CN113610104A - Algorithm management method based on spatial knowledge/model base system - Google Patents
Algorithm management method based on spatial knowledge/model base system Download PDFInfo
- Publication number
- CN113610104A CN113610104A CN202110723773.2A CN202110723773A CN113610104A CN 113610104 A CN113610104 A CN 113610104A CN 202110723773 A CN202110723773 A CN 202110723773A CN 113610104 A CN113610104 A CN 113610104A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- knowledge
- layer
- machine learning
- 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.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000003930 cognitive ability Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiments of the present disclosure provide an algorithm management method, apparatus, device and computer-readable storage medium based on a spatial knowledge/model base system. The method comprises the following steps: in the model layer, classifying machine learning algorithms prestored in a machine learning algorithm library of the resource layer; performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model; storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base; and at an application service layer, providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer. In this way, the difficulty of selecting and using a machine algorithm in the decision of the multi-granularity space-time object can be greatly reduced.
Description
Technical Field
Embodiments of the present disclosure relate generally to the field of data processing, and more particularly, to an algorithm management method, apparatus, device, and computer-readable storage medium based on a spatial knowledge/model base system.
Background
The space information system changes the traditional GIS indirect modeling method taking a map as a template, and directly describes the real world from micro to macro by using multi-granularity space-time objects, namely, the real world is simplified and abstracted into the multi-granularity space-time objects. Compared with the same common space-time object, the multi-granularity space-time object has characteristics of cognitive ability and behavioral ability besides characteristics such as space-time reference, spatial position, spatial form, attribute characteristics, composition structure and incidence relation, can describe living geographic entities with autonomous cognitive ability and behavioral ability, and can analyze external information to generate result output.
The formation of the behavior ability and the cognitive ability of the multi-granularity space-time object depends on machine learning, namely, proper algorithm knowledge is selected or the algorithms are combined into a model according to data and scenes, so that the data can be analyzed and processed, corresponding responses are made to external input, namely, the data are output, and finally the data are used as the basis of decision making.
Machine learning algorithms are numerous, but lack uniform description expression, and it is difficult to quickly select an optimal algorithm and correctly use the optimal algorithm without a certain machine learning background.
Disclosure of Invention
According to an embodiment of the present disclosure, an algorithm management scheme based on a spatial knowledge/model base system is provided.
In a first aspect of the disclosure, an algorithm management method based on a spatial knowledge/model base system is provided. The method comprises the following steps:
in the model layer, classifying machine learning algorithms prestored in a machine learning algorithm library of the resource layer; performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model;
storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base;
and at an application service layer, providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer.
Further, it is characterized in that,
the spatial knowledge/model base system comprises a resource layer, a model layer, a database layer, an application service layer and an application layer; wherein,
the resource layer is used for integrating data resources; the data resources comprise hardware resources, a machine learning algorithm library and data resources;
the model layer is used for classifying the machine learning algorithms in the machine learning algorithm library, describing the classified machine learning algorithms and forming the knowledge of the general machine learning algorithm;
the database layer is used for storing the knowledge of the general machine learning algorithm;
the application service layer is used for managing data in the resource layer; data interaction is carried out through a data interface, and services are provided for users and/or programs;
the application layer is used for providing an access function of an application program for the client and realizing interface operation of a final user and control request and call of business activities.
Further, performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model comprises:
and describing metadata, algorithm characteristic information, algorithm input information, algorithm output information, algorithm operating environment and algorithm parameter information of the classified machine learning algorithm by adopting an XML knowledge representation method to form the knowledge of the classified machine learning algorithm.
Further, the spatial algorithm description model comprises:
metadata of the algorithm, algorithm characteristic information, algorithm input information, algorithm output information, algorithm operating environment and algorithm parameter information;
wherein the metadata of the algorithm comprises: version information, setup time, and/or contact information;
the algorithm characteristic information comprises: algorithm identification, name and/or function;
the algorithm input information includes: data type, data volume, data dimension, and/or data format;
the algorithm output information includes: data type, data format, data precision and/or data dimension;
the algorithm operating environment comprises: a software environment and a hardware environment;
the algorithm parameter information includes: and (4) operating parameter information by the algorithm.
Further, still include:
and searching and managing the algorithm knowledge in the spatial knowledge/model base through the application service layer.
Further, still include:
and formulating a visual display, recommendation system and/or business intelligent function interface in the application layer.
In a second aspect of the present disclosure, an algorithm management device based on a spatial knowledge/model base system is provided. The device includes:
the processing module is used for classifying machine learning algorithms prestored in a machine learning algorithm library of the resource layer in the model layer; formalized expression of algorithm knowledge of classified machine learning algorithm according to spatial algorithm description model
The storage module is used for storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base;
and the interaction module is used for providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer at the application service layer.
In a third aspect of the disclosure, an electronic device is provided. The electronic device includes: a memory having a computer program stored thereon and a processor implementing the method as described above when executing the program.
In a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, implements a method as in accordance with the first aspect of the present disclosure.
According to the algorithm management method based on the spatial knowledge/model base system, machine learning algorithms prestored in a machine learning algorithm base of a resource layer are classified in a model layer according to an object space abstract method and a cognitive model; performing formal expression of algorithm knowledge on the classified machine learning algorithm to a spatial algorithm description model by adopting XML Schema; storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base; and in the application service layer, data interaction and processing services for algorithm knowledge in the knowledge/model base are provided for a web client of the application layer, and corresponding machine learning algorithms can be effectively selected, called or combined according to actual requirements of the web client, so that the difficulty of selecting and using the machine algorithms in decision making of multi-granularity space-time objects is greatly reduced.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:
FIG. 1 shows a flow diagram of an algorithm management method based on a spatial knowledge/model base system, according to an embodiment of the present disclosure;
FIG. 2 shows a schematic diagram of a spatial knowledge/model base system in accordance with an embodiment of the present disclosure;
FIG. 3 illustrates a UML structural description diagram of algorithm metadata according to an embodiment of the present disclosure;
FIG. 4 shows a framework description diagram of algorithmic characterization information, in accordance with an embodiment of the present disclosure;
FIG. 5 shows a framework description diagram of algorithm input information, in accordance with an embodiment of the present disclosure;
FIG. 6 shows a schematic diagram of a structural description of algorithm input information, according to an embodiment of the present disclosure;
FIG. 7 shows a framework description diagram of algorithm output information, in accordance with an embodiment of the present disclosure;
FIG. 8 shows a schematic diagram illustrating a structural description of algorithm output information, according to an embodiment of the present disclosure;
FIG. 9 shows a framework description schematic of an algorithm runtime environment according to an embodiment of the present disclosure;
FIG. 10 shows a schematic diagram of a structural description of an algorithm runtime environment, according to an embodiment of the present disclosure;
FIG. 11 shows a framework description diagram of algorithm parameter information, in accordance with an embodiment of the present disclosure;
FIG. 12 shows a schematic diagram of a structural description of algorithm parameter information, according to an embodiment of the present disclosure;
FIG. 13 shows a block diagram of an algorithm management device based on a spatial knowledge/model base system according to an embodiment of the present disclosure;
FIG. 14 illustrates a block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
FIG. 1 shows a flow diagram of an algorithm management method 100 based on a spatial knowledge/model base system, according to an embodiment of the present disclosure. The method 100 comprises:
s110, classifying machine learning algorithms pre-stored in a machine learning algorithm library of a resource layer in a model layer; and performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model.
In some embodiments, as shown in FIG. 2, the spatial knowledge/model base based system employs a multi-level architecture, including a resource layer, a model layer, a database layer, an application service layer, and an application layer;
the resource layer is used for integrating data resources, providing a functional algorithm package required for constructing a spatial knowledge/model base, and providing hardware and data support for upper-layer services and applications; the data resources comprise hardware resources, a machine learning algorithm library and data resources;
the model layer is used for classifying the machine learning algorithms in the machine learning algorithm library, describing the classified machine learning algorithms and forming the knowledge of the general machine learning algorithm;
the database layer is used for storing the knowledge of the general machine learning algorithm;
the application service layer is used for managing data in the resource layer; data interaction is carried out through a data interface, and services are provided for users and/or programs;
the application layer is used for providing an access function of an application program for the client and realizing interface operation of a final user and control request and call of business activities.
In some embodiments, machine learning algorithms pre-stored in a machine learning algorithm library of a resource layer are classified by adopting a universal objectification idea according to an object space abstract method and a cognitive model; all the needed machine learning algorithms are stored in the machine learning algorithm library.
In some embodiments, the classified machine learning algorithm adopts XML Schema to formally express algorithm knowledge of the spatial algorithm description model. Namely, the spatial algorithm description model is expressed into a form which can be understood by a computer or a human by adopting an XML Schema. The XML Schema is a construction module responsible for defining XML documents. The space algorithm description model is defined through XML Schema, and normalization and unification of data information description are facilitated.
In some embodiments, metadata, algorithm feature information, algorithm input information, algorithm output information, algorithm operating environment, and algorithm parameter information of the classified machine learning algorithm are described (UML structure) using an XML knowledge representation method to form the knowledge of the classified machine learning algorithm.
In some embodiments, the spatial algorithm description model comprises: metadata of the algorithm, algorithm characteristic information, algorithm input information, algorithm output information, algorithm operating environment, algorithm parameter information, and the like.
Wherein,
the metadata (metadata of the algorithm) includes basic information such as version information, setup time, and/or contact information (including information of the person in charge). As shown in fig. 3, the metadata is described, that is, the scientific description of the basic information of the algorithm in the algorithm library is described. In fig. 3, mla (machine Learning algorithm) represents a machine Learning algorithm; ad (algorithmic description) is the corresponding machine learning algorithm description;
the algorithm characteristic information mainly relates to performance, bearing capacity and preference characteristics of the algorithm during specific application, and the preference characteristics are basic characteristics of the algorithm summarized according to different algorithm functions, capabilities and application scenes. As shown in fig. 4, the algorithm characteristic information includes an algorithm identifier, an algorithm name, and/or an algorithm function. The algorithm characteristic information is described, so that a user can conveniently refer to the algorithm according to external conditions and internal requirements when selecting the algorithm, and the algorithm screening is carried out by data driving even in the later application;
as shown in fig. 5, the algorithm input information includes data type, data amount, and/or data dimension, etc. As shown in fig. 6, the algorithm input information is described, i.e., the input data feature (AD _ InputDataFeature) is described; the input data characteristics refer to the constraints on the functions and characteristics of the algorithm, certain requirements and limitations are imposed on the data to be processed by the algorithm, and users can conveniently input relevant parameters when using the algorithm;
as shown in fig. 7, the algorithm output information (AD _ OutputDataFeature) includes a data type, a data format, and/or a data precision, etc. As shown in fig. 8, the algorithm output information is described, that is, the limitation and feature information of the output data are described, so that a user can use (call) a corresponding algorithm according to the output requirement.
As shown in fig. 9, the algorithm execution environment includes a hardware environment and a software environment. The hardware environment (AD _ hardware envir) is a computer physical system composed of a computer and peripheral equipment, such as a CPU, a memory, etc., on which an algorithm runs; the software environment (AD _ software envir) is a software system on which an algorithm depends to calculate data, such as an operating system environment, a programming environment, a database, and the like; as shown in fig. 10, the machine learning algorithm corresponds to the description of the environment information in a one-to-one relationship;
as shown in fig. 11, the algorithm parameter information is algorithm operation parameter information including parameters and hyper-parameters, where the parameters are parameters of the algorithm, i.e. variables of the objective function, used for defining the model function, and values thereof can be obtained by data estimation or data learning, for example, weights in an artificial neural network, coefficients in a linear regression or a logistic regression, and the like; the hyper-parameters are parameters of the model, are variables outside the model, are used for defining higher-level concepts related to the model, such as complexity or learning capacity, cannot be learned directly from data in a standard model training process, and need to be manually set in advance according to experience, such as the learning rate of a training neural network, k in a k neighborhood, the number of layers of a decision tree, and the like; as shown in fig. 12, the algorithm parameter information, that is, the names, definitions, types, and the like of the parameters and the hyper-parameters are described, so as to provide information support for parameter configuration of the algorithm. It should be noted that the algorithms and the parameter information are not in a one-to-one correspondence relationship, and an algorithm may have one or more parameters or hyper-parameters; parameter information can also be absent in the algorithm, for example, the K-nearest neighbor algorithm is a nonparametric learning algorithm, and the optimal classifier is found by circularly iterating the hyperparametric K value.
And S120, storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base.
Referring to fig. 2, the formal expression of the algorithm knowledge is structurally stored in a Database Layer (Database Layer), forming a knowledge/model base.
And S130, providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to an application layer at an application service layer.
In some embodiments, the application service layer receives a user request (external information) sent by the application layer, invokes and/or combines a corresponding algorithm from a knowledge/model base in a database layer through a data interface to analyze and process data in the user request, generates an output result, and sends the output result as an output to the application layer.
In some embodiments, algorithmic knowledge in the spatial knowledge/model base is retrieved and managed by the application service layer. For example, the application service layer performs operations such as adding, deleting, modifying, querying and the like on the algorithm knowledge stored in the spatial knowledge/model base through a data interface.
Further, applications can be customized to user needs in the application layer. For example, a visualization presentation, recommendation system, and/or business intelligence function interface is formulated.
According to the embodiment of the disclosure, the following technical effects are achieved:
the disclosed spatial knowledge/model base is designed from the unified cognition angle of a machine learning algorithm, a knowledge/model base classification system related to a general machine learning algorithm is designed on the basis of researching various machine learning classification angles, an algorithm knowledge expression mode based on XML is selected, characteristic items such as input and output of the general machine learning algorithm are uniformly described, knowledge related to the machine learning algorithm is formed, comprehensive algorithm knowledge and model support are provided for spatial application, corresponding machine learning algorithms can be effectively selected, called or combined according to actual requirements, and the difficulty of selecting and using the machine algorithms in decision making of multi-granularity space-time objects is greatly reduced.
It is noted that while for simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present disclosure is not limited by the order of acts, as some steps may, in accordance with the present disclosure, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that acts and modules referred to are not necessarily required by the disclosure.
The above is a description of embodiments of the method, and the embodiments of the apparatus are further described below.
Fig. 13 shows a block diagram of an algorithm management device 1300 based on a spatial knowledge/model base system according to an embodiment of the present disclosure. The apparatus 1300 comprises:
the processing module 1301 is configured to classify, at the model layer, a machine learning algorithm pre-stored in a machine learning algorithm library of the resource layer; performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model;
a storage module 1302, configured to store the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base;
and the interaction module 1303 is used for providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer at the application service layer.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the described module may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
FIG. 14 shows a schematic block diagram of an electronic device 1400 that may be used to implement embodiments of the present disclosure. As shown, device 1400 includes a Central Processing Unit (CPU)1401 that can perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)1402 or loaded from storage unit 708 into a Random Access Memory (RAM) 1403. In the RAM1403, various programs and data required for the operation of the device 1400 can also be stored. The CPU 1401, ROM 1402, and RAM1403 are connected to each other via a bus 1404. An input/output (I/O) interface 1405 is also connected to bus 1404.
Various components in device 1400 connect to I/O interface 1405, including: an input unit 1406 such as a keyboard, a mouse, or the like; an output unit 1407 such as various types of displays, speakers, and the like; a storage unit 1408 such as a magnetic disk, optical disk, or the like; and a communication unit 1409 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1409 allows the device 1400 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processing unit 1401 performs the various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1408. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1400 via ROM 1402 and/or communication unit 1409. When the computer program is loaded into the RAM1403 and executed by the CPU 1401, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the CPU 701 may be configured to perform the method 100 in any other suitable manner (e.g., by way of firmware).
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (9)
1. An algorithm management method based on a space knowledge/model base system is characterized in that,
in the model layer, classifying machine learning algorithms prestored in a machine learning algorithm library of the resource layer; performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model;
storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base;
and at an application service layer, providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer.
2. The method of claim 1,
the spatial knowledge/model base system comprises a resource layer, a model layer, a database layer, an application service layer and an application layer; wherein,
the resource layer is used for integrating data resources; the data resources comprise hardware resources, a machine learning algorithm library and data resources;
the model layer is used for classifying the machine learning algorithms in the machine learning algorithm library, describing the classified machine learning algorithms and forming the knowledge of the general machine learning algorithm;
the database layer is used for storing the knowledge of the general machine learning algorithm;
the application service layer is used for managing data in the resource layer; data interaction is carried out through a data interface, and services are provided for users and/or programs;
the application layer is used for providing an access function of an application program for the client and realizing interface operation of a final user and control request and call of business activities.
3. The method of claim 1, wherein formalizing the algorithm knowledge of the classified machine learning algorithm according to the spatial algorithm description model comprises:
and describing metadata, algorithm characteristic information, algorithm input information, algorithm output information, algorithm operating environment and algorithm parameter information of the classified machine learning algorithm by adopting an XML knowledge representation method to form the knowledge of the classified machine learning algorithm.
4. The method of claim 3, wherein the spatial algorithm description model comprises:
metadata of the algorithm, algorithm characteristic information, algorithm input information, algorithm output information, algorithm operating environment and algorithm parameter information;
wherein the metadata of the algorithm comprises: version information, setup time, and/or contact information;
the algorithm characteristic information comprises: algorithm identification, name and/or function;
the algorithm input information includes: data type, data volume, data dimension, and/or data format;
the algorithm output information includes: data type, data format, data precision and/or data dimension;
the algorithm operating environment comprises: a software environment and a hardware environment;
the algorithm parameter information includes: and (4) operating parameter information by the algorithm.
5. The method of claim 4, further comprising:
and searching and managing the algorithm knowledge in the spatial knowledge/model base through the application service layer.
6. The method of claim 4, further comprising:
and formulating a visual display, recommendation system and/or business intelligent function interface in the application layer.
7. An algorithm management device based on a spatial knowledge/model base system, comprising:
the processing module is used for classifying machine learning algorithms prestored in a machine learning algorithm library of the resource layer in the model layer; performing formal expression of algorithm knowledge on the classified machine learning algorithm according to the spatial algorithm description model;
the storage module is used for storing the formal expression of the algorithm knowledge in a database layer to form a knowledge/model base;
and the interaction module is used for providing data interaction and processing services for the algorithm knowledge in the knowledge/model base to the application layer at the application service layer.
8. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110723773.2A CN113610104A (en) | 2021-06-29 | 2021-06-29 | Algorithm management method based on spatial knowledge/model base system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110723773.2A CN113610104A (en) | 2021-06-29 | 2021-06-29 | Algorithm management method based on spatial knowledge/model base system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113610104A true CN113610104A (en) | 2021-11-05 |
Family
ID=78336849
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110723773.2A Pending CN113610104A (en) | 2021-06-29 | 2021-06-29 | Algorithm management method based on spatial knowledge/model base system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113610104A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276456A (en) * | 2019-06-20 | 2019-09-24 | 山东大学 | A kind of machine learning model auxiliary construction method, system, equipment and medium |
CN110795567A (en) * | 2019-09-29 | 2020-02-14 | 北京远舢智能科技有限公司 | Knowledge graph platform |
CN111813870A (en) * | 2020-06-01 | 2020-10-23 | 武汉大学 | Machine learning algorithm resource sharing method and system based on unified description expression |
US20210117819A1 (en) * | 2019-10-17 | 2021-04-22 | Ranjith Pavanje Raja Rao | Scalable Architecture for Machine Learning Model Reuse |
-
2021
- 2021-06-29 CN CN202110723773.2A patent/CN113610104A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276456A (en) * | 2019-06-20 | 2019-09-24 | 山东大学 | A kind of machine learning model auxiliary construction method, system, equipment and medium |
CN110795567A (en) * | 2019-09-29 | 2020-02-14 | 北京远舢智能科技有限公司 | Knowledge graph platform |
US20210117819A1 (en) * | 2019-10-17 | 2021-04-22 | Ranjith Pavanje Raja Rao | Scalable Architecture for Machine Learning Model Reuse |
CN111813870A (en) * | 2020-06-01 | 2020-10-23 | 武汉大学 | Machine learning algorithm resource sharing method and system based on unified description expression |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10417528B2 (en) | Analytic system for machine learning prediction model selection | |
US11948003B2 (en) | System and method for automated production and deployment of packaged AI solutions | |
US10679169B2 (en) | Cross-domain multi-attribute hashed and weighted dynamic process prioritization | |
US20190014048A1 (en) | Method and system for processing data in an internet of things (iot) environment | |
US11093833B1 (en) | Multi-objective distributed hyperparameter tuning system | |
US11416754B1 (en) | Automated cloud data and technology solution delivery using machine learning and artificial intelligence modeling | |
CN110929047B (en) | Knowledge graph reasoning method and device for focusing on neighbor entity | |
US10453165B1 (en) | Computer vision machine learning model execution service | |
US10706598B2 (en) | Interface for data analysis | |
WO2019061991A1 (en) | Multi-element universal model platform modeling method, electronic device, and computer readable storage medium | |
US11861470B2 (en) | Simplistic machine learning model generation tool for predictive data analytics | |
CN108108743A (en) | Abnormal user recognition methods and the device for identifying abnormal user | |
CN112149838A (en) | Method, device, electronic equipment and storage medium for realizing automatic model building | |
US20240193481A1 (en) | Methods and systems for identification and visualization of bias and fairness for machine learning models | |
Jun et al. | Cloud-based big data analytics platform using algorithm templates for the manufacturing industry | |
US11983636B2 (en) | Automated analytical model retraining with a knowledge graph | |
EP4339843A1 (en) | Neural network optimization method and apparatus | |
US11797577B2 (en) | Smart data warehouse for cloud-based reservoir simulation | |
US20240078473A1 (en) | Systems and methods for end-to-end machine learning with automated machine learning explainable artificial intelligence | |
JP6995909B2 (en) | A method for a system that includes multiple sensors that monitor one or more processes and provide sensor data. | |
da Silva et al. | Online machine learning for auto-scaling in the edge computing | |
US11663228B2 (en) | Automated management of data transformation flows based on semantics | |
Provalov et al. | Synevarec: A framework for evaluating recommender systems on synthetic data classes | |
CN113610104A (en) | Algorithm management method based on spatial knowledge/model base system | |
US20230117893A1 (en) | Machine learning techniques for environmental discovery, environmental validation, and automated knowledge repository generation |
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 |