CN113361514A - Keyword knowledge base-based shopping receipt information analysis method and system - Google Patents
Keyword knowledge base-based shopping receipt information analysis method and system Download PDFInfo
- Publication number
- CN113361514A CN113361514A CN202110635158.6A CN202110635158A CN113361514A CN 113361514 A CN113361514 A CN 113361514A CN 202110635158 A CN202110635158 A CN 202110635158A CN 113361514 A CN113361514 A CN 113361514A
- Authority
- CN
- China
- Prior art keywords
- receipt
- keyword
- information
- knowledge base
- text
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 63
- 238000005192 partition Methods 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 11
- 239000000284 extract Substances 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- GMVPRGQOIOIIMI-DODZYUBVSA-N 7-[(1R,2R,3R)-3-hydroxy-2-[(3S)-3-hydroxyoct-1-enyl]-5-oxocyclopentyl]heptanoic acid Chemical group CCCCC[C@H](O)C=C[C@H]1[C@H](O)CC(=O)[C@@H]1CCCCCCC(O)=O GMVPRGQOIOIIMI-DODZYUBVSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of character recognition, in particular to a shopping receipt information analysis method and a shopping receipt information analysis system based on a keyword knowledge base. The implementation comprises the following steps: step 1: and processing the receipt text to remove invalid information. Step 2: and executing an analysis algorithm on the processed receipt text to obtain an analysis report. And step 3: and extracting the new keywords and putting the new keywords into a keyword knowledge base. The method and the device can be used for dealing with the tickets with different formats and different texts, and avoid designing a separate analysis rule for each ticket. And constructing a general receipt analysis flow based on the keyword knowledge base, and accurately and quickly extracting order information. By constructing a keyword knowledge base, the expandability is improved; by designing the receipt text partition algorithm, the analysis efficiency is improved.
Description
Technical Field
The invention relates to the technical field of character recognition, in particular to a shopping receipt information analysis method and system based on a keyword knowledge base.
Background
In recent years, artificial intelligence has become an important driving force for global technological and industrial changes, and the rise and development of business intelligence are promoted. Merchant shopping receipt information analysis (receipt analysis for short) is an important application in the field of business intelligence, and has attracted much attention in recent years. The receipt analysis can summarize the order and transaction information of the commercial tenant for various markets, shopping streets, shopping centers and the like, and plays an important role in the aspects of market operation analysis, market state distribution, commercial tenant rent schemes and the like.
In the patent document of chinese invention with patent number CN201910691300.1, a method for accurately extracting data of general shopping tickets is disclosed, which comprises the following steps: s1, modeling the receipt data; s2, analyzing the model; s3, accurately extracting keywords; and S4, detail output. The method is used for rapidly dividing and cutting the receipt data according to the start-stop keywords of the domain structure body and accurately extracting the data in the data domain. However, the format and text of the shopping receipt are complicated, the existing receipt character recognition technology mainly extracts specific receipts, and the defects of weak generalization capability, poor expandability, low efficiency and the like exist. In an actual scene, deployment, debugging and maintenance costs are high. Therefore, the method and the system for analyzing the shopping receipt information based on the keyword knowledge base are provided.
Disclosure of Invention
The invention discloses a shopping receipt information analysis method and system based on a keyword knowledge base, aiming at overcoming the defects of poor generalization capability, poor expandability, low efficiency and the like of the existing receipt character recognition technology which mainly extracts specific receipts and is used for solving the problems of complicated formats and texts of shopping receipts.
The invention is realized by the following technical scheme:
in a first aspect, the invention discloses a keyword knowledge base-based shopping receipt information analysis method, which comprises the following steps:
s1, acquiring text information of the receipt, executing text line filtering operation, and removing useless lines such as empty lines and separators and special symbols of each line;
s2, reading keywords corresponding to each partition of the receipt text according to the keyword knowledge base, executing text line marking, and combining the areas to obtain texts in each area of the receipt;
s3, reading keywords from the keyword knowledge base according to the information to be extracted, and sequencing the read keywords according to the weight or the sequence;
s4, selecting the text of the corresponding subarea according to the information to be extracted, and matching all the keywords in sequence until the information is extracted;
s5, executing the step S4 on each partition of the receipt text to obtain all order information and generate an analysis report;
s6 obtains a text line without a line mark from the receipt text, extracts a new keyword therefrom, and puts it into a keyword knowledge base.
