CN111291167B - Automatic product paper specification checking method based on image recognition - Google Patents
Automatic product paper specification checking method based on image recognition Download PDFInfo
- Publication number
- CN111291167B CN111291167B CN201811490816.1A CN201811490816A CN111291167B CN 111291167 B CN111291167 B CN 111291167B CN 201811490816 A CN201811490816 A CN 201811490816A CN 111291167 B CN111291167 B CN 111291167B
- Authority
- CN
- China
- Prior art keywords
- product
- checking
- database
- electronic version
- rule
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an automatic checking method of a product paper specification based on image recognition, which comprises the steps of establishing a product checking rule sub-database for different products and a product checking rule database corresponding to a product checking keyword library in advance, scanning the product paper specification to obtain a product electronic version specification, and then after judging the type of the product corresponding to the product electronic version specification, respectively matching and judging the characters and the graphic contents in the product electronic version specification with the product checking rule sub-database existing in the product checking rule database to obtain corresponding checking similarity, and outputting a qualified report that the product paper specification accords with the product checking rule when all the contents of the product electronic version specification exceed a preset similarity threshold, so that the automatic checking of the product paper specification and the corresponding product checking rule can be completed only by using a machine without manual participation judgment, and the checking efficiency is effectively improved.
Description
Technical Field
The invention relates to the field of image recognition, in particular to an automatic checking method for a paper specification of a product based on image recognition.
Background
In real life, a product manufacturer will equip the product it produces with a matching paper instruction to explain the basic condition of the product and how to operate the product. Some manufacturers also provide a service for downloading and browsing the electronic version of the product specifications through the official website, but most manufacturers prefer to deliver the required product paper specifications along with the product according to the corresponding standard requirements, and the users browse the content of the product paper specifications by themselves.
When the printed paper specification of the product is matched with a corresponding product, a product manufacturer can manually and carefully check the content (including characters and diagrams) on the paper specification of the product with the corresponding safety regulation standard regulations of the product in advance so as to check whether the paper specification of the product meets the safety regulation standard regulation requirements, namely whether the paper specification of the product is qualified, and ensure that the paper specification delivered with the product is qualified.
However, since the product manufacturer typically mass-produces the product, the number of paper instructions for the product that need to be checked manually, as well as the time and labor that need to be spent, are enormous. Thus, it has been difficult to meet the inspection requirements of product manufacturers for paper specifications of a batch of products using manual inspection of the paper specifications of the products.
Disclosure of Invention
The invention aims to solve the technical problem of providing an automatic checking method for paper specifications of products based on image recognition aiming at the prior art. The automatic checking method for the product paper specifications based on image recognition can automatically, quickly and accurately finish checking the product paper specifications under the condition of almost no manual participation so as to give out checking results of whether the product paper specifications are qualified or not.
The technical scheme adopted for solving the technical problems is as follows: the automatic checking method for the paper specifications of the product based on image recognition is characterized by comprising the following steps of:
step 1, a product checking rule database is established; the product checking rule database comprises a product checking rule sub database and a corresponding product checking keyword library, wherein the product checking rule sub database is respectively aimed at different products; the product checking rule sub-database is internally provided with rule texts corresponding to the product condition description; the checking keyword library comprises a pure text part, a graphic part and the same semantic part formed by text;
step 2, electronic scanning treatment is carried out on the paper specification of the product to be checked and the cover of the paper specification of the product to be checked, so that the electronic version specification of the product corresponding to the paper specification of the product and the type of the product corresponding to the paper specification of the product are obtained;
step 3, when judging that the product type of the product corresponding to the obtained paper specification of the product is consistent with the product type corresponding to any product checking rule sub-database in the product checking rule database, turning to step 4; otherwise, a prompt that the product checking rule sub-database is not established is sent out;
step 4, selecting a product checking rule sub-database corresponding to the product type of the product corresponding to the product paper specification from the product checking rule database, and selecting a product checking keyword library corresponding to the product checking rule sub-database from the product checking rule database to obtain a plain text part contained in the product checking keyword library;
step 5, matching the sentence content of the product electronic version instruction with the pure text part contained in the product checking keyword library in the step 4 to obtain all sentence originals which are positioned in the product electronic version instruction and contain the pure text part of the product checking keyword library;
step 6, comparing and judging all sentence texts obtained in the step 5 with the rule texts in the product checking bar example database in the step 4 to obtain checking similarity aiming at the product electronic version instruction, and judging that the product electronic version instruction accords with the rule in the product checking bar example database in the step 4 when the obtained checking similarity is larger than a preset similarity threshold; otherwise, go to step 7; the similarity of the electronic version specifications of the product is the ratio between the number of words in the sentence texts which are the same as the rule texts in the product checking rule sub-database and the number of words in the rule texts;
and 7, carrying out image recognition processing on the content of the product electronic version instruction and the graphic part contained in the product checking keyword library in the step 4 to judge whether the product electronic version instruction has the graphic part which is the same as the product checking keyword library: when the product electronic version instruction has the same graphic as the graphic part in the product checking keyword library in the step 4, judging that the product electronic version instruction accords with regulations in the product checking item example database in the step 4; otherwise, go to step 8;
step 8, matching the content of the product electronic version instruction with the same semantic parts contained in the product checking keyword library in step 5 to judge whether the product electronic version instruction has sentences with the same semantic parts as the product checking keyword library or not: when the product electronic version instruction has sentences with the same semantic parts as those in the product checking keyword library, judging that the product electronic version instruction accords with regulations in the product checking item example database in the step 4; otherwise, judging that the electronic version specification of the product does not accord with the regulations in the current product checking regulation sub-database;
step 9, outputting a qualified report of the paper specification of the product when the electronic version specification of the product is in compliance with the regulations in the judgment results of the pure text part, the graphic part and the same semantic part in the corresponding product check bar example database respectively; otherwise, outputting a failure report of the paper specification of the product, and listing the part of the paper specification of the product, which is different from the regulations in the product check bar example database in the step 4, in the failure report.
Optionally, in the automatic checking method for paper specifications of products based on image recognition, the graphic part of the checking keyword library contains any combination of five keywords including size, length, width, height and thickness.
In an improvement, the automatic checking method for the paper specifications of the product based on image recognition further comprises the following steps: and according to the unqualified report content of the paper specification of the product, manually modifying the product check list example database and the corresponding product check keyword library by using a computer.
Optionally, in the automatic checking method of the paper specification of the product based on image recognition, the electronic version specification of the product is in a PDF format or a WORD format.
Further, in the automatic checking method of the paper specification of the product based on image recognition, the preset similarity threshold is 85%.
Compared with the prior art, the invention has the advantages that: according to the automatic checking method for the product paper specifications, after the product checking rule sub-databases comprising the product checking rule sub-databases aiming at different products and the corresponding product checking keyword library are established in advance, the product paper specifications are scanned to obtain the product electronic version specifications, then after the types of the products corresponding to the product electronic version specifications are judged, the characters and the graphic contents in the product electronic version specifications are respectively matched and judged with the product checking rule sub-databases existing in the product checking rule sub-databases, so that the corresponding checking similarity is obtained, and when all the contents of the product electronic version specifications are judged to exceed the preset similarity threshold, the qualified report that the product paper specifications corresponding to the product electronic version specifications accord with the product checking rule is output, so that the automatic checking of the product paper specifications and the corresponding product checking rule is realized without manual participation judgment, and the automatic checking efficiency is effectively improved by using a machine.
Drawings
Fig. 1 is a schematic flow chart of an automatic checking method for a paper specification of a product based on image recognition in an embodiment of the invention.
Detailed Description
The invention is described in further detail below with reference to the embodiments of the drawings.
Referring to fig. 1, the embodiment provides an automatic checking method for a paper specification of a product based on image recognition, which includes the following steps:
step 1, a product checking rule database is established; the product checking rule database comprises a product checking rule sub-database and a corresponding product checking keyword library, wherein the product checking rule sub-database and the corresponding product checking keyword library are respectively aimed at different products; the product check bar example database is internally provided with a rule original text corresponding to the product condition description; the checking keyword library comprises a pure text part, a graphic part and the same semantic part formed by text;
for example, the statement for the plain text portion may be "steam cleaner must not be used when cleaning an appliance"; the product checking keyword library comprises keywords of cleaning and a keyword cleaner; the keywords of the product checking keyword library can be divided into two parts of contents, wherein one part is the text part of the common verb and the other part is the text part of the common noun; the pictorial portion of the search keyword library contains any combination of five keywords, namely size, length, width, height and thickness
The same semantic part is a synonym representing other same meanings for a word, and the part mainly establishes an equivalent relation among sentences added with the same semantic part; for example, when the check rule is executed using the same semantic part, the check of the same semantic sentence is executed at the same time. Specifically, if the checking rule is executed, the checking is executed simultaneously with the checking that the electric oven is required to be confirmed to be installed in the cabinet before the electric oven is used; the same semantic part that the electric oven can be used only after the electric oven is installed in the cabinet is confirmed to be installed in the cabinet before the electric oven is used;
step 2, electronic scanning treatment is carried out on the paper specification of the product to be checked and the cover of the paper specification of the product to be checked, so that the electronic version specification of the product corresponding to the paper specification of the product and the type of the product corresponding to the paper specification of the product are obtained; the product electronic version instruction can select PDF format or WORD format; in this embodiment, the electronic version specification of the product adopts PDF format;
step 3, when judging that the product type of the product corresponding to the obtained paper specification of the product is consistent with the product type corresponding to any product checking rule sub-database in the product checking rule database, turning to step 4; otherwise, a prompt that the product checking rule sub-database is not established is sent out;
for example, if the product checking rule database established in the early stage comprises a refrigerator checking rule example database, an air conditioner checking rule sub-database, a range hood checking rule example database and a steam box checking rule sub-database, correspondingly, the product checking rule database established in the early stage also comprises a refrigerator checking keyword library, an air conditioner checking keyword library, a range hood checking keyword library and a steam box checking keyword library;
when the paper instruction book of the product to be checked is a steam box instruction book, usually, name information about the corresponding product exists on the cover of the paper instruction book of the product, if the cover information of the scanned electronic version instruction book is subjected to text recognition processing, the product type of the product corresponding to the paper instruction book of the product is recognized and judged to be the steam box, and the product type is consistent with the product type corresponding to the steam box check bar example database in the product check rule database, and then the step 4 is carried out; of course, if the product checking rule database established in advance is not provided with the steam box checking rule example database, a prompt that the steam box checking rule sub-database is not established is sent;
step 4, selecting a product checking rule sub-database corresponding to the product type of the product corresponding to the product paper specification from the product checking rule database, and selecting a product checking keyword library corresponding to the product checking rule sub-database from the product checking rule database to obtain a plain text part contained in the product checking keyword library;
because the product checking rule database established in the earlier stage already contains the steam box checking keyword library, after executing the step 4, the steam box checking rule example database is firstly selected from the product checking rule database through a machine, then the corresponding steam box checking keyword library is also selected, and the pure text part contained in the steam box checking keyword library is obtained; that is, even if the product checking rule database actually contains a plain text portion (usually, a sentence of product introductory or/and a sentence related to operation description), a graphic digit (usually, a graphic and a reference numeral) and the same semantic portion, this step 4 is only responsible for acquiring the plain text portion in the steam box checking keyword library; wherein, supposing that the steam box checks that the keyword library has regulations in the form of pure words, the appliance heats during use, and care is taken to avoid contacting heating elements in the oven; correspondingly, the steam box is provided with three high-frequency keywords of an appliance, heating and contact in a keyword library;
step 5, matching the sentence content of the product electronic version instruction with the pure text part contained in the product checking keyword library in the step 4 to obtain all sentence originals which are positioned in the product electronic version instruction and contain the pure text part of the product checking keyword library; wherein, the matching process refers to the word recognition process for the sentence content and the pure word part;
for example, for the steam box, the sentence content of the electronic version specification of the steam box is matched with three key words of "appliance", "heating" and "contact" in the steam box checking key word library, for example, all words containing the same three words can be found out in turnSentence, sentence containing two of the words, sentence containing one of the words; it is assumed that all sentence texts which are positioned in the electronic version specification of the steam box and contain any key word are only' found "The appliance is in useTime of dayCan give out Heat of the body，Care is taken to avoid contactApplianceInternal heating element"(italics are keywords, underlined words are the same words) and"The appliance is in useTime of dayWill generate heat，PleaseLet children keep away "(italic words are keywords, underlined words are the same words);
step 6, comparing and judging all sentence texts obtained in the step 5 with the rule texts in the product checking bar example database in the step 4 to obtain checking similarity aiming at the product electronic version instruction, and judging that the product electronic version instruction accords with the rule in the product checking bar example database in the step 4 when the obtained checking similarity is larger than a preset similarity threshold; otherwise, go to step 7; the similarity of the electronic version specifications of the product is the ratio between the number of words in the sentence texts which are the same as the rule texts in the product checking rule sub-database and the number of words in the rule texts;
still illustrated by way of example in step 5, for "The appliance is in useTime of dayWill generate heat，Care is taken to avoid contactApplianceInner part Is a heating element of (a)The sentence original text is calculated, the sentence original text and an article of regulations in a product checking regulation sub-database generate heat during use, the number of words which are the same as the number of words which are used for avoiding contacting heating elements in an oven is 22, the article of regulations generates heat during use, the number of words which are used for avoiding contacting the heating elements in the oven is 25, and then the similarity of the corresponding electronic version specifications of the product is 22/25=88%; if the preset similarity threshold is 85%, the similarity 88% of the electronic version specification of the product is larger than the preset similarity threshold by 85%, and then the sentence original text of the paper specification of the steam box product is considered to accord with regulations in a steam box inspection regulation sub-database;
of course, for "The appliance is in useTime of dayWill generate heat，PleaseThe children are far away from the sentence original text, and the same calculation method is still adopted, so that the similarity of the corresponding electronic version instruction of the product is 36 percent, and the obtained similarity is 36 percent<Presetting a similarity threshold value of 85%, and judging that the sentence original text of the paper specification of the steam box product does not accord with regulations in the steam box check list example database; because in the two sentence texts, one sentence text accords with regulations in the steam box checking regulation sub-database, the paper specification of the steam box product is judged to finally accord with regulations in the steam box checking regulation sub-database;
and 7, carrying out image recognition processing on the content of the product electronic version instruction and the graphic part contained in the product checking keyword library in the step 4 to judge whether the product electronic version instruction has the same graphic part as the product checking keyword library: when the product electronic version instruction has the same graphic as the graphic part in the product checking keyword library in the step 4, judging that the product electronic version instruction accords with regulations in the product checking item example database in the step 4; otherwise, go to step 8;
by adopting the mature image recognition technology, when the product electronic version instruction book and the product checking keyword library have similar diagrams or the same diagrams, the checking similarity corresponding to the product electronic version instruction book is judged to be 100%, the checking similarity is 100% and is greater than a preset similarity threshold value of 85%, and under the condition, the product electronic version instruction book is judged to accord with regulations in the product checking bar example database in the step 4;
step 8, matching the content of the product electronic version instruction with the same semantic parts contained in the product checking keyword library in the step 5 to judge whether sentences with the same semantic parts in the product checking keyword library exist in the product electronic version instruction or not: when the electronic version instruction of the product has sentences with the same semantic parts as those in the product checking keyword library, judging that the electronic version instruction of the product accords with regulations in the product checking item example database in the step 4; otherwise, judging that the electronic version specification of the product does not accord with the regulations in the current product checking regulation sub-database; wherein, the matching processing is that the pointer carries out word recognition processing on the content of the electronic version instruction of the product and the same semantic part of the product checking keyword library;
still assume that the same semantic part in the steam box product electronic version instruction in the steam box inspection rule database has the statement that if a power cord is damaged, in order to avoid danger, the statement must be replaced by a professional in a manufacturer, a maintenance part or the like, if the steam box product electronic version instruction is compared, the statement that if the power cord is damaged, a professional should make a visit to replace the statement with the same voice after the power cord is damaged, if the statement is judged that the inspection similarity of the statement of the same semantic part in the steam box product electronic version instruction in the steam box inspection rule example database is greater than the preset similarity threshold value of 85%, and in this case, the statement of the steam box product electronic version is judged to be in line with the rule in the product inspection rule example database in step 4;
step 9, outputting a qualified report of the paper specification of the product when the electronic version specification of the product is in compliance with the regulations respectively with the judging results of the pure text part, the graphic part and the same semantic part in the corresponding product check bar example database; otherwise, outputting a paper specification reject report of the product, and listing the part of the paper specification of the product, which is different from the regulations in the product check list example database in the step 4, in the reject report.
That is, for the electronic version of the steam box instruction, if the judging results of the pure text part, the graphic part and the same semantic part in the steam box check bar example database established in the earlier stage are all in conformity with regulations, outputting a qualified report of the steam box paper instruction; otherwise, outputting a report of disqualification of the steam box paper specification, and listing the steam box specification in a part which is different from the steam box checking rule sub-database (comprising a pure text part, a diagram part and the same semantic part) for management personnel to process.
Of course, in order to improve the automatic checking accuracy of the paper specifications of the products, the database of each product checking item example and the corresponding product checking keyword library can be modified by a computer manually according to the unqualified report content of the paper specifications of the products.
Claims (5)
1. The automatic checking method for the paper specifications of the product based on image recognition is characterized by comprising the following steps of:
step 1, a product checking rule database is established; the product checking rule database comprises a product checking rule sub database and a corresponding product checking keyword library, wherein the product checking rule sub database is respectively aimed at different products; the product checking rule sub-database is internally provided with rule texts corresponding to the product condition description; the checking keyword library comprises a pure text part, a graphic part and the same semantic part formed by text;
step 2, electronic scanning treatment is carried out on the paper specification of the product to be checked and the cover of the paper specification of the product to be checked, so that the electronic version specification of the product corresponding to the paper specification of the product and the type of the product corresponding to the paper specification of the product are obtained;
step 3, when judging that the product type of the product corresponding to the obtained paper specification of the product is consistent with the product type corresponding to any product checking rule sub-database in the product checking rule database, turning to step 4; otherwise, a prompt that the product checking rule sub-database is not established is sent out;
step 4, selecting a product checking rule sub-database corresponding to the product type of the product corresponding to the product paper specification from the product checking rule database, and selecting a product checking keyword library corresponding to the product checking rule sub-database from the product checking rule database to obtain a plain text part contained in the product checking keyword library;
step 5, matching the sentence content of the product electronic version instruction with the pure text part contained in the product checking keyword library in the step 4 to obtain all sentence originals which are positioned in the product electronic version instruction and contain the pure text part of the product checking keyword library;
step 6, comparing and judging all sentence texts obtained in the step 5 with the rule texts in the product checking bar example database in the step 4 to obtain checking similarity aiming at the product electronic version instruction, and judging that the product electronic version instruction accords with the rule in the product checking bar example database in the step 4 when the obtained checking similarity is larger than a preset similarity threshold; otherwise, go to step 7; the similarity of the electronic version specifications of the product is the ratio between the number of words in the sentence texts which are the same as the rule texts in the product checking rule sub-database and the number of words in the rule texts;
and 7, carrying out image recognition processing on the content of the product electronic version instruction and the graphic part contained in the product checking keyword library in the step 4 to judge whether the product electronic version instruction has the graphic part which is the same as the product checking keyword library: when the product electronic version instruction has the same graphic as the graphic part in the product checking keyword library in the step 4, judging that the product electronic version instruction accords with regulations in the product checking item example database in the step 4; otherwise, go to step 8;
step 8, matching the content of the product electronic version instruction with the same semantic parts contained in the product checking keyword library in step 5 to judge whether the product electronic version instruction has sentences with the same semantic parts as the product checking keyword library or not: when the product electronic version instruction has sentences with the same semantic parts as those in the product checking keyword library, judging that the product electronic version instruction accords with regulations in the product checking item example database in the step 4; otherwise, judging that the electronic version specification of the product does not accord with the regulations in the current product checking regulation sub-database;
step 9, outputting a qualified report of the paper specification of the product when the electronic version specification of the product is in compliance with the regulations in the judgment results of the pure text part, the graphic part and the same semantic part in the corresponding product check bar example database respectively; otherwise, outputting a failure report of the paper specification of the product, and listing the part of the paper specification of the product, which is different from the regulations in the product check bar example database in the step 4, in the failure report.
2. The method for automatically checking paper specifications of a product based on image recognition according to claim 1, wherein the graphic part of the checking keyword library contains any combination of five keywords of size, length, width, height and thickness.
3. The automatic checking method for paper specifications of products based on image recognition according to claim 1, further comprising: and according to the unqualified report content of the paper specification of the product, manually modifying the product check list example database and the corresponding product check keyword library by using a computer.
4. The automatic checking method for paper specifications of products based on image recognition according to claim 1, wherein the electronic version specifications of the products are in PDF format or WORD format.
5. The automatic inspection method for paper specifications of products based on image recognition according to any one of claims 1 to 4, wherein the preset similarity threshold is 85%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811490816.1A CN111291167B (en) | 2018-12-07 | 2018-12-07 | Automatic product paper specification checking method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811490816.1A CN111291167B (en) | 2018-12-07 | 2018-12-07 | Automatic product paper specification checking method based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291167A CN111291167A (en) | 2020-06-16 |
| CN111291167B true CN111291167B (en) | 2023-05-05 |
Family
ID=71029763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811490816.1A Active CN111291167B (en) | 2018-12-07 | 2018-12-07 | Automatic product paper specification checking method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291167B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001159939A (en) * | 1999-12-02 | 2001-06-12 | Seiko Epson Corp | Device controller, method for displaying user interface and storage medium recording computer program for displaying user interface |
| CN101297318A (en) * | 2005-08-23 | 2008-10-29 | 株式会社理光 | Data organization and access for mixed media document system |
| CN106066848A (en) * | 2016-05-24 | 2016-11-02 | 辽宁蓝卡医疗投资管理有限公司 | Data processing method, apparatus and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8463794B2 (en) * | 2008-10-02 | 2013-06-11 | International Business Machines Corporation | Computer system, method, and computer program for extracting terms from document data including text segment |
-
2018
- 2018-12-07 CN CN201811490816.1A patent/CN111291167B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001159939A (en) * | 1999-12-02 | 2001-06-12 | Seiko Epson Corp | Device controller, method for displaying user interface and storage medium recording computer program for displaying user interface |
| CN101297318A (en) * | 2005-08-23 | 2008-10-29 | 株式会社理光 | Data organization and access for mixed media document system |
| CN106066848A (en) * | 2016-05-24 | 2016-11-02 | 辽宁蓝卡医疗投资管理有限公司 | Data processing method, apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291167A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896212B2 (en) | System and methods for automating trademark and service mark searches | |
| US10565533B2 (en) | Systems and methods for similarity and context measures for trademark and service mark analysis and repository searches | |
| US5182708A (en) | Method and apparatus for classifying text | |
| CN111310440B (en) | Text error correction method, device and system | |
| US8666982B2 (en) | Method and system to augment vehicle domain ontologies for vehicle diagnosis | |
| EP2711849A2 (en) | Learning opinion-related patterns for contextual and domain-dependent opinion detection | |
| WO2001096980A2 (en) | Method and system for text analysis | |
| US11537795B2 (en) | Document processing device, document processing method, and document processing program | |
| US10740406B2 (en) | Matching of an input document to documents in a document collection | |
| US11966444B2 (en) | Document analysis method and apparatus | |
| Seljan et al. | From digitisation process to terminological digital resources | |
| CN111291167B (en) | Automatic product paper specification checking method based on image recognition | |
| Alhafni et al. | Personalized Text Generation with Fine-Grained Linguistic Control | |
| CN110543546B (en) | Method and device for inquiring hidden danger problems in industrial equipment | |
| CN112148837A (en) | Maintenance scheme acquisition method, device, equipment and storage medium | |
| Naemi et al. | Informal-to-formal word conversion for persian language using natural language processing techniques | |
| CN112395889A (en) | Machine-synchronized translation | |
| Shanahan et al. | Mining multilingual opinions through classification and translation | |
| CN115587599B (en) | Quality detection method and device for machine translation corpus | |
| CN114064895B (en) | Method, device, equipment and medium for discovering new suggestions of user in real time | |
| CN117787800B (en) | Authentication management system based on engineering construction | |
| CN113609296B (en) | Data processing method and device for public opinion data identification | |
| CN112150251B (en) | Article name management method and device | |
| Amato et al. | Statistical and lexical analysis for semi-automatic extraction of relevant information from legal documents | |
| Otero | Extraction of translation equivalents from parallel corpora using sense-sensitive contexts |
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 |