CN110941952A - Method and device for perfecting audit analysis model - Google Patents
Method and device for perfecting audit analysis model Download PDFInfo
- Publication number
- CN110941952A CN110941952A CN201811092091.0A CN201811092091A CN110941952A CN 110941952 A CN110941952 A CN 110941952A CN 201811092091 A CN201811092091 A CN 201811092091A CN 110941952 A CN110941952 A CN 110941952A
- Authority
- CN
- China
- Prior art keywords
- audit
- analysis
- model
- work
- point information
- 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
Links
Images
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
Abstract
The invention discloses a method and a device for perfecting an audit analysis model. A method of perfecting an audit analysis model, comprising: obtaining an audit work draft; according to analysis key point information required by a pre-constructed audit analysis model, excavating audit analysis logic information corresponding to the analysis key point information from the audit work manuscript; adding the audit analysis logic information to the audit analysis model. According to the technical scheme, the audit analysis model is perfected by utilizing automatic data analysis, the automatic audit analysis model perfecting process is higher in processing speed and efficiency, and the audit analysis model can be updated and perfected more quickly.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for perfecting an audit analysis model.
Background
The audit analysis refers to a method for auditing item evaluation by applying an audit analysis model and data in an audit process by an auditor, and aims to identify the field with high risk of audit, provide guidance for further audit procedures, or perform recheckability evaluation on early-stage audit work.
The audit analysis model is used for calculating audit data under a certain specific application scene according to a specific calculation rule, analyzing according to a calculation result to obtain a conclusion, and identifying an audit risk point. The common audit analysis model is obtained by continuously accumulating and summarizing auditors with abundant experience in daily audit work, and in the analysis process of the audit manuscript, the auditors summarize and record the corresponding relation between the risk points and the audit manuscript data and generate the model, so that the model can be used for identifying the risk points of the audit manuscript data of the same type.
With the increasing quantity and types of enterprises and enterprise services in various industries and fields, the auditing workload is more and more heavy and complicated, and auditors need more complete auditing and analyzing models with more comprehensive functions to assist in completing auditing and analyzing work. However, the audit analysis model is supplemented and perfected by depending on the summary and record of auditors, and the requirement increase of the auditors on the audit analysis model is far not achieved.
Disclosure of Invention
In view of the above, the present invention has been developed to provide a method and apparatus for perfecting an audit analysis model that overcomes, or at least partially addresses, the above-identified problems.
A method of perfecting an audit analysis model, comprising:
obtaining an audit work draft;
according to analysis key point information required by a pre-constructed audit analysis model, excavating audit analysis logic information corresponding to the analysis key point information from the audit work manuscript; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
adding the audit analysis logic information to the audit analysis model.
Optionally, the mining, according to analysis point information required by a pre-constructed audit analysis model, audit analysis logic information corresponding to the analysis point information from the audit work manuscript includes:
performing word segmentation processing on the audit work manuscript;
and according to analysis key point information required by a pre-constructed audit analysis model, auditing analysis logic information corresponding to the analysis key point information is retrieved from an audit work manuscript subjected to word segmentation processing.
Optionally, according to the required analysis main point information of the audit analysis model that founds in advance, retrieve from the audit work manuscript after word segmentation processing with the audit analysis logic information that analysis main point information corresponds includes:
searching an audit work manuscript related to the analysis key point information from an audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
searching audit analysis logic information corresponding to the analysis key point information from an audit work manuscript related to the analysis key point information by using the audit analysis logic key word corresponding to the analysis key point information;
and arranging the audit analysis logic information into structured data.
Optionally, after mining audit analysis logic information corresponding to the analysis point information from the audit work manuscript, the method further includes:
and carrying out duplicate removal processing on the excavated audit analysis logic information.
Optionally, the method further includes:
and establishing an incidence relation between an analysis result of auditing analysis according to the auditing analysis logic information and a preset auditing risk point.
Optionally, before obtaining the audit work draft, the method further includes: constructing an audit analysis model;
the establishing of the audit analysis model specifically comprises the following steps:
determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis or calculation;
and selecting the analysis method and/or the calculation model which can meet the auditing work requirement from the analysis methods and/or the calculation models according to the analysis or calculation result to form an auditing analysis model.
An apparatus for perfecting an audit analysis model, comprising:
the data acquisition unit is used for acquiring an audit work manuscript;
the information mining unit is used for mining audit analysis logic information corresponding to the analysis point information from the audit work manuscript according to analysis point information required by a pre-constructed audit analysis model; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
and the model perfecting unit is used for adding the audit analysis logic information into the audit analysis model.
Optionally, the information mining unit includes:
the word segmentation processing unit is used for carrying out word segmentation processing on the audit work manuscript;
and the information retrieval unit is used for retrieving audit analysis logic information corresponding to the analysis key point information from the audit work manuscript subjected to word segmentation according to analysis key point information required by a pre-constructed audit analysis model.
A storage medium having stored thereon a program which, when executed by a processor, implements the method of perfecting an audit analysis model.
A processor for running a program, wherein the program is run to perform the method for perfecting an audit analysis model.
By means of the technical scheme, the method for perfecting the audit analysis model automatically acquires the audit work draft, the audit analysis logic information corresponding to the analysis key point information is mined from the acquired audit work draft according to the analysis key point information required by the pre-established audit analysis model, and the audit analysis logic information is added into the audit analysis model, so that the audit analysis model has the function of analyzing the analysis key points, and perfection of the audit analysis model is achieved. The processing process is an automatic audit analysis model improvement processing process, the technical scheme can be used for quickly improving the audit analysis model, and the functional requirements of audit workers on the audit analysis model are met.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart diagram illustrating a method for perfecting an audit analysis model according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating another method for perfecting an audit analysis model provided by an embodiment of the present invention;
FIG. 3 is a flow diagram illustrating a process for building an audit analysis model according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram illustrating an apparatus for perfecting an audit analysis model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram illustrating another apparatus for perfecting an audit analysis model according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention discloses a method for perfecting an audit analysis model, which is shown in figure 1 and comprises the following steps:
s101, obtaining an audit work draft;
specifically, the audit work draft refers to a data file draft serving as an audit object in an audit analysis process, and specifically may be an enterprise internal audit work draft, a business annual report audit draft, a special audit work draft, and the like, and the specific format includes data files in formats such as an Excel document, a Word document, an email, a database, and the like.
The audit analysis refers to analyzing and processing the audit work manuscript, evaluating audit items and identifying risk points in the audit items. Audit personnel are carrying out audit analysis to the audit work manuscript to after risk points among them are analyzed, generate the audit analysis model with the corresponding relation between the logic rule and the risk points in the audit process, when the audit work manuscript or the audit item of the same type are evaluated in the later stage, can go on with the help of the generated audit analysis model, promote analysis efficiency. Meanwhile, the auditing personnel can continuously supplement and perfect the auditing analysis model according to the mode in the auditing working process, so that the auditing analysis model can be suitable for more types of auditing item evaluation.
However, the workload of the auditors for perfecting the audit analysis model in work is huge, and the perfection progress of the audit analysis model is never as long as the requirements of the auditors for the audit analysis model are increased. Therefore, the embodiment of the invention proposes a mode of adopting automatic data processing and perfects an audit analysis model by analyzing the audit work manuscript. Therefore, the audit work draft acquisition is to automatically read the set type or the set number of audit work drafts so as to complete the corresponding audit analysis function of the audit analysis model.
For convenience of analysis, the audit work draft may be a file in which a content representation format is set after being collated, or a file in which a content representation format is set after the audit work draft is acquired. The file in which the content representation format is set may be, for example, a file including audit verification items, audit conclusions or bases, audit processing opinions or suggestions.
S102, excavating auditing analysis logic information corresponding to analysis point information from the auditing work manuscript according to analysis point information required by a pre-constructed auditing analysis model;
specifically, the analysis key point information refers to the item information analyzed by the audit analysis model, for example, when the audit analysis model is used for analyzing whether the business cost completion rate has a risk, the business cost completion rate is the item information analyzed by the audit analysis model, that is, the analysis key point information of the audit analysis model.
The audit analysis logic information refers to logic information including information such as an application scenario, a calculation rule, a calculation result, an analysis conclusion, an audit risk point and the like of audit analysis. According to the audit analysis logic information, under a suitable application scene, the calculation rule of the audit analysis logic information is utilized to calculate the items to be audited to obtain the calculation result, the analysis conclusion is obtained according to the analysis result, and the audit risk points in the items to be audited are identified. It can be understood that after the audit analysis logic information corresponding to the analysis key point information is obtained, the audit analysis logic can be used as an audit analysis model to realize the audit analysis of the analysis key point information of the items to be audited.
According to the embodiment of the invention, the audit analysis logic information corresponding to the analysis key point information is retrieved and mined from the audit work manuscript by utilizing the analysis key point information of the audit analysis model.
S103, adding the audit analysis logic information into the audit analysis model.
Specifically, the audit analysis logic information obtained in step S102 is added to the audit analysis model, and the audit analysis model has a function of performing audit analysis on items to be audited according to the audit analysis logic information to obtain an analysis result and identify an audit risk point included in the analysis result, that is, completing the improvement of the audit analysis model.
As can be seen from the above description, according to the technical solution of the embodiment of the present invention, an audit work manuscript is automatically obtained, audit analysis logic information corresponding to the analysis key information is extracted from the obtained audit work manuscript according to the analysis key information of the audit analysis model, and the audit analysis logic information is added to the audit analysis model, so that the audit analysis model has a function of analyzing the analysis key, and the audit analysis model is completed. The processing process is an automatic audit analysis model improvement processing process, the technical scheme can be used for quickly improving the audit analysis model, and the functional requirements of audit workers on the audit analysis model are met.
The technical scheme of the embodiment of the invention can be confirmed by the introduction, and the technical means of data analysis, artificial intelligence and the like are utilized to replace an auditor to perform audit analysis processing on an audit work manuscript, audit analysis logic information corresponding to analysis key point information is mined out, and then the audit analysis logic information is added into an audit analysis model, so that the audit analysis model is perfected. The process and the result of the automatic processing are the same as those of manual processing, but compared with the manual processing, the processing speed is higher, the efficiency is higher, and the auditing analysis model can be updated and perfected more quickly.
Based on the advantage of the processing speed of the processor, the technical scheme of the embodiment of the invention can be rapidly and circularly executed, the obtained audit work manuscript is sequentially processed, and an audit analysis model is perfected. In another mode, the processing can be simultaneously performed on a plurality of or even a large amount of audit work manuscripts, and further the audit analysis model is perfected, so that the perfection of the audit analysis model is more obvious and accurate.
Next, the embodiment of the present invention introduces a detailed description of a specific processing procedure of the method for perfecting an audit analysis model shown in fig. 1, which is provided by the embodiment of the present invention, based on obtaining multiple audit work manuscripts. It can be understood that the following embodiments are detailed implementation procedures of the method for perfecting the audit analysis model, and the technical solutions claimed in the present application can be obtained on the basis of the detailed implementation procedures. The technical scheme of the embodiment of the invention can be expanded and extracted on the basis of the method, and the expanded and extracted technical scheme is within the protection scope of the embodiment of the invention.
Referring to fig. 2, a method for perfecting an audit analysis model provided in the embodiment of the present invention specifically includes:
s201, obtaining an audit work draft;
specifically, the audit analysis manuscript refers to a data file manuscript which is used as an audit object in an audit analysis process, and specifically may be an enterprise internal audit work manuscript, a business annual report audit manuscript, a special audit work manuscript and the like, and the specific format includes data files in formats of an Excel document, a Word document, an email, a database and the like.
In addition, the embodiment of the invention sets the obtained audit work draft to be a plurality of, even a large number of audit work drafts, wherein the audit work drafts of different industries and different fields can be related, the richness and the diversity of the audit work draft are kept, and an audit analysis model which is perfected based on the audit work draft has compatibility and universal applicability to the items to be audited of each industry and each field.
S202, preprocessing the obtained audit work draft;
specifically, the audit analysis work drafts obtained in step S201 are a large number of audit analysis work drafts, and may be audit work drafts of different industries, different fields, and different formats.
The main preprocessing comprises format conversion, data deduplication, data cleaning, data sorting and the like.
Format conversion, which means to uniformly convert the obtained audit work manuscripts with different formats into audit work manuscripts with the same format in order to facilitate uniform processing of the obtained audit work manuscripts.
And data deduplication refers to removing repeated audit work manuscripts in the obtained audit work manuscripts.
And data cleaning, namely processing the audit work draft with an irregular form in the obtained audit work draft into the audit work draft with a standard form. The data cleaning function can correct the manuscript form while acquiring and acquiring the audit work manuscript, and the common data acquisition and cleaning methods mainly comprise methods of data warehouse ETL, data conversion, mapping, filtering and the like.
And data sorting, namely sorting the audit work manuscript which is subjected to format conversion, data deduplication and data cleaning into the audit work manuscript which is represented in a set content representation form. In the embodiment of the present invention, the data sorting specifically refers to sorting the audit work draft into the audit work draft represented by the audit verification items, the audit conclusion or basis, the audit processing opinions or suggestions, that is, identifying and screening specific contents in the original audit work draft, and sorting according to the audit verification items, the audit conclusion or basis, the audit processing opinions or suggestions.
It can be understood that after the above preprocessing, the remaining audit work manuscripts are uniform in format and content representation, and no duplicate audit work manuscripts exist.
S203, performing word segmentation processing on the audit work manuscript;
specifically, for the work of perfecting the audit analysis model, the essence is to compare whether the relevant information (such as risk points) in the audit analysis work manuscript is added to the model, and this work can be completed only by comparing a large number of work manuscripts, and the first step of the text analysis comparison work is to perform word segmentation processing to realize the capture and comparison of keywords.
The embodiment of the invention adopts a word segmentation processing tool commonly used in the technical field of word segmentation to realize word segmentation processing on the audit work manuscript. For Chinese word segmentation, a double natural language processing algorithm, a Chinese word segmentation algorithm, a Hadamard language technology platform, a Chinese word segmentation system of Chinese academy, and the like can be adopted for realization; for English word segmentation, the method can be realized by adopting a weighted technology TF-IDF or BM25 retrieval algorithm of information retrieval and data mining.
After the word segmentation processing is carried out on the audit work manuscript, the sentences in the audit work manuscript are divided into words or phrases which are arranged in sequence, so that comparison and identification with key words can be conveniently carried out.
S204, searching an audit work manuscript related to the analysis key point information from the audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
specifically, the analysis key point information refers to the item information analyzed by the audit analysis model, for example, when the audit analysis model is used for analyzing whether the business cost completion rate has a risk, the business cost completion rate is the item information analyzed by the audit analysis model, that is, the analysis key point information of the audit analysis model. It can be understood that the analysis key point information of the audit analysis model represents the main analysis object and the realized analysis function of the audit analysis model.
After the analysis key point information is clarified, the embodiment of the invention searches each audit work manuscript after the word segmentation processing based on the analysis key point information, searches whether the analysis key point information exists in the audit work manuscript, determines the repetition rate of the analysis key point information in the audit work manuscript through searching, and finally selects a certain number of audit work manuscripts with higher repetition rate of the analysis key point in the audit work manuscripts as the audit work manuscripts related to the analysis key point information.
For example, assuming that the analysis key information of the audit analysis model is "business cost completion rate", when the audit work draft related to the "business cost completion rate" is retrieved, the "business cost completion rate" is used as a retrieval key word to retrieve the above audit work draft after the word segmentation processing, and a certain number of audit work drafts with the highest "business cost completion rate" repetition rate are retrieved from the above audit work drafts after the word segmentation processing, that is, the audit work draft related to the "business cost completion rate" is obtained.
In the retrieval process, the analysis key point information is compared with each word or phrase in the audit work manuscript after word segmentation, and whether the analysis key point information exists in the audit work manuscript is judged.
S205, using the auditing analysis logic key words corresponding to the analysis key point information to retrieve auditing analysis logic information corresponding to the analysis key point information from the auditing work manuscript related to the analysis key point information;
specifically, the audit analysis logic keyword refers to a keyword or a phrase that represents each analysis factor in the audit analysis process and has a logic relationship with the audit analysis key information. The audit analysis logic key words specifically comprise information such as application scenes, calculation rules, calculation results, analysis conclusions, audit risk points and the like of an audit analysis process aiming at analysis key point information.
It can be understood that, since the audit analysis logic keyword includes information such as an application scenario, a calculation rule, a calculation result, an analysis conclusion, and an audit risk point for performing audit analysis on the analysis key information, the audit analysis logic information corresponding to the analysis key information retrieved from the audit work manuscript related to the analysis key information by using the audit analysis logic keyword also includes information such as an application scenario, a calculation rule, a calculation result, an analysis conclusion, and an audit risk point for performing audit analysis. According to the audit analysis logic information, under a suitable application scene, the calculation rule of the audit analysis logic information is utilized to calculate the items to be audited to obtain the calculation result, the analysis conclusion is obtained according to the analysis result, and the audit risk points in the items to be audited are identified. It can be understood that after the audit analysis logic information corresponding to the analysis key point information is obtained, the audit analysis logic can be used as an audit analysis model or a function of a design analysis model to realize the audit analysis of the analysis key point information of the items to be audited.
S206, arranging the retrieved audit analysis logic information into structured data;
specifically, after the audit analysis logic information is mined from the audit work manuscript, in order to facilitate adding the audit analysis logic information to the audit analysis model, the embodiment of the present invention performs structural processing on the mined audit analysis logic information, and arranges the mined audit analysis logic information into structural data, for example, the mined audit analysis logic information is constructed into data structures such as a dictionary.
The processing of steps S204 to S206 realizes that audit analysis logic information corresponding to the analysis point information is retrieved from the audit work draft after the word segmentation processing according to the analysis point information of the audit analysis model, and the processing of steps S203 to S206 completes the processing procedure of mining the audit analysis logic information corresponding to the analysis point information from the audit work draft.
S207, carrying out duplicate removal processing on the excavated audit analysis logic information;
specifically, after the audit analysis logic information corresponding to the analysis key information is mined from the audit work manuscript through the steps S203 to S206, the embodiment of the present invention further verifies whether the mined audit analysis logic information is repeated with the audit analysis logic information already existing in the audit analysis model, and if the audit analysis logic information repeated with the audit analysis logic information already existing in the audit analysis model exists, the repeated audit analysis logic information is removed.
The embodiment of the invention adopts a cosine method or a text similarity calculation method such as Euclidean distance and the like, calculates the cosine deviation degree or the distance between the mined audit analysis logic information and the audit analysis logic information in the audit analysis model, and then determines whether the mined audit analysis logic information is repeated audit analysis logic information or not according to the value of the deviation degree or the distance.
S208, adding audit analysis logic information into an audit analysis model;
specifically, after the re-ranking processing of the mined audit analysis logic information is executed, the remaining audit analysis logic information is added to the audit analysis model, and the audit analysis model has the functions of performing audit analysis according to the added audit analysis logic information and identifying risk points, namely, the function perfection of the audit analysis model is realized.
And the other feasible mode is that the mined audit analysis logic information is regarded as an audit analysis model, and the mined audit analysis model is added into an audit analysis model base to complete and supplement the audit analysis model base.
S209, establishing an incidence relation between an analysis result of audit analysis according to the audit analysis logic information and a preset audit risk point.
Specifically, in the embodiment of the present invention, after the completion of the audit analysis model, an association relationship is further established between an analysis result of the audit analysis model, that is, an analysis result of the audit analysis performed according to the audit analysis logic information, and a preset audit risk point.
According to the embodiment of the invention, the incidence relation between the analysis result of the audit analysis logic information and the preset audit risk point is established by counting the occurrence frequency or frequency of the preset audit risk point under different analysis results.
After the incidence relation between the analysis result of the audit analysis logic information and the audit risk point is established, namely after the incidence relation between the audit analysis model and the audit risk point is established, when the audit analysis model is applied specifically, whether the audit risk point exists can be analyzed by using the audit analysis model, and the audit analysis model corresponding to the audit risk point can be selected according to the audit risk point to be verified whether the audit risk point exists.
It can be seen from the above description that the audit analysis model perfecting method provided by the embodiment of the invention realizes that audit analysis logic information is automatically mined from massive audit work manuscripts, and the mined audit analysis logic information is used for perfecting and supplementing the audit analysis model, thereby enhancing the audit analysis function of the audit analysis model.
Optionally, in another embodiment of the present invention, it is further disclosed that the method for perfecting the audit analysis model includes a processing step of constructing the audit analysis model.
It can be understood that, since the audit analysis model is a model for calculating the audit data of the audited object according to the set calculation rule and identifying the audit risk points according to the calculation result, i.e. a model with special functions, the audit analysis model needs to be constructed first, and then the audit analysis model is perfected on the basis, i.e. the established audit analysis model is perfected by applying the technical scheme of the invention.
Referring to fig. 3, the embodiment of the present invention discloses the above-mentioned specific process for constructing the audit analysis model. The above-mentioned audit analysis model construction specifically includes:
s301, determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
specifically, the audit work requirement refers to an analysis purpose that an audit worker needs to perform audit analysis work, such as analyzing corporate liabilities, analyzing corporate losses, analyzing the authenticity of corporate production and operation activities, and the like.
In terms of auditing function, auditing analysis models can be divided into two types, one type is a general analysis model which mainly analyzes the general condition of an audited object, and the auditing analysis model can be further divided into a whole analysis model and a business analysis model according to the analysis object.
The overall analysis model is based on the financial statement of the audited unit, and the assets, liabilities, losses and profits and cash flows of the audited unit are analyzed by applying methods such as a structural analysis method and a trend analysis method to obtain an analysis conclusion. The business analysis model is basically consistent with the overall analysis model in the analysis method, only the analysis object is more detailed, the analysis object is the main production and operation business of the audited unit, taking the banking industry as an example, the business analysis model generally has a public deposit business analysis model and a deposit business analysis model.
Another type of audit analysis model is an individual analysis model, which is typically built to solve a specific problem. The general analysis model is mainly a general analysis model, and the general analysis model is mainly an overall analysis model which is mainly an overall analysis model.
The overall analysis model takes the financial statement as an analysis object, and the calculation model mainly comprises the following four types:
(1) structural analysis
The structure analysis comprises asset structure analysis, liability structure analysis and profit and loss structure analysis, and the problems are found by revealing the proportion of each item of asset, liability, income, cost and expense to the base of the item of data (assets are usually based on the total amount of assets, liabilities are based on the total amount of liabilities, and profits are based on the total income).
(2) Trend analysis
The trend analysis comprises asset trend analysis, liability trend analysis and profit-and-loss trend analysis, and the problems are discovered and the solutions are proposed by comparing the variation trends of the important projects compared with the base period.
(3) Ratio analysis
The proportion analysis refers to finding problems by calculating a financial analysis index or formula, and can be further divided into asset management indexes according to the difference of the financial analysis indexes, such as inventory turnover rate (sales cost)/[ (initial inventory + end inventory) ]/2, and inventory turnover days (360)/inventory turnover rate; liability management indicators, such as the rate of liability versus total amount of liability/total amount of liability; profitability indicators, such as net sales rate (net profit/sales revenue); cash flow analysis, such as flow ratio — flowing assets/flowing liability.
(4) Comprehensive analysis
The comprehensive analysis refers to the comprehensive application of financial analysis indexes, and the more commonly used analysis models comprise a DuPont model, a Woll ratio comprehensive scoring model and a modern comprehensive evaluation model.
It can be understood that when the audit staff carries out the audit work or constructs the audit analysis model with specific functional requirements, the specific audit work purpose or the audit analysis purpose can be achieved, the audit work purpose or the analysis purpose, namely the audit work requirement, can be determined through the introduction, and different audit work requirements are achieved through different types of audit analysis models.
Therefore, when the audit analysis model is constructed, the audit work requirement is determined, and then the analysis method and/or the calculation model are determined according to the audit work requirement.
Specifically, the analysis method and the calculation model are those which can theoretically satisfy the audit work requirement. It can be understood that the audit analysis model essentially performs a series of operations such as analysis, calculation, processing and the like on input data to finally obtain an analysis result. That is, the audit analysis model is actually an integrated process model including a series of analysis methods, calculation models.
After the audit work requirement is determined, the embodiment of the invention further determines an analysis method or a calculation model which can realize the audit work requirement.
It should be noted that the analysis method or the calculation model for realizing the audit work requirement is preliminarily selected, and theoretically, the analysis method or the calculation model for meeting the audit work requirement can be further subjected to actual data calculation verification to determine whether the combination of the selected analysis method and/or the calculation model can meet the audit work requirement.
S302, obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
specifically, after the analysis method and the calculation model are determined, the embodiment of the invention extracts and converts each item of audit data from the database of the audited object, and the converted data is used for analyzing, calculating and verifying the analysis method or the calculation model.
Further, after obtaining audit data applicable to the analysis method and/or the calculation model, the embodiment of the present invention further stores the obtained data in an audit intermediate table.
S303, respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis and/or calculation processing;
specifically, when performing calculation verification on the determined analysis method and/or calculation model, the embodiment of the present invention first instantiates the analysis method and/or calculation model, that is, represents the analysis method or calculation model in the form of program code, for example, in the embodiment of the present invention, the analysis method and/or calculation model may be instantiated in the form of SQL statement, and then the obtained audit data applicable to the analysis method and/or calculation model is respectively input into the respectively applicable analysis method or calculation model for analysis or calculation.
And S304, selecting an analysis method and/or a calculation model which can meet the requirement of the audit work from the analysis methods and/or the calculation models according to the processing result of the analysis and/or calculation processing to form an audit analysis model.
Specifically, according to the processing result of the analysis method and/or the calculation model on the input audit data, whether the analysis method and/or the calculation model can be processed to obtain the data result desired by the audit work can be identified.
If the result of the analysis or calculation of the audit data by the analysis method or the calculation model meets the requirement of the audit work data, the analysis method or the calculation model can be used for constructing the audit analysis model; and if the result of the analysis or calculation of the audit data by the analysis method or the calculation model does not meet the requirement of the audit work data, the analysis method or the calculation model cannot be used for constructing the audit analysis model.
On the basis, according to the processing results of the analysis methods and the calculation models, the analysis methods and/or the calculation models which can meet the requirements of the audit work are selected and used for forming the audit analysis model.
Specifically, the selected analysis methods and/or calculation models form an audit analysis model, and the selected analysis methods and/or calculation models are sequentially combined, cascaded and the like, so that all the selected analysis methods and/or calculation models are finally combined into a complete audit analysis model.
Another embodiment of the present invention further discloses a device for perfecting an audit analysis model, as shown in fig. 4, the device includes:
a data obtaining unit 100, configured to obtain an audit work manuscript;
the information mining unit 110 is configured to mine, according to analysis point information required by a pre-constructed audit analysis model, audit analysis logic information corresponding to the analysis point information from the audit work manuscript; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
a model perfecting unit 120, configured to add the audit analysis logic information to the audit analysis model.
Optionally, in another embodiment of the present invention, it is further disclosed that the data obtaining unit 100 is further configured to:
when the number of the audit work manuscripts is multiple, preprocessing the audit work manuscripts after the audit work manuscripts are obtained; the preprocessing comprises data deduplication, data cleaning and data sorting.
Optionally, in another embodiment of the present invention, referring to fig. 5, the information mining unit 110 includes:
a word segmentation processing unit 1101, configured to perform word segmentation processing on the audit work manuscript;
and the information retrieval unit 1102 is configured to retrieve audit analysis logic information corresponding to the analysis point information from an audit work manuscript subjected to word segmentation processing according to analysis point information required by a pre-constructed audit analysis model.
Optionally, in another embodiment of the present invention, the information retrieving unit 1102 includes:
the first retrieval unit is used for retrieving an audit work manuscript related to the analysis key point information from the audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
a second retrieval unit, configured to retrieve, from an audit work manuscript related to the analysis key point information, audit analysis logic information corresponding to the analysis key point information by using an audit analysis logic keyword corresponding to the analysis key point information;
and the data sorting unit is used for sorting the audit analysis logic information into structured data.
Optionally, in another embodiment of the present invention, the apparatus further includes:
and the re-arranging processing unit is used for carrying out re-arranging processing on the excavated audit analysis logic information.
Optionally, in another embodiment of the present invention, the apparatus further includes:
and the data association processing unit is used for establishing an association relation between an analysis result of audit analysis according to the audit analysis logic information and a preset audit risk point.
Optionally, in another embodiment of the present invention, the apparatus further includes: the model construction unit is used for constructing an audit analysis model;
when the model construction unit constructs the audit analysis model, the model construction unit is specifically configured to:
determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis or calculation;
and selecting the analysis method and/or the calculation model which can meet the auditing work requirement from the analysis methods and/or the calculation models according to the analysis or calculation result to form an auditing analysis model.
Specifically, for the specific working content of each unit in each embodiment of the apparatus for perfecting the audit analysis model, please refer to the content of the above method embodiment, which is not described herein again.
The device for perfecting the audit analysis model comprises a processor and a memory, wherein the data acquisition unit, the information mining unit, the model perfecting unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the audit analysis model is perfected by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a storage medium, on which a program is stored, where the program, when executed by a processor, implements the method for perfecting an audit analysis model.
The embodiment of the invention provides a processor, which is used for running a program, wherein the method for perfecting an audit analysis model is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:
obtaining an audit work draft;
according to analysis key point information required by a pre-constructed audit analysis model, excavating audit analysis logic information corresponding to the analysis key point information from the audit work manuscript; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
adding the audit analysis logic information to the audit analysis model.
Optionally, the mining, according to analysis point information required by a pre-constructed audit analysis model, audit analysis logic information corresponding to the analysis point information from the audit work manuscript includes:
performing word segmentation processing on the audit work manuscript;
and according to analysis key point information required by a pre-constructed audit analysis model, auditing analysis logic information corresponding to the analysis key point information is retrieved from an audit work manuscript subjected to word segmentation processing.
Optionally, according to the required analysis main point information of the audit analysis model that founds in advance, retrieve from the audit work manuscript after word segmentation processing with the audit analysis logic information that analysis main point information corresponds includes:
searching an audit work manuscript related to the analysis key point information from an audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
searching audit analysis logic information corresponding to the analysis key point information from an audit work manuscript related to the analysis key point information by using the audit analysis logic key word corresponding to the analysis key point information;
and arranging the audit analysis logic information into structured data.
Optionally, after mining audit analysis logic information corresponding to the analysis point information from the audit work manuscript, the method further includes:
and carrying out duplicate removal processing on the excavated audit analysis logic information.
Optionally, the method further includes:
and establishing an incidence relation between an analysis result of auditing analysis according to the auditing analysis logic information and a preset auditing risk point.
Optionally, before obtaining the audit work draft, the method further includes: constructing an audit analysis model;
the establishing of the audit analysis model specifically comprises the following steps:
determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis or calculation;
and selecting the analysis method and/or the calculation model which can meet the auditing work requirement from the analysis methods and/or the calculation models according to the analysis or calculation result to form an auditing analysis model.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
obtaining an audit work draft;
according to analysis key point information required by a pre-constructed audit analysis model, excavating audit analysis logic information corresponding to the analysis key point information from the audit work manuscript; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
adding the audit analysis logic information to the audit analysis model.
Optionally, the mining, according to analysis point information required by a pre-constructed audit analysis model, audit analysis logic information corresponding to the analysis point information from the audit work manuscript includes:
performing word segmentation processing on the audit work manuscript;
and according to analysis key point information required by a pre-constructed audit analysis model, auditing analysis logic information corresponding to the analysis key point information is retrieved from an audit work manuscript subjected to word segmentation processing.
Optionally, according to the required analysis main point information of the audit analysis model that founds in advance, retrieve from the audit work manuscript after word segmentation processing with the audit analysis logic information that analysis main point information corresponds includes:
searching an audit work manuscript related to the analysis key point information from an audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
searching audit analysis logic information corresponding to the analysis key point information from an audit work manuscript related to the analysis key point information by using the audit analysis logic key word corresponding to the analysis key point information;
and arranging the audit analysis logic information into structured data.
Optionally, after mining audit analysis logic information corresponding to the analysis point information from the audit work manuscript, the method further includes:
and carrying out duplicate removal processing on the excavated audit analysis logic information.
Optionally, the method further includes:
and establishing an incidence relation between an analysis result of auditing analysis according to the auditing analysis logic information and a preset auditing risk point.
Optionally, before obtaining the audit work draft, the method further includes: constructing an audit analysis model;
the establishing of the audit analysis model specifically comprises the following steps:
determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis or calculation;
and selecting the analysis method and/or the calculation model which can meet the auditing work requirement from the analysis methods and/or the calculation models according to the analysis or calculation result to form an auditing analysis model.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of perfecting an audit analysis model, comprising:
obtaining an audit work draft;
according to analysis key point information required by a pre-constructed audit analysis model, excavating audit analysis logic information corresponding to the analysis key point information from the audit work manuscript; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
adding the audit analysis logic information to the audit analysis model.
2. The method of claim 1, wherein the mining audit analysis logic information corresponding to the analysis point information from the audit work draft according to analysis point information required by a pre-constructed audit analysis model comprises:
performing word segmentation processing on the audit work manuscript;
and according to analysis key point information required by a pre-constructed audit analysis model, auditing analysis logic information corresponding to the analysis key point information is retrieved from an audit work manuscript subjected to word segmentation processing.
3. The method according to claim 2, wherein the step of retrieving audit analysis logic information corresponding to the analysis point information from an audit work manuscript subjected to word segmentation processing according to analysis point information required by a pre-constructed audit analysis model comprises the following steps:
searching an audit work manuscript related to the analysis key point information from an audit work manuscript subjected to word segmentation processing by using analysis key point information required by a pre-constructed audit analysis model;
searching audit analysis logic information corresponding to the analysis key point information from an audit work manuscript related to the analysis key point information by using the audit analysis logic key word corresponding to the analysis key point information;
and arranging the audit analysis logic information into structured data.
4. The method of any of claims 1-3, wherein after mining audit analysis logic information corresponding to the analysis point information from the audit work draft, the method further comprises:
and carrying out duplicate removal processing on the excavated audit analysis logic information.
5. The method of claim 1, further comprising:
and establishing an incidence relation between an analysis result of auditing analysis according to the auditing analysis logic information and a preset auditing risk point.
6. The method of claim 1, wherein prior to obtaining the audit work draft, the method further comprises: constructing an audit analysis model;
the establishing of the audit analysis model specifically comprises the following steps:
determining an audit work requirement, and determining an analysis method and/or a calculation model according to the audit work requirement;
obtaining audit data required by the analysis method and/or the calculation model for analysis or calculation;
respectively inputting the obtained audit data into the instantiated analysis method and/or calculation model for analysis or calculation;
and selecting the analysis method and/or the calculation model which can meet the auditing work requirement from the analysis methods and/or the calculation models according to the analysis or calculation result to form an auditing analysis model.
7. An apparatus for perfecting an audit analysis model, comprising:
the data acquisition unit is used for acquiring an audit work manuscript;
the information mining unit is used for mining audit analysis logic information corresponding to the analysis point information from the audit work manuscript according to analysis point information required by a pre-constructed audit analysis model; the audit analysis model is used for calculating audit data of an audited object according to a set calculation rule and identifying an audit risk point according to a calculation result;
and the model perfecting unit is used for adding the audit analysis logic information into the audit analysis model.
8. The apparatus of claim 7, wherein the information mining unit comprises:
the word segmentation processing unit is used for carrying out word segmentation processing on the audit work manuscript;
and the information retrieval unit is used for retrieving audit analysis logic information corresponding to the analysis key point information from the audit work manuscript subjected to word segmentation according to analysis key point information required by a pre-constructed audit analysis model.
9. A storage medium having stored thereon a program which, when executed by a processor, implements the method of perfecting an audit analysis model of any one of claims 1 to 6.
10. A processor, wherein the processor is configured to run a program, wherein the program when executed performs the method of perfecting an audit analysis model of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811092091.0A CN110941952A (en) | 2018-09-19 | 2018-09-19 | Method and device for perfecting audit analysis model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811092091.0A CN110941952A (en) | 2018-09-19 | 2018-09-19 | Method and device for perfecting audit analysis model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110941952A true CN110941952A (en) | 2020-03-31 |
Family
ID=69904253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811092091.0A Pending CN110941952A (en) | 2018-09-19 | 2018-09-19 | Method and device for perfecting audit analysis model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110941952A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612379A (en) * | 2020-06-03 | 2020-09-01 | 云南电网有限责任公司 | Audit scheme automatic generation method and device |
| CN111782712A (en) * | 2020-07-02 | 2020-10-16 | 云南省地图院 | Natural resource asset audit comprehensive space analysis system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
| US20140100910A1 (en) * | 2012-10-08 | 2014-04-10 | Sap Ag | System and Method for Audits with Automated Data Analysis |
| CN106503102A (en) * | 2016-10-17 | 2017-03-15 | 汉蓝（北京）科技有限公司 | A kind of search engine formula audit analysis method |
| CN106815125A (en) * | 2015-12-02 | 2017-06-09 | 阿里巴巴集团控股有限公司 | A kind of log audit method and platform |
| CN107330628A (en) * | 2017-07-06 | 2017-11-07 | 云南电网有限责任公司 | A kind of construction method and device of auditing risk management information bank |
-
2018
- 2018-09-19 CN CN201811092091.0A patent/CN110941952A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
| US20140100910A1 (en) * | 2012-10-08 | 2014-04-10 | Sap Ag | System and Method for Audits with Automated Data Analysis |
| CN106815125A (en) * | 2015-12-02 | 2017-06-09 | 阿里巴巴集团控股有限公司 | A kind of log audit method and platform |
| CN106503102A (en) * | 2016-10-17 | 2017-03-15 | 汉蓝（北京）科技有限公司 | A kind of search engine formula audit analysis method |
| CN107330628A (en) * | 2017-07-06 | 2017-11-07 | 云南电网有限责任公司 | A kind of construction method and device of auditing risk management information bank |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612379A (en) * | 2020-06-03 | 2020-09-01 | 云南电网有限责任公司 | Audit scheme automatic generation method and device |
| CN111782712A (en) * | 2020-07-02 | 2020-10-16 | 云南省地图院 | Natural resource asset audit comprehensive space analysis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10242016B2 (en) | Systems and methods for management of data platforms | |
| US20130006996A1 (en) | Clustering E-Mails Using Collaborative Information | |
| CN107016001A (en) | A kind of data query method and device | |
| CN113342976B (en) | Method, device, storage medium and equipment for automatically acquiring and processing data | |
| CN109325055A (en) | The screening of business association tables of data and checking method, device, electronic equipment | |
| CN111553556A (en) | Business data analysis method and device, computer equipment and storage medium | |
| CN111651552B (en) | Structured information determining method and device and electronic equipment | |
| CN114139539A (en) | Enterprise social responsibility index quantification method, system and application | |
| US20220229854A1 (en) | Constructing ground truth when classifying data | |
| CN113220885B (en) | Text processing method and system | |
| CN110941952A (en) | Method and device for perfecting audit analysis model | |
| CN107729330A (en) | The method and apparatus for obtaining data set | |
| Yu | Data mining in library reader management | |
| CN111930944A (en) | File label classification method and device | |
| EP3152678A1 (en) | Systems and methods for management of data platforms | |
| CN112699245A (en) | Construction method and device and application method and device of budget management knowledge graph | |
| CN110858214B (en) | Recommendation model training and further auditing program recommendation method, device and equipment | |
| US11880394B2 (en) | System and method for machine learning architecture for interdependence detection | |
| Priya et al. | Entity resolution for high velocity streams using semantic measures | |
| JP2019200582A (en) | Search device, search method, and search program | |
| CN110737749B (en) | Entrepreneurship plan evaluation method, entrepreneurship plan evaluation device, computer equipment and storage medium | |
| US20140280149A1 (en) | Method and system for content aggregation utilizing contextual indexing | |
| JP5399988B2 (en) | Important date expression determination method, important date expression determination device, important date expression determination program | |
| US11500933B2 (en) | Techniques to generate and store graph models from structured and unstructured data in a cloud-based graph database system | |
| US11416685B2 (en) | System and method for artificial intelligence driven document analysis, including automated reuse of predictive coding rules based on management and curation of datasets or models |
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 |