CN111581242A - Method and system for identifying enterprise bill use - Google Patents
Method and system for identifying enterprise bill use Download PDFInfo
- Publication number
- CN111581242A CN111581242A CN202010360929.0A CN202010360929A CN111581242A CN 111581242 A CN111581242 A CN 111581242A CN 202010360929 A CN202010360929 A CN 202010360929A CN 111581242 A CN111581242 A CN 111581242A
- Authority
- CN
- China
- Prior art keywords
- bill
- rule
- data
- enterprise
- bill data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 235000013372 meat Nutrition 0.000 description 3
- 235000013311 vegetables Nutrition 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method and a system for identifying the bill use of an enterprise, which belong to the field of bill management. Through the mode of the rule model of training in advance, carry out automatic identification to the bill usage of company, need not the manual handling bill, like this can greatly reduced accounting human cost, reduce the error rate, improve financial transaction's efficiency and effect.
Description
Technical Field
The invention relates to the field of bill management, in particular to a method and a system for identifying the use of an enterprise bill.
Background
Financial management is an important ring in enterprise operation, and not only can truly react to actual operation business of an enterprise, but also has important guiding significance to the operation business of the enterprise. In the enterprise finance and tax processing process, the most important thing is to enter account on the basis of the actual business of the enterprise and the bill reflecting the actual business. Therefore, each bill also has different business purposes due to different business scenes, so that the accounting subjects of the bill are different.
In traditional accounting financial software, accounting personnel handle bills completely by hand. The accounting checks the information on the bill surface manually, and in combination with the transaction information of the bill of the company, the accounting charge subject of the bill is manually judged according to years of accounting experience and the understanding of company business, so that the bill is input into the system for entry. Current methods are completely manual in that they are handled. Such work is highly different for enterprises due to the professional ability of accountants and the degree of understanding of the business. From the accounting personnel perspective, both need deep understanding the business, judge the accounting subject that the business corresponds, it is higher to the requirement of specialty, also relatively more loaded down with trivial details, seriously influence work efficiency to cause the waste of manpower resources, the same type bill front and back is handled inconsistently, makes mistakes more easily.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method and a system for automatically identifying the bill use of an enterprise, which can reduce the requirement of accountants and simultaneously improve the working efficiency of the accountants
The technical scheme adopted by the invention for solving the technical problems is as follows:
on the one hand, the method comprises the following steps of,
the method for identifying the use of the enterprise bill comprises the following steps:
acquiring bill data of the enterprise;
extracting dimension values of all dimensions of the bill data, wherein the dimensions are feature items capable of distinguishing different bills;
and obtaining the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data.
Further, the training method of the pre-trained rule model comprises the following steps:
acquiring bill data;
formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill;
decomposing the standardized data into different characteristic items;
obtaining a dimension value corresponding to the feature item;
obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base;
and recalculating to obtain the weight value of the application and updating the predefined rule base to obtain a pre-trained rule model.
Further, the method for defining the predefined rule base comprises the following steps:
acquiring the enterprise data, wherein the enterprise data comprises main business information and affiliated industry information;
acquiring bill data according to the enterprise data, wherein the bill data comprises the enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of the industry where the enterprise is located and bill data of all industries;
and respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data.
Further, the method for defining the predefined rule base comprises the following steps:
acquiring the enterprise data, wherein the enterprise data comprises main business information and affiliated industry information;
acquiring bill data according to the enterprise data, wherein the bill data comprises the enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of the industry where the enterprise is located and bill data of all industries;
and respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data.
Further, the obtaining of the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data includes:
inputting the dimension and dimension values into the pre-trained rule model to obtain a first set of corresponding usage and usage weight values;
weighting the use and use weight values in the first set according to the enterprise data to obtain a second set of use and use weight values;
and screening a preset number of purposes as the purposes of the bill according to the purpose weight values in the second set.
Further, the weighting the usage and usage weight values in the first set according to the enterprise data to obtain a second set of usage and usage weight values includes:
inputting the enterprise data into the pre-trained rule model to obtain a client rule, a main business rule, an industry rule and a general rule of the enterprise;
and weighting according to preset weights of the purposes in the first set in the customer rules, the main business rules, the industry rules and the general rules to obtain a second set of the weight values of the purposes and the purposes.
Further, screening a preset number of uses according to the use weight values in the second set as uses of the ticket comprises:
calculating under the customer rule, the main business rule, the industry rule and the general rule to obtain repeated use combination in the second set, wherein the weight value corresponding to the combined use adopts the weight value with the highest weight value of all the uses;
after the combination, the purposes are sorted from high to low according to the weight values;
and screening the use of which the weight value is arranged before the preset number as the use of the bill.
On the other hand, in the case of a liquid,
a system for identifying a use of a business instrument, comprising:
the bill data acquisition module is used for acquiring bill data of the enterprise;
the dimension value extraction module is used for extracting dimension values of all dimensions of the bill data, wherein the dimensions are feature items capable of distinguishing different bills;
and the purpose acquisition module is used for acquiring the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data.
Further, the rule model training module is used for acquiring bill data; formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill; decomposing the standardized data into different characteristic items; obtaining a dimension value corresponding to the feature item; obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base; and recalculating to obtain the weight value of the application and updating the predefined rule base to obtain a pre-trained rule model.
Further, still include: the rule base definition module is used for acquiring the enterprise data, and the enterprise data comprises main business information and affiliated industry information; acquiring bill data according to the enterprise data, wherein the bill data comprises the enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of the industry where the enterprise is located and bill data of all industries; and respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data.
This application adopts above technical scheme, possesses following beneficial effect at least:
the technical scheme of the invention provides a method and a system for identifying the bill use of an enterprise, wherein after bill data of the enterprise is obtained, the bill use is obtained by extracting dimension values of the bill data in different dimensions and inputting the dimension values and the enterprise data into a pre-trained rule model. Through the mode of the rule model of training in advance, carry out automatic identification to the bill usage of company, need not the manual handling bill, like this can greatly reduced accounting human cost, reduce the error rate, improve financial transaction's efficiency and effect.
Drawings
In order to more clearly illustrate the embodiments of the present application 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 some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying the usage of enterprise tickets according to an embodiment of the invention;
FIG. 2 is a flow diagram of an enterprise bill usage recommendation model provided by an embodiment of the invention;
FIG. 3 is a schematic diagram of a training method of a pre-trained rule model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a predefined rule base provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a system for identifying a purpose of an enterprise bill according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following detailed description of the technical solutions of the present invention is provided with reference to the accompanying drawings and examples. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without making any creative effort, shall fall within the protection scope of the present application.
In one embodiment, the present invention provides a method for identifying a use of a bill of an enterprise, as shown in fig. 1, comprising the steps of:
acquiring bill data of an enterprise;
extracting dimension values of all dimensions of bill data, wherein the dimensions are characteristic items capable of distinguishing different bills;
and obtaining the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data.
According to the method for identifying the bill use of the enterprise, provided by the embodiment of the invention, after the bill data of the enterprise is obtained, the bill use is obtained by extracting the dimension values of the bill data in different dimensions and inputting the dimension values and the enterprise data into a pre-trained rule model. Through the mode of the rule model of training in advance, carry out automatic identification to the bill usage of company, need not the manual handling bill, like this can greatly reduced accounting human cost, reduce the error rate, improve financial transaction's efficiency and effect
As a further improvement to the above embodiment, an embodiment of the present invention further provides a training method of a pre-trained rule model, including the following steps:
acquiring bill data;
formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill;
decomposing the standardized data to form different characteristic items;
obtaining a dimension value corresponding to the feature item;
obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base;
and recalculating the weight value for the purpose and updating the predefined rule base to obtain a pre-trained rule model.
Optionally, an embodiment of the present invention further provides a method for defining a predefined rule base, where the method for defining a predefined rule base includes the following steps:
acquiring enterprise data, wherein the enterprise data comprises main business information and affiliated industry information;
acquiring bill data according to the enterprise data, wherein the bill data comprises enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of industries where the enterprise is located and bill data of all the industries;
and respectively obtaining a predefined rule base containing a client rule, a main business rule, an industry rule and a general rule according to the bill data.
Wherein, respectively obtaining the predefined rule base containing the client rule, the main business rule, the industry rule and the general rule according to the bill data comprises:
splitting each bill data into at least one characteristic item;
respectively defining a dimension value in the bill data for each feature item;
the purpose of obtaining the corresponding dimension value of the feature item;
defining a weight value for a corresponding use under the dimension value;
and storing the characteristic items, the dimension values, the purposes and the weight values corresponding to the bill data.
Optionally, obtaining the corresponding use of the ticket through the pre-trained rule model according to the dimension value and the enterprise data includes:
inputting the dimension and the dimension value into a pre-trained rule model to obtain a first set of corresponding usage and usage weight values;
weighting the use and use weight values in the first set according to the enterprise data to obtain a second set of use and use weight values;
and screening a preset number of purposes as the purposes of the bill according to the purpose weight values in the second set.
Further, weighting the usage and usage weight values within the first set according to the enterprise data to obtain a second set of usage and usage weight values comprises:
inputting enterprise data into a pre-trained rule model to obtain client rules, main business rules, industry rules and general rules of the enterprise;
and weighting according to preset weights of the purposes in the first set in the customer rules, the main business rules, the industry rules and the general rules to obtain a second set of the weight values of the purposes and the purposes.
And weighting according to preset weights of the purposes in the first set in the customer rules, the main business rules, the industry rules and the general rules to obtain a second set of the weight values of the purposes and the purposes.
Optionally, screening a preset number of uses as uses of the ticket according to the use weight values in the second set comprises:
calculating under the customer rule, the main business rule, the industry rule and the general rule to obtain repeated use combination in the second set, wherein the weight value corresponding to the combined use adopts the weight value with the highest weight value of all the uses;
after merging, sorting the purposes from high to low according to the weight values;
and screening the use of which the weight value is arranged before the preset number as the use of the bill.
The invention also provides a set of use recommendation models generated by combining machine learning algorithm and accounting industry characteristics. Through the model, intelligent recommendation of the bill use purpose of the user can be realized, and then financial processing is carried out. The method comprises three parts, namely rule definition, namely a predefined rule base, a purpose learning model, namely a pre-trained rule model, and a purpose recommendation model, namely the purpose of an enterprise bill recognition. As shown in fig. 2, the usage recommendation model is mainly divided into 5 stages, model calculation, hierarchical weighting, usage merging, ranking, and optimization. Through the processing of the several stages, several optimal results are recommended.
Model calculation: and extracting the numerical values of corresponding dimensions of the bill data, and simultaneously extracting the data related to the client to be input into the rule model as input data. The rule models are calculated according to different levels (a client level, a main business level, an industry level and a general level). And fuzzy matching is carried out on the corresponding purposes and the sets of the purpose scores according to each dimension and the corresponding dimension value. The final calculation result is related usage and a score corresponding to the usage.
Hierarchical weighting: since different hierarchies have different effects on the results of the computation. For example, the result calculated by the client's own rule should have a higher credibility, while the general rule is a rule synthesized from all the tickets and has a relatively lower credibility, so that the calculated result is weighted at each layer, and the client's rule has a higher weight value.
The purposes are combined: there may be duplication of usage calculated by different rules or different dimensions, for example, usage A is calculated in the customer rule with a score of 0.9, while usage A is also calculated in the business rule with a score of 0.2, and end usage A is recommended only once, so the same usage needs to be merged, and the merged score is max (score).
Then, the optimal usage needs to be found from the usage list, and the highest 3 usages are obtained by screening according to the scores and the heights.
As long as the user (accountant) selects according to the actual purpose, the system background can automatically complete accounting processing and tax processing.
Generally, the bills of one client itself are regular. The method is characterized in that a family of enterprises mainly operating catering services purchase vegetables, meat and the like in the month for dish making, and purchase vegetables, meat and the like in the next month for dish making, and summarizes the rule of a customer, so that a set of unique rules exists for the customer. If the client is likely to purchase vegetables and meat but rice in the next day, then the client can not know what the purpose is according to the rules of the client, and if another main catering service enterprise purchases eggs, we can do or not do an analogy with the rules of the enterprise? Thus, the rules of the main business are obtained. Similarly, what if a business similar to the business has not purchased eggs? The range can continue to be expanded for analogy. Based on the above, we divide the usage rules into four levels: customer rules, main business rules, industry rules, and general rules. The business rules, the industry rules and the general rules of the main business, the industry rules and the general rules of the customers can be preset in the system preliminarily, the business rules, the industry rules and the general rules of the customers can be called in sequence firstly, the rules of the customers can be learned according to the selection of the customers, and then the business rules, the industry rules and the general rules of the customers are deduced in a reverse mode. Therefore, the customer rules are the result of learning based on the customer's billing usage; the main business rules are the result of learning according to the bill use of the similar main business; industry rules are the result of learning from industry bill usage; the general rule is the result of learning from all note uses. The client rule has the uniqueness of the client, the industry rule has the universality of the industry, and the use recommendation result of the client can be more accurate through layered processing.
The core point of usage learning is to extract feature points by learning comprehensive data such as bill information and user information, to record influence weights of the feature points on usage, to precipitate a relationship between the feature points and usage, and to use the relationship as a basis for usage recommendation. The learning model is divided into three parts, 1, dimension selection; 2. weight setting 3, storage model 4 and calculation model.
Dimension selection, also called feature screening, is to screen out meaningful and valuable feature items according to the characteristics of the accounting industry. In accounting, because of the wide variety of bills and different bills with different characteristics, a set of characteristic items is separately defined for each type of bills. For example, the value-added tax invoice definition characteristic items are as follows: bill type, seller, buyer, goods type, goods detail, goods specification, goods unit price, goods quantity, toll mark, finished oil mark and vehicle and ship tax mark, wherein if the bill is a sales bill, the characteristic item excludes the seller; if the ticket is purchased, the characteristic item excludes the purchasing party.
In these features, the influence degree of different features is different, for example, the influence of the cargo type and cargo detail is certain to be larger, and the influence of other feature items is smaller. The influence of the characteristics is measured by configuring different weight values for the characteristic items.
According to the characteristics of the characteristic items, different bill types and bill directions and different corresponding characteristic items, a directed acyclic graph is used for storing in the storage of the model, data are firstly distinguished according to the bill types and the bill directions, then characteristic dimensions are defined under each bill type and bill direction, a plurality of dimension values are mounted under each dimension, and the application and the weight value of the application under the dimension value are mounted under each dimension value. As shown in fig. 2.
The process of usage learning is divided into 4 stages, namely data formatting, feature item disassembling, usage weight value calculating and rule storing. As shown in fig. 3, the original data of the bill is various, and is first formatted according to the type of the bill and standardized data is output. And then according to the characteristic item model, the standardized data is disassembled according to different characteristic items and is decomposed into structures of characteristic items, characteristic values and purposes. Then, according to the characteristic item and the characteristic value, indexing the rule of the current rule base, and inquiring all purposes and use weights corresponding to the current characteristic item and the characteristic value. The weight values for the purpose are then recalculated according to a specific algorithm. The algorithm used here is to calculate the weight values directly according to the number of uses. For example, if the application a is selected 3 times, the application B is selected 2 times, and the application C is selected 5 times, the formula for calculating the application value of the application a is wa/(ka + kb +. kn), and the weight value of the application a is calculated to be 0.3. And finally updating the rule result into a rule base.
The embodiment of the invention learns the bill use of a company in a machine learning mode, and automatically sets the learning result on the bill, so that the manpower cost of accounting can be greatly reduced, the error rate is reduced, and the efficiency and the effect of financial processing are improved.
In an embodiment, an embodiment of the present invention further provides a system for identifying a use of an enterprise ticket, as shown in fig. 5, including:
the bill data acquisition module 501 is used for acquiring bill data of an enterprise;
the dimension value extraction module 502 is used for extracting dimension values of all dimensions of the bill data, wherein the dimensions are feature items capable of distinguishing different bills;
and the purpose obtaining module 503 is configured to obtain a purpose corresponding to the bill through a pre-trained rule model according to the dimension value and the enterprise data.
Optionally, the method further comprises: a rule model training module 504 for obtaining bill data; formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill; decomposing the standardized data to form different characteristic items; obtaining a dimension value corresponding to the feature item; obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base; and recalculating the weight value for the purpose and updating the predefined rule base to obtain a pre-trained rule model.
Further optionally, the method further comprises: the rule base definition module 505 is configured to obtain enterprise data, where the enterprise data includes business information of a main business and business information of an affiliated business; acquiring bill data according to the enterprise data, wherein the bill data comprises enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of industries where the enterprise is located and bill data of all the industries; and respectively obtaining a predefined rule base containing enterprise rules, main business rules, industry rules and general rules according to the bill data.
The embodiment of the invention provides a system for identifying the bill use of an enterprise, which comprises the steps of firstly collecting bill information and defining rules through a rule base definition module; the bill data acquisition module acquires bill data of an enterprise; the dimension value extraction module extracts dimension values of all dimensions of the bill data, wherein the dimensions are characteristic items capable of distinguishing different bills; and the purpose acquisition module acquires the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data. Through the mode of machine learning, study the bill usage of company, with the automatic bill of setting for of result of studying, can greatly reduced accounting human cost like this, reduce the error rate, improve financial processing's efficiency and effect.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. The method for identifying the use of the enterprise bill is characterized by comprising the following steps:
acquiring bill data of the enterprise;
extracting dimension values of all dimensions of the bill data, wherein the dimensions are feature items capable of distinguishing different bills;
and obtaining the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data.
2. The method of claim 1, wherein: the training method of the pre-trained rule model comprises the following steps:
acquiring bill data;
formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill;
decomposing the standardized data into different characteristic items;
obtaining a dimension value corresponding to the feature item;
obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base;
and recalculating to obtain the weight value of the application and updating the predefined rule base to obtain a pre-trained rule model.
3. The method of claim 2, wherein: the method for defining the predefined rule base comprises the following steps:
acquiring the enterprise data, wherein the enterprise data comprises main business information and affiliated industry information;
acquiring bill data according to the enterprise data, wherein the bill data comprises the enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of the industry where the enterprise is located and bill data of all industries;
and respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data.
4. The method of claim 3, wherein: the step of respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data comprises the following steps:
splitting each bill data into at least one characteristic item;
respectively defining a dimension value in the bill data for each feature item;
acquiring the use of the feature item corresponding to the dimension value;
defining a weight value for a corresponding use at the dimension value;
and storing the characteristic item, the dimension value, the application and the weight value corresponding to the bill data.
5. The method of claim 1, wherein: the obtaining of the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data comprises the following steps:
inputting the dimension and dimension values into the pre-trained rule model to obtain a first set of corresponding usage and usage weight values;
weighting the use and use weight values in the first set according to the enterprise data to obtain a second set of use and use weight values;
and screening a preset number of purposes as the purposes of the bill according to the purpose weight values in the second set.
6. The method of claim 5, wherein: the weighting the usage and usage weight values in the first set according to the enterprise data to obtain a second set of usage and usage weight values comprises:
inputting the enterprise data into the pre-trained rule model to obtain a client rule, a main business rule, an industry rule and a general rule of the enterprise;
and weighting according to preset weights of the purposes in the first set in the customer rules, the main business rules, the industry rules and the general rules to obtain a second set of the weight values of the purposes and the purposes.
7. The method of claim 6, wherein: screening a preset number of uses according to the use weight values in the second set as uses of the ticket comprises:
calculating under the customer rule, the main business rule, the industry rule and the general rule to obtain repeated use combination in the second set, wherein the weight value corresponding to the combined use adopts the weight value with the highest weight value of all the uses;
after the combination, the purposes are sorted from high to low according to the weight values;
and screening the use of which the weight value is arranged before the preset number as the use of the bill.
8. A system for identifying a use of a business instrument, comprising:
the bill data acquisition module is used for acquiring bill data of the enterprise;
the dimension value extraction module is used for extracting dimension values of all dimensions of the bill data, wherein the dimensions are feature items capable of distinguishing different bills;
and the purpose acquisition module is used for acquiring the corresponding purpose of the bill through a pre-trained rule model according to the dimension value and the enterprise data.
9. The system of claim 8, further comprising: the rule model training module is used for acquiring bill data; formatting the bill data to form standardized data so as to conveniently identify the characteristic items of the bill; decomposing the standardized data into different characteristic items; obtaining a dimension value corresponding to the feature item; obtaining the corresponding use of each feature item in the corresponding dimension value and the selection times of the use in a predefined rule base; and recalculating to obtain the weight value of the application and updating the predefined rule base to obtain a pre-trained rule model.
10. The system of claim 8, further comprising: the rule base definition module is used for acquiring the enterprise data, and the enterprise data comprises main business information and affiliated industry information; acquiring bill data according to the enterprise data, wherein the bill data comprises the enterprise bill data, enterprise bill information which is the same as the main business of the enterprise, bill data of the industry where the enterprise is located and bill data of all industries; and respectively obtaining a predefined rule base containing a customer rule, a main business rule, an industry rule and a general rule according to the bill data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010360929.0A CN111581242A (en) | 2020-04-30 | 2020-04-30 | Method and system for identifying enterprise bill use |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010360929.0A CN111581242A (en) | 2020-04-30 | 2020-04-30 | Method and system for identifying enterprise bill use |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111581242A true CN111581242A (en) | 2020-08-25 |
Family
ID=72111999
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010360929.0A Pending CN111581242A (en) | 2020-04-30 | 2020-04-30 | Method and system for identifying enterprise bill use |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111581242A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636557A (en) * | 2018-12-11 | 2019-04-16 | 厦门商集网络科技有限责任公司 | A kind of intelligent classification bookkeeping methods and equipment based on bank slip recognition |
CN110059692A (en) * | 2019-04-16 | 2019-07-26 | 厦门商集网络科技有限责任公司 | A kind of method and terminal identifying the affiliated industry of enterprise |
WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技(深圳)有限公司 | Bill recognition method, server, and computer readable storage medium |
CN110415119A (en) * | 2019-07-30 | 2019-11-05 | 中国工商银行股份有限公司 | Model training, bill business prediction technique, device, storage medium and equipment |
-
2020
- 2020-04-30 CN CN202010360929.0A patent/CN111581242A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技(深圳)有限公司 | Bill recognition method, server, and computer readable storage medium |
CN109636557A (en) * | 2018-12-11 | 2019-04-16 | 厦门商集网络科技有限责任公司 | A kind of intelligent classification bookkeeping methods and equipment based on bank slip recognition |
CN110059692A (en) * | 2019-04-16 | 2019-07-26 | 厦门商集网络科技有限责任公司 | A kind of method and terminal identifying the affiliated industry of enterprise |
CN110415119A (en) * | 2019-07-30 | 2019-11-05 | 中国工商银行股份有限公司 | Model training, bill business prediction technique, device, storage medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5764975A (en) | Data mining method and apparatus using rate of common records as a measure of similarity | |
CN111428599B (en) | Bill identification method, device and equipment | |
EP0450825B1 (en) | Method and apparatus for the classification of data | |
CN113935434A (en) | Data analysis processing system and automatic modeling method | |
CN106447476A (en) | Automatic check computation method and system of consumer tax | |
AU2020283880B2 (en) | System and method for information retrieval for noisy data | |
CN112966482A (en) | Report generation method, device and equipment | |
CN110109902A (en) | A kind of electric business platform recommender system based on integrated learning approach | |
CN111695979A (en) | Method, device and equipment for analyzing relation between raw material and finished product | |
Hu | Predicting and improving invoice-to-cash collection through machine learning | |
JP6528074B1 (en) | Accounting processor, accounting method, accounting program | |
CN117114812A (en) | Financial product recommendation method and device for enterprises | |
CN111581242A (en) | Method and system for identifying enterprise bill use | |
WO2023098034A1 (en) | Business data report classification method and apparatus | |
CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
CN114490571A (en) | Modeling method, server and storage medium | |
CN114265887A (en) | Dimension data processing method and device, storage medium and electronic equipment | |
JPH0934873A (en) | Customer classification method and system | |
JP2003280901A (en) | Program for supporting estimation evaluation and system for supporting estimation evaluation | |
JPH09282307A (en) | Commodity sales trend analysis method and system therefor | |
CN111311331A (en) | RFM analysis method | |
CN115187387B (en) | Identification method and equipment for risk merchant | |
Lal | Compilation of Input‐output Tables: Canada | |
KR19990075415A (en) | Management analysis method using company's activity information | |
CN113205270B (en) | Method and system for automatically generating satisfaction evaluation table and calculating evaluation score |
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 | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240419 |
|
AD01 | Patent right deemed abandoned |