CN110689019A - OCR recognition model determining method and device - Google Patents
OCR recognition model determining method and device Download PDFInfo
- Publication number
- CN110689019A CN110689019A CN201910921358.0A CN201910921358A CN110689019A CN 110689019 A CN110689019 A CN 110689019A CN 201910921358 A CN201910921358 A CN 201910921358A CN 110689019 A CN110689019 A CN 110689019A
- Authority
- CN
- China
- Prior art keywords
- conformity
- ocr recognition
- recognition model
- analyzed
- determining
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Character Discrimination (AREA)
Abstract
The invention provides a method and a device for determining an OCR recognition model, wherein the method comprises the following steps: acquiring parameter data of a plurality of OCR recognition models to be analyzed and equipment; determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment; determining the weight corresponding to the conformity index value; for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model; and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed. The method can determine the OCR recognition model meeting the parameter data of the equipment from the plurality of OCR recognition models, and has high accuracy.
Description
Technical Field
The invention relates to the field of Internet OCR recognition, in particular to a method and a device for determining an OCR recognition model.
Background
OCR (Optical Character Recognition) refers to a process of inspecting a Character printed on paper for an electronic device (e.g., a scanner or a digital camera), determining its shape by detecting dark and light patterns, and then translating the shape into a computer text by a Character Recognition method.
At present, there are a plurality of OCR recognition models, and different OCR recognition models have respective characteristics, for example, some OCR recognition models have good recognition effect but need to be operated on high-performance equipment; some OCR recognition models have low requirements on the operating environment of equipment, but have poor recognition effect. How to select a proper OCR recognition model under the limited resources of the existing equipment is important, and an effective method for determining the OCR recognition model is lacked at present.
Disclosure of Invention
The embodiment of the invention provides a method for determining an OCR recognition model, which is used for determining the OCR recognition model meeting the parameter data of equipment from a plurality of OCR recognition models and has high accuracy, and the method comprises the following steps:
acquiring parameter data of a plurality of OCR recognition models to be analyzed and equipment;
determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment;
determining the weight corresponding to the conformity index value;
for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed.
The embodiment of the invention provides a device for determining an OCR recognition model, which is used for determining the OCR recognition model meeting the parameter data of equipment from a plurality of OCR recognition models and has high accuracy, and the device comprises:
the data acquisition model is used for acquiring various OCR recognition models to be analyzed and parameter data of the equipment;
the index value determining module is used for determining a conformity index value between the OCR recognition model and the parameter data of the equipment, and the conformity index is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment;
the weight determining module is used for determining the weight corresponding to the conformity index value;
the conformity calculation module is used for acquiring the conformity of each OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
and the recognition module determining module is used for determining the OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the determination method of the OCR recognition model.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for determining an OCR recognition model is stored in the computer-readable storage medium.
In the embodiment of the invention, parameter data of various OCR recognition models and equipment to be analyzed are obtained; determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment; determining the weight corresponding to the conformity index value; for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model; and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed. In the above process, the conformity of each OCR recognition model to be analyzed is obtained in consideration of the conformity of the OCR recognition model with the parameter data of the device and the corresponding weight is determined, and therefore, the accuracy of the OCR recognition model conforming to the parameter data of the device determined from the plurality of OCR recognition models to be analyzed is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart of a method for determining an OCR recognition model in an embodiment of the present invention;
FIG. 2 is an architecture diagram of an apparatus supporting input-output decoupling in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an apparatus for determining an OCR recognition model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
At present, there are many OCR recognition models, including deep learning models, character template matching models, etc., and different OCR recognition models have respective characteristics, for example, some recognition models have good recognition effect but need to be operated on a high-performance processor; some methods have low requirements on the operating environment, but have poor recognition effect. For example, banks have a large number of images of certificates and impact data of special bills. Some OCR recognition models have low requirements on the computing power of a processor, but have poor recognition effect, while deep learning models require the OCR processor to have large computing power and require purchasing a high-performance GPU server. At present, for the recognition of the same banking image, an OCR recognition model is generally selected, and based on this, the embodiment of the present invention provides a method for determining the OCR recognition model.
Fig. 1 is a flowchart of a method for determining an OCR recognition model in an embodiment of the present invention, as shown in fig. 1, the method includes:
104, for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
and 105, determining the OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed.
In the embodiment of the invention, parameter data of various OCR recognition models and equipment to be analyzed are obtained; determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment; determining the weight corresponding to the conformity index value; for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model; and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed. In the above process, the conformity of each OCR recognition model to be analyzed is obtained in consideration of the conformity of the OCR recognition model with the parameter data of the device and the corresponding weight is determined, and therefore, the accuracy of the OCR recognition model conforming to the parameter data of the device determined from the plurality of OCR recognition models to be analyzed is high.
In specific implementation, the parameters of the device may include supporting multiple languages, cluster deployment capability, supporting a customized output content format (a customized template file for a fixed format form is used for performing structured output of a recognition result), supporting multi-directional recognition of text, supporting multiple input file formats (including docx, xlsx, double-layer PDF, XML, TXT, CSV, etc.), supporting multiple output file formats (including docx, xlsx, double-layer PDF, XML, TXT, CSV, etc.), memory capacity, and operation speed, and in addition, supporting high concurrency, supporting decoupling of input and output, supporting Docker container installation, supporting different computing cores (e.g., supporting GPU/CPU and obtaining optimal performance on GPU server), supporting multiple image formats (e.g., scanner, high-speed camera, JPEG photographed by mobile phone, BMP, PNG, and image format for multiple types (e.g., scanner, high-speed camera, JPEG photographed by mobile phone, and BMP, etc.) File in TIFF, PDF format), fig. 2 is an architecture diagram of a device supporting input/output decoupling in the embodiment of the present invention, as shown in fig. 2, the device supporting input/output decoupling has the following characteristics: the API interface is adopted, JSON data return is adopted, the access to a service system is easy, and various identification modules can be contained.
In an embodiment, the conformity index includes one or any combination of a multi-language conformity index, a cluster deployment capability conformity index, a custom output content format conformity index, a multi-directional identification conformity index of characters, a multi-input file format conformity index, a multi-output file format conformity index, a memory capacity conformity index and a computation speed conformity index.
In the above embodiment, the multi-language conformity index indicates whether the OCR recognition model and the device support multiple languages, including chinese, english, german, french, and the like; the cluster deployment capability conformity index is whether the cluster deployment capability required by the OCR model is matched with the existing cluster deployment capability of the equipment; the user-defined output content format conformity index indicates whether the OCR recognition model and the equipment both support the user-defined output content format; the character multidirectional identification conformity index is that whether an OCR identification model and equipment support character multidirectional identification or not; the multiple input file format conformity degree index indicates whether the OCR recognition model and the equipment support multiple input file formats; the index of the conformity degree of the formats of the multiple output files refers to whether the OCR recognition model and the equipment support multiple output file formats, and the index of the conformity degree of the memory capacity refers to whether the memory capacity required by the calculation of the OCR recognition model is matched with the existing memory capacity of the equipment; the calculation speed conformity index is used for judging whether the calculation speed required by OCR recognition model calculation is matched with the existing calculation speed of equipment. Of course, it is understood that there may be other conformity indicators, and all such modifications are intended to fall within the scope of the present invention.
In an embodiment, the OCR recognition model to be analyzed includes a classifier character recognition model, a character template matching model, or a deep learning model.
The plurality of OCR recognition models to be analyzed can be a plurality of classifier character recognition models with different parameters, a plurality of character template matching models with different parameters or a plurality of deep learning models with different parameters.
In one embodiment, the plurality of OCR recognition models to be analyzed may also be deep learning models of a plurality of different vendors.
The determination of the index value of the correspondence between the OCR recognition model and the parameter data of the device may be determined according to practical situations, for example, for the index of the correspondence between multiple languages, when the OCR recognition model supports three languages and the device supports four languages, the index value of the correspondence between multiple languages may be 0.75.
In specific implementation, there are various methods for determining the weight corresponding to the conformity index value, for example, an expert intuitive determination method, an analytic hierarchy process, a ranking method, and the like.
In an embodiment, for each OCR recognition model to be analyzed, the following formula is adopted to obtain the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model:
m is the conformity of the OCR recognition model to be analyzed;
Wiis the ith conformity index value;
Fiis the ith conformity fingerAnd (5) weighting corresponding to the scalar value.
And finally, obtaining the conformity of each OCR recognition model to be analyzed, and determining the OCR recognition model with the maximum conformity as the OCR recognition model conforming to the parameter data of the equipment. By applying the OCR recognition model to the equipment, the most accurate OCR recognition result can be obtained under the condition of fully utilizing the computing resources of the equipment.
The equipment in the embodiment of the invention can be various image bill centers and various OCR recognition platforms, and also can be various terminal equipment or cloud servers.
In the method provided by the embodiment of the invention, parameter data of various OCR recognition models and equipment to be analyzed are obtained; determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment; determining the weight corresponding to the conformity index value; for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model; and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed. In the above process, the conformity of each OCR recognition model to be analyzed is obtained in consideration of the conformity of the OCR recognition model with the parameter data of the device and the corresponding weight is determined, and therefore, the accuracy of the OCR recognition model conforming to the parameter data of the device determined from the plurality of OCR recognition models to be analyzed is high.
Based on the same inventive concept, the embodiment of the present invention further provides a device for determining an OCR recognition model, as described in the following embodiments. Since the principles of solving the problems are similar to the determination method of the OCR recognition model, the implementation of the apparatus can be referred to the implementation of the method, and the repeated details are not repeated.
Fig. 3 is a schematic diagram of an apparatus for determining an OCR recognition model in an embodiment of the present invention, as shown in fig. 3, the apparatus includes:
a data acquisition model 301 for acquiring parameter data of a plurality of OCR recognition models to be analyzed and devices;
an index value determination module 302, configured to determine a conformity index value between the OCR recognition model and the parameter data of the device, where the conformity index is used to characterize a conformity degree between the OCR recognition model and the parameter data of the device;
a weight determining module 303, configured to determine a weight corresponding to the conformity index value;
the conformity calculation module 304 is used for acquiring the conformity of each OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
the recognition module determining module 305 is configured to determine, according to the conformity of the plurality of OCR recognition models to be analyzed, an OCR recognition model which conforms to the parameter data of the device from the plurality of OCR recognition models to be analyzed.
In an embodiment, the OCR recognition model to be analyzed includes a classifier character recognition model, a character template matching model, or a deep learning model.
In an embodiment, the conformity index includes one or any combination of a multi-language conformity index, a cluster deployment capability conformity index, a custom output content format conformity index, a multi-directional identification conformity index of characters, a multi-input file format conformity index, a multi-output file format conformity index, a memory capacity conformity index and a computation speed conformity index.
In an embodiment, the conformity calculation module is specifically configured to:
for each OCR recognition model to be analyzed, the following formula is adopted, and the conformity of the OCR recognition model to be analyzed is obtained according to the conformity index value and the corresponding weight of the OCR recognition model:
m is the conformity of the OCR recognition model to be analyzed;
Wiis the ith conformity index value;
Fithe corresponding weight of the ith conformity index value.
In the device provided by the embodiment of the invention, parameter data of various OCR recognition models and equipment to be analyzed are obtained; determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment; determining the weight corresponding to the conformity index value; for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model; and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed. In the above process, the conformity of each OCR recognition model to be analyzed is obtained in consideration of the conformity of the OCR recognition model with the parameter data of the device and the corresponding weight is determined, and therefore, the accuracy of the OCR recognition model conforming to the parameter data of the device determined from the plurality of OCR recognition models to be analyzed is high.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for determining an OCR recognition model, comprising:
acquiring parameter data of a plurality of OCR recognition models to be analyzed and equipment;
determining a conformity index value between the OCR recognition model and the parameter data of the equipment, wherein the conformity index value is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment;
determining the weight corresponding to the conformity index value;
for each OCR recognition model to be analyzed, obtaining the conformity of the OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
and determining an OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed.
2. A method of determining an OCR recognition model as recited in claim 1, wherein the OCR recognition model to be analyzed includes a classifier character recognition model, a character template matching model or a deep learning model.
3. The method for determining an OCR recognition model as claimed in claim 1, wherein the conformity index comprises one or any combination of a plurality of language conformity indexes, a cluster deployment capability conformity index, a custom output content format conformity index, a character multidirectional recognition conformity index, a plurality of input file format conformity indexes, a plurality of output file format conformity indexes, a memory capacity conformity index and a computation speed conformity index.
4. A method for determining an OCR recognition model as claimed in claim 1, wherein for each OCR recognition model to be analyzed, the conformity of the OCR recognition model to be analyzed is obtained according to the conformity index value and the corresponding weight of the OCR recognition model by using the following formula:
m is the conformity of the OCR recognition model to be analyzed;
Wiis the ith conformity index value;
Fithe corresponding weight of the ith conformity index value.
5. An apparatus for determining an OCR recognition model, comprising:
the data acquisition model is used for acquiring various OCR recognition models to be analyzed and parameter data of the equipment;
the index value determining module is used for determining a conformity index value between the OCR recognition model and the parameter data of the equipment, and the conformity index is used for representing the conformity degree between the OCR recognition model and the parameter data of the equipment;
the weight determining module is used for determining the weight corresponding to the conformity index value;
the conformity calculation module is used for acquiring the conformity of each OCR recognition model to be analyzed according to the conformity index value and the corresponding weight of the OCR recognition model;
and the recognition module determining module is used for determining the OCR recognition model which accords with the parameter data of the equipment from the plurality of OCR recognition models to be analyzed according to the conformity of the plurality of OCR recognition models to be analyzed.
6. An OCR recognition model determining apparatus as recited in claim 5 wherein the OCR recognition model to be analyzed comprises a classifier character recognition model, a character template matching model or a deep learning model.
7. An apparatus for determining an OCR recognition model according to claim 5, wherein the conformity index comprises one or any combination of a plurality of language conformity indexes, a cluster deployment capability conformity index, a custom output content format conformity index, a character multidirectional recognition conformity index, a plurality of input file format conformity indexes, a plurality of output file format conformity indexes, a memory capacity conformity index and a computation speed conformity index.
8. An apparatus for determining an OCR recognition model as recited in claim 5, wherein the conformity calculation module is specifically configured to:
for each OCR recognition model to be analyzed, the following formula is adopted, and the conformity of the OCR recognition model to be analyzed is obtained according to the conformity index value and the corresponding weight of the OCR recognition model:
m is the conformity of the OCR recognition model to be analyzed;
Wiis the ith conformity index value;
Fithe corresponding weight of the ith conformity index value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910921358.0A CN110689019B (en) | 2019-09-27 | 2019-09-27 | OCR recognition model determining method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910921358.0A CN110689019B (en) | 2019-09-27 | 2019-09-27 | OCR recognition model determining method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110689019A true CN110689019A (en) | 2020-01-14 |
CN110689019B CN110689019B (en) | 2022-05-24 |
Family
ID=69110511
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910921358.0A Active CN110689019B (en) | 2019-09-27 | 2019-09-27 | OCR recognition model determining method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110689019B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118014072A (en) * | 2024-04-10 | 2024-05-10 | 中国电建集团昆明勘测设计研究院有限公司 | Construction method and system of knowledge graph for hydraulic and hydroelectric engineering |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991317A (en) * | 2016-12-30 | 2017-07-28 | 中国银联股份有限公司 | Safe verification method, platform, device and system |
CN107230005A (en) * | 2017-06-29 | 2017-10-03 | 国信优易数据有限公司 | A kind of data processing method and equipment |
CN108846219A (en) * | 2018-06-22 | 2018-11-20 | 武汉大学 | High-pressure grinding material water jet process unit process parameter optimizing method and system |
CN108871311A (en) * | 2018-05-31 | 2018-11-23 | 北京字节跳动网络技术有限公司 | Pose determines method and apparatus |
CN109656733A (en) * | 2018-12-27 | 2019-04-19 | 厦门商集网络科技有限责任公司 | The method and apparatus of the more OCR recognition engines of intelligent scheduling |
CN110175171A (en) * | 2019-05-16 | 2019-08-27 | 贵州电网有限责任公司 | The system of rack position on a kind of information technoloy equipment intelligent recommendation |
-
2019
- 2019-09-27 CN CN201910921358.0A patent/CN110689019B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991317A (en) * | 2016-12-30 | 2017-07-28 | 中国银联股份有限公司 | Safe verification method, platform, device and system |
CN107230005A (en) * | 2017-06-29 | 2017-10-03 | 国信优易数据有限公司 | A kind of data processing method and equipment |
CN108871311A (en) * | 2018-05-31 | 2018-11-23 | 北京字节跳动网络技术有限公司 | Pose determines method and apparatus |
CN108846219A (en) * | 2018-06-22 | 2018-11-20 | 武汉大学 | High-pressure grinding material water jet process unit process parameter optimizing method and system |
CN109656733A (en) * | 2018-12-27 | 2019-04-19 | 厦门商集网络科技有限责任公司 | The method and apparatus of the more OCR recognition engines of intelligent scheduling |
CN110175171A (en) * | 2019-05-16 | 2019-08-27 | 贵州电网有限责任公司 | The system of rack position on a kind of information technoloy equipment intelligent recommendation |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118014072A (en) * | 2024-04-10 | 2024-05-10 | 中国电建集团昆明勘测设计研究院有限公司 | Construction method and system of knowledge graph for hydraulic and hydroelectric engineering |
CN118014072B (en) * | 2024-04-10 | 2024-08-16 | 中国电建集团昆明勘测设计研究院有限公司 | Construction method and system of knowledge graph for hydraulic and hydroelectric engineering |
Also Published As
Publication number | Publication date |
---|---|
CN110689019B (en) | 2022-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10482174B1 (en) | Systems and methods for identifying form fields | |
US20200273078A1 (en) | Identifying key-value pairs in documents | |
US10452700B1 (en) | Systems and methods for parsing log files using classification and plurality of neural networks | |
US20200125954A1 (en) | Systems and methods for selecting and generating log parsers using neural networks | |
US9619209B1 (en) | Dynamic source code generation | |
CN111783974A (en) | Model construction and image processing method and device, hardware platform and storage medium | |
CN109902190B (en) | Image retrieval model optimization method, retrieval method, device, system and medium | |
CN110347855A (en) | Paintings recommended method, terminal device, server, computer equipment and medium | |
CN110826706B (en) | Data processing method and device for neural network | |
CN112200296A (en) | Network model quantification method and device, storage medium and electronic equipment | |
CN112464927B (en) | Information extraction method, device and system | |
CN110941951A (en) | Text similarity calculation method, text similarity calculation device, text similarity calculation medium and electronic equipment | |
CN116797533B (en) | Appearance defect detection method and system for power adapter | |
CN110689019B (en) | OCR recognition model determining method and device | |
CN106611148B (en) | Image-based offline formula identification method and device | |
CN111353039B (en) | File category detection method and device | |
EP3640861A1 (en) | Systems and methods for parsing log files using classification and a plurality of neural networks | |
US10705810B2 (en) | Automatic code generation | |
CN111639161A (en) | System information processing method, apparatus, computer system and medium | |
CN116303820A (en) | Label generation method, label generation device, computer equipment and medium | |
CN114219091A (en) | Network model reasoning acceleration method, device, equipment and storage medium | |
CN114373068A (en) | Industry-scene OCR model implementation system, method and equipment | |
JP5824429B2 (en) | Spam account score calculation apparatus, spam account score calculation method, and program | |
CN111475403A (en) | Dynamic generation method of test script and related device | |
CN111783572A (en) | Text detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |