CN111695979A - Method, device and equipment for analyzing relation between raw material and finished product - Google Patents
Method, device and equipment for analyzing relation between raw material and finished product Download PDFInfo
- Publication number
- CN111695979A CN111695979A CN202010558852.8A CN202010558852A CN111695979A CN 111695979 A CN111695979 A CN 111695979A CN 202010558852 A CN202010558852 A CN 202010558852A CN 111695979 A CN111695979 A CN 111695979A
- Authority
- CN
- China
- Prior art keywords
- target
- commodity
- industry
- enterprise
- finished product
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/10—Tax strategies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for analyzing the relation between raw materials and finished products, wherein the method comprises the following steps: determining an enterprise needing to be analyzed as a target enterprise, and determining an industry to which the target enterprise belongs as a target industry; sequentially determining target enterprises and target industries as target units, extracting raw materials and finished products from invoices of the target units, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; any finished product and raw materials required for producing the any finished product have a corresponding relation; and comparing the ratio information of the raw materials required by each finished product extracted from the invoice of the target enterprise with the ratio information of the raw materials required by the same finished product extracted from the invoice of the target industry, and determining whether the invoice containing information of the target enterprise is abnormal or not based on the comparison result. The method and the device can determine whether the enterprise taxes through the invoice based on the actual production condition of the enterprise.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a method, a device, equipment and a storage medium for analyzing the relation between a raw material and a finished product.
Background
In the field of tax, the tax payment condition of an enterprise generally needs to be analyzed, and whether the enterprise has false invoices, less taxes and the like as a taxpayer is identified; however, how to judge whether the enterprise taxes based on the actual situation is an urgent problem to be solved when analyzing the taxes situation of the enterprise by the technical personnel in the field.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a storage medium for analyzing the relation between raw materials and finished products, which can determine whether an enterprise taxes through invoices based on the actual production condition.
In order to achieve the above purpose, the invention provides the following technical scheme:
a method for analyzing the relation between raw materials and finished products comprises the following steps:
determining an enterprise needing to be analyzed as a target enterprise, wherein the industry to which the target enterprise belongs is a target industry;
sequentially determining the target enterprise and the target industry as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; wherein, any finished product and the raw material needed for producing the product have corresponding relation;
and comparing the ratio information of the raw materials required by each finished product extracted from the target enterprise invoice with the ratio information of the raw materials required by the same finished product extracted from the target enterprise invoice, and determining whether the information contained in the target enterprise invoice is abnormal or not based on the comparison result.
Preferably, the obtaining of the correspondence between the extracted raw material and the finished product includes:
and constructing a relation map of the extracted raw materials and finished products, and analyzing the relation map to obtain the corresponding relation between the corresponding raw materials and finished products.
Preferably, the determining that the industry to which the target enterprise belongs is the target industry includes:
extracting purchase and sale item data from the invoices of the target enterprise, inputting the purchase and sale item data into an industry identification model to obtain an industry output by the industry identification model, and determining the industry as the target industry; the industry identification model is obtained by utilizing purchase and sale item data extracted from invoices of various industries and names of various industries in advance for training.
Preferably, before extracting the corresponding information from the invoice, the method further includes:
extracting the commodity name of each commodity from the invoice, and sequentially determining each commodity as a target commodity; wherein the commodity comprises raw materials and finished products;
after the target commodity is determined each time, if the commodity name matched with the commodity name of the target commodity exists in the core commodity name library, determining that the commodity code corresponding to the matched commodity name is the commodity code of the target commodity, otherwise, inputting the commodity name of the target commodity into a commodity identification model to obtain the commodity code output by the commodity identification model, and determining that the commodity code is the commodity code of the target commodity; after the commodity code of the target commodity is determined, updating the target commodity by using the commodity code corresponding to the target commodity; the core commodity name library comprises commodity names of various industries and corresponding commodity codes obtained through statistics in advance, and the commodity identification model is obtained through training by utilizing the commodity names of the various industries and the commodity codes in advance.
Preferably, after determining that the industry to which the target enterprise belongs is the target industry, the method further includes:
respectively calculating the ratio of the sum of the sold finished products of each enterprise in the target industry to the sum of the purchased raw materials, and the proportion of the sum of the sold finished products to the total sum of the sold finished products of all enterprises in the target industry, and deleting the enterprises of which the ratio is greater than the specified ratio and/or the proportion is not in the preset range.
Preferably, after deleting the enterprises whose ratio is greater than the specified ratio and/or whose ratio is not within the preset range, the method further includes:
and respectively calculating the proportion of the sum of the finished products sold by each enterprise in the target industry to the total sum of the finished products sold by all enterprises in the target industry, and deleting the enterprises of which the proportion is less than the specified proportion.
Preferably, after obtaining the corresponding relationship between the extracted raw material and the finished product, the method further includes:
and displaying the corresponding relation between the obtained raw materials and the finished products in a list or a related network diagram mode.
A raw material to finished product relationship analysis apparatus comprising:
a first determination module to: determining an enterprise needing to be analyzed as a target enterprise, wherein the industry to which the target enterprise belongs is a target industry;
a second determination module to: sequentially determining the target enterprise and the target industry as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; wherein, any finished product and the raw material needed for producing the product have corresponding relation;
an analysis module to: and comparing the ratio information of the raw materials required by each finished product extracted from the target enterprise invoice with the ratio information of the raw materials required by the same finished product extracted from the target enterprise invoice, and determining whether the information contained in the target enterprise invoice is abnormal or not based on the comparison result.
A raw material to finished product relationship analysis apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for analyzing the relationship between the raw material and the finished product as described in any one of the above when the computer program is executed.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method for relational analysis of raw material and finished product according to any one of the preceding claims.
The invention provides a method, a device, equipment and a storage medium for analyzing the relation between raw materials and finished products, wherein the method comprises the following steps: determining an enterprise needing to be analyzed as a target enterprise, wherein the industry to which the target enterprise belongs is a target industry; sequentially determining the target enterprise and the target industry as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; wherein, any finished product and the raw material needed for producing the product have corresponding relation; and comparing the ratio information of the raw materials required by each finished product extracted from the target enterprise invoice with the ratio information of the raw materials required by the same finished product extracted from the target enterprise invoice, and determining whether the information contained in the target enterprise invoice is abnormal or not based on the comparison result. The technical scheme disclosed by the application determines the raw material proportioning information when all enterprises in any industry produce each finished product and the raw material proportioning information when any enterprise produces each finished product, based on the invoices reported by all enterprises in any industry and the invoices reported by any enterprise in any industry, and the proportioning information for producing each finished product can embody the production condition of the finished product, correspondingly, the proportion information of each finished product produced by an enterprise can embody the production condition of the enterprise, the proportion information of each finished product produced by all enterprises in the industry can embody the production condition of the industry, the actual production condition of the enterprise is in accordance with the actual production condition of the industry under normal conditions, and the proportion information of each finished product produced, which is obtained from invoices reported by all enterprises in the industry, is taken as the actual production condition of the industry in the application; therefore, the method and the device can acquire whether the production condition embodied in the invoice reported by the enterprise accords with the actual production condition of the industry to which the enterprise belongs or not based on the comparison of the proportion information of each finished product produced by the enterprise and the proportion information of the same finished product produced by all enterprises in the industry to which the finished product belongs, namely whether the production condition of the enterprise embodied in the invoice accords with the actual production condition of the enterprise or not, and further determine whether the enterprise taxes through the invoice based on the actual production condition of the enterprise or not.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for analyzing relationship between raw material and finished product according to an embodiment of the present invention;
fig. 2 is a relational graph obtained by constructing raw materials and finished products in a method for analyzing a relationship between raw materials and finished products according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a product A and corresponding raw materials in a method for analyzing a relationship between raw materials and a finished product according to an embodiment of the present invention;
fig. 4 is a relational graph of purchased commodities and sold commodities in the wire and cable industry in the method for analyzing a relationship between a raw material and a finished product according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of a device for analyzing a relationship between a raw material and a finished product according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart of a method for analyzing a relationship between a raw material and a finished product according to an embodiment of the present invention is shown, where the method includes:
s11: and determining that the enterprise needing to be analyzed is a target enterprise, and the industry to which the target enterprise belongs is a target industry.
The execution main body of the method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can be a corresponding relationship analysis device. At present, based on corresponding standards, 20 primary industries, namely door industries, exist; 97 second-level industries, i.e., major-class industries; 475 three-level industries, i.e., the middle-class industry; and 1979 detail industries; the industries involved in the embodiments of the present application may all indicate detailed industries, so that data of the industries is similar to data characteristics of corresponding enterprises (the enterprises in the present application may be specifically industrial enterprises that need to realize finished product production based on raw materials). For any enterprise needing to analyze the tax payment condition, the enterprise can be determined as a target enterprise, and then the industry to which the target enterprise belongs is determined as the target industry, so that the corresponding analysis can be conveniently realized subsequently.
S12: sequentially determining target enterprises and target industries as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring corresponding relations between the extracted raw materials and the finished products, and determining the proportion information of the raw materials required for producing each finished product based on the corresponding relations; wherein, any finished product and the raw material needed for producing the product have corresponding relation.
For the target industry and the target enterprise, the implementation principle of the steps required for determining the matching information of the finished products produced by the target industry is consistent, and the difference is that when the matching information of the finished products produced by the target industry is determined, the matching information is determined based on the extracted corresponding information after corresponding information is extracted from invoices of all enterprises contained in the target industry, and when the matching information of the finished products produced by the target enterprise is determined, the matching information is determined based on the extracted corresponding information after corresponding information is extracted from the invoices of the target enterprise. Specifically, when determining the proportioning information of raw materials required by each finished product produced by the target industry, all invoices of all enterprises in the target industry are obtained first, raw materials and finished products contained in the invoices are extracted, the corresponding relation between the extracted raw materials and the finished products is determined, namely the corresponding relation between each finished product and the raw materials required by each finished product is determined, and for any finished product, the proportion of the sum of a single raw material for producing the finished product to the total sum of all raw materials for producing the finished product can be calculated (the sum of the single raw material for the finished product is the total sum of all raw materials purchased by all enterprises, and the total sum of all raw materials for producing the finished product is the total sum of all raw materials purchased by all enterprises), namely the proportioning information of the raw materials for the finished product; when determining the proportioning information of the raw materials required by the target enterprise to produce each finished product, all invoices of the target enterprise are firstly obtained, the raw materials and the finished products contained in the invoices are extracted, the corresponding relation between the extracted raw materials and the finished products is determined, namely the corresponding relation between each finished product and the raw materials required by producing each finished product is determined, and for any finished product, the proportion of the sum of the single raw material for producing the finished product to the total sum of all the raw materials for producing the finished product can be calculated, namely the proportioning information of the raw materials of the finished product.
In addition, when the raw materials and the finished products contained in the invoice are extracted from the invoice, the purchased products and the sold products are specifically extracted from the invoice, wherein the purchased products are the raw materials, and the sold products are the finished products.
S13: and comparing the ratio information of the raw materials required by each finished product extracted from the invoice of the target enterprise with the ratio information of the raw materials required by the same finished product extracted from the invoice of the target industry, and determining whether the invoice containing information of the target enterprise is abnormal or not based on the comparison result.
After the matching information of each finished product produced by the target industry and the matching information of each finished product produced by the target enterprise are obtained, for any finished product in each finished product produced by the target enterprise, the matching information of the finished product is compared with the matching information of the same finished product produced by the target industry, so that whether the invoice containing information of the target enterprise is abnormal or not can be determined based on the comparison result; specifically, for any finished product, if the difference value between the ratio information of the finished product produced by the target industry and the ratio information of the finished product produced by the target enterprise is within a preset certain range, the finished product and the finished product are considered to be matched, so that the information in the invoice containing the finished product reported by the target enterprise can be determined to accord with the corresponding actual condition in the industry, and the actual condition of the finished product produced by the target enterprise is met, that is, the invoice containing the finished product of the target enterprise has no abnormality; otherwise, the two are not matched, that is, the information in the invoice containing the finished product reported by the target enterprise does not conform to the corresponding actual situation in the industry, and does not conform to the actual situation that the target enterprise produces the finished product, that is, the invoice containing the finished product of the target enterprise has an abnormality. For example, aluminum is used as a raw material, an electric wire is a finished product, 1 electric wire is generated by 1 aluminum in the target industry, but only 0.5 electric wire is generated by 1 aluminum in the target enterprise, and then it is considered that the information in the invoice of the target enterprise accounts for 0.5 electric wire less, that is, the information in the invoice including the electric wire reported by the target enterprise is not in accordance with the actual production condition thereof, and there is an abnormality.
The technical scheme disclosed by the application determines the raw material proportioning information when all enterprises in any industry produce each finished product and the raw material proportioning information when any enterprise produces each finished product, based on the invoices reported by all enterprises in any industry and the invoices reported by any enterprise in any industry, and the proportioning information for producing each finished product can embody the production condition of the finished product, correspondingly, the proportion information of each finished product produced by an enterprise can embody the production condition of the enterprise, the proportion information of each finished product produced by all enterprises in the industry can embody the production condition of the industry, the actual production condition of the enterprise is in accordance with the actual production condition of the industry under normal conditions, and the proportion information of each finished product produced, which is obtained from invoices reported by all enterprises in the industry, is taken as the actual production condition of the industry in the application; therefore, the method and the device can acquire whether the production condition embodied in the invoice reported by the enterprise accords with the actual production condition of the industry to which the enterprise belongs or not based on the comparison of the proportion information of each finished product produced by the enterprise and the proportion information of the same finished product produced by all enterprises in the industry to which the finished product belongs, namely whether the production condition of the enterprise embodied in the invoice accords with the actual production condition of the enterprise or not, and further determine whether the enterprise taxes through the invoice based on the actual production condition of the enterprise or not.
The method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention is used for obtaining the corresponding relationship between the extracted raw material and the finished product, and the method can comprise the following steps:
and constructing a relation map of the extracted raw materials and the finished products, and analyzing the relation map to obtain the corresponding relation between the corresponding raw materials and the finished products.
When the corresponding relation between the raw materials and the finished products is obtained, the corresponding relation between the raw materials and the finished products of an enterprise can be excavated through a graph algorithm and rules; in particular, the map widely exists in the real world, and from social network to financial relationship, a large amount of highly-associated data are involved, and the data form a huge map and are stored in a map database; a graph, in the form of a collection of nodes (or nodes) and edges (edges), in a graph, a node represents an entity, such as a person, a city, a company, etc., and an edge is a relationship (relationship) that relates these nodes, such as "i" living "in" shanghai ". Graph algorithms are one of the tools for graph analysis, and they provide the most efficient way to analyze connected data, describing how to process graphs to find some qualitative or quantitative conclusions; the graph algorithm is based on graph theory, and the structure and the change of a complex system are deduced by utilizing the relation between nodes, so that the algorithms can be used for discovering hidden information, verifying service hypothesis and predicting behaviors; common graph algorithms are: PageRank, Louvain, and tag propagation algorithms, among others. Based on this, in order to effectively and quickly obtain the corresponding relationship between the raw material and the finished product, the relationship map between the extracted raw material and the finished product may be constructed, and then the relationship map may be analyzed through the graph algorithm, the corresponding rule, and the like, so as to obtain the corresponding relationship between the extracted raw material and the finished product, that is, the relationship between any finished product and the raw material required for producing the any finished product.
In a specific implementation, the relationship graph obtained by constructing the raw materials and the finished products can be as shown in fig. 2, where the commodities 1 to 10 represent purchased commodities, that is, raw materials, the products a, B and C represent sold commodities, that is, finished products, and je on the connecting line represents the amount of purchasing the raw materials connected by the connecting line on the issued invoice; after obtaining fig. 2, the relationship between other raw materials and the finished product can be obtained by using a graph algorithm and corresponding rules to find out which raw materials correspond to which finished product from the relationship map, and further obtaining the result corresponding to the product a as shown in fig. 3 according to the same method.
The method for analyzing the relationship between the raw material and the finished product, provided by the embodiment of the invention, determines the industry to which a target enterprise belongs as a target industry, and can comprise the following steps:
extracting purchase and sale data from invoices of a target enterprise, inputting the purchase and sale data into an industry identification model to obtain an industry output by the industry identification model, and determining the industry as the target industry; the industry identification model is obtained by utilizing purchase and sale item data extracted from invoices of all industries and names of all industries in advance.
It should be noted that, the industry selected by many enterprises when registering the industry is not the actual industry operated by the enterprise, so that the industry of the enterprise needs to be corrected first when analyzing, and the actual industry operated by the enterprise is found out. Particularly, the real invoice data of the enterprise can well reflect the industry characteristics of the enterprise, so the real industry of the enterprise can be predicted by utilizing the sales item data of the enterprise, corresponding industry identification models can be obtained by utilizing the sales item data extracted from invoices of various industries and the names of the industries to which the sales item data belong in advance through training, then only the sales item data in the invoice of the target enterprise needs to be input into the industry identification models, and the industry of the names output by the industry identification models is the industry to which the target enterprise belongs, so that the industry deviation correction of the enterprise can be effectively and quickly realized through the mode. In addition, in the application, the industry identification model can use a machine learning algorithm (such as an LSI (large Semantic Indexing) model, which is a simple and practical topic model and can obtain a text topic based on a Singular Value Decomposition (SVD) method), and further, based on the industry identification model, differences between the marketing item data of an enterprise and the marketing item data of each industry can be compared, so that the industry to which the enterprise belongs is determined, and thus, the effect of correcting the industry is achieved.
The method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise the following steps before extracting corresponding information from the invoice:
extracting the commodity name of each commodity from the invoice, and sequentially determining each commodity as a target commodity; wherein, the commodity comprises raw materials and finished products;
after the target commodity is determined each time, if the commodity name matched with the commodity name of the target commodity exists in the core commodity name library, determining that the commodity code corresponding to the matched commodity name is the commodity code of the target commodity, otherwise, inputting the commodity name of the target commodity into a commodity identification model to obtain the commodity code output by the commodity identification model, and determining that the commodity code is the commodity code of the target commodity; after the commodity code of the target commodity is determined, updating the target commodity by using the commodity code of the target commodity corresponding to the commodity; the core commodity name library comprises the commodity names of all industries and the corresponding relations of corresponding commodity codes which are obtained through statistics in advance, and the commodity identification model is obtained through training by utilizing the commodity names of all industries and the commodity codes in advance.
The commodity code is classified and coded by commodity and service tax, which means that in the upgrade edition of value-added tax invoice, the commodity on the bill surface should be associated with the tax code checked by the tax administration when the taxpayer issues the invoice, and the invoice is issued according to the tax rate and the collection rate marked on the classified code; this also enables the tax authority to count, screen, analyze, compare data, etc., with the ultimate goal of enforcing collection management. According to the requirement of the State tax administration, when an enterprise invoices, value-added tax invoices need to be issued according to corresponding codes; according to the requirement, before invoicing, an enterprise must map all goods and service details related to the enterprise one by one into a tax bureau code table, and the number of the goods code classes exceeds 4000 classes; due to the large number of classes, enterprises can easily correspond commodity names to wrong commodity codes during invoicing. According to statistics, the accuracy rate of the existing commodity code development is less than 70%, and in order to utilize the commodity code, the commodity code is corrected. Firstly, statistical screening is carried out through national invoice data, a core commodity name library is constructed, the accuracy of commodity codes of the library is higher than 90%, then commodities on the invoice of an enterprise are compared with the commodities of the core library, and similar commodity codes are given to the core commodity name library; finally, if the goods do not exist in the core goods name library, the national goods names and the goods codes are trained through an NLP model (such as a TextCNN model), and then the trained algorithm model (namely the goods identification model) is used for correcting the goods codes. The full English name of NLP is Natural language Processing, which is an important research direction in the fields of computer science and artificial intelligence, and the research uses computers to process, understand and use human languages (such as Chinese and English) to achieve effective communication between people and computers.
When each commodity in the core commodity name library is compared with the commodity on the invoice, the commodity name of the commodity is extracted from the invoice, then the extracted commodity name of the commodity is compared with each commodity name in the core commodity name library, if the keywords (the keywords can be words or words which are predetermined and represent a class of commodities, such as copper, iron and the like) contained in the commodity name library and the extracted commodity name are the same, the commodity code of the commodity name which is matched with the extracted commodity name and is positioned in the core commodity name library is considered as the commodity code of the commodity, and if the keywords contained in the commodity name library and the extracted commodity code are different, the extracted commodity name is input into the commodity identification model, so that the commodity code output by the commodity identification model is the commodity code of the commodity of the extracted commodity name; further, after the product code is determined in the above manner, the product corresponding to the product code (which may generally include the same type of product) may be determined to be the product corresponding to the extracted product name.
When raw materials and finished products are analyzed, the names of commodities issued in invoices need to be counted, different enterprise invoicing habits are different, the same commodities can be issued to be different names, such as 'copper', enterprises can issue 'copper materials, copper products' and the like, the final results and proportion of the raw materials and the finished products can be influenced by the irregular names of the commodities, therefore, the similar commodities are aggregated into the same commodity through commodity codes, the influence of different issued names of different enterprises of the same commodity is eliminated, and the accuracy of the analyzed results is improved.
In addition, non-commodity information contained in the invoice, including but not limited to water charges, office charges, etc., may also be removed prior to extracting the information from the invoice.
The method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise the following steps after determining the industry to which the target enterprise belongs as the target industry:
respectively calculating the ratio of the sum of the sold finished products of each enterprise in the target industry to the sum of the purchased raw materials, and the proportion of the sum of the sold finished products to the total sum of the sold finished products of all enterprises in the target industry, and deleting the enterprises of which the ratio is greater than the specified ratio and/or the proportion is not in the preset range.
When the industry is analyzed, a plurality of irregular enterprises can influence the condition of the whole industry, so that representative enterprises in a batch of industries need to be found out to represent the whole industry, certain characteristics of the enterprises can represent the real condition of the whole industry, and the analyzed production condition can reflect the normal production condition of the industry; specifically, the proportion of the sum of finished products sold by each enterprise in the industry to the sum of finished products sold by the whole industry is calculated and recorded as R1; calculating the ratio of the sum of the finished products sold by each enterprise in the industry to the sum of the raw materials purchased, namely the sum of the seller/the sum of the buyer, and recording as R2; a threshold is set, the predetermined range may be between 0.1% and 2% (inclusive), and the specified ratio may be 100%, so that only businesses with R1 within the predetermined range and R2 greater than the specified ratio are retained. The selection of the preset range can select and utilize a quartile (also called a quartile point, which means that all numerical values are arranged from small to large and divided into four equal parts in statistics, and the numerical values are at the positions of three dividing points), the R1 of each enterprise in the industry are arranged according to the sequence from small to large or from large to small, and then the R1 of the middle two parts is selected to correspond to the enterprises, so that the enterprises with over-high or over-low R1 are removed; the revenue of a business for long-term sales is not sufficient to pay the purchase expense, and the business may have a problem that it cannot be counted as an industry representative business, so the designated ratio is chosen to be 100%, thereby at least ensuring that the revenue of the sales is greater than the purchase expense of the goods.
The method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise the following steps after an enterprise of which the ratio is greater than the specified ratio and/or the ratio is not in the preset range is deleted:
and respectively calculating the proportion of the sum of the finished products sold by each enterprise in the target industry to the total sum of the finished products sold by all enterprises in the target industry, and deleting the enterprises of which the proportion is less than the specified proportion.
Obtaining an industry representative enterprise, marked as A, and in order to further improve the rationality of the production situation represented by the representative enterprise, the application can calculate the ratio of the sum of the finished products sold by each enterprise in A to the sum of the finished products sold by all enterprises, marked as R3, and screen out data with smaller ratio of the sum of R3 (smaller than a specified ratio which can be set according to actual needs, such as 1%).
The method for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise the following steps of after acquiring the corresponding relationship between the extracted raw material and the finished product:
and displaying the corresponding relation between the obtained raw materials and the finished products in a list or a related network diagram mode.
After the corresponding relationship between the raw material and the finished product is obtained, the corresponding relationship can be displayed for viewing when needed, and the display can be prohibited in a list or associated network diagram mode when the corresponding relationship is displayed.
In a specific application scenario, the method for analyzing a relationship between a raw material and a finished product provided in the embodiment of the present application may specifically include the following steps:
the first step is as follows: industry deviation rectification
The industry selected by a plurality of enterprises when registering the industry is not the actual industry operated by the enterprises, so that the industry needs to be corrected when performing industry analysis to find out the real industry operated by the enterprises; the real invoice data of the enterprise can well reflect the industry characteristics of the enterprise, so the real industry of the enterprise can be predicted by utilizing the sales item data of the enterprise. When the industry deviation correction is realized, a machine learning algorithm, such as an LSI model, can be used for training a model by learning the purchase and sale item data of an enterprise, and then the industry to which the enterprise belongs is determined by comparing the difference between the purchase and sale item data of the enterprise and the purchase and sale item data of the industry through the model, so that the effect of the deviation correction industry is achieved.
The second step is that: commodity code correction
According to the requirement of the State tax administration, when an enterprise invoices, value-added tax invoices need to be issued according to corresponding codes; according to the requirement, before invoicing, an enterprise must map all goods and service details related to the enterprise one by one into a tax bureau code table, and the number of the goods code classes exceeds 4000 classes; due to the large number of classes, enterprises can easily correspond commodity names to wrong commodity codes during invoicing. According to statistics, the accuracy rate of the existing commodity code development is less than 70%, and in order to utilize the commodity code, the commodity code needs to be corrected. Firstly, the national invoice data is counted and screened to construct a core commodity name library, the accuracy of commodity codes of the library is higher than 90%, then the invoice of an enterprise is compared with the commodities of the core library, and similar commodity codes are given to the core word library. And finally, if the commodity names do not exist in the word stock, training the commodity names and the commodity codes through an NLP (non line segment) model (such as a TextCNN model), and correcting the commodity codes by using the trained algorithm model.
The third step: screening industry representative enterprises
When the industry is analyzed, a plurality of irregular enterprises can influence the condition of the whole industry, so that a batch of industry representative enterprises need to be found to represent the whole industry, certain characteristics of the enterprises can represent the real condition of the whole industry, and the specific execution thought is as follows:
(1) and calculating the proportion of the sales amount of the enterprise in the whole industry, and recording the proportion as R1.
(2) Calculating the ratio of the sum of the finished products sold by the enterprise to the sum of the purchased raw materials, namely: the seller amount/buyer amount is denoted as R2. The calculation is to screen out the enterprises whose sale amount is less than the purchase amount, and the enterprises whose purchase amount is more than the sale amount have a high possibility of problems and need to be screened out.
(3) Set thresholds, such as R1 should be between 0.1% and 2% (inclusive) and R2 should be greater than 100%. The threshold selection of R1 may be selected to utilize a quartile, and the threshold selection of R2 is 100% to at least ensure that revenue for the sale is greater than the expenditure for the purchase of the good. The revenue from long-term sales of a business is not sufficient to pay the cost of the purchase, and the business may have problems that do not account for the business's representatives.
(4) And obtaining an industry representative enterprise marked as A.
The fourth step: digging raw material and finished product
(1) And selecting the commodities in the A, and removing non-commodities, namely removing expenses such as water fees, business fees and the like.
(2) And calculating the ratio of the sum of the finished products sold by the enterprises in the step A to the sum of all the enterprises, and recording the ratio as R3.
(3) The data with smaller R3 amount is screened out, for example, the threshold of R3 is set to be more than 1%, and the data with smaller proportion is screened out. And then constructing a relation map of the commodities purchased in the industry and the sold commodities.
(4) And finding out which raw materials correspond to which finished product from the relational graph by using a rule + graph algorithm, and obtaining the relation between the raw materials and the finished product through the algorithm.
The fifth step: calculation of the ratio
Digging out raw materials, finished products and corresponding relations according to the results of the previous step, and calculating the ratio of the sum of a single raw material to the sum of all raw materials of a certain finished product, namely the raw material ratio of the certain finished product; the proportion of the sum of a single finished product to the sum of all finished products is calculated, and the proportion of each finished product can be obtained.
And a sixth step: risk identification
By comparing the ratio of the raw materials to the finished products of the enterprise with the ratio of the raw materials to the finished products of the industry, whether the production mode of the enterprise is abnormal or not can be analyzed, and therefore risks of the enterprise are identified.
Taking the wire and cable industry as an example, digging out raw materials and finished products in the industry, and specifically comprising the following steps:
the first step is as follows: industry and commodity code deviation correction
And (4) screening invoice data of the wire and cable industry from all industries, and correcting the commodity code.
The second step is that: screening of representative enterprises within the industry
(1) And calculating the proportion of the enterprise sales amount in the whole industry, and recording as xfjezb.
(2) And calculating the ratio of the seller amount and the buyer amount of the enterprise, namely the seller amount/the buyer amount, and recording as gxfzb.
(3) The calculation is to screen out the enterprises whose sale amount is less than the purchase amount, and the enterprises whose purchase amount is more than the sale amount have a high possibility of problems and need to be screened out.
(4) Setting a threshold value, setting xfjezb between 0.1% and 2% (inclusive) and gxfzb greater than 100% of enterprises. The xfjezb threshold is calculated by quartile, the gxfzb threshold is chosen to be greater than 100% in order to ensure that sales are greater than purchases, since a normal business should sell more than purchases.
The third step: digging raw material and finished product
(1) The commodities in the representative enterprise a are selected, and non-commodities, i.e., fees like water fees, office fees, etc., are removed.
(2) And calculating the ratio of the sum of the commodities sold by the enterprises in the step A to the sum of all the enterprises, and recording as jezb.
(3) And screening data with smaller amount of money, and setting the threshold value to be more than 1%. Then, a relation graph of the commodities purchased in the industry and the sold commodities is constructed, and a rule + graph algorithm is utilized to find out which raw materials correspond to which finished product from the relation graph, as shown in fig. 4, the raw materials in the wire and cable industry are copper, aluminum, plastic products, semi-finished products, auxiliary materials and the like, and the finished product is a wire and cable.
It can be seen that the following advantages exist in the present application:
1. the invention does not need manual intervention, and solves the problem by counting the invoice data and utilizing an intelligent algorithm, thereby greatly reducing the cost of manpower and material resources.
2. The invention is based on real transaction data, utilizes a graph method to dig out real raw materials and finished products of enterprises, and can effectively avoid artificial subjective judgment.
3. The invention can correct the deviation of the industry, can more truly realize the conditions in the industry, and can analyze the relation between the raw materials and the finished products of the enterprises in the industry and the relation between the raw materials and the finished products, thereby identifying the risks of the enterprises.
4. The invention can correct the unqualified commodity codes produced by enterprises to obtain the commodity codes meeting the national regulations, thereby achieving the purpose of aggregating the names of the same type of commodities.
An embodiment of the present invention further provides a device for analyzing a relationship between a raw material and a finished product, as shown in fig. 5, the device may include:
a first determining module 11, configured to: determining an enterprise needing to be analyzed as a target enterprise, and determining an industry to which the target enterprise belongs as a target industry;
a second determining module 12, configured to: sequentially determining target enterprises and target industries as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring corresponding relations between the extracted raw materials and the finished products, and determining the proportion information of the raw materials required for producing each finished product based on the corresponding relations; wherein, any finished product and the raw material needed for producing the product have corresponding relation;
an analysis module 13 for: and comparing the ratio information of the raw materials required by each finished product extracted from the invoice of the target enterprise with the ratio information of the raw materials required by the same finished product extracted from the invoice of the target industry, and determining whether the invoice containing information of the target enterprise is abnormal or not based on the comparison result.
In the device for analyzing a relationship between a raw material and a finished product provided in an embodiment of the present invention, the second determining module may include:
an acquisition unit configured to: and constructing a relation map of the extracted raw materials and the finished products, and analyzing the relation map to obtain the corresponding relation between the corresponding raw materials and the finished products.
In an apparatus for analyzing a relationship between a raw material and a finished product provided in an embodiment of the present invention, a first determining module may include:
a determination unit configured to: extracting purchase and sale data from invoices of a target enterprise, inputting the purchase and sale data into an industry identification model to obtain an industry output by the industry identification model, and determining the industry as the target industry; the industry identification model is obtained by utilizing purchase and sale item data extracted from invoices of all industries and names of all industries in advance.
The device for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise:
the coding deviation rectifying module is used for: before extracting corresponding information from the invoice, extracting the commodity name of each commodity from the invoice, and sequentially determining each commodity as a target commodity; after the target commodity is determined each time, if the commodity name matched with the commodity name of the target commodity exists in the core commodity name library, determining that the commodity code corresponding to the matched commodity name is the commodity code of the target commodity, otherwise, inputting the commodity name of the target commodity into a commodity identification model to obtain the commodity code output by the commodity identification model, and determining that the commodity code is the commodity code of the target commodity; after the commodity code of the target commodity is determined, updating the target commodity by using the commodity code of the target commodity corresponding to the commodity; the commodity comprises raw materials and finished products, the core commodity name library comprises commodity names of various industries and corresponding relations of corresponding commodity codes, which are obtained through statistics in advance, and the commodity identification model is obtained through training by utilizing the commodity names of the various industries and the commodity codes in advance.
The device for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise:
a first screening module to: after determining that the industry to which the target enterprise belongs is the target industry, respectively calculating the ratio of the sum of the sold finished products of the enterprises in the target industry to the sum of the purchased raw materials and the ratio of the sum of the sold finished products to the total sum of the sold finished products of all the enterprises in the target industry, and deleting the enterprises of which the ratio is greater than the specified ratio and/or the ratio is not in the preset range
The device for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise:
a second screening module to: and respectively calculating the proportion of the sum of the finished products sold by each enterprise in the target industry to the total sum of the finished products sold by all enterprises in the target industry, and deleting the enterprises of which the proportion is less than the specified proportion.
The device for analyzing the relationship between the raw material and the finished product provided by the embodiment of the invention can further comprise:
a display module for: and after the corresponding relation between the extracted raw materials and the finished products is obtained, displaying the obtained corresponding relation between the raw materials and the finished products in a list or associated network diagram mode.
The embodiment of the invention also provides a device for analyzing the relationship between the raw material and the finished product, which can comprise:
a memory for storing a computer program;
a processor for implementing the steps of the method for analyzing the relationship between the raw material and the finished product.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program can realize the steps of the method for analyzing the relationship between the raw material and the finished product.
It should be noted that for the description of the relevant parts in the raw material and finished product relationship analysis apparatus, device and storage medium provided in the embodiment of the present invention, reference is made to the detailed description of the corresponding parts in the raw material and finished product relationship analysis method provided in the embodiment of the present invention, and details are not repeated herein. In addition, parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for analyzing the relation between raw materials and finished products is characterized by comprising the following steps:
determining an enterprise needing to be analyzed as a target enterprise, wherein the industry to which the target enterprise belongs is a target industry;
sequentially determining the target enterprise and the target industry as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; wherein, any finished product and the raw material needed for producing the product have corresponding relation;
and comparing the ratio information of the raw materials required by each finished product extracted from the target enterprise invoice with the ratio information of the raw materials required by the same finished product extracted from the target enterprise invoice, and determining whether the information contained in the target enterprise invoice is abnormal or not based on the comparison result.
2. The method of claim 1, wherein the obtaining the correspondence between the extracted raw material and the finished product comprises:
and constructing a relation map of the extracted raw materials and finished products, and analyzing the relation map to obtain the corresponding relation between the corresponding raw materials and finished products.
3. The method of claim 2, wherein determining the industry to which the target enterprise belongs is a target industry, comprises:
extracting purchase and sale item data from the invoices of the target enterprise, inputting the purchase and sale item data into an industry identification model to obtain an industry output by the industry identification model, and determining the industry as the target industry; the industry identification model is obtained by utilizing purchase and sale item data extracted from invoices of various industries and names of various industries in advance for training.
4. The method of claim 3, further comprising, prior to extracting the corresponding information from the invoice:
extracting the commodity name of each commodity from the invoice, and sequentially determining each commodity as a target commodity; wherein the commodity comprises raw materials and finished products;
after the target commodity is determined each time, if the commodity name matched with the commodity name of the target commodity exists in the core commodity name library, determining that the commodity code corresponding to the matched commodity name is the commodity code of the target commodity, otherwise, inputting the commodity name of the target commodity into a commodity identification model to obtain the commodity code output by the commodity identification model, and determining that the commodity code is the commodity code of the target commodity; after the commodity code of the target commodity is determined, updating the target commodity by using the commodity code corresponding to the target commodity; the core commodity name library comprises commodity names of various industries and corresponding commodity codes obtained through statistics in advance, and the commodity identification model is obtained through training by utilizing the commodity names of the various industries and the commodity codes in advance.
5. The method of claim 4, wherein determining the industry to which the target enterprise belongs is a target industry, further comprises:
respectively calculating the ratio of the sum of the sold finished products of each enterprise in the target industry to the sum of the purchased raw materials, and the proportion of the sum of the sold finished products to the total sum of the sold finished products of all enterprises in the target industry, and deleting the enterprises of which the ratio is greater than the specified ratio and/or the proportion is not in the preset range.
6. The method of claim 5, wherein after deleting the businesses for which the ratio is greater than the specified ratio and/or for which the ratio is not within the preset range, further comprising:
and respectively calculating the proportion of the sum of the finished products sold by each enterprise in the target industry to the total sum of the finished products sold by all enterprises in the target industry, and deleting the enterprises of which the proportion is less than the specified proportion.
7. The method of claim 6, wherein after obtaining the correspondence between the extracted raw material and the finished product, the method further comprises:
and displaying the corresponding relation between the obtained raw materials and the finished products in a list or a related network diagram mode.
8. A device for analyzing a relationship between a raw material and a finished product, comprising:
a first determination module to: determining an enterprise needing to be analyzed as a target enterprise, wherein the industry to which the target enterprise belongs is a target industry;
a second determination module to: sequentially determining the target enterprise and the target industry as target units, extracting raw materials and finished products from invoices of the target units after the target units are determined each time, acquiring the corresponding relation between the extracted raw materials and the finished products, and determining the proportioning information of the raw materials required for producing each finished product based on the corresponding relation; wherein, any finished product and the raw material needed for producing the product have corresponding relation;
an analysis module to: and comparing the ratio information of the raw materials required by each finished product extracted from the target enterprise invoice with the ratio information of the raw materials required by the same finished product extracted from the target enterprise invoice, and determining whether the information contained in the target enterprise invoice is abnormal or not based on the comparison result.
9. A raw material to finished product relationship analysis apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for analyzing the relationship between raw material and finished product according to any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method for relational analysis of raw material and finished product according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558852.8A CN111695979A (en) | 2020-06-18 | 2020-06-18 | Method, device and equipment for analyzing relation between raw material and finished product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558852.8A CN111695979A (en) | 2020-06-18 | 2020-06-18 | Method, device and equipment for analyzing relation between raw material and finished product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695979A true CN111695979A (en) | 2020-09-22 |
Family
ID=72481563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010558852.8A Pending CN111695979A (en) | 2020-06-18 | 2020-06-18 | Method, device and equipment for analyzing relation between raw material and finished product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695979A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112328839A (en) * | 2020-11-05 | 2021-02-05 | 航天信息股份有限公司 | Enterprise risk identification method and system based on enterprise sales relationship map |
| CN112529664A (en) * | 2020-12-15 | 2021-03-19 | 航天信息股份有限公司 | Method and device for comparing commodities sold in advance, storage medium and electronic equipment |
| CN113869802A (en) * | 2021-12-01 | 2021-12-31 | 神州数码信息系统有限公司 | Production enterprise invoice false invoice risk assessment method based on sales entry comparison |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003005160A2 (en) * | 2001-07-03 | 2003-01-16 | Great Northern Enterprises Llc | Cross vertical application software development system and method |
| CN103377454A (en) * | 2013-07-11 | 2013-10-30 | 西安交通大学 | Abnormal tax return data detection method based on cosine similarity |
| CN104134128A (en) * | 2014-08-11 | 2014-11-05 | 税友软件集团股份有限公司 | Invoice processing method and system |
| CN104166934A (en) * | 2014-08-29 | 2014-11-26 | 税友软件集团股份有限公司 | Tax revenue analysis method and system of index model for industries and tax categories |
| CN104636972A (en) * | 2013-11-06 | 2015-05-20 | 航天信息股份有限公司 | Method of monitoring enterprise false deduction invoice through commodity composition and system thereof |
| CN106933814A (en) * | 2015-12-28 | 2017-07-07 | 航天信息股份有限公司 | Tax data exception analysis method and system |
| CN109872163A (en) * | 2018-12-27 | 2019-06-11 | 航天信息股份有限公司 | The recognition methods of abnormal production enterprise and device |
| CN110009364A (en) * | 2019-01-08 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of industry identification model determines method and apparatus |
| CN110287218A (en) * | 2019-06-26 | 2019-09-27 | 浙江诺诺网络科技有限公司 | A kind of matched method of tax revenue sorting code number, system and equipment |
| CN110597995A (en) * | 2019-09-20 | 2019-12-20 | 税友软件集团股份有限公司 | Commodity name classification method, commodity name classification device, commodity name classification equipment and readable storage medium |
| CN110647845A (en) * | 2019-09-23 | 2020-01-03 | 税友软件集团股份有限公司 | Invoice data identification device, related method and related device |
| CN110851587A (en) * | 2018-07-25 | 2020-02-28 | 阿里巴巴集团控股有限公司 | Commodity code prediction model generation and commodity code determining method, device and equipment |
-
2020
- 2020-06-18 CN CN202010558852.8A patent/CN111695979A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003005160A2 (en) * | 2001-07-03 | 2003-01-16 | Great Northern Enterprises Llc | Cross vertical application software development system and method |
| CN103377454A (en) * | 2013-07-11 | 2013-10-30 | 西安交通大学 | Abnormal tax return data detection method based on cosine similarity |
| CN104636972A (en) * | 2013-11-06 | 2015-05-20 | 航天信息股份有限公司 | Method of monitoring enterprise false deduction invoice through commodity composition and system thereof |
| CN104134128A (en) * | 2014-08-11 | 2014-11-05 | 税友软件集团股份有限公司 | Invoice processing method and system |
| CN104166934A (en) * | 2014-08-29 | 2014-11-26 | 税友软件集团股份有限公司 | Tax revenue analysis method and system of index model for industries and tax categories |
| CN106933814A (en) * | 2015-12-28 | 2017-07-07 | 航天信息股份有限公司 | Tax data exception analysis method and system |
| CN110851587A (en) * | 2018-07-25 | 2020-02-28 | 阿里巴巴集团控股有限公司 | Commodity code prediction model generation and commodity code determining method, device and equipment |
| CN109872163A (en) * | 2018-12-27 | 2019-06-11 | 航天信息股份有限公司 | The recognition methods of abnormal production enterprise and device |
| CN110009364A (en) * | 2019-01-08 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of industry identification model determines method and apparatus |
| CN110287218A (en) * | 2019-06-26 | 2019-09-27 | 浙江诺诺网络科技有限公司 | A kind of matched method of tax revenue sorting code number, system and equipment |
| CN110597995A (en) * | 2019-09-20 | 2019-12-20 | 税友软件集团股份有限公司 | Commodity name classification method, commodity name classification device, commodity name classification equipment and readable storage medium |
| CN110647845A (en) * | 2019-09-23 | 2020-01-03 | 税友软件集团股份有限公司 | Invoice data identification device, related method and related device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112328839A (en) * | 2020-11-05 | 2021-02-05 | 航天信息股份有限公司 | Enterprise risk identification method and system based on enterprise sales relationship map |
| CN112328839B (en) * | 2020-11-05 | 2024-02-27 | 航天信息股份有限公司 | Enterprise risk identification method and system based on enterprise marketing relationship graph |
| CN112529664A (en) * | 2020-12-15 | 2021-03-19 | 航天信息股份有限公司 | Method and device for comparing commodities sold in advance, storage medium and electronic equipment |
| CN113869802A (en) * | 2021-12-01 | 2021-12-31 | 神州数码信息系统有限公司 | Production enterprise invoice false invoice risk assessment method based on sales entry comparison |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107154880B (en) | System monitoring method and device | |
| CN103294592B (en) | User instrument is utilized to automatically analyze the method and system of the defect in its service offering alternately | |
| CN111695979A (en) | Method, device and equipment for analyzing relation between raw material and finished product | |
| CN110728422A (en) | Building information model, method, device and settlement system for construction project | |
| CN112860769B (en) | Energy planning data management system | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN108572988A (en) | A kind of house property assessment data creation method and device | |
| CN110163683B (en) | Value user key index determination method, advertisement delivery method and device | |
| CN105405051A (en) | Financial event prediction method and apparatus | |
| CN116151840B (en) | User service data intelligent management system and method based on big data | |
| CN111046947B (en) | Training system and method of classifier and recognition method of abnormal sample | |
| CN117114812A (en) | Financial product recommendation method and device for enterprises | |
| CN110796381A (en) | Method and device for processing evaluation indexes of modeling data, terminal equipment and medium | |
| CN116228402A (en) | Financial credit investigation feature warehouse technical support system | |
| CN115495587A (en) | Alarm analysis method and device based on knowledge graph | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| CN107291722B (en) | Descriptor classification method and device | |
| CN115271514A (en) | Communication enterprise monitoring method and device, electronic equipment and storage medium | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN114331355A (en) | Remote multi-stage approval method and system for flexible employment platform | |
| JP2003280901A (en) | Program for supporting estimation evaluation and system for supporting estimation evaluation | |
| CN108242019A (en) | The monitoring method and system of the taxable sales volume of small-scale taxpayer year based on SPARK | |
| CN112380321A (en) | Primary and secondary database distribution method based on bill knowledge graph and related equipment | |
| CN112488572B (en) | Audit object recommendation method, device, equipment and medium | |
| CN114547163A (en) | Electronic commerce platform construction method and system based on artificial intelligence |
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 |