WO2019109589A1

WO2019109589A1 - Method and device for performing circuit design based on artificial intelligence

Info

Publication number: WO2019109589A1
Application number: PCT/CN2018/085647
Authority: WO
Inventors: 武春明; 石佳; 刘洁
Original assignee: 石家庄创天电子科技有限公司
Priority date: 2017-12-04
Filing date: 2018-05-04
Publication date: 2019-06-13
Also published as: CN109871558A

Abstract

A method and device for performing circuit design based on artificial intelligence. The method comprises the following steps: initializing circuit design according to a preset initialization circuit element (S201); creating a plurality of circuit design domains on the basis of an artificial intelligence algorithm (S202); performing matching on the basis of the respective circuit design domains and valuation values (S203); and conducting circuit design according to the valuation values of the respective circuit design domains and a design library (S204). The invention reduces risks in a circuit design process, increases quality of circuit design, and improves efficiency of circuit design.

Description

Method and device for circuit design based on artificial intelligence

This application claims the priority of the Chinese Patent Application filed on Dec. 4, 2017, filed on Dec. In this application.

Technical field

The embodiments of the present invention relate to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for circuit design based on artificial intelligence.

Background technique

The traditional electronic circuit design work requires complete components and instruments to be repeatedly adjusted and tested in the laboratory to complete. This requires a lot of time, effort and experiment costs. With the development of computer technology, the design of electronic circuit system has entered the stage of computer-aided design, and the electronic design CAD software has realized the function of computer-aided design.

For example, microwave/millimeter wave circuits are designed by computer-aided design (CAD). This design method involves the use of multiple discrete tools/programs and files in multiple formats. The design flow is manual and relatively fragmented. Specifically, for example, the database technology is used to process the circuit, that is, the name, position, size, and use image of each component in the circuit diagram are saved in a record of the database table, and the modification of each component is actually modifying the database. Corresponding to the recorded content, the components in the circuit diagram can be moved, deleted and saved separately in the form of separate components. The program results show that using the database technology to process the circuit diagram, it is very convenient to adjust the individual components, and after saving, you can adjust them arbitrarily.

However, the above computer-aided circuit design involves a number of involved links, such as functional design, circuit design, physical design, product testing and verification, each process generates highly relevant data, making the circuit design process risky and circuit design The poor quality ultimately leads to lower circuit design efficiency.

Summary of the invention

In view of this, one of the technical problems to be solved by the embodiments of the present invention is to provide a method and apparatus for circuit design based on artificial intelligence to overcome or alleviate the above-mentioned drawbacks in the prior art.

The embodiment of the present application provides a method for circuit design based on artificial intelligence, which includes the following steps:

Initializing the circuit design according to a preset initialization circuit element;

Creating multiple circuit design domains based on artificial intelligence algorithms;

Matching value evaluation values for each circuit design domain;

The circuit design is based on the value evaluation values of each circuit design domain and the design library.

Optionally, in any embodiment of the present invention, initializing the circuit design according to the preset initialization circuit element includes: selecting an initialization circuit element from the database to perform initialization of the circuit design according to the input circuit design element.

Optionally, in any embodiment of the present invention, the initialization circuit element includes at least one of the following: an active component, a passive component, a box, an input and output, and a circuit board template.

Optionally, in any embodiment of the present invention, creating the plurality of circuit design domains based on the artificial intelligence algorithm comprises: creating a plurality of circuit design first domain and second domain based on the artificial intelligence algorithm.

Optionally, in any embodiment of the present invention, creating the plurality of circuit designs based on the artificial intelligence algorithm, the first domain and the second domain comprise: creating the circuit design based on the artificial intelligence algorithm to create a relationship between the parent and the child domain The domain is designed with the second domain of the circuit.

Optionally, in any of the embodiments of the present invention, the domain matching value evaluation value for each circuit includes: designing a domain matching value evaluation value for each circuit according to the value evaluation model established based on the big data analysis.

Optionally, in any embodiment of the present invention, according to the value evaluation model established based on the big data analysis, the domain matching value evaluation value for each circuit includes: according to the value evaluation model established based on the big data analysis, for each The circuit design fields match at least one of an action value function, a reward function, and an evaluation state value function to determine a corresponding value evaluation value.

Optionally, in any embodiment of the present invention, performing circuit design according to the value evaluation value of each circuit design domain and the design library includes: performing circuit according to value evaluation value of each circuit design domain and design library and agent design.

Optionally, in any of the embodiments of the present invention, the circuit design according to the value evaluation value of each circuit design domain and the design library and the agent includes: evaluating the value according to the value of each circuit design domain, and designing the library and the intelligence. The body forms multiple circuit design tasks, and performs multi-tasking circuit design according to each circuit design task and design library and agent.

Embodiments of the present invention provide an apparatus for circuit design based on artificial intelligence, including:

a first unit for initializing a circuit design according to a preset initialization circuit element;

a second unit for creating a plurality of circuit design domains based on an artificial intelligence algorithm;

a third unit for matching the value of the value of each circuit design field;

The fourth unit is used for circuit design based on the value evaluation value of each circuit design domain and the design library.

In the embodiment of the present application, the circuit design is initialized according to a preset initialization circuit element; multiple circuit design domains are created based on the artificial intelligence algorithm; the domain matching value evaluation value is designed for each circuit; according to the value of each circuit design domain The evaluation value and the design library perform circuit design, which reduces the risk in the circuit design process, improves the quality of the circuit design, and ultimately improves the efficiency of the circuit design.

DRAWINGS

Some specific embodiments of the embodiments of the present application will be described in detail, by way of example, and not limitation, The same reference numbers in the drawings identify the same or similar parts. Those skilled in the art should understand that the drawings are not necessarily drawn to scale. In the figure:

1 is a schematic diagram showing the design logic of an artificial intelligence circuit design according to Embodiment 1 of the present invention;

2 is a schematic flowchart of a method for circuit design based on artificial intelligence according to Embodiment 2 of the present invention;

3 is a schematic flowchart of circuit design based on artificial intelligence combined with reinforcement learning according to Embodiment 3 of the present invention;

4 is a schematic diagram showing a preliminary structure of an optimal circuit according to Embodiment 4 of the present invention;

FIG. 5 is a schematic diagram of an agent system according to Embodiment 5 of the present invention; FIG.

FIG. 6 is a schematic structural diagram of an apparatus for designing a circuit based on artificial intelligence according to Embodiment 6 of the present invention.

Detailed ways

Any technical solution for implementing the embodiments of the present invention necessarily does not necessarily need to achieve all of the above advantages at the same time.

For a better understanding of the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments are only a part of the embodiments of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art should be within the scope of protection of the embodiments of the present invention based on the embodiments in the embodiments of the present invention.

The specific implementation of the embodiments of the present invention is further described below in conjunction with the accompanying drawings.

1 is a schematic logic diagram of a design of an artificial intelligence circuit according to Embodiment 1 of the present invention; as shown in FIG. 1 , in this embodiment, a design logic link of an artificial intelligence circuit design mainly includes: intelligent logic setting, intelligent logic design task, and intelligence. Logic design environment, intelligent logic design agent, in which intelligent logic settings include initialization related tasks, intelligent logic design tasks mainly include design task definitions to meet the actual needs of the user, intelligent logic design environment including relevant value evaluation values and design library recommendations And the selection of optional components or combination circuits in the design library. The artificial intelligence logic design agent includes setting up a corresponding data access interface for the design environment and the like.

2 is a schematic flowchart of a method for circuit design based on artificial intelligence according to Embodiment 2 of the present invention; as shown in FIG. 2, the method includes the following steps S201-S204:

S201, performing initialization of circuit design according to a preset initialization circuit element;

Optionally, in this embodiment or any other embodiment, performing initialization of the circuit design according to the preset initialization circuit element in step S201 may specifically include: selecting an initialization circuit from the database according to the input circuit design element. The element is initialized for circuit design.

The input circuit design elements may specifically include the function of the molding circuit, the size of the molding circuit, the cost of the molding circuit, and the like.

Further, in this embodiment, the initialization circuit element includes at least one of the following: an active component, a passive component, a box, an input and output, and a circuit board template. It should be noted that the initialization circuit elements can also be updated. In addition, the initialization circuit budget is only an example here, and is not a unique limitation.

Specifically, in the embodiment, when the initialization of the circuit design is performed according to the preset initialization circuit element in step S201, the initialization circuit element may be selected from the database to initialize the circuit design according to the input circuit design element.

Here, it should be noted that a large number of initialization elements are stored in the database, and these initialization elements are obtained through a large number of machine trainings, and have a variety of choices.

S202. Create multiple circuit design domains based on an artificial intelligence algorithm.

Optionally, in this embodiment or any other embodiment, when multiple circuit design domains are created based on the artificial intelligence algorithm in step S202, multiple circuit design first domains and second domains are specifically created based on the artificial intelligence algorithm.

Specifically, in step S202, when the plurality of circuit design first domain and the second domain are created based on the artificial intelligence algorithm, the first domain of the circuit design and the circuit design may be created based on the artificial intelligence algorithm to establish a mutual parent-child relationship. Second domain.

As shown in FIG. 1 above, the circuit design domain herein may include intelligent logic settings, logical design tasks, logical human-machine design environments, and logical design agents. The domains have parent-child domain logical relationships as shown in FIG. 1, and smart logic. Set to logic design task, logical man-machine design environment, parent domain of logic design agent, or logical design task, logical man-machine design environment, logical design agent set sub-domain for intelligent logic; logical design task is logical man-machine design The parent domain of the environment, or the logical human machine design environment, is a subdomain of the logical design task.

S203. Match value evaluation values for each circuit design domain;

Optionally, when the domain matching value evaluation value is designed for each circuit in step S203, the value evaluation value of each domain may be matched according to the value evaluation model established based on the big data analysis.

Further, in step S203, according to the value evaluation model established based on the big data analysis, when the domain matching value evaluation value is designed for each circuit, the value of each circuit design field is matched according to the value evaluation model established based on the big data analysis. At least one of a function, a reward function, and an evaluation state value function to determine a corresponding value evaluation value.

S204: Perform circuit design according to the value evaluation value of each circuit design domain and the design library.

Optionally, in the step S204, according to the value evaluation value of each circuit design domain and the design library, the circuit design may be performed according to the value evaluation value of each circuit design domain and the design library and the intelligent body.

Further, when the circuit design is performed according to the value evaluation value of each circuit design domain and the design library and the agent in step S204, a plurality of circuits may be formed according to the value evaluation value of each circuit design domain and the design library and the smart body. Design tasks, multi-tasking circuit design based on each circuit design task and design library and agent.

In summary, the above value evaluation system is equivalent to the reinforcement learning system, and a value evaluation value defines a policy framework for enhancing the interaction between the agent and the corresponding design environment. In the process of interaction, it is equivalent to enhancing the interaction between the agent and the design environment. When performing a circuit design operation, the agent moves from one state to another in the design environment, and the quality definition of a state operation combination An action value function. The action value function determines the expected utility of a (best choice) action. The reward function informs the agent of the current actions, status, and rewards received in each state. Preferably, the reward is provided directly by the design environment, but the value is pre-estimated based on the circuit design made by the agent.

In addition, in the above embodiment, each domain (and corresponding sub-domain) domain agent related to the circuit design is captured in the interaction behavior of the circuit design process, and can be stored in a database for subsequent circuit design. reference.

FIG. 3 is a schematic flowchart of circuit design based on artificial intelligence in combination with reinforcement learning according to Embodiment 3 of the present invention; it should be noted that, in this embodiment, only a brief description is provided. For more complicated or detailed description, please refer to the above figure. 1 Example is described.

S301. Acquire a design indicator input;

In this embodiment, the design specifications are not limited to the size, volume, and cost of the molding circuit, and the functions to be realized by the molding circuit.

S302, initializing circuit design;

Please refer to the description of Figure 1 above for the initialization circuit design.

S303, creation or setting of a circuit design domain;

For a description of the circuit design field, please refer to the description of Figure 1 above.

S304. Generate a value evaluation value of each circuit design domain.

Please refer to Figure 1 above for the generation of the value evaluation value.

S305. The optimal circuit preliminary structure for obtaining the maximum mechanism evaluation value;

S306. Cache the optimal circuit preliminary structure into the database;

S307. Optimize the preliminary structure of the optimal circuit.

In this embodiment, the optimization may not be optimized after the simulation test of the optimal circuit preliminary structure, and the experience optimization may be directly performed based on the manual.

4 is a schematic diagram of a preliminary structure of an optimal circuit according to Embodiment 4 of the present invention; as shown in FIG. 4, the method includes the following steps:

S401 extracts an initialization circuit element from the data;

S402, performing initialization;

After the initialization, the following steps S403A, S403B, and S403C are performed:

S403A, performing the configuration related to FIG. 1 in the circuit design domain 1;

S403B, performing the configuration related to FIG. 1 in the circuit design domain 2;

S403C, performing the configuration related to FIG. 1 in the circuit design domain 3;

In the above steps S403A, S403B, S403C, simultaneously through step S404, using the graphics library and database of the specific circuit in the design library to participate in steps S403A, S403B, S403C;

S404. A graphics library and a database using specific circuits in the design library;

S405. Perform related configuration of FIG. 1 based on multiple targets.

S406. Performing a circuit design for the multi-target related configuration preferably obtains a preliminary structure of the circuit design.

5 is a description of an agent system according to Embodiment 5 of the present invention; as shown in FIG. 5, a definition and update of a signal interconnection agent, a component agent, and a structure agent are performed based on a big data processing engine, and at the same time In the definition and process of the reference, the basic circuit sample library is obtained, and finally the multi-processing agent is obtained; in order to improve the accuracy or effectiveness of the agent, the processing process of the verification agent is also added, and at the same time, combined with the existing in the database The circuit design elements are verified to output the initial structure of the circuit design or the final structure of the circuit design during circuit design.

6 is a schematic structural diagram of an apparatus for designing a circuit based on artificial intelligence according to Embodiment 6 of the present invention; as shown in FIG. 6, the method includes:

The first unit 601 is configured to perform initialization of the circuit design according to the preset initialization circuit element;

a second unit 602, configured to create multiple circuit design domains based on an artificial intelligence algorithm;

a third unit 603, configured to match a value evaluation value for each circuit design field;

The fourth unit 604 is configured to perform circuit design according to the value evaluation value of each circuit design domain and the design library.

Optionally, the first unit 601 is further configured to select an initialization circuit element from the database to perform initialization of the circuit design according to the input circuit design element. The initialization circuit element includes at least one of the following: an active component, a passive component, a case, an input and output, and a circuit board template.

Optionally, the second unit 602 is further configured to create a plurality of circuit design first domain and second domain based on an artificial intelligence algorithm.

Optionally, the second unit 602 is further configured to create the first domain of the circuit and the second domain of the circuit design based on an artificial intelligence algorithm to create a mutual parent domain relationship.

Optionally, the second unit 602 is further configured to design a domain matching value evaluation value for each circuit according to a value evaluation model established based on big data analysis.

Optionally, in any embodiment of the present invention, the second unit 602 is further configured to match an action value function, a reward function, and an evaluation state for each circuit design domain according to a value evaluation model established based on big data analysis. At least one of the value functions determines a corresponding value estimate.

Optionally, in any embodiment of the present invention, the second unit 602 is further configured to perform circuit design according to a value evaluation value of each circuit design domain and a design library and an agent.

Optionally, in any embodiment of the present invention, the fourth unit 604 is further configured to form a plurality of circuit design tasks according to the value evaluation value of each circuit design domain and the design library and the agent, according to each circuit Design tasks and design libraries as well as intelligent multi-tasking circuit design.

In the embodiment of the foregoing apparatus, the first unit 601, the second unit 602, the third unit 603, and the fourth unit 604 may be multiplexed with each other.

In the embodiment of the foregoing apparatus, the first unit 601, the second unit 602, the third unit 603, and the fourth unit 604 may be set based on a distributed architecture, and the total number thereof may not be only four or more than four or less than four. One.

In the above embodiment of the present application, the circuit design is initialized according to a preset initialization circuit element; a plurality of circuit design fields are created based on the artificial intelligence algorithm; and the domain matching value evaluation value is designed for each circuit; according to each circuit design domain The value evaluation value and the design library perform circuit design, which reduces the risk in the circuit design process, improves the quality of the circuit design, and finally improves the efficiency of the circuit design.

The device of FIG. 6 above may be disposed on the electronic terminal at the front end and may be disposed on a server in the background.

In various embodiments, reference is made to the accompanying drawings. However, some embodiments may be without one or more of these specific details, or in combination with other known methods and structures. In the following description, numerous specific details are set forth, such as the specific structure, In other instances, well known semiconductor processing techniques and fabrication techniques have not been described in detail to avoid obscuring the present invention. Throughout the specification, "one embodiment" means that a particular feature, structure, configuration, or feature described in this embodiment is included in at least one embodiment of the invention. Thus, the appearance of the phrase "in one embodiment", "the" Furthermore, the particular features, structures, configurations, or characteristics may be combined in any suitable manner in one or more embodiments.

The terms "generating," "in," "in," "in," and "in" as used herein may refer to the relative position relative to another layer. One layer "generates", "is", or "at" another layer or another layer that may be in direct contact with another layer or may have one or more intervening layers. A layer "on" layer may be in direct contact with the layer or may have one or more intervening layers.

Before the following detailed description, the definitions of certain words and phrases used throughout this patent document may be useful: the terms "include" and "comprise" and variations thereof mean The term "or" is inclusive, meaning and/or; the phrase "associated with" and "associated therewith" and variations thereof may be meant to include , included, "connected with", included, included, "connected to..." or "connected to", "coupled to" or "coupled with", "communicable with" "cooperating with", interlaced, juxtaposed, close to, "constrained to" or "constrained with", possessed, "having a property of", etc.; and the term "controller" means controlling at least one operation Any equipment, system or part thereof,

Such devices may be implemented in hardware, firmware or software, or in some combination of at least two of hardware, firmware and software. It should be noted that the functionality associated with any particular controller may be centralized or distributed locally or remotely. The definitions of certain words and phrases are provided throughout this patent document, and those skilled in the art will appreciate that in many cases, if not the most cases, such definitions apply to the prior art and to the words so defined. And the future use of phrases.

In the present disclosure, the expression "include" or "may include" refers to the existence of the corresponding function, operation or element, and does not limit one or more additional functions, operations or elements. In the present disclosure, terms such as "include" and / or "have" are understood to mean certain features, numbers, steps, operations, components, elements or combinations thereof, and are not to be construed as being excluded. The existence or additional possibility of one or more other characteristics, numbers, steps, operations, constituent elements, elements or combinations thereof.

In the present disclosure, the expression "A or B", "at least one of A or / and B" or "one or more of A or / and B" may include all possible combinations of the listed items. For example, the expression "A or B", "at least one of A and B" or "at least one of A or B" may include: (1) at least one A, (2) at least one B, or (3) at least One A and at least one B.

The expression "first", "second", "the first" or "the second" as used in the various embodiments of the present disclosure may modify various components regardless of order and/or importance. , but these statements do not limit the corresponding components. The above statements are only used for the purpose of distinguishing components from other components. For example, the first user device and the second user device represent different user devices, although both are user devices. For example, a first element could be termed a second element, and a second element could be termed a first element, without departing from the scope of the disclosure.

When an element (eg, a first element) is referred to as being "operably or communicably coupled" or "operably or communicably" coupled to another element (eg, a second element) An element (e.g., a second element) or "connected to" another element (e.g., a second element) is understood to mean that the one element is directly connected to the other element or the one element is via the other element (e.g., The third component is indirectly connected to the other component. Rather, it will be understood that when an element (e.g., a first element) is referred to as "directly connected" or "directly connected" to another element (the second element), then no element (e.g., the third element) is inserted in either Between the people.

The expression "configured to" as used herein may be used interchangeably with the following expressions: "suitable to", "capable of having", "designed as", "suitable", "manufactured as" or "capable of being able to" ". The phrase "configured to" does not necessarily mean "designed specifically" on hardware. Alternatively, in some cases, the expression "a device configured as" may mean that the device "can..." with other devices or components. For example, the phrase "a processor adapted to (or configured to) perform A, B, and C" may mean a dedicated processor (eg, an embedded processor) for performing only the corresponding operations or may be stored in the storage device by execution A general purpose processor (eg, a central processing unit (CPU) or an application processor (AP)) in which one or more software programs perform corresponding operations.

The terms used in the present disclosure are only used to describe specific embodiments and are not intended to limit the disclosure. A singular form as used herein may also include a plural form, unless the context clearly dictates otherwise.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Unless explicitly defined in the present disclosure, such a term as defined in a commonly used dictionary may be interpreted as having the same meaning as in the context of the related art, and should not be construed as having an ideal. Or too formal meaning. In some instances, the terms defined in the present disclosure are not to be construed as limiting the embodiments of the present disclosure.

The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules, ie may be located A place, or it can be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Through the description of the above embodiments, those skilled in the art can clearly understand that the various embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on such an understanding, portions of the above technical solutions that contribute substantially or to the prior art may be embodied in the form of a software product that may be stored in a computer readable storage medium, the computer readable record The medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer). For example, a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , an infrared signal, a digital signal, etc., etc., the computer software product comprising instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the various embodiments or portions of the embodiments described Methods.

Finally, it should be noted that the above embodiments are only used to explain the technical solutions of the embodiments of the present application, and are not limited thereto; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that The technical solutions described in the foregoing embodiments may be modified, or some of the technical features may be equivalently replaced; and the modifications or substitutions do not deviate from the spirit of the technical solutions of the embodiments of the present application. range.

Those skilled in the art will appreciate that embodiments of the embodiments of the invention may be provided as a method, apparatus (device), or computer program product. Thus, embodiments of the invention may be in the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, embodiments of the invention may take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Embodiments of the invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Claims

A method for circuit design based on artificial intelligence, comprising:

Initializing the circuit design according to a preset initialization circuit element;

Creating multiple circuit design domains based on artificial intelligence algorithms;

Matching value evaluation values for each circuit design domain;

The circuit design is based on the value evaluation values of each circuit design domain and the design library.
The method for circuit design based on artificial intelligence according to claim 1, wherein the initializing the circuit design according to the preset initialization circuit element comprises: selecting an initialization circuit element from the database according to the input circuit design element. Initialization of the circuit design.
The method for circuit design based on artificial intelligence according to claim 2, wherein the initialization circuit element comprises at least one of: an active component, a passive component, a box, an input and output, and a circuit. Board template.
The method for circuit design based on artificial intelligence according to claim 1, wherein the creating the plurality of circuit design domains based on the artificial intelligence algorithm comprises: creating a plurality of circuit design first domain and second domain based on the artificial intelligence algorithm.
The method for circuit design based on artificial intelligence according to claim 4, wherein the creating the plurality of circuit designs based on the artificial intelligence algorithm, the first domain and the second domain comprise: creating a mutual relationship as a parent-child domain relationship based on the artificial intelligence algorithm The circuit design first domain and the circuit design second domain.
The method for circuit design based on artificial intelligence according to claim 1, wherein the design value matching value for each circuit design field comprises: matching each circuit design domain according to a value evaluation model established based on big data analysis. Value evaluation value.
The method for circuit design based on artificial intelligence according to claim 6, wherein, according to the value evaluation model established based on the big data analysis, the evaluation value of the matching value of each circuit design domain includes: according to the analysis based on the big data analysis. The value evaluation model matches at least one of an action value function, a reward function, and an evaluation state value function for each circuit design field to determine a corresponding value evaluation value.
The method for circuit design based on artificial intelligence according to claim 1, wherein the circuit design according to the value evaluation value of each circuit design domain and the design library comprises: evaluating values and designing values according to each circuit design domain. The library and the agent perform circuit design.
The method for circuit design based on artificial intelligence according to claim 8, wherein the circuit design according to the value evaluation value of each circuit design domain and the design library and the agent comprises: evaluating the value according to each circuit design domain Values and design libraries and agents form multiple circuit design tasks, with multi-tasking circuit design based on each circuit design task and design library and agent.
An apparatus for circuit design based on artificial intelligence, comprising:

a first unit for initializing a circuit design according to a preset initialization circuit element;

a second unit for creating a plurality of circuit design domains based on an artificial intelligence algorithm;

a third unit for matching the value of the value of each circuit design field;

The fourth unit is used for circuit design based on the value evaluation value of each circuit design domain and the design library.