CN117132244B - Classification processing method, device and storage medium for intelligent compliance management system - Google Patents
Classification processing method, device and storage medium for intelligent compliance management system Download PDFInfo
- Publication number
- CN117132244B CN117132244B CN202311401598.0A CN202311401598A CN117132244B CN 117132244 B CN117132244 B CN 117132244B CN 202311401598 A CN202311401598 A CN 202311401598A CN 117132244 B CN117132244 B CN 117132244B
- Authority
- CN
- China
- Prior art keywords
- compliance
- character
- data
- examination
- preset separation
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000000926 separation method Methods 0.000 claims abstract description 213
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000007689 inspection Methods 0.000 claims description 27
- 238000012015 optical character recognition Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012552 review Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 31
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000001503 joint Anatomy 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
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The invention provides a classification processing method, a classification processing device and a storage medium for an intelligent compliance management system, wherein the classification processing method comprises the following steps: acquiring a first position corresponding to each preset separation character in the examination data; segmenting the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments; identifying the text in the title text or the data segment corresponding to each preset separation character based on the examination model so as to classify and process each data segment and add a corresponding classification label; highlighting a corresponding data segment in the examination data based on the classification label, highlighting an examination column corresponding to the compliance requirement table, and then sending the highlighted examination column to a compliance examination terminal; and after judging that the compliance requirement tables fed back by the compliance approval ends corresponding to all the classification labels have preset compliance information, the intelligent compliance management system judges corresponding examination data to finish compliance processing.
Description
Technical Field
The present invention relates to data processing technologies, and in particular, to a classification processing method and apparatus for an intelligent compliance management system, and a storage medium.
Background
The contract is an agreement between civil subjects to set up, alter and terminate civil legal relations. The contracts include multiple types, such as trade contracts. Whether the contents of the trade contract are compliant is a precondition for effective guarantee of trade between trade principals, and thus compliance inspection is required.
In general, a contract involves many departments, including, for example, a financial department corresponding to payment content, a transportation department corresponding to transportation content, a legal department corresponding to obligation content, and the like. In the prior art, when compliance checking is performed on a contract, a user who is in butt joint with one transaction often checks the content corresponding to the contract. However, since the departments involved in the contract are more, one user cannot fully understand the inspection requirements of each department, so that the inspection data cannot conform to the inspection requirements of the inspection end at each department.
Therefore, how to customize the examination data by combining different contents of the contract makes the examination data to be synchronously examined in multiple ends corresponding to different examination ends so as to meet the examination requirements of each examination end, and the examination method becomes an urgent problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a classification processing method, a classification processing device and a storage medium for an intelligent compliance management system, which can be used for customizing the examination data by combining different contents of a contract, so that the examination data can be subjected to multi-terminal synchronous examination corresponding to different examination terminals, and the examination requirements of all examination terminals can be met.
In a first aspect of the embodiments of the present invention, a classification processing method for an intelligent compliance management system is provided, including:
after judging that the uploaded examination data is received, the intelligent compliance management system carries out OCR (optical character recognition) on the examination data to determine corresponding preset separation characters, and obtains a first position corresponding to each preset separation character in the examination data;
segmenting the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation;
identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model, classifying each data segment, adding a corresponding classification label, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table;
highlighting a corresponding data segment in the examination data based on the classification label, highlighting an examination column corresponding to the compliance requirement table, and then sending the highlighted examination column to a compliance examination terminal;
and after judging that the compliance requirement tables fed back by the compliance approval ends corresponding to all the classification labels have preset compliance information, the intelligent compliance management system judges corresponding examination data to finish compliance processing.
Optionally, after judging that the uploaded censored data is received, the intelligent compliance management system performs OCR recognition on the censored data to determine a corresponding preset separation character, and obtains a first position corresponding to each preset separation character in the censored data, including:
after judging that the uploaded examination data is received, determining page number information and row number information in the examination data, wherein the examination data has preset page number information and row number information;
performing OCR (optical character recognition) on the inspection data to determine corresponding preset separation characters, and extracting page number information and line code information of the preset separation characters as first positions corresponding to the preset separation characters in the inspection data.
Optionally, the segmenting the censored data according to the character correspondence between preset separation characters to obtain a plurality of data segments, where the start position and the end position of each data segment correspond to adjacent preset separation characters in the character correspondence, including:
acquiring a character corresponding relation between preset separation characters to determine a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character;
Obtaining a corresponding second position according to a preset adjustment mode based on the first position of the second preset separation character;
and carrying out segmentation processing on the examination data based on the first position of the first preset separation character and the second position of the second preset separation character to obtain a plurality of data segments, wherein the initial position of the data segments corresponds to the first position of the first preset separation character, and the end position of the data segments corresponds to the second position of the second preset separation character.
Optionally, the acquiring the character correspondence between the preset separation characters determines a first preset separation character and a second preset separation character that are adjacent, where a first position of the first preset separation character is in front of a first position of the second preset separation character, and the method includes:
acquiring a character corresponding relation between preset separation characters, wherein the character corresponding relation comprises a front-back corresponding relation of digital logic;
dividing preset separation characters with front-back correspondence into a plurality of groups, wherein each group is provided with a first preset separation character and a second preset separation character which correspond to each other, and the first position of the number of the first preset separation character is in front of the first position of the number of the second preset separation character.
Optionally, the obtaining the corresponding second position according to the preset adjustment mode based on the first position of the second preset separation character includes:
acquiring page number information and row number information corresponding to the first position;
if the line code information is judged not to be the 1 st line of the corresponding page code information, subtracting 1 from the line code information to obtain updated line code information, and taking the page code information and the updated line code information as a second position of a second preset separation character.
Optionally, the obtaining the corresponding second position according to the preset adjustment mode based on the first position of the second preset separation character includes: if the line code information is judged to be the 1 st line of the corresponding page code information, subtracting 1 from the page code information to obtain updated page code information, determining the line code information of the last line of the updated page code information, and taking the updated page code information and the line code information of the last line as the second position of the second preset separation character.
Optionally, the identifying text in the header text or the data segment corresponding to each preset separation character based on the censoring model, so as to classify and process each data segment and add a corresponding classification label, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table, which includes:
Determining preset target classified texts and classified labels based on text recognition in a title text or a data segment corresponding to each preset separation character by using an examination model, wherein each target classified text is provided with the preset classified label;
the compliance requirement table is provided with a plurality of groups of columns, each group of columns is provided with a corresponding label sub-column and a corresponding paragraph sub-column, classification labels of all data segments are counted and added into the label column in the compliance requirement table, and a first position and a second position of the data segment corresponding to each classification label are added into the paragraph sub-column in the compliance requirement table.
Optionally, the highlighting the corresponding data segment in the examination data based on the classification label and highlighting the examination column corresponding to the compliance requirement table are then sent to the compliance end, which includes:
copying the examination data according to the number of the tag columns so that each classified tag has corresponding examination data;
determining corresponding data segments in the inspection data based on the first position and the second position in the paragraph column corresponding to the corresponding classification label, and generating a highlighting frame corresponding to the corresponding data segments;
And establishing examination columns in a plurality of groups of column grids of the classification labels corresponding to the compliance requirement list, highlighting the examination columns, and sending the highlighted examination data and the compliance requirement list to a compliance examination terminal.
Optionally, after the intelligent compliance management system determines that the compliance requirement table fed back by the compliance approval end corresponding to all the classification labels has preset compliance information, the intelligent compliance management system determines that the corresponding censored data completes compliance processing, including:
the intelligent compliance management system analyzes compliance requirement tables fed back by compliance approval ends corresponding to all the classification labels, and judges that the corresponding compliance requirement tables meet requirements if the review columns of each compliance requirement table have corresponding preset compliance information;
and after judging that the compliance requirement tables of all the classification labels meet the requirements, judging that the corresponding inspection data finish compliance processing.
Optionally, the method further comprises:
and if the compliance requirement table fed back by the compliance terminal is judged to be the non-compliance information, extracting the non-compliance data corresponding to the non-compliance information, wherein the non-compliance data is actively filled by the compliance terminal based on the data segment.
In a second aspect of the embodiments of the present invention, there is provided a classification processing apparatus for an intelligent compliance management system, including:
The recognition module is used for enabling the intelligent compliance management system to carry out OCR recognition on the examination data to determine corresponding preset separation characters after judging that the uploaded examination data are received, and obtaining a first position corresponding to each preset separation character in the examination data;
the processing module is used for carrying out segmentation processing on the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, and the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation;
the statistics module is used for identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model so as to classify and process each data segment and add a corresponding classification label, and the classification labels of all the data segments are counted to generate a corresponding compliance requirement table;
the sending module is used for highlighting the corresponding data segment in the examination data based on the classification label and sending the examination column corresponding to the compliance requirement table to the compliance examination terminal after highlighting the examination column;
and the approval management module is used for judging that the corresponding approval data is subjected to the approval processing after the intelligent approval management system judges that the approval demand tables fed back by the approval ends corresponding to all the classification labels have preset approval information.
In a third aspect of an embodiment of the present invention, there is provided an electronic device including: a memory, a processor and a computer program stored in the memory, the processor running the computer program to perform the first aspect of the invention and the methods that the first aspect may relate to.
In a fourth aspect of embodiments of the present invention, there is provided a storage medium having stored therein a computer program for implementing the method of the first aspect and the various possible aspects of the first aspect when executed by a processor.
According to the classification processing method, the classification processing device and the storage medium for the intelligent compliance management system, the examination data can be classified in sections through the preset separation characters, then the title text corresponding to each preset separation character or the text in the data section are identified, so that each data section is classified, the corresponding classification label is added, the corresponding data section in the examination data is highlighted by combining the classification label, and therefore customization processing can be carried out on the examination data by combining different contents of a contract, multi-terminal synchronous examination is carried out on the examination data corresponding to different examination terminals, and examination requirements of each examination terminal are met.
Drawings
FIG. 1 is a schematic diagram of a classification processing device for an intelligent compliance management system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a classification processing device for an intelligent compliance management system according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.
It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.
It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Referring to fig. 1, a flow chart of a classification processing method for an intelligent compliance management system according to an embodiment of the present invention is shown, where the method includes S1-S5:
s1, after judging that the uploaded examination data is received, the intelligent compliance management system performs OCR (optical character recognition) on the examination data to determine corresponding preset separation characters, and obtains a first position corresponding to each preset separation character in the examination data.