Furthermore, the method utilizes keywords to mark the partition of each row of the receipt, and collects the text rows of the receipt in the same partition to obtain the partition result.
Further, the keyword knowledge base comprises one or more of the following items: the number id of the keyword, the key of the keyword, the extraction rule pattern of the information, the type of the information corresponding to the keyword, the partition group to which the keyword belongs, or the weight or the sequence weight of the keyword.
Furthermore, the partition group to which the keyword belongs includes one or more of the following items: the system comprises a receipt head front, commodity detail, payment information payment, member information membership and a receipt tail rear.
Further, the analytic report includes one or more of the following: order number order _ no, order time order _ time, order amount pay _ amount, payment method pay _ method, membership card number vip _ card _ id, membership card type vip _ card _ type, or cashier case.
In a second aspect, the invention discloses a keyword-knowledge-base-based shopping receipt information analysis system, which is used for supporting the implementation of the keyword-knowledge-base-based shopping receipt information analysis method in the first aspect.
Furthermore, the intelligent cash register and the intelligent bill printer are applied to the scenes of business surpassing, farmer trade, law enforcement, industry and the like.
Furthermore, the intelligent cash register sends the order information to the intelligent bill printer, and the intelligent bill printer calls an algorithm through a network to realize quick and real-time analysis of the receipt.
Furthermore, the receipt information analysis module comprises a partition algorithm submodule and an analysis algorithm submodule.
The system further comprises a cloud server, wherein the cloud server is used for constructing a keyword knowledge base and deploying a receipt text processing module, a receipt information analysis module and a knowledge base expansion module.
The invention has the beneficial effects that:
the method and the device can be used for dealing with the tickets with different formats and different texts, and avoid designing a separate analysis rule for each ticket. And constructing a general receipt analysis flow based on the keyword knowledge base, and accurately and quickly extracting order information. By constructing a keyword knowledge base, the expandability is improved; by designing the receipt text partition algorithm, the analysis efficiency is improved.
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 some embodiments of the present invention, 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 the overall implementation of the present invention;
FIG. 2 is a flowchart of the receipt text processing of an embodiment of the present invention;
FIG. 3 is a flowchart of parsing a ticket text according to an embodiment of the invention;
FIG. 4 is a flow chart of a partitioning algorithm according to an embodiment of the present invention;
FIG. 5 is a flow chart of a parsing algorithm according to an embodiment of the present invention;
FIG. 6 is a flow chart of knowledge base expansion according to an embodiment of the present invention;
FIG. 7 is a diagram of an example keyword knowledge base in accordance with an embodiment of the present invention;
FIG. 8 is a diagram of an example of a ticket according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating an example of partitioning results according to an embodiment of the present invention;
FIG. 10 is a diagram illustrating an example of a resolved report according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.
Example 1
The embodiment discloses a shopping receipt information analysis method based on a keyword knowledge base, which comprises the following steps:
s1, acquiring text information of the receipt, executing text line filtering operation, and removing useless lines such as empty lines and separators and special symbols of each line;
s2, reading keywords corresponding to each partition of the receipt text according to the keyword knowledge base, executing text line marking, and combining the areas to obtain texts in each area of the receipt;
s3, reading keywords from the keyword knowledge base according to the information to be extracted, and sequencing the read keywords according to the weight or the sequence;
s4, selecting the text of the corresponding subarea according to the information to be extracted, and matching all the keywords in sequence until the information is extracted;
s5, executing the step S4 on each partition of the receipt text to obtain all order information and generate an analysis report;
s6 obtains a text line without a line mark from the receipt text, extracts a new keyword therefrom, and puts it into a keyword knowledge base.
In the embodiment, each row of the receipt is marked with the partition to which the row belongs by using the keywords, and the text rows of the receipt in the same partition are collected to obtain the partition result.
In this embodiment, the keyword knowledge base includes one or more of the following items: the number id of the keyword, the key of the keyword, the extraction rule pattern of the information, the type of the information corresponding to the keyword, the partition group to which the keyword belongs, or the weight or the sequence weight of the keyword.
In this embodiment, the partition group to which the keyword belongs includes one or more of the following items: the system comprises a receipt head front, commodity detail, payment information payment, member information membership and a receipt tail rear.
The analysis report of this embodiment includes one or more of the following items: order number order _ no, order time order _ time, order amount pay _ amount, payment method pay _ method, membership card number vip _ card _ id, membership card type vip _ card _ type, or cashier case.
Example 2
The embodiment discloses a shopping receipt information analysis system based on a keyword knowledge base, and the shopping receipt information analysis system is completed based on an intelligent cash register and an intelligent receipt printer. The T2 cash register and the 58 bill printer are commercial devices developed and produced by Shanghai Kaishi group of science and technology, and can be applied to scenes such as Shanghai, farmer trade, law enforcement, industry and the like. The established keyword knowledge base and the analysis algorithm are deployed in the cloud, the T2 cash register sends order information to the 58 bill printer, and the printer calls the algorithm through the network to realize quick and real-time receipt analysis.
The cash register in this embodiment: the system is a commercial management device for merchant operation, and can be provided with various commercial software for commodity management, commodity transaction, cash collection and the like.
A bill printer: refers to printers that are used exclusively for printing tickets, such as tickets for shops and supermarkets, corporate financial invoices and the like.
Analyzing shopping receipt information: the analysis of the tickets refers to extracting required order information or operation information, such as order numbers, order placing time, order amount and the like, from the shopping tickets of the merchants. An example of a ticket according to this embodiment is shown in fig. 8.
As shown in fig. 1, the implementation process of this embodiment includes three modules: processing the text of the receipt, analyzing the information of the receipt and expanding a knowledge base.
The implementation of the embodiment comprises the following steps:
step 1: and processing the receipt text to remove invalid information.
Step 2: and executing an analysis algorithm on the processed receipt text to obtain an analysis report.
And step 3: and extracting the new keywords and putting the new keywords into a keyword knowledge base.
The embodiment also comprises a cloud server, wherein the cloud server is used for constructing the keyword knowledge base and deploying the receipt text processing module, the receipt information analysis module and the knowledge base expansion module.
The embodiment can deal with the tickets with different formats and different texts, and avoids designing a separate analysis rule for each ticket. The performance of the receipt analysis algorithm mainly can consider three aspects of generalization capability, expansibility and efficiency.
In the embodiment, a general receipt analysis flow is constructed based on the keyword knowledge base, and order information is accurately and quickly extracted. By constructing a keyword knowledge base, the expandability is improved; by designing a receipt text partition algorithm, the analysis efficiency is improved.
Example 3
The embodiment discloses that the execution of the receipt text processing module shown in fig. 2 comprises the following steps:
step 1.1: and executing text line filtering operation to remove useless lines such as empty lines, separators and the like.
Step 1.2: and executing text block filtering operation, removing special symbols of each line and the like.
The embodiment discloses that the execution of the receipt information analysis module shown in fig. 3 includes the following steps:
step 2.1: and executing a partition algorithm on the receipt text according to the keyword knowledge base to obtain the texts of the areas of the receipt.
Step 2.2: and executing an analysis algorithm on each partition according to the keyword knowledge base to obtain order information and generate an analysis report.
The embodiment discloses that the sub-module of the partition algorithm shown in fig. 4 comprises the following steps:
step 2.1.1: and reading out the keywords corresponding to each partition from the keyword knowledge base.
Step 2.1.2: and performing text line marking, namely marking the partition of each line of the receipt by using keywords.
Step 2.1.3: and (4) executing region merging, namely collecting the text lines of the tickets in the same partition to obtain a partition result.
