classification result, to obtain a risk identification result of the material data to be audited, includes:
if the classification result indicates that the material data to be checked is video data, video segmentation processing is carried out on the material data to be checked to obtain a video stream to be checked and an audio stream to be checked;
inquiring a video stream quality check point corresponding to the video stream to be checked and an audio stream quality check point corresponding to the audio stream to be checked in the preset quality check library;
according to the video stream quality inspection point, performing first risk identification on text information and picture information in the video stream to be checked to obtain a first risk identification result;
performing second risk identification on the audio information in the audio stream to be checked according to the audio fluid detection point to obtain a second risk identification result;
and generating the risk identification result according to the first risk identification result and the second risk identification result.
7. A material auditing device, comprising:
the material to be checked data module is used for acquiring material to be checked data uploaded by a user;
the classification result module is used for carrying out multi-level classification on the material data to be checked to obtain a classification result;
the risk identification result module is used for carrying out risk identification on the material data to be checked according to the classification result to obtain a risk identification result of the material data to be checked;
and the auditing result module is used for conducting risk auditing on the material data to be audited according to the risk identification result, and generating an auditing result of the material data to be audited.
8. The material auditing device of claim 7, wherein the classification result module comprises:
the data format unit is used for acquiring the data format of the material data to be checked;
and the classification result unit is used for carrying out multi-level classification on the material data to be checked according to the data format to obtain the classification result.
9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor, when executing the computer readable instructions, implements the material audit method according to any of claims 1 to 6.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the material auditing method of any of claims 1 to 6.
CN202311417864.9A 2023-10-26 2023-10-26 Material auditing method, device, computer equipment and storage medium Pending CN117474479A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311417864.9A CN117474479A (en) 2023-10-26 2023-10-26 Material auditing method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311417864.9A CN117474479A (en) 2023-10-26 2023-10-26 Material auditing method, device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117474479A true CN117474479A (en) 2024-01-30

Family

ID=89628661

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311417864.9A Pending CN117474479A (en) 2023-10-26 2023-10-26 Material auditing method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117474479A (en)

Similar Documents

Publication Publication Date Title
US11348352B2 (en) Contract lifecycle management
CN109829628B (en) Risk early warning method and device based on big data and computer equipment
CN110597964B (en) Double-recording quality inspection semantic analysis method and device and double-recording quality inspection system
WO2021169111A1 (en) Resume screening method and apparatus, computer device and storage medium
US20230004604A1 (en) Ai-augmented auditing platform including techniques for automated document processing
CN109829629B (en) Risk analysis report generation method, apparatus, computer device and storage medium
CN109992664B (en) Dispute focus label classification method and device, computer equipment and storage medium
CN110377632B (en) Litigation result prediction method, litigation result prediction device, litigation result prediction computer device and litigation result prediction storage medium
US11914963B2 (en) Systems and methods for determining and using semantic relatedness to classify segments of text
CN110674131A (en) Financial statement data processing method and device, computer equipment and storage medium
CN112632268B (en) Complaint work order detection processing method, complaint work order detection processing device, computer equipment and storage medium
CN117707922A (en) Method and device for generating test case, terminal equipment and readable storage medium
CN110532229B (en) Evidence file retrieval method, device, computer equipment and storage medium
CN110362592B (en) Method, device, computer equipment and storage medium for pushing arbitration guide information
US11880798B2 (en) Determining section conformity and providing recommendations
CN118396786A (en) Contract document auditing method and device, electronic equipment and computer readable storage medium
US20230267283A1 (en) System and method for automatic text anomaly detection
CN115393094A (en) Prediction model training method, data analysis method, device and medium
CN114580398A (en) Text information extraction model generation method, text information extraction method and device
CN117859122A (en) AI-enhanced audit platform including techniques for automated document processing
CN117474479A (en) Material auditing method, device, computer equipment and storage medium
CN113901817A (en) Document classification method and device, computer equipment and storage medium
CN114154480A (en) Information extraction method, device, equipment and storage medium
CN110046200B (en) Text credible model analysis method, equipment and device
KR20200112353A (en) Method of analyzing relationships of words or documents by subject and device implementing the same

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination