CN112116008B - Processing method of target detection model based on intelligent decision and related equipment thereof - Google Patents
Processing method of target detection model based on intelligent decision and related equipment thereof Download PDFInfo
- Publication number
- CN112116008B CN112116008B CN202010990029.4A CN202010990029A CN112116008B CN 112116008 B CN112116008 B CN 112116008B CN 202010990029 A CN202010990029 A CN 202010990029A CN 112116008 B CN112116008 B CN 112116008B
- Authority
- CN
- China
- Prior art keywords
- target detection
- model parameters
- detection model
- model
- central server
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 300
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 89
- 239000002131 composite material Substances 0.000 claims abstract description 86
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000003860 storage Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application belongs to the field of artificial intelligence, and relates to a target detection model processing method, a device, computer equipment and a storage medium based on intelligent decision, wherein the method comprises the following steps: training an initial multi-target detection model according to the acquired local data set to obtain a relay multi-target detection model; calculating composite model parameters according to the generated additional random numbers and model parameters of the relay multi-target detection model; transmitting the composite model parameters to a central server to instruct the central server to generate global model parameters according to the composite model parameters of each node; receiving global model parameters to update a relay multi-target detection model; and taking the updated relay multi-target detection model as an initial multi-target detection model for next training, and performing iterative training until the model converges to obtain the multi-target detection model. In addition, the present application relates to blockchain technology, wherein a local data set can be stored in a blockchain. The application improves the accuracy of target detection.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a processing method of a target detection model based on intelligent decision and relevant equipment thereof.
Background
With the development of artificial intelligence, the application of target detection in life and production is becoming wider and wider. The object detection involves a detection model in intelligent decision making, and an image can be input into the object detection model, processed by the object detection model and output the object in the image. For example, in a garbage classification application, garbage pictures may be first input into a target detection model to identify garbage, thereby guiding people to recycle and classify the identified garbage.
In the traditional target detection technology, the target detection model can only focus on a single target for detection during detection, and when the target detection model is trained, the target detection model is difficult to sufficiently train because the data volume of a local data set is usually limited, so that the detection accuracy of the target detection model is lower.
Disclosure of Invention
The embodiment of the application aims to provide a processing method, a processing device, computer equipment and a storage medium of a target detection model based on intelligent decision, so as to solve the problem of low detection accuracy of the target detection model.
In order to solve the above technical problems, an embodiment of the present application provides a processing method of a target detection model based on intelligent decision, where the target detection model is a multi-target detection model, and the following technical scheme is adopted:
Acquiring a local data set and an initial multi-target detection model;
training the initial multi-target detection model according to the local data set to obtain a relay multi-target detection model;
Generating an additional random number, and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-target detection model;
Transmitting the composite model parameters to a central server to instruct the central server to generate global model parameters according to the composite model parameters of each node;
Receiving the global model parameters from the central server to update the relay multi-objective detection model;
And taking the updated relay multi-target detection model as an initial multi-target detection model for next training, and performing iterative training until the model converges to obtain the multi-target detection model.
Further, before the step of obtaining the local dataset and the initial multi-objective detection model, the method further comprises:
Acquiring global model parameters from a central server;
and constructing an initial multi-target detection model according to the global model parameters.
Further, the step of training the initial multi-target detection model according to the local data set to obtain a relay multi-target detection model includes:
Inputting the target image in the local data set into the initial multi-target detection model to obtain a target prediction result;
Determining a prediction error according to the target prediction result and the image tag in the local dataset;
Performing parameter adjustment on the initial multi-target detection model based on the prediction error;
And taking the initial multi-target detection model after parameter adjustment as an initial multi-target detection model for next training to carry out iterative training until the iteration times reach a preset value, thereby obtaining the relay multi-target detection model.
Further, the step of generating an additional random number and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-objective detection model includes:
generating an additional random number; wherein, the added random numbers generated by each node in the alliance network are zero;
and carrying out linear operation on the generated additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters.
Further, the step of sending the composite model parameters to a central server to instruct the central server to generate global model parameters according to the composite model parameters of each node includes:
communicating with a central server to determine an encryption key;
encrypting the composite model parameters according to the encryption key to obtain encryption model parameters;
And sending the encryption model parameters to the central server to instruct the central server to decrypt the encryption model parameters of each node, and operating according to the composite model parameters obtained after decryption to generate global model parameters.
Further, after the step of iteratively training the updated relay multi-target detection model as the initial multi-target detection model of the next training until the model converges to obtain the multi-target detection model, the method further includes:
Acquiring an image to be detected;
Inputting the image to be detected into the multi-target detection model to obtain a target object in the image to be detected;
And displaying the detected target object.
Further, after the step of displaying the detected target object, the method further includes:
When a triggered calibration instruction is received, a calibration information input page is displayed;
Acquiring an image to be calibrated and calibration indication information input in the calibration information input page;
Generating a calibration data set according to the image to be calibrated and the calibration indication information;
and performing calibration training on the multi-target detection model through the calibration data set.
In order to solve the above technical problems, the embodiment of the present application further provides a processing device for a target detection model based on intelligent decision, where the target detection model is a multi-target detection model, and the following technical scheme is adopted:
The acquisition module is used for acquiring a local data set and an initial multi-target detection model;
The model training module is used for training the initial multi-target detection model according to the local data set to obtain a relay multi-target detection model;
The parameter calculation module is used for generating an additional random number and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-target detection model;
the parameter sending module is used for sending the composite model parameters to a central server so as to instruct the central server to generate global model parameters according to the composite model parameters of each node;
A model updating module for receiving the global model parameters from the central server to update the relay multi-objective detection model;
and the iterative training module is used for carrying out iterative training by taking the updated relay multi-target detection model as an initial multi-target detection model for next training until the model converges to obtain the multi-target detection model.
In order to solve the above technical problems, an embodiment of the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the above processing method for an intelligent decision-based object detection model when executing the computer program.
In order to solve the above technical problem, an embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the method for processing an object detection model based on intelligent decision.
Compared with the prior art, the embodiment of the application has the following main beneficial effects: firstly training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model; generating an additional random number, wherein the additional random number is used for calculating the model parameters of the relay multi-target detection model so as to encrypt the model parameters; the encrypted parameters conforming to the model are sent to a central server in the alliance network, the central server generates global model parameters according to the composite model parameters of all the nodes, and the global model parameters are sent to the terminal to update the relay multi-target detection model and perform iterative training; the global model parameters are obtained on the basis of the local data sets of the terminals, the characteristics of a plurality of local data sets are fused, the multi-target detection model is trained by using a larger-scale data set on the basis of protecting the local data sets, and the accuracy of the multi-target detection model obtained after the training is finished is improved.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method of intelligent decision-based object detection model processing in accordance with the present application;
FIG. 3 is a schematic diagram of one embodiment of an intelligent decision-based object detection model processing device in accordance with the present application;
FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminals 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminals 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 105 via the network 104 using the terminals 101, 102, 103 to receive or send messages or the like. The terminals 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, and the like.
Terminals 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture ExpertsGroup Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving PictureExperts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminals 101, 102, 103.
It should be noted that, the processing method of the target detection model based on the intelligent decision provided by the embodiment of the application is generally executed by the terminal, and correspondingly, the processing device of the target detection model based on the intelligent decision is generally arranged in the terminal.
It should be understood that the number of terminals, networks and servers in fig. 1 is merely illustrative. There may be any number of terminals, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of a method of processing an intelligent decision-based object detection model in accordance with the present application is shown. The target detection model is a multi-target detection model, and the processing method of the target detection model based on intelligent decision comprises the following steps:
Step S201, a local data set and an initial multi-objective detection model are acquired.
In this embodiment, the electronic device (for example, the terminal shown in fig. 1) on which the processing method of the target detection model based on the intelligent decision is running may communicate with other terminals or servers through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.
Wherein the local data set may be a data set stored in the terminal; the initial multi-target detection model may be an initial multi-target detection model.
Specifically, an application program for target detection may be installed in the terminal, and when the application program is started, the terminal loads an initial multi-target detection model located locally and acquires a local data set stored in the terminal.
The application uses the multi-target detection model, and the multi-target detection model can detect a plurality of targets at one time, thereby improving the efficiency of target detection. In one embodiment, the multi-objective detection model may be a RETINANET network.
The multi-target detection model is a lightweight model, can be deployed in various terminals besides a server, and a holder of the terminal can expand a local data set according to own needs, for example, the local data set can be expanded by photographing or acquiring images from the Internet, so that the expansion difficulty of the local data set is reduced, and the data volume of the local data set is enriched.
In one embodiment, the processing method of the intelligent decision-based object detection model may also be performed by a server that loads the initial multi-object detection model and obtains a local data set. After the training of the server is completed, a target detection interface is provided, and a user can call the target detection interface at the terminal to carry out target detection.
It is emphasized that to further guarantee the privacy and security of the local data set, the local data set may also be stored in a node of a blockchain.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Step S202, training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model.
Specifically, the terminal trains an initial multi-target detection model according to the local data set, and stops training when the training stopping condition is met, so as to obtain a relay multi-target detection model. The training stop condition may be that the number of iterations in training reaches a preset value, or that the prediction error obtained in training is smaller than a preset error threshold.
The relay multi-target detection model obtained by the terminal can be convergent or non-convergent.
Step S203, generating an additional random number, and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-target detection model.
The additional random number may be a parameter for implementing an encryption function on the model parameter of the relay multi-target detection model.
Specifically, the terminal performs federal learning, and the terminal may be a node in the federation network. Each node in the coalition network generates an additional random number, and the added value of the obtained additional random number is zero. The terminal extracts the model parameters of the relay multi-target detection model, and calculates the additional random number and the model parameters to obtain composite model parameters so as to protect the data privacy of the model parameters of the local relay multi-target detection model.
Step S204, the composite model parameters are sent to the central server to instruct the central server to generate global model parameters according to the composite model parameters of each node.
The central server can be a server playing a role in central control in federal learning and is used for indicating each node to perform federal learning.
Specifically, the terminal transmits the composite model parameters to the central server. After the central server receives the composite model parameters of each node, the central server may perform a linear operation on the composite model parameters of each model, and in one embodiment, the central server averages the composite model parameters of each model to obtain global model parameters.
In step S205, global model parameters are received from the central server to update the relay multi-objective detection model.
Specifically, the central server sends global model parameters to each node. And after the terminal receives the global model parameters, updating the local relay multi-target detection model according to the global model parameters, and particularly replacing the model parameters in the relay multi-target detection model with the global model parameters.
And S206, performing iterative training by taking the updated relay multi-target detection model as an initial multi-target detection model of next training until the model converges to obtain the multi-target detection model.
Specifically, after the terminal completes updating the relay multi-target detection model, the relay multi-target detection model is used as an initial multi-target detection model, training is continuously performed on the obtained initial multi-target detection model according to the local data set, namely, the steps S202 to S206 are iterated until the model converges, and the terminal stops training to obtain the multi-target detection model. The condition for model convergence may be that the prediction error obtained in training is smaller than a preset error threshold.
In one embodiment, gradient information is communicated between the terminal and the central server. And the terminal calculates the model gradient of the additional random number and the relay multi-target detection model to obtain a conforming model gradient, and sends the conforming model gradient to the central server. The central server accumulates the gradient of the coincidence model, then averages the gradient, and sends the average value to each node as the global average gradient to update the relay multi-target detection model.
In one embodiment, when each node in the alliance network realizes model convergence, each node stops training, and the relay multi-target detection model when the training is stopped is used as the multi-target detection model of each node.
In the embodiment, training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model; generating an additional random number, wherein the additional random number is used for calculating the model parameters of the relay multi-target detection model so as to encrypt the model parameters; the encrypted parameters conforming to the model are sent to a central server in the alliance network, the central server generates global model parameters according to the composite model parameters of all the nodes, and the global model parameters are sent to the terminal to update the relay multi-target detection model and perform iterative training; the global model parameters are obtained on the basis of the local data sets of the terminals, the characteristics of a plurality of local data sets are fused, the multi-target detection model is trained by using a larger-scale data set on the basis of protecting the local data sets, and the accuracy of the multi-target detection model obtained after the training is finished is improved.
Further, the step S201 may further include: acquiring global model parameters from a central server; and constructing an initial multi-target detection model according to the global model parameters.
Specifically, the terminal needs to be initialized before training. At initialization, the terminal receives global model parameters from the central server, and the global model parameters obtained at this time are initialized global model parameters, for example, may be randomly generated by the central server. The terminal replaces the model parameters stored in the local multi-target detection model with the obtained global model parameters, so that an initial multi-target detection model is obtained.
In this embodiment, the terminal constructs an initial multi-target detection model according to the global model parameters issued by the central server, so as to implement model initialization.
Further, the step S202 may include: inputting a target image in a local data set into an initial multi-target detection model to obtain a target prediction result; determining a prediction error according to the target prediction result and the image tag in the local dataset; parameter adjustment is carried out on the initial multi-target detection model based on the prediction error; and taking the initial multi-target detection model after parameter adjustment as an initial multi-target detection model for next training to carry out iterative training until the iteration times reach a preset value, thereby obtaining the relay multi-target detection model.
Wherein the target image may be an image about the target object.
Specifically, the terminal extracts a target image and an image tag from the local data set respectively, and inputs the target image into an initial multi-target detection model to obtain a target prediction result. And the terminal calculates a prediction error according to the target prediction result and the image label, and adjusts model parameters in the initial multi-target detection model by taking the prediction error as a target.
And the terminal carries out iterative training on the initial multi-target detection model after parameter adjustment according to the local data set, and once the terminal adjusts the model parameters, the terminal realizes one iteration until the iteration times reach a preset value, and the terminal stops the iteration to obtain the relay multi-target detection model.
In one embodiment, the terminal calculates the prediction error using a Focal Loss function, which is as follows:
Where y is the image label and γ is the adjustment factor.
In this embodiment, the initial multi-target detection model is subjected to iterative training for a preset number of times according to the target image and the image tag in the local data set, so as to obtain a relay multi-target detection model, and the relay multi-target detection model is used for federal learning, so that the realization of federal learning is ensured.
Further, the step S203 may include: generating an additional random number; wherein, the added random numbers generated by each node in the alliance network are zero; and carrying out linear operation on the generated additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters.
Specifically, the terminal generates an additional random number. The terminal is a node in the alliance network, each node in the alliance network generates an additional random number, and the added value of the additional random numbers of each node is zero. And the terminal extracts the model parameters of the relay multi-target detection model, and performs linear operation on the model parameters and the generated additional random numbers to obtain the composite model parameters. The composite model parameters are different from the model parameters of the relay multi-target detection model, and can play a role in data confidentiality of the relay multi-target detection model.
In one embodiment, the terminal performs addition and subtraction operation on the generated additional random number and the model parameters of the relay multi-target detection model, and the generated composite model parameters are as follows:
wherein omega k is a model parameter of the relay multi-target detection model, S uv is an additional random number, K is a set of all nodes in the alliance network, u and v represent nodes in the alliance network and are elements in K.
In this embodiment, after generating the additional random number, the additional random number and the model parameter of the relay multi-target detection model are subjected to linear operation to obtain the composite model parameter, so as to encrypt the data of the model parameter.
Further, the step S204 may include: communicating with a central server to determine an encryption key; encrypting the composite model parameters according to the encryption key to obtain encryption model parameters; and sending the encryption model parameters to a central server to instruct the central server to decrypt the encryption model parameters of each node, and operating according to the composite model parameters obtained after decryption to generate global model parameters.
The encryption key may be a key used to encrypt the composite model parameters.
Specifically, the terminal may communicate with the central server in advance, and determine the encryption key with the central server based on DH key Exchange protocol/algorithm (Diffie-Hellman key Exchange protocol/algorithm, diffie-HELLMAN KEY Exchange/AGREEMENT ALGORITHM, which may enable both parties requiring secure communication to determine the shared key by the method).
When the terminal sends the composite model parameters to the central server, the composite model parameters can be encrypted according to the encryption key to obtain the encryption model parameters, and the encryption model parameters are sent to the central server, so that the privacy security of data in communication with the central server is ensured.
After the central server obtains the encryption model parameters of each node, the encryption model parameters are decrypted according to the decryption key, and the composite model parameters of each node are obtained. The central server performs addition operation on the composite model parameters of each node, so that the additional random numbers in each group of composite model parameters are zeroed, namely:
wherein omega k is a model parameter of the relay multi-target detection model, K is a set of all nodes in the federated network, which is a composite model parameter.
And the central server performs weighted linear operation on the composite model parameters to obtain global model parameters.
When the global model parameters are calculated, the weights of all groups of composite model parameters can be the same or different; when not identical, the central server may calculate global model parameters based on the FedAvg secure aggregation algorithm, as follows:
Wherein ω k is a model parameter of the relay multi-target detection model, ω is a global model parameter, n k is a data amount of a kth node, n is a total data amount of each node in the federation network, K is a set of all nodes in the federation network, K represents the kth node, and t represents the t-th update.
In the embodiment, the composite model parameters are encrypted according to the encryption key to obtain the encryption model parameters so as to further protect the data privacy in federal learning; after the encryption model parameters are sent to the central server, the central server decrypts the encryption model parameters, and generates global model parameters according to the composite model parameters obtained after decryption, wherein the global model parameters are used for updating the relay multi-target detection model in each node, so that the realization of federal learning is ensured.
Further, the step S206 may further include: acquiring an image to be detected; inputting the image to be detected into a multi-target detection model to obtain a target object in the image to be detected; and displaying the detected target object.
The image to be detected can be an image used for inputting a multi-target detection model for target detection.
Specifically, when the multi-target detection model is applied, a user can operate the terminal, collect an image to be detected through an image collecting device of the terminal, or select an image stored in the terminal as the image to be detected, and instruct the terminal to perform target detection on the image to be detected.
The terminal inputs the image to be detected into a multi-target detection model, processes the image to be detected through the multi-target detection model, identifies a target object in the image to be detected, and displays the target object through a screen. When the target object is displayed, the multi-target detection model can add a detection frame and an object description to the target object, the object description is used for displaying the category of the target object, and the detection frame can select different colors according to the category of the target object so as to display the information of the target object more clearly.
In one embodiment, when the user clicks on the presented target object, the terminal may also present an introduction of the category target object and related information. For example, when the multi-target detection model is applied to garbage classification, the terminal can display the garbage articles in the image to be detected, the user clicks the detected garbage articles, the terminal can introduce the garbage classification to which the garbage articles belong, and provide classification suggestions of the garbage articles of the classification so that the user can perform garbage classification better.
In the embodiment, the multi-target detection model for performing target detection on the image to be detected is obtained through federal learning, and a rich data set is used for training in federal learning, so that the accuracy of target detection is improved.
Further, after the displaying the detected target object, the method may further include: when a triggered calibration instruction is received, a calibration information input page is displayed; acquiring an image to be calibrated and calibration indication information input in a calibration information input page; generating a calibration data set according to the image to be calibrated and the calibration indication information; and performing calibration training on the multi-target detection model through the calibration data set.
Specifically, the terminal provides a model calibration function, and when the user considers that the detection result of the multi-target detection model is inaccurate, a virtual calibration button in the display page can be clicked to trigger a calibration instruction. After receiving the calibration instruction, the terminal displays a calibration information input page and instructs a user to input an image to be calibrated and calibration instruction information in the calibration information input page. The terminal can also directly take the image to be detected in target detection as an image to be calibrated. The user can input words, describe the position, shape, color, size, name and other information of the target object, or directly encircle the target object in the image to be calibrated in a mode of identifying a frame through a screen, so as to obtain calibration indication information.
The terminal generates a calibration data set according to the image to be calibrated and the calibration indication information, wherein the calibration data set comprises the image to be calibrated and the corresponding image tag, and the calibration data set is used for carrying out calibration training on the multi-target detection model so as to improve the detection accuracy of the multi-target detection model.
The terminal can perform calibration training on the multi-target detection model only locally; the multi-target detection model can be immediately calibrated and trained in a federal learning mode; the multi-target detection model can be trained in a federal learning mode after the preset time or after the preset times of calibration training are locally carried out.
In this embodiment, when a calibration instruction is received, a calibration information input page is displayed, and a calibration data set is generated according to an image to be calibrated and calibration indication information input in the calibration information input page, so as to calibrate and train the multi-target detection model, thereby improving the accuracy of multi-target detection model detection.
The following describes the processing method of the intelligent decision-based object detection model according to the present application through a specific embodiment. Specifically, the terminal is provided with a garbage classification application, and a user can shoot garbage pictures through the terminal to expand a local data set. The terminal acquires global model parameters from the central server to obtain an initialized multi-target detection model. And training N rounds (N is an integer greater than zero) of the initialized multi-target detection model according to the local data set to obtain the relay multi-target detection model.
The terminal determines the key required for communication with the central server via the DH key exchange protocol. And the terminal generates an additional random number, and adds the additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters. And the terminal encrypts the composite model parameters by using the encryption key to obtain encryption model parameters, and sends the encryption model parameters to the central server.
The central server decrypts the encryption model parameters to obtain composite model parameters of each node, and the composite model parameters are added to eliminate the influence of the additional random number. The central server may calculate global model parameters according to the security aggregation algorithm of FedAvg, and issue the global model parameters to each node, so that each node updates the relay multi-target detection model according to the global model parameters.
And the terminal carries out iterative training on the updated relay multi-target detection model according to the local data set until the model converges to obtain the multi-target detection model.
When the method is applied, a user can shoot the garbage articles through the terminal to obtain an image to be detected, and the multi-target detection image can identify a plurality of garbage articles in the image to be detected at one time and display the identified garbage articles. When the garbage articles are displayed, the garbage articles can be marked by the detection frames, and the types of the garbage articles are displayed, for example, the garbage articles are recyclable or harmful garbage, and different kinds of garbage articles can be distinguished by using the detection frames with different colors.
When the user considers that the target detection is accurate, namely the garbage classification is correct, the user can click on the detected garbage articles, the terminal introduces the garbage articles of the type and displays garbage classification description, so that the user can better classify the garbage.
When the user considers that the target detection is inaccurate, namely the garbage classification is wrong, the virtual calibration button can be clicked, an image which is considered to be inaccurate in detection by the user is uploaded on the calibration information input page to serve as an image to be calibrated, explanatory characters are input to serve as calibration indication information, and the terminal carries out calibration training on the multi-target detection model according to the image to be calibrated and the calibration indication information.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an object detection model processing apparatus based on intelligent decision, where the object detection model is a multi-object detection model, and the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 3, the processing apparatus 300 of the intelligent decision-based object detection model according to the present embodiment includes: an acquisition module 301, a model training module 302, a parameter calculation module 303, a parameter transmission module 304, a model updating module 305, and an iterative training module 306, wherein:
An acquisition module 301 is configured to acquire a local data set and an initial multi-target detection model.
The model training module 302 is configured to train the initial multi-target detection model according to the local data set, so as to obtain a relay multi-target detection model.
The parameter calculation module 303 is configured to generate an additional random number, and calculate a composite model parameter according to the additional random number and the model parameter of the relay multi-objective detection model.
The parameter sending module 304 is configured to send the composite model parameter to the central server, so as to instruct the central server to generate a global model parameter according to the composite model parameter of each node.
The model update module 305 is configured to receive global model parameters from the central server to update the relay multi-objective detection model.
And the iterative training module 306 is configured to perform iterative training with the updated relay multi-target detection model as an initial multi-target detection model for next training until the model converges, so as to obtain a multi-target detection model.
In the embodiment, training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model; generating an additional random number, wherein the additional random number is used for calculating the model parameters of the relay multi-target detection model so as to encrypt the model parameters; the encrypted parameters conforming to the model are sent to a central server in the alliance network, the central server generates global model parameters according to the composite model parameters of all the nodes, and the global model parameters are sent to the terminal to update the relay multi-target detection model and perform iterative training; the global model parameters are obtained on the basis of the local data sets of the terminals, the characteristics of a plurality of local data sets are fused, the multi-target detection model is trained by using a larger-scale data set on the basis of protecting the local data sets, and the accuracy of the multi-target detection model obtained after the training is finished is improved.
In some optional implementations of the present embodiment, the processing apparatus 300 of the intelligent decision-based object detection model further includes: the system comprises a parameter acquisition module and a model construction module, wherein:
And the parameter acquisition module is used for acquiring the global model parameters from the central server.
And the model construction module is used for constructing an initial multi-target detection model according to the global model parameters.
In this embodiment, the terminal constructs an initial multi-target detection model according to the global model parameters issued by the central server, so as to implement model initialization.
In some alternative implementations of the present embodiment, model training module 302 includes: the system comprises an image input sub-module, an error determination sub-module, a parameter adjustment sub-module and an iterative training sub-module, wherein:
and the image input sub-module is used for inputting the target image in the local data set into the initial multi-target detection model to obtain a target prediction result.
And the error determination submodule is used for determining a prediction error according to the target prediction result and the image tag in the local data set.
And the parameter adjustment sub-module is used for carrying out parameter adjustment on the initial multi-target detection model based on the prediction error.
And the iterative training sub-module is used for carrying out iterative training by taking the initial multi-target detection model with the adjusted parameters as the initial multi-target detection model of the next training until the iteration times reach a preset value, so as to obtain the relay multi-target detection model.
In this embodiment, the initial multi-target detection model is subjected to iterative training for a preset number of times according to the target image and the image tag in the local data set, so as to obtain a relay multi-target detection model, and the relay multi-target detection model is used for federal learning, so that the realization of federal learning is ensured.
In some alternative implementations of the present embodiment, the parameter calculation module 303 includes: an additional generation sub-module and a parameter operation sub-module, wherein:
an additional generation sub-module for generating an additional random number; wherein the added random numbers generated by the nodes in the alliance network are zero.
And the parameter operation sub-module is used for carrying out linear operation on the generated additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters.
In this embodiment, after generating the additional random number, the additional random number and the model parameter of the relay multi-target detection model are subjected to linear operation to obtain the composite model parameter, so as to encrypt the data of the model parameter.
In some optional implementations of the present embodiment, the parameter sending module 304 includes: the system comprises a key determination submodule, a parameter encryption submodule and a parameter sending submodule, wherein:
The key determination submodule is used for communicating with the central server to determine the encryption key.
And the parameter encryption sub-module is used for encrypting the composite model parameters according to the encryption key to obtain the encryption model parameters.
And the parameter sending sub-module is used for sending the encryption model parameters to the central server so as to instruct the central server to decrypt the encryption model parameters of each node, and calculating according to the composite model parameters obtained after decryption to generate global model parameters.
In the embodiment, the composite model parameters are encrypted according to the encryption key to obtain the encryption model parameters so as to further protect the data privacy in federal learning; after the encryption model parameters are sent to the central server, the central server decrypts the encryption model parameters, and generates global model parameters according to the composite model parameters obtained after decryption, wherein the global model parameters are used for updating the relay multi-target detection model in each node, so that the realization of federal learning is ensured.
In some optional implementations of the present embodiment, the processing apparatus 300 of the intelligent decision-based object detection model further includes: the system comprises an image acquisition module, an image input module and a target display module, wherein:
And the image acquisition module is used for acquiring the image to be detected.
The image input module is used for inputting the image to be detected into the multi-target detection model to obtain a target object in the image to be detected.
And the target display module is used for displaying the detected target object.
In the embodiment, the multi-target detection model for performing target detection on the image to be detected is obtained through federal learning, and a rich data set is used for training in federal learning, so that the accuracy of target detection is improved.
In some optional implementations of the present embodiment, the processing apparatus 300 of the intelligent decision-based object detection model further includes: the system comprises a page display module, a calibration acquisition module, a calibration generation module and a calibration training module, wherein:
and the page display module is used for displaying the calibration information input page when receiving the triggered calibration instruction.
The calibration acquisition module is used for acquiring the image to be calibrated and the calibration indication information which are input in the calibration information input page.
And the calibration generation module is used for generating a calibration data set according to the image to be calibrated and the calibration indication information.
And the calibration training module is used for performing calibration training on the multi-target detection model through the calibration data set.
In this embodiment, when a calibration instruction is received, a calibration information input page is displayed, and a calibration data set is generated according to an image to be calibrated and calibration indication information input in the calibration information input page, so as to calibrate and train the multi-target detection model, thereby improving the accuracy of multi-target detection model detection.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is generally used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of an object detection model processing method based on intelligent decision, and the like. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the intelligent decision-based object detection model processing method.
The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.
The computer device provided in this embodiment may execute the above-described target detection model processing method based on intelligent decision. The intelligent decision-based target detection model processing method may be the intelligent decision-based target detection model processing method of each of the above embodiments.
In the embodiment, training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model; generating an additional random number, wherein the additional random number is used for calculating the model parameters of the relay multi-target detection model so as to encrypt the model parameters; the encrypted parameters conforming to the model are sent to a central server in the alliance network, the central server generates global model parameters according to the composite model parameters of all the nodes, and the global model parameters are sent to the terminal to update the relay multi-target detection model and perform iterative training; the global model parameters are obtained on the basis of the local data sets of the terminals, the characteristics of a plurality of local data sets are fused, the multi-target detection model is trained by using a larger-scale data set on the basis of protecting the local data sets, and the accuracy of the multi-target detection model obtained after the training is finished is improved.
The present application also provides another embodiment, namely, a computer readable storage medium storing computer readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the intelligent decision-based object detection model processing method as described above.
In the embodiment, training an initial multi-target detection model according to a local data set to obtain a relay multi-target detection model; generating an additional random number, wherein the additional random number is used for calculating the model parameters of the relay multi-target detection model so as to encrypt the model parameters; the encrypted parameters conforming to the model are sent to a central server in the alliance network, the central server generates global model parameters according to the composite model parameters of all the nodes, and the global model parameters are sent to the terminal to update the relay multi-target detection model and perform iterative training; the global model parameters are obtained on the basis of the local data sets of the terminals, the characteristics of a plurality of local data sets are fused, the multi-target detection model is trained by using a larger-scale data set on the basis of protecting the local data sets, and the accuracy of the multi-target detection model obtained after the training is finished is improved.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (9)
1. The processing method of the target detection model based on intelligent decision is characterized by being applied to a terminal, wherein the target detection model is a multi-target detection model, and the method comprises the following steps of:
Acquiring a local data set and an initial multi-target detection model;
training the initial multi-target detection model according to the local data set to obtain a relay multi-target detection model;
Generating an additional random number, and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-target detection model;
The composite model parameters are sent to a central server to instruct the central server to generate global model parameters according to the composite model parameters of all the nodes, wherein the central server averages the composite model parameters of all the models to obtain the global model parameters; when the composite model parameters are sent to the central server, the composite model parameters are encrypted according to an encryption key to obtain encryption model parameters, and the encryption model parameters are sent to the central server; after obtaining the encryption model parameters of each node, the central server decrypts the encryption model parameters according to the decryption key to obtain the composite model parameters of each node; the central server performs addition operation on the composite model parameters of each node, so that the additional random numbers in each group of composite model parameters are zeroed; the central server performs weighted linear operation on the composite model parameters to obtain the global model parameters;
Receiving the global model parameters from the central server to update the relay multi-objective detection model;
performing iterative training by taking the updated relay multi-target detection model as an initial multi-target detection model of next training until the model converges to obtain the multi-target detection model;
The step of generating an additional random number and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-objective detection model comprises the following steps:
generating an additional random number; wherein, the added random numbers generated by each node in the alliance network are zero;
and carrying out linear operation on the generated additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters.
2. The method of intelligent decision-based object detection model processing of claim 1, wherein prior to the step of acquiring a local dataset and an initial multi-object detection model, the method further comprises:
Acquiring global model parameters from a central server;
and constructing an initial multi-target detection model according to the global model parameters.
3. The method of claim 1, wherein the step of training the initial multi-target detection model based on the local data set to obtain a relay multi-target detection model comprises:
Inputting the target image in the local data set into the initial multi-target detection model to obtain a target prediction result;
Determining a prediction error according to the target prediction result and the image tag in the local dataset;
Performing parameter adjustment on the initial multi-target detection model based on the prediction error;
And taking the initial multi-target detection model after parameter adjustment as an initial multi-target detection model for next training to carry out iterative training until the iteration times reach a preset value, thereby obtaining the relay multi-target detection model.
4. The method of claim 1, wherein the step of sending the composite model parameters to a central server to instruct the central server to generate global model parameters from the composite model parameters of each node comprises:
communicating with a central server to determine an encryption key;
encrypting the composite model parameters according to the encryption key to obtain encryption model parameters;
And sending the encryption model parameters to the central server to instruct the central server to decrypt the encryption model parameters of each node, and operating according to the composite model parameters obtained after decryption to generate global model parameters.
5. The method for processing the intelligent decision-based object detection model according to claim 1, wherein after the step of iteratively training the updated relay multi-object detection model as an initial multi-object detection model for next training until the model converges to obtain the multi-object detection model, the method further comprises:
Acquiring an image to be detected;
Inputting the image to be detected into the multi-target detection model to obtain a target object in the image to be detected;
And displaying the detected target object.
6. The method of claim 5, wherein after the step of presenting the detected target object, the method further comprises:
When a triggered calibration instruction is received, a calibration information input page is displayed;
Acquiring an image to be calibrated and calibration indication information input in the calibration information input page;
Generating a calibration data set according to the image to be calibrated and the calibration indication information;
and performing calibration training on the multi-target detection model through the calibration data set.
7. A processing device of an object detection model based on intelligent decision, which is applied to a terminal, wherein the object detection model is a multi-object detection model, and the device comprises:
The acquisition module is used for acquiring a local data set and an initial multi-target detection model;
The model training module is used for training the initial multi-target detection model according to the local data set to obtain a relay multi-target detection model;
The parameter calculation module is used for generating an additional random number and calculating composite model parameters according to the additional random number and the model parameters of the relay multi-target detection model;
The parameter sending module is used for sending the composite model parameters to a central server so as to instruct the central server to generate global model parameters according to the composite model parameters of all the nodes, wherein the central server averages the composite model parameters of all the models to obtain the global model parameters; when the composite model parameters are sent to the central server, the composite model parameters are encrypted according to an encryption key to obtain encryption model parameters, and the encryption model parameters are sent to the central server; after obtaining the encryption model parameters of each node, the central server decrypts the encryption model parameters according to the decryption key to obtain the composite model parameters of each node; the central server performs addition operation on the composite model parameters of each node, so that the additional random numbers in each group of composite model parameters are zeroed; the central server performs weighted linear operation on the composite model parameters to obtain the global model parameters;
A model updating module for receiving the global model parameters from the central server to update the relay multi-objective detection model;
The iterative training module is used for carrying out iterative training by taking the updated relay multi-target detection model as an initial multi-target detection model of next training until the model converges to obtain the multi-target detection model;
The parameter calculation module is also used for generating an additional random number; wherein, the added random numbers generated by each node in the alliance network are zero; and carrying out linear operation on the generated additional random number and the model parameters of the relay multi-target detection model to obtain composite model parameters.
8. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the method of processing an intelligent decision-based object detection model according to any of claims 1 to 6.
9. A computer readable storage medium, characterized in that it has stored thereon computer readable instructions, which when executed by a processor, implement the steps of the method for processing an intelligent decision based object detection model according to any of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010990029.4A CN112116008B (en) | 2020-09-18 | 2020-09-18 | Processing method of target detection model based on intelligent decision and related equipment thereof |
| PCT/CN2020/124439 WO2021174877A1 (en) | 2020-09-18 | 2020-10-28 | Processing method for smart decision-based target detection model, and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010990029.4A CN112116008B (en) | 2020-09-18 | 2020-09-18 | Processing method of target detection model based on intelligent decision and related equipment thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116008A CN112116008A (en) | 2020-12-22 |
| CN112116008B true CN112116008B (en) | 2024-07-05 |
Family
ID=73800792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010990029.4A Active CN112116008B (en) | 2020-09-18 | 2020-09-18 | Processing method of target detection model based on intelligent decision and related equipment thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112116008B (en) |
| WO (1) | WO2021174877A1 (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116248256A (en) * | 2021-12-03 | 2023-06-09 | 华为技术有限公司 | Communication method and device, storage medium, and program product |
| CN114241305A (en) * | 2021-12-07 | 2022-03-25 | 中原动力智能机器人有限公司 | Target detection model updating method and device |
| CN114358316A (en) * | 2022-01-14 | 2022-04-15 | 中国人民解放军总医院 | Federal learning system and large-scale image training method and device thereof |
| CN115225344B (en) * | 2022-06-28 | 2024-05-14 | 华润智算科技(广东)有限公司 | Network information security processing method and device, computer equipment and storage medium |
| CN115085921B (en) * | 2022-07-22 | 2023-01-20 | 北京智芯微电子科技有限公司 | Model training method, node detection method, device, equipment and medium |
| CN115718930A (en) * | 2022-11-30 | 2023-02-28 | 北京航天数据股份有限公司 | User service system and method based on user portrait and electronic equipment |
| CN117395083B (en) * | 2023-12-11 | 2024-03-19 | 东信和平科技股份有限公司 | Data protection method and system based on federal learning |
| CN117671385B (en) * | 2023-12-20 | 2024-09-03 | 北京斯年智驾科技有限公司 | A training method, system, device and storage medium for target recognition model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110572253A (en) * | 2019-09-16 | 2019-12-13 | 济南大学 | A method and system for enhancing the privacy of federated learning training data |
| CN111462174A (en) * | 2020-03-06 | 2020-07-28 | 北京百度网讯科技有限公司 | Multi-target tracking method and device and electronic equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5860556B1 (en) * | 2015-02-06 | 2016-02-16 | 日本電信電話株式会社 | Inconsistency detection method, inconsistency detection system, inconsistency detection apparatus, and program |
| CN109214238B (en) * | 2017-06-30 | 2022-06-28 | 阿波罗智能技术(北京)有限公司 | Multi-target tracking method, device, equipment and storage medium |
| CN110704860B (en) * | 2019-11-18 | 2024-10-29 | 深圳前海微众银行股份有限公司 | Longitudinal federal learning method, equipment, system and storage medium for improving safety |
| CN111126303B (en) * | 2019-12-25 | 2023-06-09 | 北京工业大学 | A Multi-Space Detection Method for Intelligent Parking |
| CN111611610B (en) * | 2020-04-12 | 2023-05-30 | 西安电子科技大学 | Federated learning information processing method, system, storage medium, program, terminal |
-
2020
- 2020-09-18 CN CN202010990029.4A patent/CN112116008B/en active Active
- 2020-10-28 WO PCT/CN2020/124439 patent/WO2021174877A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110572253A (en) * | 2019-09-16 | 2019-12-13 | 济南大学 | A method and system for enhancing the privacy of federated learning training data |
| CN111462174A (en) * | 2020-03-06 | 2020-07-28 | 北京百度网讯科技有限公司 | Multi-target tracking method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021174877A1 (en) | 2021-09-10 |
| CN112116008A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112116008B (en) | Processing method of target detection model based on intelligent decision and related equipment thereof | |
| WO2021120676A1 (en) | Model training method for federated learning network, and related device | |
| CN110189192B (en) | Information recommendation model generation method and device | |
| CN112101437B (en) | Fine granularity classification model processing method based on image detection and related equipment thereof | |
| CN112287244B (en) | Product recommendation method, device, computer equipment and medium based on federated learning | |
| US20190080148A1 (en) | Method and apparatus for generating image | |
| WO2022095352A1 (en) | Abnormal user identification method and apparatus based on intelligent decision, and computer device | |
| CN112508075B (en) | DBSCAN clustering method based on transverse federation and related equipment thereof | |
| CN112529101B (en) | Classification model training method and device, electronic equipment and storage medium | |
| CN113220734A (en) | Course recommendation method and device, computer equipment and storage medium | |
| CN107729928A (en) | Information acquisition method and device | |
| CN111641517A (en) | Community division method and device for homogeneous network, computer equipment and storage medium | |
| WO2022001233A1 (en) | Pre-labeling method based on hierarchical transfer learning and related device | |
| CN111382403A (en) | Training method, device, equipment and storage medium of user behavior recognition model | |
| CN111651749B (en) | Method, device, computer equipment and storage medium for retrieving account based on password | |
| CN104168117A (en) | Voice digital signature method | |
| CN112507141B (en) | Investigation task generation method, investigation task generation device, computer equipment and storage medium | |
| CN114780701A (en) | Automatic question-answer matching method, device, computer equipment and storage medium | |
| CN112085469B (en) | Data approval method, device, equipment and storage medium based on vector machine model | |
| CN114241411A (en) | Counting model processing method and device based on target detection and computer equipment | |
| CN113936677A (en) | Tone conversion method, device, computer equipment and storage medium | |
| CN116956326A (en) | Authority data processing method and device, computer equipment and storage medium | |
| CN114004206B (en) | Form generation method, device, computer equipment and storage medium | |
| CN110175283A (en) | A kind of generation method and device of recommended models | |
| CN116188887A (en) | Attribute recognition pre-training model generation method and attribute recognition model generation method |
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 |