CN109919931B - Coronary stenosis degree evaluation model training method and evaluation system - Google Patents
Coronary stenosis degree evaluation model training method and evaluation system Download PDFInfo
- Publication number
- CN109919931B CN109919931B CN201910176706.6A CN201910176706A CN109919931B CN 109919931 B CN109919931 B CN 109919931B CN 201910176706 A CN201910176706 A CN 201910176706A CN 109919931 B CN109919931 B CN 109919931B
- Authority
- CN
- China
- Prior art keywords
- specific
- sample
- cloud
- samples
- sample set
- 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
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a coronary stenosis degree evaluation model training method, which comprises the following steps: s1, collecting samples from hospitals through a cloud method to form a cloud sample set; s2, manually labeling and classifying the samples extracted from the cloud sample set and obtaining the cloud scores of the classified samples; s3, training an image classification model based on the labeled classification sample; s4, collecting a specific sample from a specific hospital to form a specific sample set; inputting a specific sample set into a classification model for classification; s5, determining the difficulty value of the specific sample: s6, confirming the difficulty degree of the specific sample set; s7, extracting samples in corresponding proportion from the cloud sample set according to the difficulty degree distribution of the specific sample set, and generating a sample subset; and S8, training a coronary stenosis degree evaluation model by using the sample subset. Meanwhile, the invention also discloses a coronary stenosis degree evaluation system. The invention fully considers the differences of the scoring strategies of different experts, so that the output result of the invention is more in line with the scoring habits of specific doctors and is more practical.
Description
Technical Field
The invention relates to the field of coronary image analysis, in particular to a training method and an evaluation system of a coronary stenosis degree evaluation model.
Background
AI automatically monitors features such as calcification, soft spots, etc., and obtains a prediction model from a large number of samples for training, so the samples are important inputs. The sample includes raw scan data that can be quickly acquired by the instrument and a label (i.e., an answer) that requires a significant amount of manual intervention.
An important intermediate result of coronary diagnosis and treatment is stenosis degree, which is quantified in combination with the original scan data, and which is useful for the diagnosis of the patient by the expert, and the difficulty of calculating stenosis degree is especially the identification of soft plaque and the identification of partially punctiform calcified mixed plaque, for which the identification requires a certain experience, which is usually evaluated by the expert. However, since different hospitals or doctors have different evaluation strategies and make and break the evaluation of the same original data, the AI has great limitations in practical application, and the analysis result has great limitations, and cannot give a corresponding reference to a specific expert, but may cause misleading.
Disclosure of Invention
The invention aims to provide a coronary stenosis evaluation model training method to obtain a coronary stenosis evaluation model which accords with a specific expert evaluation strategy as much as possible.
In order to achieve the purpose, the invention adopts the following technical scheme:
the training method of the coronary stenosis degree evaluation model comprises the following steps:
s1, obtaining a cloud sample set: collecting samples from each hospital by a cloud method, the samples comprising raw scan data and stenosis score to form a cloud sample set;
s2, manually labeling and classifying the samples extracted from the cloud sample set and obtaining the cloud scores of the classified samples;
s3, training an image classification model based on the labeled classification sample;
s4, obtaining a specific sample set and classifying: collecting specific samples corresponding to a certain hospital or a certain expert in the hospital from the certain hospital to form a specific sample set; inputting a specific sample set into a classification model for classification;
s5, determining the difficulty value of the specific sample: determining the difficulty value of the specific sample according to the difference between the actual score of the specific sample and the cloud score of the class where the specific sample is located based on the classification result;
s6, confirming the difficulty degree of the specific sample set based on the difficulty value of the specific sample;
s7, extracting samples in corresponding proportion from the class samples corresponding to the cloud sample set corresponding to the difficulty degree distribution condition in the specific sample set, and generating a sample subset;
and S8, training a coronary stenosis degree evaluation model by using the sample subset.
Further, in S1, the cloud sample set is generated based on the same model data, and samples in subsequent steps are extracted based on the same model data.
Further, the difficulty value is calculated by the following formula:
in the formula, M1 is the cloud score of the class where a specific sample is located, and M2 is the actual score of a specific sample.
The invention also discloses a coronary stenosis degree evaluation system, which comprises:
a cloud sample set acquisition module that collects samples from each hospital by a cloud method, the samples including raw scan data and stenosis degree scores to form a cloud sample set;
the cloud expert manually extracts samples from the cloud sample set through the human-computer interaction module, labels and classifies the samples, and meanwhile obtains cloud scores of all classified samples;
the system comprises a sample classification module, a data processing module and a data processing module, wherein an image classification model is arranged in the sample classification module and is trained on labeled classification samples;
a specific sample set collecting module which collects specific samples corresponding to a specific hospital or a specific expert in the hospital from the specific hospital to form a specific sample set and inputs the specific sample set into a sample classifying module for classification;
the specific sample evaluation module determines a difficulty value of the specific sample according to the difference between the actual score of the specific sample and the cloud score of the class of the specific sample based on the classification result; confirming the difficulty degree of the specific sample set based on the difficulty value of the specific sample;
the sample extraction module extracts samples in corresponding proportion from the class samples corresponding to the cloud sample set based on the difficulty degree distribution condition in the specific sample set to generate a sample subset;
a coronary stenosis degree evaluation module, which is internally provided with a coronary stenosis degree evaluation model, and the coronary stenosis degree evaluation model is trained based on the sample subset.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
the method fully considers the differences of the evaluation strategies of different hospitals or different experts, evaluates and classifies the sample difficulty to obtain the difficulty degree distribution condition of the samples in a specific hospital, extracts the model training samples according to the difficulty degree distribution condition, enables the model training samples to accord with the grading habit of the specific hospital or the specific experts in the specific hospital, enables the grading result to be more referential, and improves the efficiency of doctors.
Drawings
FIG. 1 is a flow chart of a coronary stenosis degree evaluation model training method of the present invention;
fig. 2 is a block diagram of a coronary stenosis degree evaluation system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the present invention, it should be noted that the terms "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are all based on the orientation or positional relationship shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the apparatus or element of the present invention must have a specific orientation, and thus, should not be construed as limiting the present invention.
Example 1
Referring to fig. 1, the invention discloses a coronary stenosis degree evaluation model training method, which mainly includes 8 core steps.
S1, obtaining a cloud sample set: samples, including raw scan data and stenosis score, are collected from various hospitals by a cloud method to form a cloud sample set.
In consideration of differences generated by different model data, in S1, the cloud sample set is generated based on the same model data, that is, for the same model data, data of different hospitals may be mixed together to form a large data set, and samples in subsequent steps are extracted based on the same model data.
And S2, manually labeling and classifying the samples extracted from the cloud sample set and obtaining the cloud scores of the classified samples.
Collecting samples, manually classifying the samples based on image quality and the occurrence positions of the focuses, classifying the occurrence positions of the focuses and the similar image quality into one class, giving classification labels to the classes, and obtaining training samples. Meanwhile, one cloud score (i.e., a homogeneous score) may be generated for each classification sample. The cloud score may be an average score of the narrowness of each sample in the classified sample set, or may be a comprehensive score given by a cloud expert for the type of sample.
And S3, training an image classification model based on the labeled classification sample.
Through the processing of S2, the training samples are all images which are manually annotated whether the images are similar to certain types of images, and the image classification model can be trained and obtained by obtaining the 'stacking' annotation.
S4, obtaining a specific sample set and classifying: collecting specific samples corresponding to a certain hospital or a certain expert in the hospital from the certain hospital to form a specific sample set; and inputting the specific sample set into a classification model for classification.
The acquisition of the specific sample set can be performed by randomly drawing 100-200 specific samples corresponding to the hospital or a specific expert in the hospital in units of years, so that the specific samples relatively conform to natural distribution.
S5, determining the difficulty value of the specific sample: and determining the difficulty value of the specific sample according to the difference between the actual score of the specific sample and the cloud score of the class of the specific sample based on the classification result.
The concept of a difficulty value is derived from the actual score of a particular expert and the cloud score of that type of sample. The lower the score is, the closer the scoring habit representing the specific expert is to the cloud, the more consistent the scoring of different experts on the sample is, and the simpler the sample is represented; the higher the score is, the greater the difference between the scoring habit representing the specific expert and the cloud, and the more difficult the specific expert represents the sample because the strategies adopted by the specific expert are different in the scoring result of the sample.
The difficulty value is calculated by the following formula:
in the formula, M1 is the cloud score of the class where a specific sample is located, and M2 is the actual score of a specific sample.
And S6, confirming the difficulty degree of the specific sample set based on the difficulty value of the specific sample.
The difficulty level can be divided into a plurality of grades according to the sequence from easy to difficult.
For example, there are 8 samples. The difficulty values of the samples are respectively 32%, 35%, 48%, 60%, 62%, 69%, 70% and 78%, and the difficulty is divided into 4 grades, namely, one class is divided from 0-100% at intervals of 25%. Then 32%, 35%, 48% belong to the second category; 60%, 62%, 69%, 70% belong to the third category; 78% belong to the fourth category.
And S7, extracting samples in corresponding proportion from the class samples corresponding to the cloud sample set corresponding to the difficulty degree distribution condition in the specific sample set, and generating a sample subset.
For difficulty level 4, the distribution of easy-to-difficult in a particular sample set is 3: 3: 2: 2, the sample is extracted from the cloud sample set according to the ratio to generate the sample subset.
And S8, training a coronary stenosis degree evaluation model by using the sample subset.
Example 2
The invention also discloses a coronary stenosis degree evaluation system, which comprises:
a cloud sample set acquisition module that collects samples from each hospital by a cloud method, the samples including raw scan data and stenosis degree scores to form a cloud sample set;
the cloud expert manually extracts samples from the cloud sample set through the human-computer interaction module, labels and classifies the samples, and meanwhile obtains cloud scores of all classified samples;
the system comprises a sample classification module, a data processing module and a data processing module, wherein an image classification model is arranged in the sample classification module and is trained on labeled classification samples;
a specific sample set collecting module which collects specific samples corresponding to a specific hospital or a specific expert in the hospital from the specific hospital to form a specific sample set and inputs the specific sample set into a sample classifying module for classification;
the specific sample evaluation module determines a difficulty value of the specific sample according to the difference between the actual score of the specific sample and the cloud score of the class of the specific sample based on the classification result; confirming the difficulty degree of the specific sample set based on the difficulty value of the specific sample;
the sample extraction module extracts samples in corresponding proportion from the class samples corresponding to the cloud sample set based on the difficulty degree distribution condition in the specific sample set to generate a sample subset;
a coronary stenosis degree evaluation module, which is internally provided with a coronary stenosis degree evaluation model, and the coronary stenosis degree evaluation model is trained based on the sample subset.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (4)
1. The coronary stenosis degree evaluation model training method is characterized by comprising the following steps:
s1, obtaining a cloud sample set: collecting samples from each hospital by a cloud method, the samples comprising raw scan data and stenosis score to form a cloud sample set;
s2, manually labeling and classifying the samples extracted from the cloud sample set and obtaining cloud scores of the classified samples, wherein the cloud scores are average scores of narrowness of the samples in the classified sample set or comprehensive scores given by cloud experts aiming at the classified samples;
s3, training an image classification model based on the labeled classification sample;
s4, obtaining a specific sample set and classifying: collecting specific samples corresponding to a certain hospital or a certain expert in the hospital from the certain hospital to form a specific sample set; inputting a specific sample set into a classification model for classification;
s5, determining the difficulty value of the specific sample: determining the difficulty value of the specific sample according to the difference between the actual score of the specific sample and the cloud score of the class of the specific sample based on the classification result, wherein the concept of the difficulty value is obtained by the actual score of a specific expert and the cloud score of the class of the specific sample, the lower the score is, the closer the scoring habit representing the specific expert is to the cloud end, the more the different experts tend to be consistent in scoring the specific sample, and the simpler the representing of the specific sample is; the higher the score is, the greater the difference between the scoring habit of the specific expert and the cloud, and the more difficult the specific expert is to represent the specific sample, because the strategies adopted by the specific expert are different in the scoring result of the specific sample;
s6, confirming the difficulty degree of the specific sample set based on the difficulty value of the specific sample, wherein the difficulty degree is divided into a plurality of grades according to the sequence from easy to difficult;
s7, extracting samples in corresponding proportion from the class samples corresponding to the cloud sample set corresponding to the difficulty degree distribution condition in the specific sample set, and generating a sample subset;
and S8, training a coronary stenosis degree evaluation model by using the sample subset.
2. The coronary stenosis degree evaluation model training method according to claim 1, wherein: in S1, the cloud sample set is generated based on the same model data, and samples in subsequent steps are extracted based on the same model data.
3. The coronary stenosis degree evaluation model training method of claim 1, wherein the difficulty value is calculated by the following formula: d = (| M1-M2 |/M1)%, where M1 is the cloud score of the class where a particular sample is located, and M2 is the actual score of a particular sample.
4. A coronary stenosis degree evaluation system is characterized by comprising:
a cloud sample set acquisition module that collects samples from each hospital by a cloud method, the samples including raw scan data and stenosis degree scores to form a cloud sample set;
the cloud expert manually extracts samples from the cloud sample set through the human-computer interaction module, labels and classifies the samples, and meanwhile obtains the cloud score of each classified sample, wherein the cloud score is the average score of the narrowness of each sample in the classified sample set or the comprehensive score given by the cloud expert aiming at the classified sample;
the system comprises a sample classification module, a data processing module and a data processing module, wherein an image classification model is arranged in the sample classification module and is trained on labeled classification samples;
a specific sample set collecting module which collects specific samples corresponding to a specific hospital or a specific expert in the hospital from the specific hospital to form a specific sample set and inputs the specific sample set into a sample classifying module for classification;
the specific sample evaluation module determines a difficulty value according to the difference between the actual score of the specific sample and the cloud score of the class of the specific sample based on the classification result, the concept of the difficulty value is obtained by the actual score of a specific expert and the cloud score of the class of the specific sample, the lower the score is, the closer the scoring habit representing the specific expert is to the cloud, the more consistent the scores of different experts on the specific sample are, and the simpler the score represents the specific sample; the higher the score is, the greater the difference between the scoring habit of the specific expert and the cloud, and the more difficult the specific expert is to represent the specific sample, because the strategies adopted by the specific expert are different in the scoring result of the specific sample; confirming difficulty degrees of the specific sample set based on the difficulty values of the specific samples, wherein the difficulty degrees are divided into a plurality of grades according to the sequence from easy to difficult;
the sample extraction module extracts samples in corresponding proportion from the class samples corresponding to the cloud sample set based on the difficulty degree distribution condition in the specific sample set to generate a sample subset;
a coronary stenosis degree evaluation module, which is internally provided with a coronary stenosis degree evaluation model, and the coronary stenosis degree evaluation model is trained based on the sample subset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910176706.6A CN109919931B (en) | 2019-03-08 | 2019-03-08 | Coronary stenosis degree evaluation model training method and evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910176706.6A CN109919931B (en) | 2019-03-08 | 2019-03-08 | Coronary stenosis degree evaluation model training method and evaluation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919931A CN109919931A (en) | 2019-06-21 |
| CN109919931B true CN109919931B (en) | 2020-12-25 |
Family
ID=66963936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910176706.6A Active CN109919931B (en) | 2019-03-08 | 2019-03-08 | Coronary stenosis degree evaluation model training method and evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919931B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751642A (en) * | 2015-03-11 | 2015-07-01 | 同济大学 | Real-time estimating method for high-grade road traffic flow running risks |
| CN108135003A (en) * | 2017-12-25 | 2018-06-08 | 广东海格怡创科技有限公司 | The construction method and system of interference type identification model |
| CN108197545A (en) * | 2017-12-25 | 2018-06-22 | 广东海格怡创科技有限公司 | The recognition methods of interference type and system |
| CN108280462A (en) * | 2017-12-11 | 2018-07-13 | 北京三快在线科技有限公司 | A kind of model training method and device, electronic equipment |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100527132C (en) * | 2007-06-22 | 2009-08-12 | 腾讯科技（深圳）有限公司 | Classified sample set optimizing method and content-related advertising server |
| US8515777B1 (en) * | 2010-10-13 | 2013-08-20 | ProcessProxy Corporation | System and method for efficient provision of healthcare |
| CN105320957B (en) * | 2014-07-10 | 2022-02-15 | 腾讯科技（深圳）有限公司 | Classifier training method and device |
| CN104572820B (en) * | 2014-12-03 | 2017-11-24 | 百度在线网络技术（北京）有限公司 | The generation method and device of model, importance acquisition methods and device |
| CN104679860B (en) * | 2015-02-27 | 2017-11-07 | 北京航空航天大学 | A kind of sorting technique of unbalanced data |
| CN105550747A (en) * | 2015-12-09 | 2016-05-04 | 四川长虹电器股份有限公司 | Sample training method for novel convolutional neural network |
| CN107133628A (en) * | 2016-02-26 | 2017-09-05 | 阿里巴巴集团控股有限公司 | A kind of method and device for setting up data identification model |
| US20190017119A1 (en) * | 2017-07-12 | 2019-01-17 | The General Hospital Corporation | Genetic Risk Predictor |
| CN107392259B (en) * | 2017-08-16 | 2021-12-07 | 北京京东尚科信息技术有限公司 | Method and device for constructing unbalanced sample classification model |
| CN108171175B (en) * | 2017-12-29 | 2020-06-23 | 苏州科达科技股份有限公司 | Deep learning sample enhancement system and operation method thereof |
| CN108389201B (en) * | 2018-03-16 | 2020-06-30 | 北京推想科技有限公司 | Lung nodule benign and malignant classification method based on 3D convolutional neural network and deep learning |
| CN108573040A (en) * | 2018-04-08 | 2018-09-25 | 西北工业大学 | A kind of sample set optimization algorithm based on target distribution |
| CN108830155B (en) * | 2018-05-10 | 2021-10-15 | 北京红云智胜科技有限公司 | Heart coronary artery segmentation and identification method based on deep learning |
| CN108985369A (en) * | 2018-07-06 | 2018-12-11 | 太原理工大学 | A kind of same distribution for unbalanced dataset classification integrates prediction technique and system |
| CN109036551B (en) * | 2018-07-10 | 2021-05-11 | 北京心世纪医疗科技有限公司 | Coronary artery physiological index relation establishing and applying method and device |
| CN109146667B (en) * | 2018-08-20 | 2021-06-08 | 众安在线财产保险股份有限公司 | Method for constructing external interface comprehensive application model based on quantitative statistics |
| CN109272514B (en) * | 2018-10-05 | 2021-07-13 | 数坤(北京)网络科技股份有限公司 | Sample evaluation method and model training method of coronary artery segmentation model |
| CN109327464A (en) * | 2018-11-15 | 2019-02-12 | 中国人民解放军战略支援部队信息工程大学 | Class imbalance processing method and processing device in a kind of network invasion monitoring |
| CN109346179B (en) * | 2018-12-10 | 2022-08-26 | 山东管理学院 | Coronary heart disease interventional postoperative recurrence prediction model and modeling method and device thereof |
-
2019
- 2019-03-08 CN CN201910176706.6A patent/CN109919931B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751642A (en) * | 2015-03-11 | 2015-07-01 | 同济大学 | Real-time estimating method for high-grade road traffic flow running risks |
| CN108280462A (en) * | 2017-12-11 | 2018-07-13 | 北京三快在线科技有限公司 | A kind of model training method and device, electronic equipment |
| CN108135003A (en) * | 2017-12-25 | 2018-06-08 | 广东海格怡创科技有限公司 | The construction method and system of interference type identification model |
| CN108197545A (en) * | 2017-12-25 | 2018-06-22 | 广东海格怡创科技有限公司 | The recognition methods of interference type and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919931A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107247881B (en) | Multi-mode intelligent analysis method and system | |
| RU2739974C1 (en) | Method for bone marrow cell marking and system for implementation thereof | |
| CN112184617B (en) | Spine MRI image key point detection method based on deep learning | |
| CN112037910B (en) | Health information management method, device, equipment and storage medium | |
| CN106845147B (en) | Method for building up, the device of medical practice summary model | |
| CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
| CN109582875A (en) | A kind of personalized recommendation method and system of online medical education resource | |
| CN108846828A (en) | A kind of pathological image target-region locating method and system based on deep learning | |
| CN109003269A (en) | A kind of mark extracting method for the medical image lesion that can improve doctor's efficiency | |
| CN113662664B (en) | Instrument tracking-based objective and automatic evaluation method for surgical operation quality | |
| CN117237351B (en) | Ultrasonic image analysis method and related device | |
| CN116504392A (en) | Intelligent auxiliary diagnosis prompt system based on data analysis | |
| Gaber et al. | Comprehensive assessment of facial paralysis based on facial animation units | |
| Li et al. | Current status of objectification of four diagnostic methods on constitution recognition of Chinese medicine | |
| CN109919931B (en) | Coronary stenosis degree evaluation model training method and evaluation system | |
| Mallet et al. | Morphometrical distinction between sheep (Ovis aries) and goat (Capra hircus) using the petrosal bone: application on French protohistoric sites | |
| CN106294751B (en) | Abnormal examination based on keyword network correlation analysis reports automatic identifying method | |
| CN116956138A (en) | Image gene fusion classification method based on multi-mode learning | |
| AU2021102129A4 (en) | Automatic labeling method of emphysema in CT image based on image report | |
| CN114145844A (en) | Laparoscopic surgery artificial intelligence cloud auxiliary system based on deep learning algorithm | |
| CN113191141A (en) | Method, device and equipment for generating inquiry regular expression and storage medium | |
| CN112927808A (en) | Thyroid ultrasound image-based nodule grading system and method | |
| Kauppi et al. | A framework for constructing benchmark databases and protocols for retinopathy in medical image analysis | |
| CN115019045B (en) | Small data thyroid ultrasound image segmentation method based on multi-component neighborhood | |
| CN118262220B (en) | Quality assessment method, device and equipment for radiographic image report |
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 | ||
| CP03 | Change of name, title or address |
Address after: 100120 rooms 303, 304, 305, 321 and 322, building 3, No. 11, Chuangxin Road, science and Technology Park, Changping District, Beijing Patentee after: Shukun (Beijing) Network Technology Co.,Ltd. Address before: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee before: SHUKUN (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230117 Address after: 518026 Rongchao Economic and Trade Center A308-D9, No. 4028, Jintian Road, Fuzhong Community, Lianhua Street, Futian District, Shenzhen, Guangdong Province Patentee after: Shukun (Shenzhen) Intelligent Network Technology Co.,Ltd. Address before: 100120 rooms 303, 304, 305, 321 and 322, building 3, No. 11, Chuangxin Road, science and Technology Park, Changping District, Beijing Patentee before: Shukun (Beijing) Network Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |