CN109670026B - Test data report generation method and report generation system - Google Patents
Test data report generation method and report generation system Download PDFInfo
- Publication number
- CN109670026B CN109670026B CN201811576607.9A CN201811576607A CN109670026B CN 109670026 B CN109670026 B CN 109670026B CN 201811576607 A CN201811576607 A CN 201811576607A CN 109670026 B CN109670026 B CN 109670026B
- Authority
- CN
- China
- Prior art keywords
- file
- test
- data source
- value
- test data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a test data report generation method, which comprises the following steps: preprocessing is carried out, a result file is created, a first data table page is created in the result file according to the data source label, a first waveform diagram and a second waveform diagram are constructed, a second data table page is created in the result file, and a third waveform diagram is constructed. The test data source file is loaded, the result file is created, test point information in the test data source file is written into the result file, a first oscillogram and a second oscillogram are constructed, then the second oscillogram is constructed, an analysis file is obtained, information can be extracted from a file name, a plurality of test data source files are processed, information can be automatically extracted from the test data source files, manual operation is not needed, and the working efficiency and the accuracy are greatly improved. The invention also provides a report generating system for realizing the test data report generating method.
Description
Technical Field
The present invention relates to the field of semiconductor technologies, and in particular, to a test data report generation method and a report generation system.
Background
In a semiconductor research and development stage, a product test engineer performs various batch tests on samples of the semiconductor test engineer to verify whether the samples meet industrial standards, such as test items of function verification, direct current characteristics and the like, and test data of the test items are scanned and output through test equipment, so that a large batch of test data can be generated in a test process, the engineer needs to analyze and extract results of the large batch of test data to analyze and extract the results to analyze and measure the yield of products and measure the performance of the products, the process is long in time consumption due to the large amount of test data, and once a new research and development product is provided, a large amount of test data needs to be analyzed from the beginning, and a large amount of time is wasted.
Chinese patent application publication No. CN105095165A discloses a test analysis report generation method and a test analysis report generation apparatus, in which test data is obtained, the test data is counted according to each statistical item in a test analysis report, the statistical results of each statistical item are correspondingly filled into the test analysis report, a test analysis report document is generated, and according to the test process data, extraction, induction and analysis are performed according to a uniform requirement and format, and the test analysis report document is automatically generated, so as to solve the problems of high compiling threshold, large workload, poor timeliness and low accuracy in the test analysis report formation process.
Therefore, there is a need to provide a new test data report generation method to solve the above-mentioned problems in the prior art.
Disclosure of Invention
The invention aims to provide a test data report generation method, which avoids the problem that a great deal of time is wasted due to the analysis of a large amount of test data by an engineer.
In order to achieve the above object, a test data report generating method according to the present invention includes the steps of:
s1: preprocessing is carried out, and a threshold value distinguishing file library is generated;
s2: loading a test data source file, and extracting a data source label from a document name of the test data source file;
s3: creating a result file, creating a first data table page in the result file according to the data source label, creating a matrix in the first data table page, and writing test point information in the test data source file into the matrix;
s4: comparing the measured value in the test point information with the threshold value in the threshold value discrimination file library to obtain a judgment result, and constructing a first oscillogram and a second oscillogram according to the judgment result;
s5: obtaining an extreme value and an average value of the measured values, constructing a first data table, carrying out classification judgment processing on the extreme value to obtain a classification result, and storing the classification result into a first new matrix and a second new matrix;
s6: and creating a second data table page in the result file, creating a second data table in the second data table page according to the extreme value, and constructing a third oscillogram according to the first new matrix and the second new matrix.
The invention has the beneficial effects that: by loading the test data source file, extracting the data source tag from the document name of the test data source file, creating the result file, writing test point information in the test data source file into the result file, comparing the measured value in the test point information with the threshold value, constructing a first waveform diagram and a second waveform diagram according to the judgment result, comparing the extreme value of the measured value with the threshold value, classifying the information of the test points, constructing a third waveform diagram according to the classified test point information so as to obtain an analysis file, extracting information from the document name of the test data source file, therefore, a plurality of test data source files can be processed simultaneously, information can be automatically extracted from the test data source files without manual operation, and the working efficiency and the accuracy are greatly improved.
Preferably, the pre-treatment comprises: and performing keyword training on the incremental documents to extract keywords, combining the keywords to obtain a threshold value discrimination label, and combining a threshold value with the threshold value discrimination label to obtain the threshold value discrimination file library.
Further preferably, the keyword training includes: establishing a first class set by using a test name, establishing a second class set by using a test condition, and judging whether the first class set and the second class set contain the keywords in the incremental documents or not;
if the first class set and the second class set do not contain the keywords, adding the keywords into the first class set and the second class set;
and traversing the keywords in the first class set and the second class set if the keywords are contained in the first class set and the second class set.
Further preferably, the incremental document is a document obtained by combining the keywords.
Preferably, the test point information includes a measurement value and test point position information.
Preferably, the data source tag includes a test name and a test condition.
Preferably, when the measured value is judged to be within the range of the limit value, the measured value is marked as a passing measured value, and the first oscillogram is created according to the test point information.
Preferably, when the measured value is judged to be outside the threshold value range, the measured value is marked as a failing measured value, and the second oscillogram is created according to the test point information.
Further preferably, the failing measurement is stored in an information array, and the position of the failing measurement in the second waveform map is marked.
Preferably, the classification determination process includes: and comparing the extreme value with the threshold value in the threshold value discrimination file library.
Further preferably, if the extreme value is determined to be within the range of the threshold value, the test point information is stored in the first new matrix.
Further preferably, if the extreme value is judged to be outside the range of the limit value, the test point information is stored in the second new matrix.
The invention also provides a report generating system, which comprises a threshold discrimination file library generating module, a data source file inputting module, a data source label extracting module, a result file creating module, a result file reading and writing module and a processing module, wherein the threshold discrimination file library generating module is used for generating the threshold discrimination file library, the data source file inputting module is used for receiving the test data source file, the data source label extracting module is used for extracting the data source label from the file name of the test data source file, the result file creating module is used for creating a result file, the result file reading and writing module is used for reading and writing information to the result file, and the processing module is used for processing the result file.
The report generating system of the invention has the advantages that: the threshold discrimination file library is obtained through the threshold discrimination file library generating module, the key words in the file name of the data source file are extracted through the data source label extracting module, after the result file creating module establishes the result file, the data in the data source file is processed through the processing module to obtain the test information integration table and the oscillogram, so that the analysis report of the test data is rapidly obtained, the time of artificial statistics is saved, and the efficiency and the accuracy are greatly improved.
Drawings
FIG. 1 is a flow chart of a test data report generation method of the present invention;
FIG. 2 is a block diagram of a report generation system according to the present invention;
FIG. 3 is a waveform of the fail measurement of the present invention;
FIG. 4 is a waveform of the passing measurement of the present invention;
fig. 5 is a final analysis waveform of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages 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 accompanying drawings 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. Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. As used herein, the word "comprising" and similar words are intended to mean that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items.
To solve the problems in the prior art, an embodiment of the present invention provides a test data report generating method, and referring to fig. 1, the test data report generating method includes:
s1: preprocessing is carried out, and a threshold value distinguishing file library is generated;
s2: loading a test data source file, and extracting a data source label from a document name of the test data source file;
s3: creating a result file, creating a first data table page in the result file according to the data source label, creating a matrix in the first data table page, and writing test point information in the test data source file into the matrix;
s4: comparing the measured value in the test point information with the threshold value in the threshold value discrimination file library to obtain a judgment result, and constructing a first oscillogram and a second oscillogram according to the judgment result;
s5: obtaining an extreme value and an average value of the measured values, constructing a first data table, carrying out classification judgment processing on the extreme value to obtain a classification result, and storing the classification result into a first new matrix and a second new matrix;
s6: and creating a second data table page in the result file, creating a second data table in the second data table page according to the extreme value, and constructing a third oscillogram according to the first new matrix and the second new matrix.
In some embodiments of the invention, the pre-processing comprises: and performing keyword training on the incremental documents to extract keywords, combining the keywords to obtain a threshold value discrimination label, and combining a threshold value with the threshold value discrimination label to obtain the threshold value discrimination file library.
In some embodiments of the invention, the keyword training comprises: establishing a first class set by using a test name, establishing a second class set by using a test condition, and judging whether the first class set and the second class set contain the keywords in the incremental documents or not;
if the first class set and the second class set do not contain the keywords, adding the keywords into the first class set and the second class set;
and traversing the keywords in the first class set and the second class set if the keywords are contained in the first class set and the second class set.
In some embodiments of the invention, the incremental document is a document obtained by combining the keywords.
In some embodiments of the present invention, the test point information includes measurement values and test point location information.
In some embodiments of the invention, the data source tag includes a test name and a test condition.
In some embodiments of the present invention, if it is determined that the measured value is within the threshold range, the measured value is marked as a passing measured value, and the first waveform diagram is created according to the test point information.
In some embodiments of the present invention, if it is determined that the measured value is outside the threshold range, the measured value is marked as a failing measured value, and the second waveform diagram is created according to the test point information.
In some embodiments of the present invention, the failing measurement is stored in an information array and the location of the failing measurement in the second waveform map is marked.
In some embodiments of the present invention, the classification determination process includes: and comparing the extreme value with the threshold value in the threshold value discrimination file library.
In some embodiments of the present invention, if the extreme value is determined to be within the range of the threshold value, the test point information is stored in the first new matrix.
In some embodiments of the present invention, if the extreme value is determined to be outside the threshold range, the test point information is stored in the second new matrix.
Fig. 2 is a block diagram of the report generation system according to some embodiments of the present invention. Referring to fig. 2, the report generating system includes a threshold discrimination file library generating module 1, a data source file recording module 2, a data source tag extracting module 3, a result file creating module 4, a result file reading and writing module 5, and a processing module 6, where the threshold discrimination file library generating module 1 is configured to generate the threshold discrimination file library, the data source file recording module 2 is configured to receive the test data source file, the data source tag extracting module 3 is configured to extract the data source tag from a document name of the test data source file, the result file creating module 4 is configured to create a result file, the result file reading and writing module 5 is configured to read and write information to the result file, and the processing module 6 is configured to process the result file.
In some embodiments of the present invention, the test point information carries the test condition of the test point information itself in the test data report generation process.
In some embodiments of the invention, the result file is an Excel file.
In some specific embodiments of the present invention, the keyword in the threshold value discrimination tag is a hot plug current value, the hot plug current value is the measured value, and the threshold value is smaller than 1mA, so that the hot plug current value is smaller than 1 mA.
In some embodiments of the invention, the document name of the test data source file is defined by a first keyword, a second keyword, a third keyword, a fourth keyword, a fifth keyword, and a sixth keyword.
In some embodiments of the present invention, the first keyword is a hot swap, the second keyword is a sample process, the third keyword is a chip number, the fourth keyword is a test temperature, the fifth keyword is a test voltage, the sixth keyword is a pin name, the hot swap is the test name, and the sample process, the chip number, the test temperature, the test voltage, and the pin name are test conditions.
In some embodiments of the present invention, the document name of the first set of test data source files is a hotspot _ Type1_ -50C _3.3V _ pin2.log, where the hotspot is the hot swap, the Type is the sample process, the 1 is the chip number, the-50C is the test temperature, the 3.3V is the test voltage, the pin2 is the pin name, and the log is a document format, and the log is not used as the keyword because the log is a document format.
In some embodiments of the present invention, the document name formats of the six test data source files, the second test data source file, the third test data source file, the fourth test data source file, the fifth test data source file and the sixth test data source file are the same as the document name format of the first test data source file, the data source file recording module 2 loads six groups of test data source files, the data source label extracting module 3 extracts the data source labels from the document names of the six groups of test data source files, taking a first group of the test data source files as an example, extracting document names of the first group of the test data source files, matching the document names with the keywords, and extracting Type, 1, -50C, 3.3V, pin2 and hotspot to obtain the data source tags;
the result file creating module 4 creates the result file, creates a hot plug table page according to a hotspot in the data source label, the hot plug table page is the first data table page, the result file read-write module 5 writes the test point information in six groups of test data source files into the hot plug table page, and stores the test point information into a matrix, the test point information has the hot plug current value and the test point position information, the processing module 6 compares the hot plug current value with a threshold value corresponding to the hot plug current value in the threshold value discrimination file library, determines whether the hot plug current value is less than 1mA, if the hot plug current value is less than 1mA, the hot plug current value is the passing measurement value, and constructs the passing measurement value waveform diagram according to the passing measurement value, the passing measurement value oscillogram is the first oscillogram, if the hot plug current value is larger than 1mA, the hot plug current value is the failing measurement value, a failing measurement value oscillogram is constructed according to the failing measurement value, the failing measurement value oscillogram is the second oscillogram, the test point information where the failing measurement value is located is stored in the information array, and the position corresponding to the failing measurement value in the failing measurement value oscillogram is marked.
The result file read-write module 5 reads six groups of hot plug current values and transmits the six groups of hot plug current values to the processing module 6, the processing module 6 obtains extreme values and average values of the six groups of hot plug current values in a matrix, then an extreme value table is constructed according to the hot plug current values, the extreme value table is the first data table, the processing module 6 judges whether the extreme values are smaller than 1mA, the result file read-write module 5 stores the test point information of which the extreme values are smaller than 1mA into the first new matrix of which the label is in a pass state, and the result file read-write module 5 stores the test point information of which the extreme values are larger than 1mA into the second new matrix of which the label is in a fail state;
the result file creating module 4 creates a summarized table page in the result file, where the summarized table page is the second data table page, the processing module 6 creates the test information integration table according to the hot plug current value, the test point position information, and the threshold value, where the test information integration table is the second data table, and marks the test point information with a pass and a fail in the test information integration table, and then creates the final analysis waveform map according to the hot plug current value and the test point position information in the first new matrix and the second new matrix, where the final analysis waveform map is the third waveform map.
FIG. 3 is a waveform diagram of a fail measurement in some embodiments of the invention. Referring to fig. 3, the test point information is created according to the first group of test data source files, the third test data source files, and the fifth test data source files, and the test point information has three waveform lines, the ordinate is the hot plug current value, the unit is mA (milliampere), the abscissa is the test point position information, and 15 test point position information in total, three hot plug current values at the 12 th test point position information are all greater than 1mA, are the failing measurement value, and the hot plug current values at the remaining 14 test points are all less than 1mA, and are the passing measurement value.
FIG. 4 is a waveform diagram of a passing measurement in some embodiments of the invention. Referring to fig. 4, the test point information of the second group of test data source files, the fourth group of test data source files, and the sixth group of test data source files is created, and the test point information has three wavy lines, where the ordinate is the hot plug current value, the unit is mA, the abscissa is the test point position information, and the total 15 test point position information, and the passing measurement value is when the hot plug current values of the 15 test points are all less than 1 mA.
FIG. 5 is a waveform diagram of the final analysis of the test data source file in some embodiments of the invention. Fig. 5 is created from the test point information of the six sets of test data source files, and thus fig. 5 has all waveform lines in fig. 3 and 4.
In some embodiments of the present invention, the data table of the matrix is shown in table 1, where the first column is test points 1 to 15, the second column is a first set of hot plug current values, the third column is a second set of hot plug current values, the fourth column is a third set of hot plug current values, the fifth column is a fourth set of hot plug current values, the sixth column is a fifth set of hot plug current values, the seventh column is a sixth set of hot plug current values, row 17 is the maximum current value of each set of hot plug current values, row 18 is the minimum current value of each set of hot plug current values, row 19 is the average value of each set of hot plug current values, the maximum current values of the second group of hot plug current values, the fourth group of hot plug current values and the sixth group of hot plug current values are larger than 1mA, and the maximum current values of the first group of hot plug current values, the third group of hot plug current values and the fifth group of hot plug current values are smaller than 1 mA.
TABLE 1
In some embodiments of the invention, the test information integration table is shown in table 2, where the first column in the table is a test file name, the test file name has a first group of test data source files, a second group of test data source files, a third group of test data source files, a fourth group of test data source files, a fifth group of test data source files and a sixth group of test data source files, the second column is a limit value, the limit values are all 1mA, the third column is a maximum current value, the fourth column is a test result, the maximum current value of the first group of test data source files is 0.240mA, since 0.240mA is less than 1mA, the test result is marked as pass, the maximum current value of the second group of test data source files is 1.047mA, since 1.047mA is greater than 1mA, the test result is marked as fail, the maximum current value of the third group of test data source files is 0.245mA, since 0.245mA is less than 1mA, the test, the maximum current value of the fourth group of test data source files is 1.274mA, the test result is marked as failing due to the fact that 1.274mA is larger than 1mA, the maximum current value of the fifth group of test data source files is 0.266mA, the test result is marked as passing due to the fact that 0.266mA is smaller than 1mA, the maximum current value of the sixth group of test data source files is 1.052mA, and the test result is marked as failing due to the fact that 1.052mA is larger than 1 mA.
TABLE 2
Although the embodiments of the present invention have been described in detail hereinabove, it is apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it is to be understood that such modifications and variations are within the scope and spirit of the present invention as set forth in the following claims. Moreover, the invention as described herein is capable of other embodiments and of being practiced or of being carried out in various ways.
Claims (10)
1. A method for generating a test data report, comprising the steps of:
s1: performing keyword training on the incremental documents to extract keywords, combining the keywords to obtain a threshold value discrimination label, and combining a threshold value with the threshold value discrimination label to generate a threshold value discrimination file library;
s2: loading a test data source file, and extracting a data source label from a document name of the test data source file, wherein the data source label comprises a test name and a test condition, and the test data source file is in a log format;
s3: creating a result file, creating a first data table page in the result file according to the data source label, creating a matrix in the first data table page, and writing test point information in the test data source file into the matrix;
s4: comparing the measured value in the test point information with the threshold value in the threshold value discrimination file library to obtain a judgment result, and constructing a first oscillogram and a second oscillogram according to the judgment result;
s5: obtaining an extreme value and an average value of the measured values, constructing a first data table, comparing the extreme value with the threshold value in the threshold value discrimination file library to obtain a classification result, and storing the classification result in a first new matrix and a second new matrix;
s6: and creating a second data table page in the result file, creating a second data table in the second data table page according to the extreme value, and constructing a third oscillogram according to the first new matrix and the second new matrix.
2. The method of claim 1, wherein the keyword training comprises:
establishing a first class set by using a test name, establishing a second class set by using a test condition, and judging whether the first class set and the second class set contain the keywords in the incremental documents or not;
if the first class set and the second class set do not contain the keywords, adding the keywords into the first class set and the second class set;
and traversing the keywords in the first class set and the second class set if the keywords are contained in the first class set and the second class set.
3. The method of claim 1, wherein the incremental documents are obtained by combining the keywords.
4. The method of claim 1, wherein the site information comprises measurement values and site location information.
5. The method of claim 1, wherein if the measurement value is determined to be within the threshold range, the measurement value is marked as a passing measurement value, and the first waveform diagram is created according to the test point information.
6. The method of claim 1, wherein if the measurement value is determined to be outside the threshold range, the measurement value is marked as a failed measurement value, and the second waveform diagram is created according to the test point information.
7. The method of claim 6, wherein the failing measurement is stored in an information array and the position of the failing measurement in the second waveform map is marked.
8. The method of claim 1, wherein if the extreme value is determined to be within the threshold range, the test point information is stored in the first new matrix.
9. The method of claim 1, wherein if the extreme value is determined to be outside the threshold range, the test point information is stored in the second new matrix.
10. A report generating system, characterized in that the report generating system is used for implementing the test data report generating method according to any one of claims 1 to 9, the report generating system comprises a threshold discrimination file library generating module, a data source file entry module, a data source tag extracting module, a result file creating module, a result file reading and writing module and a processing module, the threshold discrimination file library generating module is used for generating the threshold discrimination file library, the data source file entry module is used for receiving the test data source file, the data source tag extracting module is used for extracting the data source tag from the file name of the test data source file, the result file creating module is used for creating a result file, the result file reading and writing module is used for reading and writing information to the result file, the processing module is used for processing the result file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576607.9A CN109670026B (en) | 2018-12-23 | 2018-12-23 | Test data report generation method and report generation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576607.9A CN109670026B (en) | 2018-12-23 | 2018-12-23 | Test data report generation method and report generation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670026A CN109670026A (en) | 2019-04-23 |
| CN109670026B true CN109670026B (en) | 2021-06-18 |
Family
ID=66146001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811576607.9A Active CN109670026B (en) | 2018-12-23 | 2018-12-23 | Test data report generation method and report generation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670026B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112799672A (en) * | 2020-12-31 | 2021-05-14 | 杭州广立微电子股份有限公司 | Test data processing method based on keywords |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1245696C (en) * | 2003-06-13 | 2006-03-15 | 北京大学计算机科学技术研究所 | Text classification incremental training learning method supporting vector machine by compromising key words |
| TW200540610A (en) * | 2004-06-04 | 2005-12-16 | Hon Hai Prec Ind Co Ltd | System and method for automatically comparing test points of two different boards |
| CN102331983A (en) * | 2010-07-15 | 2012-01-25 | 鸿富锦精密工业（深圳）有限公司 | Test report generation system and method |
| TW201241780A (en) * | 2011-04-06 | 2012-10-16 | Hon Hai Prec Ind Co Ltd | System and method for optimizing the test data reports |
| CN102737031A (en) * | 2011-04-06 | 2012-10-17 | 鸿富锦精密工业（深圳）有限公司 | Test data report arranging system and method |
| CN105975452B (en) * | 2016-05-12 | 2019-02-05 | 中国电子科技集团公司第四十一研究所 | Testing journal sheet's integration method and system based on Map Profile and indicator template |
-
2018
- 2018-12-23 CN CN201811576607.9A patent/CN109670026B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109670026A (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9690788B2 (en) | File type recognition analysis method and system | |
| CN110457302B (en) | Intelligent structured data cleaning method | |
| KR101983538B1 (en) | Systems and methods for calculating category proportions | |
| CN110704633A (en) | Named entity recognition method and device, computer equipment and storage medium | |
| CN106294222A (en) | A kind of method and device determining PCIE device and slot corresponding relation | |
| CN104750852A (en) | Method for finding and classifying Chinese address data | |
| CN104731977A (en) | Phone number data search and classification method | |
| CN105630656A (en) | Log model based system robustness analysis method and apparatus | |
| CN113836038A (en) | Test data construction method, device, equipment and storage medium | |
| CN109670026B (en) | Test data report generation method and report generation system | |
| CN111815162A (en) | Digital auditing tool and method | |
| CN102902984B (en) | Remote-sensing image semi-supervised projection dimension reducing method based on local consistency | |
| CN110399432A (en) | A kind of classification method of table, device, computer equipment and storage medium | |
| CN109604191A (en) | Semiconductor device sorting system and semiconductor device | |
| PODANI | SYN-TAX II. Computer programs for data analysis in ecology and systematics | |
| CN110927587B (en) | Method and device for generating battery pack charge and discharge test report | |
| CN112464660A (en) | Text classification model construction method and text data processing method | |
| CN114021716A (en) | Model training method and system and electronic equipment | |
| CN102955761A (en) | Size information output system and size information output method | |
| CN112463791A (en) | Nuclear power station document data acquisition method and device, computer equipment and storage medium | |
| CN104731978A (en) | Chinese name data discovering and classifying method | |
| Li et al. | Multi-label classification based on association rules with application to scene classification | |
| CN107741956A (en) | A kind of blog search method based on web container configuration file | |
| Kerwat et al. | Detecting knowledge artifacts in scientific document images-comparing deep learning architectures | |
| CN115017872B (en) | Method and device for intelligently labeling table in PDF file and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 200434 Room 202, building 5, No. 500, Memorial Road, Hongkou District, Shanghai Applicant after: Shanghai Anlu Information Technology Co.,Ltd. Address before: Room 501-504, building 9, Pudong Software Park, 498 GuoShouJing Road, Pudong New Area, Shanghai 200082 Applicant before: SHANGHAI ANLOGIC INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |