CN112230956A - Artificial intelligence model updating method, system, electronic equipment and storage medium - Google Patents
Artificial intelligence model updating method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112230956A CN112230956A CN202011101574.XA CN202011101574A CN112230956A CN 112230956 A CN112230956 A CN 112230956A CN 202011101574 A CN202011101574 A CN 202011101574A CN 112230956 A CN112230956 A CN 112230956A
- Authority
- CN
- China
- Prior art keywords
- model
- artificial intelligence
- intelligence model
- byte stream
- data
- 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.)
- Withdrawn
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013480 data collection Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004806 packaging method and process Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 description 16
- 238000011161 development Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 235000013550 pizza Nutrition 0.000 description 8
- 238000005096 rolling process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013523 data management Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- 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
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/71—Version control; Configuration management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an artificial intelligence model updating method, a system, electronic equipment and a storage medium, wherein the technical scheme of the method comprises the steps of collecting real-time data of embedded equipment; developing and training an artificial intelligence model; serializing the artificial intelligence model into a model byte stream; and receiving the model byte stream on the embedded equipment and deserializing to obtain an updated artificial intelligence model. The invention solves the problem of low real-time updating efficiency of the artificial intelligence model on the embedded equipment.
Description
Technical Field
The invention belongs to the field of data processing, and particularly relates to an artificial intelligence model updating method, an artificial intelligence model updating system, electronic equipment and a storage medium.
Background
In the field of artificial intelligence, both mature traditional machine learning methods and emerging deep learning methods need to update a model to adapt to new data and scenes along with the increase of data volume and the change of scenes. The updating speed of the model directly affects the effect of the current model, and the model which is often desired is as follows: data that is long enough is considered, so more cases can be considered; meanwhile, the latest data is considered, so that the latest change can be reflected, and the influence of the hysteresis on the effect is reduced.
The development of machine hardware and big data technology partially solve the problem of processing enough data, but the real-time model updating is a challenging problem, and especially the models running on embedded devices have higher requirements.
At present, the problems of 'embedded environment deployment, model dynamic rolling upgrade' and the like are solved in the updating and deployment of an artificial intelligent model of embedded equipment in an artificial mode, and the method is low in efficiency and easy to make mistakes.
Disclosure of Invention
The embodiment of the application provides an artificial intelligence model updating method, an artificial intelligence model updating system, electronic equipment and a storage medium, and aims to at least solve the problem of real-time updating of an artificial intelligence model on embedded equipment.
In a first aspect, an embodiment of the present application provides an artificial intelligence model updating method, including:
s101, collecting real-time data of the embedded equipment;
s102, developing and training an artificial intelligence model;
s103, serializing the artificial intelligence model into a model byte stream;
and S104, receiving the model byte stream on the embedded equipment and deserializing to obtain an updated artificial intelligence model.
Preferably, the step S101 is implemented by kafka.
Preferably, the serializing in step S103 includes packaging the artificial intelligence model into a Docker image, and then encoding the Docker image into the model byte stream through Base 64; further comprising model distributing the model byte stream; the model distribution is realized by kafka.
Preferably, the step S104 includes deploying the updated artificial intelligence model through the k3S platform.
In a second aspect, an embodiment of the present application provides an artificial intelligence model updating system, which is applicable to the artificial intelligence model updating method, and includes:
a data collection unit: collecting real-time data of the embedded equipment;
a model training unit: developing and training an artificial intelligence model;
a serialization unit: serializing the artificial intelligence model into a model byte stream;
a model receiving unit: the model byte stream is received and deserialized at the embedded device.
In some embodiments, the step S101 implements data collection by kafka.
In some embodiments, the serializing in step S103 includes packaging the artificial intelligence model into a Docker image and encoding the Docker image into the model byte stream by Base 64; further comprising model distributing the model byte stream; the model distribution is realized by kafka.
In some embodiments, the step S104 includes obtaining the updated artificial intelligence model through the k3S platform.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements an artificial intelligence model updating method as described in the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements an artificial intelligence model updating method as described in the first aspect above.
