Method and device for identifying germ-remaining rice and cooking utensil

A technology of retaining embryos and embryos, which is applied in the field of image processing, can solve the problems of unsatisfactory recognition effect, low efficiency and accuracy, and low accuracy, so as to avoid the interference of human subjective factors and improve classification accuracy and speed , to solve the effect of low accuracy

Inactive Publication Date: 2020-07-21
GREE ELECTRIC APPLIANCES INC OF ZHUHAI
5 Cites 1 Cited by

AI-Extracted Technical Summary

Problems solved by technology

The traditional embryo retention rate detection method is highly subjective, slow in detection speed, low in efficiency and accuracy. The technology of using computer vision and improved support vector machines to measure the embryo retention rate is also devel...
View more

Method used

Based on the scheme that the above-mentioned embodiments of the application provide, obtain grain of rice image; Use convolution neural network model to identify grain of rice image, determine the type of grain of rice in the grain of rice image, wherein, the type of grain of rice includes at least: whole rice, broken rice and adhesion rice; obtain the contour area of ​​the whole rice in the rice grain image; divide the contour area of ​​the whole rice, and determine whether the rice grain is germ rice by comparing the areas of different divided areas. The above scheme is based on artificial intelligence technology, uses CNN in the deep learning algorithm to distinguish and identify whole rice, broken rice and sticky rice, and detects the embryo retention rate through contour clustering, avoiding the interference of human subjective factors in the detection of embryo retention rate in traditional methods, and improving the accuracy of classification Accuracy and speed indirectly improve the accuracy of the subsequent detection of the remaining embryo rate, thereby solving the technical problems of low accuracy and slow detection speed in the existing technology to identify whether the rice grains are rice with retained embryos.
By above-mentioned scheme, obtain grain of rice image; Use convolutional neural network model to identify grain of rice image, determine the type of grain of rice in grain of rice image, wherein, the type of grain of rice includes at least: whole rice, broken rice and sticky rice; Obtain in grain of rice image The contour area of ​​the whole rice; divide the contour area of ​​the whole rice, and compare the areas of different divided areas to determine whether the rice grains are germ rice. Compared with the existing technology, the above-mentioned scheme is based on artificial intelligence technology, uses CNN in the deep learning algorithm to distinguish and identify whole rice, broken rice and sticky rice, and detects the embryo retention rate through contour clustering, avoiding the human-subjective detection of embryo retention rate in traditional methods The interference of factors improves the classification accuracy and speed, and indirectly improves the accuracy of the subsequent detection of the remaining germ rate, thereby solving the technical problems of low accuracy and slow detection speed in the existing technology of identifying whether the rice grains are germ-retained rice. At the same time, the rice cooking mode is automatically selected to provide users with the best rice cooking mode, which improves the quality of life.
Convolutional neural network is mainly made up of three parts, is input layer, hidden layer and output layer respectively. Among them, the input layer and the output layer have only one layer, and the hidden layer can have multiple layers. A deep neural network is a neural network with many hidden layers. The input layer of the convolutional neural network is the rice grain image. By using the convolutional neural network to calculate the rice grain image, all the rice grain contour areas of the rice grain image are marked, and then the area area of ​​each contour is calculated to realize the whole rice, broken rice and The division of sticky rice types facilitates the ca...
View more

Abstract

The invention discloses a method and device for identifying germ-remaining rice and a cooking utensil. The method comprises the following steps: acquiring a rice grain image; identifying the rice grain image by using a convolutional neural network model, and determining the types of rice grains in the rice grain image, the types of the rice grains at least comprising whole rice, broken rice and adhered rice; obtaining the contour area of the whole rice in the rice grain image; dividing the contour area of the whole rice, and determining whether the rice grains are germ-remaining rice or not bycomparing the areas of different divided areas. The scheme is based on the artificial intelligence technology, and the technical problems that in the prior art, the accuracy of identifying whether rice grains are germ-remaining rice is low, and the detection speed is low are solved.

Application Domain

Character and pattern recognitionNeural architectures

Technology Topic

HorticultureBroken rice +4

Image

  • Method and device for identifying germ-remaining rice and cooking utensil
  • Method and device for identifying germ-remaining rice and cooking utensil
  • Method and device for identifying germ-remaining rice and cooking utensil

Examples

  • Experimental program(5)

Example Embodiment

[0033] Example 1
[0034] According to an embodiment of the present invention, an embodiment of a method for identifying embryonic rice is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and Although the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here.
[0035] figure 1 It is a flowchart of a method for identifying embryonic rice according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:
[0036] Step S102, acquiring a rice grain image.
[0037] In an optional solution, the above-mentioned rice grains may be rice. The aforementioned rice grain image may be a randomly selected tiled rice grain image without overlap. The above-mentioned acquisition methods can be acquired through image acquisition devices such as cameras, video cameras, and image sensors.
[0038] Spread randomly selected rice grains evenly on a flat surface, choose a suitable distance and lighting conditions, and use a digital camera to shoot images with clear outlines and full field of view characteristics of the measured rice grains.
[0039] In step S104, the convolutional neural network model is used to identify the rice grain image, and the type of rice grain in the rice grain image is determined, where the type of rice grain includes at least whole rice, broken rice, and bonded rice.
[0040] Convolutional neural network is a supervised learning algorithm, which is a special case of deep neural network. Compared with deep artificial neural network, it has the advantages of fewer weights and fast training speed.
[0041] Convolutional neural network is mainly composed of three parts, namely input layer, hidden layer and output layer. Among them, the input layer and output layer have only one layer, while the hidden layer can have multiple layers. A deep neural network is a neural network with many hidden layers. The input layer of the convolutional neural network is the rice grain image. By using the convolutional neural network to calculate the rice grain image, all the rice grain contour areas of the rice grain image are marked, and then the area area of ​​each contour is obtained to realize the whole rice, broken rice and The division of sticking rice types facilitates the calculation of the subsequent embryo retention rate.
[0042] Step S106: Obtain the contour area of ​​the whole rice in the rice grain image.
[0043] Since the embryo retention rate parameter is meaningful for whole meters, only the contour area of ​​all whole meters is extracted.
[0044] In step S108, the contour area of ​​the whole rice is divided, and by comparing the areas of different divided regions, it is determined whether the rice grains are embryonic rice.
[0045] In an optional solution, the above-mentioned division method may be divided along the plane where the symmetry axis of the rice grain is located.
[0046] Since embryonic rice retains the germ part of ordinary rice, it is more symmetrical in structure than ordinary rice, showing an approximate oval shape. Therefore, the rice grains can be divided into several areas along the plane of the symmetry axis of the rice grains, and the area of ​​each area can be compared to determine whether the rice grains are embryonic rice. If the area of ​​several areas is not much different, it means that the rice grain is embryonic rice. If the area of ​​one area is obviously different from the area of ​​other areas, it means that the rice grain is not embryonic rice.
[0047] In an optional embodiment, first, randomly selected rice grains are evenly spread on a flat surface, and an appropriate distance and lighting conditions are selected to take images with clear outlines and full field of view with the characteristics of the measured rice grains using a digital camera. All the rice grain contour areas of the image are marked, and then the area of ​​each contour is obtained, and the convolutional neural network model is used to realize the division of whole rice, broken rice and bonded rice. Secondly, extract all the contour areas of all whole meters, calculate the area of ​​each piece using the area equal division method, and compare the area differences between them to determine whether it is embryonic rice, and then calculate the finishing embryo retention rate.
[0048] Based on the solution provided by the above-mentioned embodiment of the present application, the rice grain image is obtained; the convolutional neural network model is used to identify the rice grain image, and the type of the rice grain in the rice grain image is determined, where the types of rice grains include at least whole rice, broken rice, and bonded rice; The contour area of ​​the whole rice in the rice grain image; divide the contour area of ​​the whole rice, and by comparing the areas of different divided areas, determine whether the rice grains are embryonic rice. The above scheme is based on artificial intelligence technology, uses CNN in the deep learning algorithm to distinguish between whole rice, broken rice and sticky rice, and detects the embryo retention rate through contour clustering, avoiding the interference of subjective factors in detecting the embryo retention rate in traditional methods, and improving the classification accuracy The accuracy and speed indirectly improve the accuracy of the subsequent detection of embryo retention rate, thereby solving the technical problems of low accuracy and slow detection speed in identifying whether rice grains are embryonic rice in the prior art.
[0049] Optionally, using a convolutional neural network model to identify the rice grain image and determine the type of rice grain in the rice grain image includes: extracting the contour area of ​​each rice grain from the rice grain image; calculating the area area of ​​the contour area of ​​each rice grain; The area area of ​​the contour area of ​​the rice grain is compared with the area threshold to determine the type of each rice grain in the rice grain image.
[0050] In an optional solution, the area of ​​the aforementioned contour area may be the projected area of ​​rice grains.
[0051] Since the total area or projected area of ​​tiled whole rice, broken rice, and bonded rice is very different, the type of each rice grain in the rice grain image can be quickly determined by comparing the area thresholds.
[0052] Optionally, extracting the contour area of ​​each rice grain from the rice grain image includes: scanning the image area corresponding to each rice grain in the rice grain image through each convolution kernel in the convolution layer of the convolutional neural network to obtain each image The feature layer of the rice grains contained in the area; the feature layer of the rice grains contained in each image area is de-redundant through the pooling layer of the convolutional neural network; at least one fully connected layer of the convolutional neural network After de-redundant processing, multiple feature layers are converted to obtain the image feature of each rice grain; by marking the image feature of each rice grain, the contour area of ​​each rice grain is obtained.
[0053] In an optional solution, the extraction of the contour area of ​​each rice grain may be the minimum area of ​​the edge of the extracted rice grain contour mark.
[0054] In the above steps, the input layer is connected to the convolutional layer. The convolutional layer is mainly composed of a convolution kernel. The convolution kernel starts from the upper left corner of the rice grain image and scans from left to right and from top to bottom. Each scan unit In the area (convolution kernel area), the pixel points in the rice grain image and the convolution kernel are matrix calculated to obtain a mapping area, that is, a feature map. Many feature maps form a convolution feature layer. The pooling layer performs de-redundancy processing on the feature layers of rice grains contained in each image area, and then converts the de-redundant feature layers through at least one fully connected layer to obtain the image features of each rice grain.
[0055] The convolutional layer and the pooling layer can have many different combinations, and the fully connected layer can also have multiple layers. The specific layer and network depth can be selected according to actual needs. The more layers, the more accurate the recognition results and the more complex the network.
[0056] figure 2 It is a flow chart for realizing the classification of rice grain types according to the convolutional neural network of the embodiment of the present application, and finally realizes the classification process of whole rice, broken rice or bonded rice. First of all, to obtain the rice grain image, affected by the photographing distance, lighting conditions, and camera angle, the rice grains are approximately evenly spread on the selected area and appropriate methods are taken to take photos of the rice grains to ensure that the outline of the rice grains is clear and its characteristics fill the field of view. Secondly, denoise the rice grain image to prevent image noise from submerging the rice grain characteristics. Thirdly, input the preprocessed image into the convolutional neural network model to realize the marking of the contour area of ​​the rice grain and calculate the minimum area of ​​the contour marking of the rice grain. Finally, set the threshold value of the rice grain type area division, and realize the classification of whole rice, broken rice and sticky rice through the output layer.
[0057] Optionally, the softmax layer of the convolutional neural network is used to determine whether the area of ​​the contour area of ​​each grain of rice is greater than or equal to an area threshold, wherein the grains of which the area of ​​the contour area is greater than or equal to the area threshold are whole rice.
[0058] The output layer is the softmax layer, and the softmax classification function is used to classify the output results of the fully connected layer to realize the division of whole rice, broken rice and bonded rice. When the area of ​​the contour area is greater than or equal to the area threshold and within a certain range, it indicates that the rice grain is a whole rice. Only whole rice has the meaning of calculating embryo retention rate.
[0059] Optionally, dividing the contour area of ​​the whole meter, and comparing the areas of different divided regions to determine whether the rice grains are embryonic rice, includes: dividing the contour area of ​​the whole meter equally by using the quartet method to obtain four areas with the same area. Areas; by comparing the area differences of the four areas, determine whether the rice grains are embryonic rice.
[0060] In an alternative solution, the shape of the rice grain is considered to be approximately elliptical, and the above-mentioned quarter method can be divided along the plane where the two symmetry axes of the rice grain are located, and the whole rice is divided into four regions. By comparing the difference between the projected area or total area of ​​the four regions, it is judged whether the rice grain is embryonic rice.
[0061] Optionally, among the four regions, if there is no difference between the area value of any one of the regions and the area values ​​of the other three regions, the rice grains are determined to be embryonic rice.
[0062] The outline of the whole meter is divided into 4 parts and then judged. If the area of ​​several areas is not much different, it means that the rice grain is embryonic rice. If the area of ​​one area is obviously different from the area of ​​other areas, it means that the rice grain has no embryo and is not embryonic rice.
[0063] Optionally, after determining whether the rice grains are embryonic rice, the method further includes: cyclically determining the types of all rice grains in the rice grain image, and calculating the embryo retention rate of the rice grains by determining the number of embryonic rice in the rice grain image; The relationship model between embryo rate and corresponding cooking mode.
[0064] In an optional solution, the above-mentioned cooking mode may be the time of rice soaking, heating, boiling, braising and keeping warm, which may be stored in the memory of the rice cooker in the form of a graph. The above-mentioned relationship model may be the corresponding relationship between the embryo retention rate of rice grains and the cooking mode, or may be stored in the memory of the rice cooker in advance.
[0065] In the same way, determine whether each whole rice is embryonic rice or not, and then calculate the embryonic embryo rate. Due to the slightly different cooking methods between embryonic rice and ordinary rice, in order to cook more sweet and delicious rice grains, selecting the cooking mode according to the embryonic embryo rate is an important application of deep learning algorithms to detect the embryonic rice embryonic rate. Therefore, after the embryo retention rate of the rice grains is obtained, the best cooking mode is selected according to the relationship curve between the overall embryo retention rate and the corresponding cooking mode, which provides a healthier cooking method with higher nutritional value.
[0066] image 3 It is a flowchart for selecting embryo retention rate and cooking mode according to the embodiment of the application. Such as image 3 As shown, the classification results of the rice grain types are output from the convolutional neural network model, the contour area of ​​all the whole meters is extracted, and the area quarter method is used to evenly divide the edge rectangular area of ​​the contour area. By calculating the area value of the four areas and comparing the four Whether there is a significant difference between the area of ​​one of them and the other three, judge whether it is embryonic rice, and then traversely calculate the embryonic rate of the whole rice grain, and give the corresponding relationship between the overall embryonic rate and the cooking mode, according to the corresponding relationship Choose the best cooking mode. The intelligent and humanized cooking mode greatly facilitates people's life needs and improves the pursuit of quality of life.
[0067] Optionally, after obtaining the relationship model between the embryo retention rate of the rice grains and the corresponding cooking mode, the method further includes: acquiring an image of the rice grains to be cooked; and obtaining the overall embryo retention rate of the rice grains to be cooked based on the image of the rice grains to be cooked: Based on the overall embryo retention rate of the rice grains to be cooked, the corresponding rice cooking mode is matched from the relation model; the rice cooking equipment is controlled to work according to the matching cooking mode.
[0068] In an optional solution, the above-mentioned rice grains to be cooked are rice grains used when the user is about to cook rice.
[0069] Figure 4 It is an overall flow chart of matching the embryo retention rate and the cooking mode according to the embodiment of the application. Such as Figure 4 As shown, the overall flow chart can be divided into three modules: convolutional neural network model, the corresponding relationship between embryo retention rate and cooking mode, and intelligent matching of cooking mode. Input the rice grain image into the convolutional neural network model, calculate the area of ​​each contour area through the full mark of the contour area, compare it with the set area threshold, and finally output the whole rice, broken rice and glued rice from the softmax layer Types of. Contour clustering detects the embryo retention rate. First, extract the contour area of ​​the entire meter, and use the area quadrant method to divide the contour of the entire meter equivalently to compare the differences between the areas to determine whether the entire meter is embryonic rice. After rice, calculate the embryo retention rate. Finally, through the correlation curve diagram between the embryo retention rate and the cooking mode, the best cooking mode is intelligently selected, so that the cooked rice grains are more fragrant and delicious, and the user pursues high-quality nutritional value. For users, they only need to extract samples from the rice to be cooked, and the cooking appliance can work according to the matching cooking mode, so that the nutritional value of the rice to be cooked can be optimally eaten, which greatly improves user satisfaction.
[0070] Optionally, the above method for identifying embryonic rice is applied to a cooking appliance, which may include a heating component, a timing module, a decision-making module, a display module, a communication module, and an alarm module.
[0071] Optionally, after the convolutional neural network model is used to identify the rice grain image and determine the type of rice grain in the rice grain image, the method further includes: the decision-making module determines the cooking data according to the set cooking data and the type of food, where the cooking data is at least Including: heating data of heating resistance, exhaust time of exhaust valve and heating temperature of different cooking stages; control cooking appliance to cook food based on cooking data.
[0072] In an optional solution, the decision-making module has an executive mechanism, such as a heating resistor, a timing module, etc. The cooking data set above may be the cooking data preset by the user, such as taste and preference (soft, moderate, hard, porridge, soup, etc. modes).
[0073] The decision module automatically selects the cooking method according to the type of food output by the convolutional neural network model, combined with user preferences, such as soaking time, heating temperature of heating resistor, heating time, exhaust time of exhaust valve, exhaust valve Opening degree and holding time, etc., in order to obtain the best cooking method, to ensure the taste of the food, and to ensure that the nutrition will not be lost.
[0074] Optionally, in the process of controlling the cooking appliance to cook the food based on the cooking data, the method further includes: detecting the steam data of the exhaust port of the exhaust valve through the temperature and humidity sensor; the decision module is based on the steam data detected by the temperature and humidity sensor , Obtain feedback information, where the feedback information is used to trigger the steam recovery mechanism to start working.
[0075] In an optional solution, the above-mentioned temperature and humidity sensor may be a sensor with waterproof and high temperature resistance functions.
[0076] It should be noted that only when the steam data exceeds a certain threshold can the wind wheel rotate. Therefore, when the steam data detected by the temperature and humidity sensor is greater than the steam data threshold, the decision-making module sends feedback information to trigger the steam recovery mechanism to start working.
[0077] Optionally, before the decision-making module determines the cooking data according to the set cooking data and the type of food, the method further includes: the decision-making module receives the type of food in the food image transmitted by the communication module, and receives the information received by the external interactive interface Cooking data.
[0078] In an optional solution, the aforementioned communication module may be a wired communication module or a wireless communication module, such as a wifi module. The above-mentioned external interaction interface may be a display panel provided on the outer surface of the cooking appliance, or may be a remote control.
[0079] In the actual cooking process, the food type identified by the convolutional neural network is transmitted to the decision-making module through the communication module. The decision-making module can select the best cooking data by combining the cooking data and the type of food preset by the user.
[0080] Optionally, the communication module is also used to receive an update instruction transmitted by the remote server, where the update instruction is used to upgrade the function of the cooking appliance.
[0081] The rice cooker with the same function is bound to not meet the increasing demand of users. When new functions are developed, the server can transmit the new version of the running program to the rice cooker through the communication module to realize remote update and make the service effect more ideal.
[0082] Obtain the rice grain image through the above scheme; use the convolutional neural network model to identify the rice grain image and determine the type of rice grain in the rice grain image. The types of rice grains include at least: whole rice, broken rice and bonded rice; obtain the whole rice in the rice image Contour area: Divide the contour area of ​​the whole meter, and determine whether the rice grains are embryonic rice by comparing the areas of different divided areas. Compared with the prior art, the above scheme is based on artificial intelligence technology, uses CNN in the deep learning algorithm to distinguish and recognize whole rice, broken rice and sticky rice, and detects embryo retention rate through contour clustering, avoiding traditional methods of detecting embryo retention rate. Factor interference improves the classification accuracy and speed, and indirectly improves the accuracy of the subsequent detection of embryo retention rate, thereby solving the technical problems of low accuracy and slow detection speed in identifying whether rice grains are embryonic rice in the prior art. At the same time, the cooking mode is automatically selected to provide users with the best cooking mode and improve the quality of life.

Example Embodiment

[0083] Example 2
[0084] According to an embodiment of the present invention, a device for identifying embryonic rice is provided, Figure 5 It is a schematic diagram of a device for identifying embryonic rice according to an embodiment of the present application. Such as Figure 5 As shown, the device 500 includes:
[0085] The first acquisition module 502 is used to acquire rice grain images.
[0086] The first determining module 504 is configured to use a convolutional neural network model to identify rice grain images and determine the types of rice grains in the rice grain images. The types of rice grains include at least whole rice, broken rice, and bonded rice.
[0087] The second obtaining module 506 is used to obtain the contour area of ​​the whole rice in the rice grain image.
[0088] The second determining module 508 is used to divide the contour area of ​​the whole rice, and determine whether the rice grains are embryonic rice by comparing the areas of different divided regions.
[0089] Optionally, the first determining module includes: an extraction module, used to extract the contour area of ​​each rice grain from the rice grain image; a calculation module, used to calculate the area area of ​​the contour area of ​​each rice grain; The area of ​​the contour area of ​​each rice grain is compared with the area threshold to determine the type of each rice grain in the rice grain image.
[0090] Optionally, the extraction module includes: a scanning module for scanning the image area corresponding to each rice grain in the rice grain image through each convolution kernel in the convolutional layer of the convolutional neural network to obtain the rice grains contained in each image area The feature layer of the; pooling module, used to de-redundate the feature layer of the rice grains contained in each image area through the pooling layer of the convolutional neural network; the conversion module, used to pass the convolutional neural network At least one fully connected layer converts the multiple feature layers after de-redundancy processing to obtain the image feature of each rice grain; the marking module is used to obtain the contour area of ​​each rice grain by marking the image feature of each rice grain.
[0091] Optionally, the comparison module includes: a comparison sub-module for judging whether the area of ​​the contour area of ​​each rice grain is greater than or equal to an area threshold through the softmax layer of the convolutional neural network, wherein the area of ​​the contour area is greater than or equal to The rice grain of the area threshold is the whole rice.
[0092] Optionally, the second determination module includes: a division module, which is used to divide the contour area of ​​a whole meter by the quarter method to obtain four areas with the same area; a comparison module, which is used to compare the area differences of the four areas , To determine whether the rice grains are embryonic rice.
[0093] Optionally, among the four regions, if there is no difference between the area value of any one of the regions and the area values ​​of the other three regions, the rice grains are determined to be embryonic rice.
[0094] Optionally, the device further includes: a embryo retention rate calculation module, which is used to determine the type of all rice grains in the rice image in a loop after determining whether the rice grains are embryonic rice, and calculate the number of embryonic rice in the rice image Embryo retention rate; corresponding module, used to obtain the relationship model between the embryo retention rate of rice grains and the corresponding cooking mode.
[0095] Optionally, the device further includes: a third acquisition module for acquiring an image of the rice grains to be cooked after acquiring the relationship model between the embryo retention rate of the rice grains and the corresponding cooking mode; The image of the rice grains to obtain the overall embryo retention rate of the rice grains to be cooked: the matching module is used to match the overall embryo retention rate of the rice grains to be cooked to obtain the corresponding cooking mode from the relationship model; the control module is used to control the cooking equipment Work according to the matching cooking mode.
[0096] It should be noted that, for alternative or preferred implementations of this embodiment, reference may be made to the related description in Embodiment 1, but is not limited to the content disclosed in Embodiment 1, and will not be repeated here.

Example Embodiment

[0097] Example 3
[0098] According to an embodiment of the present invention, a storage medium is provided, the storage medium includes a stored program, wherein the device where the storage medium is located is controlled to execute the method for identifying embryonic rice in Embodiment 1 while the program is running.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.

Similar technology patents

Ground wire monitoring method and device

InactiveCN108109332AImprove monitoring efficiencylow resolution accuracy
Owner:STATE GRID BEIJING ELECTRIC POWER +1

Stripe three-dimensional imaging calibration method and system

PendingCN112857260Aimprove accuracylow resolution accuracy
Owner:CHENGDU TIEAN SCI & TECH

Chinese word segmentation method and device

InactiveCN108763200AImprove word segmentation accuracylow resolution accuracy
Owner:DATAGRAND TECH INC

Case judgment result obtaining method and system

PendingCN110858353Aimprove accuracylow resolution accuracy
Owner:ALIBABA GRP HLDG LTD

Carrier network link packet loss rate reasoning method based on service characteristics

ActiveCN113285835Alow resolution accuracy
Owner:GUANGDONG POWER GRID CO LTD +1
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products