The embodiment discloses that the sub-module of the parsing algorithm shown in fig. 5 comprises the following steps:
step 2.2.1: and reading the keywords from the keyword knowledge base according to the information to be extracted.
Step 2.2.2: and sorting the read keywords according to the weight or the sequence.
Step 2.2.3: and selecting the text of the corresponding partition according to the information to be extracted.
Step 2.2.4: in this partition, all keywords are sequentially matched until the information is extracted.
Step 2.2.5: and (5) repeating the steps 1-4 to obtain all order information and generate an analysis report.
The embodiment discloses that the knowledge base expansion module shown in fig. 6 comprises the following steps when executed:
step 3.1: from the ticket text, the text lines are obtained without line markers.
Step 3.2: extracting new keywords from the database and putting the extracted new keywords into a keyword knowledge base.
Example 4
The embodiment is an example of the keyword knowledge base shown in fig. 7:
description 1: the keyword knowledge base includes but is not limited to id, key, pattern, type, group, weight, etc. knowledge.
Description 2: wherein id is the serial number of the keyword, key is the keyword, pattern is the extraction rule of the information, type is the information type corresponding to the keyword, group is the partition to which the keyword belongs, and weight is the weight or sequence of the keyword.
This embodiment discloses a partition result example as shown in fig. 9:
description 1: partitions (i.e., groups in the keyword repository) include, but are not limited to, front, detail, payment, membership, rear, and the like.
Description 2: wherein, front is the small ticket head, detail is the commodity detail, payment is the payment information, membership is the member information, and rear is the small ticket tail.
The embodiment discloses an example of the analytic report shown in fig. 10:
description 1: the parsing report includes, but is not limited to, order _ no, order _ time, pay _ amount, pay _ method, vip _ card _ id, vip _ card _ type, case, etc. information types (i.e. types in the keyword repository).
Description 2: the order _ no is an order number, the order _ time is an order placing time, the pay _ amount is an order amount, the pay _ method is a payment method, the vip _ card _ id is a member card number, the vip _ card _ type is a member card type, and the case is a cashier.
In summary, the method of the present invention has the advantages of strong versatility and low deployment and maintenance costs in the general analysis process. The text processing flow, the information analysis flow and the knowledge base expansion flow are formulated, the steps are comprehensive, and the universality is high.
According to the invention, in the text processing flow, the invalid text is removed from the receipt text, so that the interference on the analysis is reduced. In the information analysis process, a keyword knowledge base and a receipt partition algorithm are added, and the analysis capability is improved. In the knowledge base expansion process, the keyword information can be updated and analyzed in time, the expandability of the algorithm is ensured, the prior information of the receipt text is fully exerted on the keyword knowledge base, and the adaptability and the expandability are strong.
The invention brings keywords appearing in various tickets into the knowledge base, enhances the adaptability to different types of tickets and avoids setting special analysis rules for each type of tickets. Setting weight values or matching sequences and the like for the keywords, preferentially matching the keywords with higher determinacy, and enabling the matching to be more accurate.
According to the invention, on the basis of the receipt partition algorithm, the prior information of the receipt format is fully exerted, the matching cost is reduced, and the analysis efficiency is improved. The receipt is divided into a plurality of areas such as commodity details, payment information and the like, different information is analyzed from the corresponding partitions, full-text matching is avoided, and the analysis speed is higher.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A shopping receipt information analysis method based on a keyword knowledge base is characterized by comprising the following steps:
s1, acquiring text information of the receipt, executing text line filtering operation, and removing useless lines such as empty lines and separators and special symbols of each line;
s2, reading keywords corresponding to each partition of the receipt text according to the keyword knowledge base, executing text line marking, and combining the areas to obtain texts in each area of the receipt;
s3, reading keywords from the keyword knowledge base according to the information to be extracted, and sequencing the read keywords according to the weight or the sequence;
s4, selecting the text of the corresponding subarea according to the information to be extracted, and matching all the keywords in sequence until the information is extracted;
s5, executing the step S4 on each partition of the receipt text to obtain all order information and generate an analysis report;
s6 obtains a text line without a line mark from the receipt text, extracts a new keyword therefrom, and puts it into a keyword knowledge base.
2. The shopping receipt information analysis method based on the keyword knowledge base as claimed in claim 1, wherein the method is characterized in that each row of the receipt is marked with the partition to which the row belongs by using keywords, and text rows of the receipt in the same partition are collected to obtain partition results.
3. The keyword-knowledge-base-based shopping receipt information parsing method according to claim 1, wherein the keyword knowledge base comprises one or more of the following items: the number id of the keyword, the key of the keyword, the extraction rule pattern of the information, the type of the information corresponding to the keyword, the partition group to which the keyword belongs, or the weight or the sequence weight of the keyword.
4. The keyword-knowledge-base-based shopping receipt information analysis method according to claim 3, wherein the partition group to which the keyword belongs includes one or more of the following items: the system comprises a receipt head front, commodity detail, payment information payment, member information membership and a receipt tail rear.
5. The keyword-knowledge-base-based shopping receipt information parsing method according to claim 1, wherein the parsed report includes one or more of the following items: order number order _ no, order time order _ time, order amount pay _ amount, payment method pay _ method, membership card number vip _ card _ id, membership card type vip _ card _ type, or cashier case.
6. A shopping receipt information analysis system based on a keyword knowledge base is used for supporting and realizing the shopping receipt information analysis method based on the keyword knowledge base as claimed in any one of claims 1 to 5, and is characterized by comprising an intelligent cash register, an intelligent receipt printer, a receipt text processing module, a receipt information analysis module and a knowledge base expansion module.
7. The keyword knowledge base-based shopping receipt information parsing system as claimed in claim 6, wherein the intelligent cash register and intelligent receipt printer are applied to business super, farm trade, law enforcement or industry scenes.
8. The keyword knowledge base-based shopping receipt information analysis system according to claim 6, wherein the intelligent cash register sends order information to an intelligent receipt printer, and the intelligent receipt printer calls an algorithm through a network to realize rapid and real-time receipt analysis.
9. The keyword-knowledge-base-based shopping receipt information parsing system of claim 6, wherein the receipt information parsing module comprises a partition algorithm sub-module and a parsing algorithm sub-module.
10. The keyword-knowledge-base-based shopping receipt information analysis system according to claim 6, further comprising a cloud server, wherein the cloud server is used for constructing the keyword knowledge base and deploying the receipt text processing module, the receipt information analysis module and the knowledge base expansion module at the same time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635158.6A CN113361514A (en) | 2021-06-08 | 2021-06-08 | Keyword knowledge base-based shopping receipt information analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635158.6A CN113361514A (en) | 2021-06-08 | 2021-06-08 | Keyword knowledge base-based shopping receipt information analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113361514A true CN113361514A (en) | 2021-09-07 |
Family
ID=77533063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110635158.6A Pending CN113361514A (en) | 2021-06-08 | 2021-06-08 | Keyword knowledge base-based shopping receipt information analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113361514A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140207631A1 (en) * | 2013-01-23 | 2014-07-24 | Jason M. FISHER | Systems and Method for Analyzing and Validating Invoices |
| CN105630817A (en) * | 2014-11-03 | 2016-06-01 | 航天信息股份有限公司 | Electronic invoice content analysis method and system |
| CN108596750A (en) * | 2018-05-09 | 2018-09-28 | 西安交通大学 | A kind of invoice voiding recognition methods based on parallel association rules |
| CN109460725A (en) * | 2018-10-29 | 2019-03-12 | 苏州派维斯信息科技有限公司 | Receipt consumption details content mergence and extracting method |
| CN110413659A (en) * | 2019-07-29 | 2019-11-05 | 南京沁恒微电子股份有限公司 | General shopping receipt accurate data extracting method |
| CN111209827A (en) * | 2019-12-31 | 2020-05-29 | 中国南方电网有限责任公司 | OCR (optical character recognition) bill problem recognition method and system based on feature detection |
| CN111583004A (en) * | 2020-05-11 | 2020-08-25 | 南京迪巴戈软件科技有限公司 | Intelligent financial management tool based on cloud framework |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN112651340A (en) * | 2020-12-28 | 2021-04-13 | 上海商米科技集团股份有限公司 | Character recognition method, system, terminal device and storage medium for shopping receipt |
| CN213072876U (en) * | 2020-07-31 | 2021-04-27 | 上海商米科技集团股份有限公司 | Article picture data acquisition system |
-
2021
- 2021-06-08 CN CN202110635158.6A patent/CN113361514A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140207631A1 (en) * | 2013-01-23 | 2014-07-24 | Jason M. FISHER | Systems and Method for Analyzing and Validating Invoices |
| CN105630817A (en) * | 2014-11-03 | 2016-06-01 | 航天信息股份有限公司 | Electronic invoice content analysis method and system |
| CN108596750A (en) * | 2018-05-09 | 2018-09-28 | 西安交通大学 | A kind of invoice voiding recognition methods based on parallel association rules |
| CN109460725A (en) * | 2018-10-29 | 2019-03-12 | 苏州派维斯信息科技有限公司 | Receipt consumption details content mergence and extracting method |
| CN110413659A (en) * | 2019-07-29 | 2019-11-05 | 南京沁恒微电子股份有限公司 | General shopping receipt accurate data extracting method |
| CN111209827A (en) * | 2019-12-31 | 2020-05-29 | 中国南方电网有限责任公司 | OCR (optical character recognition) bill problem recognition method and system based on feature detection |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN111583004A (en) * | 2020-05-11 | 2020-08-25 | 南京迪巴戈软件科技有限公司 | Intelligent financial management tool based on cloud framework |
| CN213072876U (en) * | 2020-07-31 | 2021-04-27 | 上海商米科技集团股份有限公司 | Article picture data acquisition system |
| CN112651340A (en) * | 2020-12-28 | 2021-04-13 | 上海商米科技集团股份有限公司 | Character recognition method, system, terminal device and storage medium for shopping receipt |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105138652B (en) | A kind of enterprise's incidence relation recognition methods and system | |
| CN111726248A (en) | Alarm root cause positioning method and device | |
| CN102722713B (en) | Handwritten numeral recognition method based on lie group structure data and system thereof | |
| CN104463195A (en) | Printing style digital recognition method based on template matching | |
| JPH1091712A (en) | Document analyzing system and its process | |
| CN110909123B (en) | Data extraction method and device, terminal equipment and storage medium | |
| Taghiyarrenani et al. | Transfer learning based intrusion detection | |
| CN105139041A (en) | Method and device for recognizing languages based on image | |
| CN112559771A (en) | Intelligent capital transaction monitoring method and system based on knowledge graph | |
| Wang et al. | Time-variant graph classification | |
| CN105678323A (en) | Image-based-on method and system for analysis of users | |
| CN111461266B (en) | Vehicle damage assessment abnormity identification method, device, server and storage medium | |
| Yang et al. | Vision-based layout detection from scientific literature using recurrent convolutional neural networks | |
| CN112328792A (en) | Optimization method for recognizing credit events based on DBSCAN clustering algorithm | |
| CN115171143A (en) | Method and system for extracting full-face information of electronic invoice | |
| CN113656768B (en) | Method, system and storage medium for tracking digital asset flow direction in block chain | |
| CN113469005B (en) | Bank receipt identification method, related device and storage medium | |
| CN104966109A (en) | Medical laboratory report image classification method and apparatus | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| CN109902215A (en) | A kind of method and system of deals match | |
| CN113361514A (en) | Keyword knowledge base-based shopping receipt information analysis method and system | |
| CN109670162A (en) | The determination method, apparatus and terminal device of title | |
| CN112949778A (en) | Intelligent contract classification method and system based on locality sensitive hashing and electronic equipment | |
| CN107169030A (en) | A kind of method and system of identification check integration | |
| CN109344254B (en) | Address information classification method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |
|
| RJ01 | Rejection of invention patent application after publication |