Compared with the related art, the artificial intelligence model updating method provided by the embodiment of the application comprises the following steps:
1. the real-time updating of the artificial intelligence model on the embedded equipment is realized;
2. links such as model serialization, model rolling upgrade, deployment of an artificial intelligence model environment of embedded equipment and the like are accelerated;
3. the lightweight containerization platform k3s is pre-installed at the embedded end, the k3s containerization technology is applied, the whole deployment is realized, manual intervention is not needed, and the rolling upgrade of the Docker image can be realized, namely, an online new version, API switching, an offline old version and the like.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of an artificial intelligence model updating method according to an embodiment of the application;
FIG. 2 is a flowchart of an application of an artificial intelligence model updating method according to an embodiment of the application;
FIG. 3 is a framework diagram of an artificial intelligence model update system in accordance with an embodiment of the present application;
FIG. 4 is a block diagram of an electronic device according to an embodiment of the present application;
in the above figures:
11. a data collection unit; 12. a model training unit; 13. a serialization unit; 14. a model receiving unit; 20. a bus; 21. a processor; 22. a memory; 23. a communication interface.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase 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 ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the field of artificial intelligence, both mature traditional machine learning methods and emerging deep learning methods need to update a model to adapt to new data and scenes along with the increase of data volume and the change of scenes. The updating speed of the model directly affects the effect of the current model, and the model which is often desired is as follows: data that is long enough is considered, so more cases can be considered; meanwhile, the latest data is considered, so that the latest change can be reflected, and the influence of the hysteresis on the effect is reduced.
The development of machine hardware and the development of big data technology partially solve the problem of handling enough data, but is still a challenging problem for real-time model updating. Especially for models running on embedded devices, the requirements are higher.
Existing model update techniques, focusing more on the "data-training-model update-new data" loop, can be described as an automation of this loop, making the data pipeline faster, such as streaming data through data pipeline techniques like kafka, or concatenating data directly through TCP. The prior art focuses more on the cycle of 'data-training-model updating-new data', but for artificial intelligence application, the whole process is lack of attention, and in practical application, it is found that acceleration of other parts can accelerate the updating speed of the model more, and the links include: model serialization, model rolling upgrade, deployment of an embedded device environment, distributed new data collection and the like. The acceleration of these links can actually accelerate the whole process. For western restaurants, unlike internet enterprises, the most important devices are not large servers but embedded devices with weak computing power, so that the acceleration of the links is the key point of the acceleration of the whole process.
The pizza is a common food in western food shops, for chain-operated brands, the pizza quality of each storefront directly influences the sales volume of the pizza, the embodiment of the invention can be used for updating the artificial intelligent model of the embedded equipment for quality detection of the pizza shop in real time, wherein the related details are as follows: the method comprises the following steps of embedded equipment data collection, model training, model generation, model serialization, model distribution, model deserialization, embedded equipment environment preparation, model rolling upgrade and the like, so that the modules are automatically connected without manual intervention.
Some of the terms of art to which the invention relates are described below:
kafka is an open source stream processing platform developed by the Apache software foundation, written in Scala and Java. Kafka is a high-throughput distributed publish-subscribe messaging system that can handle all the action flow data of a consumer in a web site. This action (web browsing, searching and other user actions) is a key factor in many social functions on modern networks. These data are typically addressed by handling logs and log aggregations due to throughput requirements. This is a viable solution to the limitations of Hadoop-like log data and offline analysis systems, but which require real-time processing. The purpose of Kafka is to unify online and offline message processing through the parallel loading mechanism of Hadoop, and also to provide real-time messages through clustering.
Docker is an open source project, born in 2013, originally an amateur project within the company dotCloud. It is based on the Go language implementation introduced by Google corporation. Projects were later added to the Linux foundation, following the Apache 2.0 protocol, with project code maintained on the GitHub. Docker has received extensive attention and discussion since its inception, so that the company dotCloud has since been renamed to Docker Inc. Redcat has centrally supported Docker in its RHEL 6.5; google is also widely used in its PaaS product. The goal of the Docker project is to implement a lightweight operating system virtualization solution. The basis of Docker is Linux container (LXC) and other technologies. In Docker's terminology, a read-only layer is called a mirror, and a mirror is permanent. Docker images are used to display the locally existing images.
Base64 is one of the most common encoding methods for transmitting 8-Bit byte codes on a network, and Base64 is a method for representing binary data based on 64 printable characters. RFCs 2045-2049 can be viewed, above which is the detailed specification of MIME. Base64 encoding is a binary to character process that may be used to convey longer identification information in the HTTP environment. Encoding using Base64 is not readable and requires decoding before reading. Base64 is widely used in various fields of computers due to the above advantages, however, since more than two "symbol-like" characters (+,/, ═ are included in the output content, various "variants" of Base64 have been developed in different application scenarios. To unify and normalize the output of Base64, Base62x is considered an unsigned, improved version.
k3s is a highly available CNCF certified kubernets release designed for unattended, resource-constrained, remote locations or production workloads within internet of things devices. k3s is packaged into a single binary file of less than 60MB, reducing the dependencies and steps required to run an installation, run and automatically update a production kubernets cluster. kubernets, K8s for short, is an abbreviation for 8 instead of 8 characters "ubernet". The kubernets is an open source and used for managing containerized applications on multiple hosts in a cloud platform, the goal of kubernets is to make it simple and efficient (powerfull) to deploy containerized applications, and the kubernets provides a mechanism for application deployment, planning, updating and maintenance. In the embodiment of the invention, the k3s is used for receiving and deploying the artificial intelligence model updated by the embedded terminal in real time, so that convenience and automation of deployment are realized.
Serialization (Serialization) is the process of converting state information of an object into a form that can be stored or transmitted. During serialization, the object writes its current state to a temporary or persistent store. The object may later be recreated by reading or deserializing the state of the object from storage. Serialization allows other code to be viewed or modified, and object instance data that cannot be accessed without serialization.
The embedded device is composed of hardware and software and is a device capable of operating independently. The software content of the software only comprises a software running environment and an operating system thereof. The hardware content includes various contents including a signal processor, a memory, a communication module, and the like. Compared with a common computer processing system, the embedded system has larger difference, and cannot realize the large-capacity storage function because no large-capacity medium matched with the embedded system exists, most of the adopted storage media are E-PROM and the like, and the software part takes an API (application programming interface) as the core of a development platform.
Referring to fig. 1, a flowchart of an artificial intelligence model updating method according to an embodiment of the present application includes the following steps:
s101, collecting real-time data of the embedded equipment;
s102, developing and training an artificial intelligence model;
s103, serializing the artificial intelligence model into a model byte stream;
and S104, receiving the model byte stream on the embedded equipment and deserializing to obtain an updated artificial intelligence model.
After step S104 is completed, real-time data of the embedded device will be collected, looping from step S101.
It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here.
Wherein, the step S101 realizes data collection through Kafka. When the method is used for the first time, collecting data refers to historical data of the embedded device; and after the first round of artificial intelligence model deployment is finished, collecting real-time data of the embedded equipment.
In this embodiment, Kafka is used to collect data, and the data is classified by different topics, and each is required. On the other hand, the characteristics of kafka streaming data are the basis of real-time updating.
In step S102, when the method is executed for the first time, an artificial intelligence model of the first version is trained by artificial development; in some of these embodiments, off-the-shelf models can also be applied directly.
The serialization in the step S103 includes packaging the artificial intelligence model into a Docker image, and then encoding the Docker image into the model byte stream through Base 64; further comprising model distributing the model byte stream; the model distribution is realized by kafka.
After the model development is completed, the serialization process is carried out, wherein a containerization technology is used for packaging the model and the whole environment on which the model depends into a Docker image, and the Docker image is binary data and cannot be directly transmitted, so that the model is immediately changed into a transmittable model byte stream in a Base64 encoding mode.
The model byte stream is sent out through the model distributor, here again implemented with kafka, with the advantage that data can be buffered for 7 days, so that if a model pull fails, it can be directly recovered from the buffer, and no redistribution is required.
At the embedded device end, after the serialized artificial intelligence model is received through the step S104, the deserialization of the model is carried out, so that the Docker image is restored.
Preferably, the step S104 includes deploying the updated artificial intelligence model through the k3S platform.
The embedded terminal is pre-provided with a lightweight containerization platform k3s, so that the rolling upgrade of the Docker image can be realized, namely, an online new version, API switching, an offline old version and the like. And the k3s containerization technology is applied, and the whole deployment is realized without manual intervention.
And for the new data generated by the embedded device, the new data enters the data collection pipeline again through the pipeline of the new data. The data can automatically generate a new model only by reentering the model training process, thereby completing the full-automatic circulation and updating of the whole process.
The embodiment of the application provides an artificial intelligence model updating system, which is suitable for the artificial intelligence model updating method. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Referring to fig. 2, fig. 2 is a flowchart illustrating an application of an artificial intelligence model updating method according to an embodiment of the present application. The work intelligence model updating method of the inventor is specifically described as follows with reference to fig. 2:
1) and the data collection pipeline is used for collecting historical data and new data, is realized by Kafka, and classifies the data according to different topics and respectively acquires the data. On the other hand, the characteristics of kafka streaming data are the basis of real-time updating.
2) Historical data, through a data management model, a first version of pizza detection model is developed and trained by a model developer, and for the first time, the process is manually completed, if an existing model is directly applied, the step can also be automatically executed, but considering the effect problem of the model, the step is generally completed manually.
3) After the model development is completed, the serialization process is carried out, wherein a containerization technology is firstly used for packaging the model and the whole environment on which the model depends into a docker image, and the docker image is binary data and cannot be directly transmitted, so that the model is immediately changed into or transmitted by a mode of Base64 coding.
4) The model byte stream is sent to the data management by the model distributor, here again implemented with kafka, with the advantage that data can be temporarily stored for 7 days, so that if a model pull fails, it can be directly recovered from temporary storage, and no redistribution is required.
5) And at the embedded end of pizza production, receiving the model from the data pipeline through the model receiving module, and performing deserialization on the model so as to restore the docker image.
6) At the embedded end, a lightweight containerization platform such as k3s is pre-installed, so that rolling upgrade of the docker image, namely, an online new version, API switching and an offline old version can be realized. The pizza detection part does not need to care, and the seamless upgrade of the model is realized.
7) And for the new data generated at the pizza detection embedding end, the new data enters the data collection pipeline again through the pipeline of the new data.
8) The new data can automatically generate a new model only by reentering the model training process, thereby completing the full-automatic circulation and updating of the whole process.
Fig. 3 is a framework diagram of an artificial intelligence model updating system according to an embodiment of the present application, including a data collection unit 11, a model training unit 12, a serialization unit 13, and a model receiving unit 14, where:
the data collection unit 11: collecting real-time data of the embedded equipment;
the model training unit 12: developing and training an artificial intelligence model;
the serialization unit 13: serializing the artificial intelligence model into a model byte stream;
the model receiving unit 14: the model byte stream is received and deserialized at the embedded device.
In some of these embodiments, the data collection unit 11 performs data collection by kafka, and sorts the data by different topics, each as needed. On the other hand, the characteristics of kafka streaming data are the basis of real-time updating.
In some of these embodiments, the model training unit 12, when executed for the first time, trains a first version of the artificial intelligence model from human development; in some of these embodiments, off-the-shelf models can also be applied directly.
In some of these embodiments, the serialization in the serialization unit 13 includes packaging the artificial intelligence model as a Docker image, which is then encoded as the model byte stream by Base 64; further comprising model distributing the model byte stream; the model distribution is realized by kafka.
After the model development is completed, the serialization process is carried out, wherein a containerization technology is used for packaging the model and the whole environment on which the model depends into a Docker image, and the Docker image is binary data and cannot be directly transmitted, so that the model is immediately changed into a transmittable model byte stream in a Base64 encoding mode.
The model byte stream is sent out through the model distributor, here again implemented with kafka, with the advantage that data can be buffered for 7 days, so that if a model pull fails, it can be directly recovered from the buffer, and no redistribution is required.
At the embedded device end, after the serialized artificial intelligence model is received by the model receiving unit 14, the model is deserialized, so that the Docker image is restored.
In some of these embodiments, the model receiving unit 14 includes obtaining the updated artificial intelligence model via the k3s platform implementation.
The embedded terminal is pre-provided with a lightweight containerization platform k3s, so that the rolling upgrade of the Docker image can be realized, namely, an online new version, API switching, an offline old version and the like. And the k3s containerization technology is applied, and the whole deployment is realized without manual intervention.
And for the new data generated by the embedded device, the new data enters the data collection unit 11 again through the new data pipeline. The data only needs to re-enter the model training unit 12, and a new model can be automatically generated, so that the full-automatic circulation and updating of the whole process are completed.
The above units may be functional units or program units, and may be implemented by software or hardware. For units implemented by hardware, the units may be located in the same processor; or the units may be located in different processors in any combination.
In addition, the method for updating the artificial intelligence model in the embodiment of the present application described in conjunction with fig. 1 may be implemented by an electronic device. Fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
The computer device may comprise a processor 21 and a memory 22 in which computer program instructions are stored.
Specifically, the processor 21 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 22 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions executed by the processor 21.
The processor 21 implements any one of the artificial intelligence model updating methods in the above embodiments by reading and executing computer program instructions stored in the memory 22.
In some of these embodiments, the computer device may also include a communication interface 23 and a bus 20. As shown in fig. 3, the processor 21, the memory 22, and the communication interface 23 are connected via the bus 20 to complete mutual communication.
The communication port 23 may be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.
The bus 20 includes hardware, software, or both to couple the components of the electronic device to one another. Bus 20 includes, but is not limited to, at least one of the following: data Bus (Data Bus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 20 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (FSB), a Hyper Transport (HT) Interconnect, an ISA (ISA) Bus, an InfiniBand (InfiniBand) Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a PCI (Peripheral Component Interconnect) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Video Electronics Bus (audio Electronics Association), abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 20 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.
The computer device can execute the artificial intelligence model updating method in the embodiment of the application.
In addition, in combination with the artificial intelligence model updating method in the foregoing embodiments, the embodiments of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the artificial intelligence model updating methods in the above embodiments.
And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An artificial intelligence model updating method, comprising:
s101, collecting real-time data of the embedded equipment;
s102, developing and training an artificial intelligence model;
s103, serializing the artificial intelligence model into a model byte stream;
and S104, receiving the model byte stream on the embedded equipment and deserializing to obtain an updated artificial intelligence model.
2. The artificial intelligence model updating method of claim 1, wherein the step S101 implements data collection by kafka.
3. The method of updating an artificial intelligence model of claim 1, wherein the serializing at step S103 comprises packaging the artificial intelligence model as a Dockerimage and encoding into the model byte stream via Base 64.
4. The artificial intelligence model updating method of claim 3, wherein said step S103 further comprises model distributing said model byte stream; the model distribution is realized by kafka.
5. The artificial intelligence model updating method of claim 1, wherein the step S104 includes deploying the updated artificial intelligence model through a k3S platform.
6. An artificial intelligence model update system, comprising:
a data collection unit: collecting real-time data of the embedded equipment;
a model training unit: developing and training an artificial intelligence model;
a serialization unit: serializing the artificial intelligence model into a model byte stream;
a model receiving unit: the model byte stream is received and deserialized at the embedded device.
7. The artificial intelligence model updating system of claim 6, wherein the serialization unit includes packaging the artificial intelligence model as a Dockerimage and encoding it as the model byte stream via Base 64.
8. The artificial intelligence model updating system of claim 7, wherein the serialization element further comprises model distribution of the model byte stream; the model distribution is realized by kafka.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements an artificial intelligence model updating method as claimed in any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out an artificial intelligence model updating method as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011101574.XA CN112230956A (en) | 2020-10-15 | 2020-10-15 | Artificial intelligence model updating method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011101574.XA CN112230956A (en) | 2020-10-15 | 2020-10-15 | Artificial intelligence model updating method, system, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112230956A true CN112230956A (en) | 2021-01-15 |
Family
ID=74113066
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011101574.XA Withdrawn CN112230956A (en) | 2020-10-15 | 2020-10-15 | Artificial intelligence model updating method, system, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112230956A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112394950A (en) * | 2021-01-19 | 2021-02-23 | 共达地创新技术(深圳)有限公司 | AI model deployment method, device and storage medium |
CN117250911A (en) * | 2023-11-13 | 2023-12-19 | 西北工业大学 | CAM software model calling method, system, equipment and medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297659A (en) * | 2018-03-21 | 2019-10-01 | 北京京东尚科信息技术有限公司 | Algorithm model disposes loading method and device |
CN111083722A (en) * | 2019-04-15 | 2020-04-28 | 中兴通讯股份有限公司 | Model pushing method, model requesting method, model pushing device, model requesting device and storage medium |
CN111399853A (en) * | 2020-02-20 | 2020-07-10 | 四川新网银行股份有限公司 | Templated deployment method of machine learning model and custom operator |
-
2020
- 2020-10-15 CN CN202011101574.XA patent/CN112230956A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297659A (en) * | 2018-03-21 | 2019-10-01 | 北京京东尚科信息技术有限公司 | Algorithm model disposes loading method and device |
CN111083722A (en) * | 2019-04-15 | 2020-04-28 | 中兴通讯股份有限公司 | Model pushing method, model requesting method, model pushing device, model requesting device and storage medium |
CN111399853A (en) * | 2020-02-20 | 2020-07-10 | 四川新网银行股份有限公司 | Templated deployment method of machine learning model and custom operator |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112394950A (en) * | 2021-01-19 | 2021-02-23 | 共达地创新技术(深圳)有限公司 | AI model deployment method, device and storage medium |
CN117250911A (en) * | 2023-11-13 | 2023-12-19 | 西北工业大学 | CAM software model calling method, system, equipment and medium |
CN117250911B (en) * | 2023-11-13 | 2024-03-19 | 西北工业大学 | CAM software model calling method, system, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11327814B2 (en) | Semaphores for serverless computing | |
KR102414096B1 (en) | Create and deploy packages for machine learning on end devices | |
CN109067890B (en) | CDN node edge computing system based on docker container | |
US11982999B2 (en) | Defect detection task processing method, device, apparatus and storage medium | |
CN111860835A (en) | Neural network model training method and device | |
CN111507476A (en) | Method, apparatus and computer program product for deploying machine learning model | |
CN112230956A (en) | Artificial intelligence model updating method, system, electronic equipment and storage medium | |
US20190163533A1 (en) | Computing task management using tree structures | |
CN110391938B (en) | Method and apparatus for deploying services | |
CN111782660A (en) | Data compression method and system based on key value storage | |
US10877807B2 (en) | Method, apparatus and computer program product for allocating processing resource to application | |
CN113641413A (en) | Target model loading and updating method and device, readable medium and electronic equipment | |
CN111062521B (en) | Online prediction method, system and server | |
CN114327399A (en) | Distributed training method, apparatus, computer device, storage medium and product | |
CN117011397A (en) | Data processing method, apparatus, device, readable storage medium, and program product | |
CN115244511A (en) | Distributed computing pipeline processing | |
CN116721007B (en) | Task control method, system and device, electronic equipment and storage medium | |
CN111444148B (en) | Data transmission method and device based on MapReduce | |
US20230325149A1 (en) | Data processing method and apparatus, computer device, and computer-readable storage medium | |
CN111414343B (en) | Log writing method, device, electronic equipment and medium | |
CN113971455A (en) | Distributed model training method and device, storage medium and computer equipment | |
CN115240654A (en) | Speech recognition model training method, device, equipment and storage medium | |
CN111813529B (en) | Data processing method, device, electronic equipment and storage medium | |
CN115174541A (en) | H5 resource loading method and device, electronic equipment and storage medium | |
US20220086217A1 (en) | Method for managing artificial intelligence application, device, and program product |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210115 |
|
WW01 | Invention patent application withdrawn after publication |