The intelligent compliance management system can process the examination data, wherein the examination data is contract data. The scheme can conduct classified examination on the contract, so that different contents in the contract have different responsible persons or different departments to conduct correspondence examination. For example, the content of the payment portion may be reviewed by a financial department; the content of the transport section may be reviewed by the transport department.
It will be appreciated that there will be many terms in the contract data, such as second, third, first, fourth, money and payment means. The above terms are preset separation characters of the scheme, and character recognition can be performed by utilizing an OCR technology.
After the preset separation characters are obtained, the scheme can determine the first position corresponding to each preset separation character in the examination data.
In some embodiments, after determining that the uploaded censored data is received, the intelligent compliance management system performs OCR recognition on the censored data to determine a corresponding preset separation character, and obtains a first position corresponding to each preset separation character in the censored data, including S11-S12:
s11, after judging that the uploaded examination data is received, determining page number information and row number information in the examination data, wherein the examination data has preset page number information and row number information.
After judging that the uploaded examination data is received, the intelligent compliance management system of the scheme determines page number information and row number information in the examination data, wherein the examination data has preset page number information and row number information. For example, the inspection data a has 10 pages, 30 lines per page.
S12, OCR recognition is carried out on the inspected data to determine corresponding preset separation characters, and page number information and line code information of the preset separation characters are extracted to serve as first positions corresponding to the preset separation characters in the inspected data.
The scheme can perform OCR (optical character recognition) on the checked data to obtain corresponding preset separation characters, wherein the preset separation characters are obligations of a second party and a second party, obligations of a third party and a first party, and data similar to fourth party, money and payment modes can be preset by a manager.
After the preset separation character is determined, page number information and line number information of the preset separation character are obtained as the corresponding first position in the inspection data. For example, the second, b party obligation, which corresponds to the first location page 3, line 10.
S2, segmenting the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation.
In order to classify the examination data, the scheme uses preset separation characters as separation points to divide the data. When dividing, the scheme combines the character corresponding relation among the preset separation characters, and performs segmentation processing on the checked data to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation. The above-mentioned character correspondence is the front-back correspondence of the digital logic, and specific reference is made to the following description.
In some embodiments, the method includes the steps of segmenting the inspection data according to a character correspondence between preset separation characters to obtain a plurality of data segments, wherein a start position and an end position of each data segment correspond to adjacent preset separation characters in the character correspondence, and the method includes S21-S23:
s21, acquiring a character corresponding relation between preset separation characters to determine a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character.
The scheme can combine the character corresponding relation between the preset separation characters to determine the adjacent first preset separation characters and second preset separation characters.
Wherein the first position of the first preset separation character is in front of the first position of the second preset separation character. It can be understood that the scheme finds two preset separation characters adjacent to each other, takes the former preset separation character as a first preset separation character and takes the latter preset separation character as a second preset separation character.
The method comprises the steps of obtaining a character corresponding relation between preset separation characters to determine a first preset separation character and a second preset separation character which are adjacent, wherein a first position of the first preset separation character is in front of a first position of the second preset separation character, and the method comprises the following steps of S211-S212:
s211, acquiring a character corresponding relation between preset separation characters, wherein the character corresponding relation comprises a front-back corresponding relation of digital logic.
For example, the two adjacent preset separation characters are respectively the 2 nd preset separation character and the 3 rd preset separation character, and then the 2 nd preset separation character is positioned in front of the 3 rd preset separation character.
S212, dividing preset separation characters with front-back correspondence into a plurality of groups, wherein each group is provided with a first preset separation character and a second preset separation character which correspond to each other, and the first position of the number of the first preset separation character is in front of the first position of the number of the second preset separation character.
The scheme divides preset separation characters with front-back correspondence into a plurality of groups, wherein each group is provided with a first preset separation character and a second preset separation character which correspond to each other. For example, 12, 23, 34.
Wherein the first position of the number of the first preset separation character is in front of the first position of the number of the second preset separation character.
S22, obtaining a corresponding second position according to a preset adjustment mode based on the first position of the second preset separation character.
The scheme can combine the first position of the second preset separation character to obtain the corresponding second position according to the preset adjustment mode. See below for specific ways of adjustment.
In some embodiments, obtaining the corresponding second position according to the preset adjustment manner based on the first position of the second preset separation character includes S221-S223:
s221, page number information and row number information corresponding to the first position are acquired.
First, the scheme obtains page number information and line code information corresponding to the first position, that is, the position information of the first preset separation character located at the front part.
S222, if the line code information is judged not to be the 1 st line of the corresponding page code information, subtracting 1 from the line code information to obtain updated line code information, and taking the page code information and the updated line code information as a second position of a second preset separation character.
If the line code information is judged not to be the 1 st line of the corresponding page number information, namely not to be positioned at the top position of the corresponding page number, at the moment, the line code information is subtracted by 1 according to the scheme to obtain updated line code information. For example, the first location is page 5, line 3, and the second location is page 5, line 2. The scheme takes the page number information and the updated line number information as the second position of the second preset separation character.
S223, if the line number information is judged to be the 1 st line of the corresponding page number information, subtracting 1 from the page number information to obtain updated page number information, determining the line number information of the last line of the updated page number information, and taking the updated page number information and the line number information of the last line as the second position of the second preset separation character.
If the line number information is judged to be the 1 st line of the corresponding page number information, for example, the 1 st line of the 5 th page, the page number information is subtracted by 1 to obtain updated page number information, namely, the 4 th page, and meanwhile, the scheme can determine the line number information of the last line of the updated page number information, for example, the 30 th line of the 4 th page.
The scheme takes the updated page number information and the line number information of the last line as the second position of the second preset separation character.
S23, segmenting the inspection data based on the first position of the first preset separation character and the second position of the second preset separation character to obtain a plurality of data segments, wherein the initial position of the data segments corresponds to the first position of the first preset separation character, and the end position of the data segments corresponds to the second position of the second preset separation character.
After the first position of the first preset separation character and the second position of the second preset separation character are obtained, the method can be used for carrying out segmentation processing on the examination data by combining the first position of the first preset separation character and the second position of the second preset separation character to obtain a plurality of data segments.
The starting position of the data segment corresponds to the first position of the first preset separation character, and the ending position of the data segment corresponds to the second position of the second preset separation character.
S3, identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model, classifying each data segment, adding corresponding classification labels, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table.
After the inspection data is divided into a plurality of data segments, the method can utilize an inspection model to identify the title text corresponding to each preset separation character or the text in the data segments so as to classify and process each data segment and add a corresponding classification label.
For example, the title text is the sixth, transportation mode, and then a classification tag for transportation may be added thereto.
After all the data segments are added with the classification labels, the scheme can count the classification labels of all the data segments to generate a corresponding compliance requirement table.
In some embodiments, based on the text recognition in the header text or the data segment corresponding to each preset separation character by the examination model, the classification processing is performed on each data segment and corresponding classification labels are added, and the classification labels of all data segments are counted to generate a corresponding compliance requirement table, which comprises S31-S32:
s31, determining preset target classified texts and classified labels based on text recognition in the title text or the data segment corresponding to each preset separation character by using the examination model, wherein each target classified text is provided with the preset classified label.
Firstly, the examination model of the scheme can identify the text in the title text or the data segment corresponding to each preset separation character, and determine the preset target classification text and classification label.
Each target classified text is provided with a preset classified label. For example, if the target class text is in a shipping mode, then its corresponding class label may be shipping.
S32, the compliance requirement table is provided with a plurality of groups of columns, each group of columns is provided with a corresponding label sub-column and a corresponding paragraph sub-column, classification labels of all data segments are counted and added into the label column in the compliance requirement table, and a first position and a second position of the data segment corresponding to each classification label are added into the paragraph sub-column in the compliance requirement table.
The compliance requirement table of the scheme is provided with a plurality of groups of columns, wherein each group of columns is provided with a corresponding label sub-column and a corresponding paragraph sub-column. It is understood that the tag sub-field is used to fill in the classification tag of the data segment, and the paragraph sub-field is used to fill in the first location and the second location of the corresponding data segment.
And adding the classification labels of all the data segments into a label column in the compliance requirement table, and adding the first position and the second position of the data segment corresponding to each classification label into a paragraph column in the compliance requirement table.
S4, highlighting the corresponding data segment in the examination data based on the classification label, highlighting the examination column corresponding to the compliance requirement table, and then sending the highlighted examination column to the compliance examination end.
The scheme can be combined with the classification label to highlight the corresponding data segment in the examination data, and the examination column corresponding to the compliance requirement table is highlighted and then sent to the compliance terminal.
It should be noted that the compliance and approval terminals are multiple, and can be held by different personnel or different departments.
In some embodiments, highlighting the corresponding data segment in the inspection data based on the classification label, and highlighting the inspection column corresponding to the compliance requirement table and then sending the highlighted data segment to the compliance end, including S41-S43:
s41, copying the examination data according to the number of the tag columns so that each classified tag has corresponding examination data.
The proposal can copy the examination data by combining the number of the tag columns so that each classified tag has corresponding examination data. By the method, the examination data can be processed differently by combining different tag columns.
S42, determining the corresponding data segment in the inspection data based on the first position and the second position in the paragraph column corresponding to the corresponding classification label, and generating a highlighting frame corresponding to the corresponding data segment.
The scheme can combine the first position and the second position in the paragraph column corresponding to the corresponding classification label to determine the corresponding data segment in the examination data, and simultaneously generate the highlighting frame corresponding to the corresponding data segment.
The highlighting frame may be a square frame, and an upper position of the square frame may correspond to the first position, and a lower position of the square frame may correspond to the second position. It should be noted that, when the first position and the second position are not located in the same page, the last line and the first line of the corresponding page may be used as separate interlacing to obtain a corresponding square frame. For example, the first position is page 2, line 20, and the second position is page 3, line 10, then one highlighting frame can be obtained with page 2, line 20, and page 2, line 30 (the last line of page 2), and then one highlighting frame can be obtained with page 3, line 1, and page 3, line 10.
S43, establishing examination columns in a plurality of groups of columns of the classification labels corresponding to the compliance requirement list, highlighting the examination columns, and sending the highlighted examination data and the compliance requirement list to a compliance examination end.
The proposal can establish examination columns and highlight the examination columns in a plurality of groups of columns corresponding to the classification labels of the compliance requirement table, and the highlighting can be yellow. And then sending the highlighted examination data and the compliance requirement list to a compliance terminal.
And S5, after the intelligent compliance management system judges that the compliance requirement tables fed back by the compliance approval ends corresponding to all the classification labels have preset compliance information, judging that the corresponding examination data finish compliance processing.
After judging that the compliance requirement tables fed back by the compliance ends corresponding to all the classification labels have preset compliance information, the intelligent compliance management system of the scheme can judge that corresponding examination data is subjected to compliance processing. It can be appreciated that through the above manner, interaction with the compliance end is possible, and classification review is performed for multiple dimensions.
In some embodiments, after determining that the compliance requirement table fed back by the compliance end corresponding to all the classification tags has preset compliance information, the intelligent compliance management system determines that the corresponding censored data completes the compliance processing, including S51-S52:
s51, the intelligent compliance management system analyzes the compliance requirement tables fed back by the compliance approval ends corresponding to all the classification labels, and judges that the corresponding compliance requirement tables meet the requirements if the examination columns of each compliance requirement table have corresponding preset compliance information.
The intelligent compliance management system analyzes the compliance requirement table fed back by the compliance end corresponding to all the classification labels.
And if the examination column of each compliance requirement table has corresponding preset compliance information, indicating that all dimensions are qualified, judging that the corresponding compliance requirement table meets the requirements.
S52, after judging that the compliance requirement tables of all the classification labels meet the requirements, judging that the corresponding inspection data is subjected to compliance processing.
And after the compliance requirement tables of all the classification labels meet the requirements, judging that the corresponding inspection data is subjected to compliance processing.
On the basis of the above embodiment, the method further comprises:
and if the compliance requirement table fed back by the compliance terminal is judged to be the non-compliance information, extracting the non-compliance data corresponding to the non-compliance information, wherein the non-compliance data is actively filled by the compliance terminal based on the data segment.
If the compliance requirement table fed back by the compliance terminal is judged to be the non-compliance information, the scheme can extract the non-compliance data corresponding to the non-compliance information. The non-compliance data are actively filled in by the compliance terminal based on the data segment.
Referring to fig. 2, a schematic structural diagram of a classification processing device for an intelligent compliance management system according to an embodiment of the present invention is provided, where the system includes:
the recognition module is used for enabling the intelligent compliance management system to carry out OCR recognition on the examination data to determine corresponding preset separation characters after judging that the uploaded examination data are received, and obtaining a first position corresponding to each preset separation character in the examination data;
The processing module is used for carrying out segmentation processing on the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, and the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation;
the statistics module is used for identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model so as to classify and process each data segment and add a corresponding classification label, and the classification labels of all the data segments are counted to generate a corresponding compliance requirement table;
the sending module is used for highlighting the corresponding data segment in the examination data based on the classification label and sending the examination column corresponding to the compliance requirement table to the compliance examination terminal after highlighting the examination column;
and the approval management module is used for judging that the corresponding approval data is subjected to the approval processing after the intelligent approval management system judges that the approval demand tables fed back by the approval ends corresponding to all the classification labels have preset approval information.
The embodiment of the invention provides electronic equipment, which comprises: a processor, a memory and a computer program; wherein the method comprises the steps of
And a memory for storing the computer program, which may also be a flash memory (flash). Such as application programs, functional modules, etc. implementing the methods described above.
And the processor is used for executing the computer program stored in the memory to realize each step executed by the equipment in the method. Reference may be made in particular to the description of the embodiments of the method described above.
In the alternative, the memory may be separate or integrated with the processor.
When the memory is a device separate from the processor, the apparatus may further include:
and the bus is used for connecting the memory and the processor.
The present invention also provides a storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.
The storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the storage medium may reside as discrete components in a communication device. The storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.
The present invention also provides a program product comprising execution instructions stored in a storage medium. The at least one processor of the device may read the execution instructions from the storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. The classification processing method for the intelligent compliance management system is characterized by comprising the following steps of:
after judging that the uploaded examination data is received, the intelligent compliance management system carries out OCR (optical character recognition) on the examination data to determine corresponding preset separation characters, and obtains a first position corresponding to each preset separation character in the examination data;
segmenting the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation;
identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model, classifying each data segment, adding a corresponding classification label, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table;
highlighting a corresponding data segment in the examination data based on the classification label, highlighting an examination column corresponding to the compliance requirement table, and then sending the highlighted examination column to a compliance examination terminal;
after judging that the compliance requirement tables fed back by the compliance approval ends corresponding to all the classification labels have preset compliance information, the intelligent compliance management system judges corresponding examination data to finish compliance processing;
After judging that the uploaded examination data is received, the intelligent compliance management system performs OCR (optical character recognition) on the examination data to determine corresponding preset separation characters, and obtains a first position corresponding to each preset separation character in the examination data, wherein the method comprises the following steps:
after judging that the uploaded examination data is received, determining page number information and row number information in the examination data, wherein the examination data has preset page number information and row number information;
performing OCR (optical character recognition) on the inspection data to determine corresponding preset separation characters, and extracting page number information and line code information of the preset separation characters as first positions corresponding to the preset separation characters in the inspection data;
the step of segmenting the examination data according to the character correspondence between preset separation characters to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character correspondence, and the step of segmenting comprises the following steps:
acquiring a character corresponding relation between preset separation characters to determine a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character;
Obtaining a corresponding second position according to a preset adjustment mode based on the first position of the second preset separation character;
segmenting the examination data based on the first position of the first preset separation character and the second position of the second preset separation character to obtain a plurality of data segments, wherein the initial position of the data segment corresponds to the first position of the first preset separation character, and the end position of the data segment corresponds to the second position of the second preset separation character;
the acquiring the character correspondence between the preset separation characters determines a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character, and the method comprises the following steps:
acquiring a character corresponding relation between preset separation characters, wherein the character corresponding relation comprises a front-back corresponding relation of digital logic;
dividing preset separation characters with front-back correspondence into a plurality of groups, wherein each group is provided with a corresponding first preset separation character and a corresponding second preset separation character, and the first position of the number of the first preset separation character is in front of the first position of the number of the second preset separation character;
The obtaining the corresponding second position based on the first position of the second preset separation character according to a preset adjustment mode comprises the following steps:
acquiring page number information and row number information corresponding to the first position;
if the line code information is judged not to be the 1 st line of the corresponding page code information, subtracting 1 from the line code information to obtain updated line code information, and taking the page code information and the updated line code information as a second position of a second preset separation character;
the obtaining the corresponding second position based on the first position of the second preset separation character according to a preset adjustment mode comprises the following steps: if the line code information is judged to be the 1 st line of the corresponding page code information, subtracting 1 from the page code information to obtain updated page code information, determining the line code information of the last line of the updated page code information, and taking the updated page code information and the line code information of the last line as a second position of a second preset separation character;
identifying the text in the title text or the data segment corresponding to each preset separation character based on the examination model, classifying and processing each data segment, adding corresponding classification labels, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table, wherein the method comprises the following steps:
Determining preset target classified texts and classified labels based on text recognition in a title text or a data segment corresponding to each preset separation character by using an examination model, wherein each target classified text is provided with the preset classified label;
the compliance requirement table is provided with a plurality of groups of columns, each group of columns is provided with a corresponding label sub-column and a corresponding paragraph sub-column, classification labels of all data segments are counted and added into the label column in the compliance requirement table, and a first position and a second position of the data segment corresponding to each classification label are added into the paragraph sub-column in the compliance requirement table;
the highlighting of the corresponding data segment in the examination data based on the classification label and the highlighting of the examination column corresponding to the compliance requirement table are then sent to the compliance examination terminal, and the method comprises the following steps:
copying the examination data according to the number of the tag columns so that each classified tag has corresponding examination data;
determining corresponding data segments in the inspection data based on the first position and the second position in the paragraph column corresponding to the corresponding classification label, and generating a highlighting frame corresponding to the corresponding data segments;
and establishing examination columns in a plurality of groups of column grids of the classification labels corresponding to the compliance requirement list, highlighting the examination columns, and sending the highlighted examination data and the compliance requirement list to a compliance examination terminal.
2. The classification processing method for intelligent compliance management system of claim 1, wherein,
after judging that the compliance requirement tables fed back by the compliance ends corresponding to all the classification labels have preset compliance information, the intelligent compliance management system judges that corresponding examination data finish compliance processing, and the intelligent compliance management system comprises the following steps:
the intelligent compliance management system analyzes compliance requirement tables fed back by compliance approval ends corresponding to all the classification labels, and judges that the corresponding compliance requirement tables meet requirements if the review columns of each compliance requirement table have corresponding preset compliance information;
and after judging that the compliance requirement tables of all the classification labels meet the requirements, judging that the corresponding inspection data finish compliance processing.
3. The classification processing method for an intelligent compliance management system according to claim 2, further comprising:
and if the compliance requirement table fed back by the compliance terminal is judged to be the non-compliance information, extracting the non-compliance data corresponding to the non-compliance information, wherein the non-compliance data is actively filled by the compliance terminal based on the data segment.
4. A classification processing device for wisdom compliance management system, its characterized in that includes:
The recognition module is used for enabling the intelligent compliance management system to carry out OCR recognition on the examination data to determine corresponding preset separation characters after judging that the uploaded examination data are received, and obtaining a first position corresponding to each preset separation character in the examination data;
the processing module is used for carrying out segmentation processing on the examination data according to the character corresponding relation among the preset separation characters to obtain a plurality of data segments, and the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character corresponding relation;
the statistics module is used for identifying the title text corresponding to each preset separation character or the text in the data segment based on the examination model so as to classify and process each data segment and add a corresponding classification label, and the classification labels of all the data segments are counted to generate a corresponding compliance requirement table;
the sending module is used for highlighting the corresponding data segment in the examination data based on the classification label and sending the examination column corresponding to the compliance requirement table to the compliance examination terminal after highlighting the examination column;
the intelligent compliance management system is used for judging that corresponding examination data finish compliance processing after judging that the compliance demand form fed back by the compliance approval end corresponding to all the classification labels has preset compliance information;
After judging that the uploaded examination data is received, the intelligent compliance management system performs OCR (optical character recognition) on the examination data to determine corresponding preset separation characters, and obtains a first position corresponding to each preset separation character in the examination data, wherein the method comprises the following steps:
after judging that the uploaded examination data is received, determining page number information and row number information in the examination data, wherein the examination data has preset page number information and row number information;
performing OCR (optical character recognition) on the inspection data to determine corresponding preset separation characters, and extracting page number information and line code information of the preset separation characters as first positions corresponding to the preset separation characters in the inspection data;
the step of segmenting the examination data according to the character correspondence between preset separation characters to obtain a plurality of data segments, wherein the starting position and the ending position of each data segment correspond to the adjacent preset separation characters in the character correspondence, and the step of segmenting comprises the following steps:
acquiring a character corresponding relation between preset separation characters to determine a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character;
Obtaining a corresponding second position according to a preset adjustment mode based on the first position of the second preset separation character;
segmenting the examination data based on the first position of the first preset separation character and the second position of the second preset separation character to obtain a plurality of data segments, wherein the initial position of the data segment corresponds to the first position of the first preset separation character, and the end position of the data segment corresponds to the second position of the second preset separation character;
the acquiring the character correspondence between the preset separation characters determines a first preset separation character and a second preset separation character which are adjacent, wherein the first position of the first preset separation character is in front of the first position of the second preset separation character, and the method comprises the following steps:
acquiring a character corresponding relation between preset separation characters, wherein the character corresponding relation comprises a front-back corresponding relation of digital logic;
dividing preset separation characters with front-back correspondence into a plurality of groups, wherein each group is provided with a corresponding first preset separation character and a corresponding second preset separation character, and the first position of the number of the first preset separation character is in front of the first position of the number of the second preset separation character;
The obtaining the corresponding second position based on the first position of the second preset separation character according to a preset adjustment mode comprises the following steps:
acquiring page number information and row number information corresponding to the first position;
if the line code information is judged not to be the 1 st line of the corresponding page code information, subtracting 1 from the line code information to obtain updated line code information, and taking the page code information and the updated line code information as a second position of a second preset separation character;
the obtaining the corresponding second position based on the first position of the second preset separation character according to a preset adjustment mode comprises the following steps: if the line code information is judged to be the 1 st line of the corresponding page code information, subtracting 1 from the page code information to obtain updated page code information, determining the line code information of the last line of the updated page code information, and taking the updated page code information and the line code information of the last line as a second position of a second preset separation character;
identifying the text in the title text or the data segment corresponding to each preset separation character based on the examination model, classifying and processing each data segment, adding corresponding classification labels, and counting the classification labels of all the data segments to generate a corresponding compliance requirement table, wherein the method comprises the following steps:
Determining preset target classified texts and classified labels based on text recognition in a title text or a data segment corresponding to each preset separation character by using an examination model, wherein each target classified text is provided with the preset classified label;
the compliance requirement table is provided with a plurality of groups of columns, each group of columns is provided with a corresponding label sub-column and a corresponding paragraph sub-column, classification labels of all data segments are counted and added into the label column in the compliance requirement table, and a first position and a second position of the data segment corresponding to each classification label are added into the paragraph sub-column in the compliance requirement table;
the highlighting of the corresponding data segment in the examination data based on the classification label and the highlighting of the examination column corresponding to the compliance requirement table are then sent to the compliance examination terminal, and the method comprises the following steps:
copying the examination data according to the number of the tag columns so that each classified tag has corresponding examination data;
determining corresponding data segments in the inspection data based on the first position and the second position in the paragraph column corresponding to the corresponding classification label, and generating a highlighting frame corresponding to the corresponding data segments;
and establishing examination columns in a plurality of groups of column grids of the classification labels corresponding to the compliance requirement list, highlighting the examination columns, and sending the highlighted examination data and the compliance requirement list to a compliance examination terminal.
5. An electronic device, comprising: a memory, a processor and a computer program stored in the memory, the processor running the computer program to perform the method of any one of claims 1 to 3.
6. A storage medium having stored therein a computer program for implementing the method of any of claims 1 to 3 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311401598.0A CN117132244B (en) | 2023-10-26 | 2023-10-26 | Classification processing method, device and storage medium for intelligent compliance management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311401598.0A CN117132244B (en) | 2023-10-26 | 2023-10-26 | Classification processing method, device and storage medium for intelligent compliance management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117132244A CN117132244A (en) | 2023-11-28 |
| CN117132244B true CN117132244B (en) | 2024-01-09 |
Family
ID=88851211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311401598.0A Active CN117132244B (en) | 2023-10-26 | 2023-10-26 | Classification processing method, device and storage medium for intelligent compliance management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117132244B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008305292A (en) * | 2007-06-11 | 2008-12-18 | Cfj Kk | Automatic contract system and computer program |
| JP2010231743A (en) * | 2009-03-30 | 2010-10-14 | Ntt Data Corp | Device and method for supporting document examination and program |
| CN104424337A (en) * | 2013-09-11 | 2015-03-18 | 北大方正集团有限公司 | Document division system and document division method |
| CN111274782A (en) * | 2020-02-25 | 2020-06-12 | 平安科技（深圳）有限公司 | Text auditing method and device, computer equipment and readable storage medium |
| CN111738674A (en) * | 2020-05-29 | 2020-10-02 | 南京华盾电力信息安全测评有限公司 | Contract mobile approval implementation method and system |
| CN112329418A (en) * | 2020-11-03 | 2021-02-05 | 平安信托有限责任公司 | Parallel approval method, equipment and computer readable storage medium |
| CN112734181A (en) * | 2020-12-30 | 2021-04-30 | 平安养老保险股份有限公司 | Business information approval method and device, computer equipment and storage medium |
| CN113590823A (en) * | 2021-07-30 | 2021-11-02 | 中国平安财产保险股份有限公司 | Contract approval method and device, storage medium and electronic equipment |
| CN114186532A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Order examination processing method and device |
| CN114841658A (en) * | 2022-04-07 | 2022-08-02 | 中国矿业大学 | Classification-based mandatory regulation compliance inspection method for special construction scheme |
| CN114862334A (en) * | 2022-03-30 | 2022-08-05 | 北京幂律智能科技有限责任公司 | Design method of intelligent contract examination rule configuration platform |
| CN115269874A (en) * | 2022-08-01 | 2022-11-01 | 北京幂律智能科技有限责任公司 | Intelligent contract examination method based on natural language understanding |
| CN115630843A (en) * | 2022-11-01 | 2023-01-20 | 卓望信息技术（北京）有限公司 | Contract clause automatic checking method and system |
-
2023
- 2023-10-26 CN CN202311401598.0A patent/CN117132244B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008305292A (en) * | 2007-06-11 | 2008-12-18 | Cfj Kk | Automatic contract system and computer program |
| JP2010231743A (en) * | 2009-03-30 | 2010-10-14 | Ntt Data Corp | Device and method for supporting document examination and program |
| CN104424337A (en) * | 2013-09-11 | 2015-03-18 | 北大方正集团有限公司 | Document division system and document division method |
| CN111274782A (en) * | 2020-02-25 | 2020-06-12 | 平安科技（深圳）有限公司 | Text auditing method and device, computer equipment and readable storage medium |
| CN111738674A (en) * | 2020-05-29 | 2020-10-02 | 南京华盾电力信息安全测评有限公司 | Contract mobile approval implementation method and system |
| CN112329418A (en) * | 2020-11-03 | 2021-02-05 | 平安信托有限责任公司 | Parallel approval method, equipment and computer readable storage medium |
| CN112734181A (en) * | 2020-12-30 | 2021-04-30 | 平安养老保险股份有限公司 | Business information approval method and device, computer equipment and storage medium |
| CN113590823A (en) * | 2021-07-30 | 2021-11-02 | 中国平安财产保险股份有限公司 | Contract approval method and device, storage medium and electronic equipment |
| CN114186532A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Order examination processing method and device |
| CN114862334A (en) * | 2022-03-30 | 2022-08-05 | 北京幂律智能科技有限责任公司 | Design method of intelligent contract examination rule configuration platform |
| CN114841658A (en) * | 2022-04-07 | 2022-08-02 | 中国矿业大学 | Classification-based mandatory regulation compliance inspection method for special construction scheme |
| CN115269874A (en) * | 2022-08-01 | 2022-11-01 | 北京幂律智能科技有限责任公司 | Intelligent contract examination method based on natural language understanding |
| CN115630843A (en) * | 2022-11-01 | 2023-01-20 | 卓望信息技术（北京）有限公司 | Contract clause automatic checking method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117132244A (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872162B (en) | Wind control classification and identification method and system for processing user complaint information | |
| US20160307067A1 (en) | Method and apparatus for determining a document type of a digital document | |
| CN110597995B (en) | Commodity name classification method, commodity name classification device, commodity name classification equipment and readable storage medium | |
| CN110909123B (en) | Data extraction method and device, terminal equipment and storage medium | |
| WO2021072876A1 (en) | Identification image classification method and apparatus, computer device, and readable storage medium | |
| CN112418812A (en) | Distributed full-link automatic intelligent clearance system, method and storage medium | |
| CN110532449B (en) | Method, device, equipment and storage medium for processing service document | |
| CN112579781B (en) | Text classification method, device, electronic equipment and medium | |
| CN112699671A (en) | Language marking method and device, computer equipment and storage medium | |
| CN117275025A (en) | Processing system for batch image annotation | |
| CN117132244B (en) | Classification processing method, device and storage medium for intelligent compliance management system | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| CN115565178A (en) | Font identification method and apparatus | |
| CN111640025B (en) | Method for realizing information labeling processing based on label system | |
| CN114741501A (en) | Public opinion early warning method and device, readable storage medium and electronic equipment | |
| CN113537964A (en) | Application form processing method, device, storage medium and device | |
| CN113449506A (en) | Data detection method, device and equipment and readable storage medium | |
| CN112597295A (en) | Abstract extraction method and device, computer equipment and storage medium | |
| CN110688842A (en) | Document title level analysis method and device and server | |
| CN113362151B (en) | Data processing method and device for financial business, electronic equipment and storage medium | |
| US20230140546A1 (en) | Randomizing character corrections in a machine learning classification system | |
| CN116311321A (en) | Double-record operation mode recognition method based on OCR automatic recognition | |
| CN117877016A (en) | Video text extraction method, device, equipment and storage medium | |
| CN117612182A (en) | Document classification method, device, electronic equipment and medium | |
| CN114357005A (en) | Method and device for generating scientific information, terminal and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |