CN117094260B - Command interaction system based on natural language - Google Patents
Command interaction system based on natural language Download PDFInfo
- Publication number
- CN117094260B CN117094260B CN202311334126.8A CN202311334126A CN117094260B CN 117094260 B CN117094260 B CN 117094260B CN 202311334126 A CN202311334126 A CN 202311334126A CN 117094260 B CN117094260 B CN 117094260B
- Authority
- CN
- China
- Prior art keywords
- description
- function
- natural language
- feature vector
- command
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 18
- 230000006870 function Effects 0.000 claims abstract description 139
- 230000004044 response Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 82
- 238000013507 mapping Methods 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 3
- 238000013461 design Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/32—Circuit design at the digital level
- G06F30/337—Design optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/32—Circuit design at the digital level
- G06F30/33—Design verification, e.g. functional simulation or model checking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the EDA field, in particular to a command interaction system based on natural language, which automatically executes commands and feeds back results after a user inputs a natural language text request in a conversation window, and specifically obtains objective function description and objective function definition according to the natural language text request, and inputs the objective function description and the natural language text request of the user into a second natural language model interface to obtain function parameters; and finally, automatically feeding back a response result after the command is executed in a natural language mode, wherein the user does not need to input a corresponding command preset by the EDA tool in the whole process, so that the learning cost of the user is reduced, and the usability of the EDA tool is improved.
Description
Technical Field
The invention relates to the EDA field, in particular to a command interaction system based on natural language.
Background
EDA, collectively Electronic Design Automation, chinese is electronic design automation. It is simply understood that EDA is software specially used for designing a chip, and because of the high trial-and-error cost of the chip in the actual production link, EDA is required to have strong and professional simulation and verification capabilities, so that the success rate of chip streaming and even production links is improved. EDA is widely applied to a plurality of links such as chip design, manufacturing, packaging and the like, and bears a plurality of core works such as chip development including circuit design, circuit verification, performance analysis and the like.
Mastering the EDA requires familiarity with preset various command operations, and as the EDA tool provides an increasingly wide range of design functions, it has a huge number of command operations, and the number of command operations increases, which greatly increases the learning cost of the user. Therefore, how to reduce the learning cost of the user is a technical problem to be solved.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme: a natural language based command interaction system, the system comprising a human-machine interaction session window, an EDA command interface, a first natural language model interface and a second natural language model interface; when a user inputs a natural language text request in a man-machine interaction session window to specify EDA to execute a specified command, the following steps are executed:
s100, acquiring an objective function description and an objective function definition according to a natural language text request input by a user, wherein the method comprises the following steps:
s110, inputting the natural language text request into a first natural language model interface to obtain a request feature vector.
S120, inquiring a description feature vector library according to the request feature vector to obtain a target description feature vector matched with the request feature vector; wherein the descriptive feature vector library includes descriptive feature vectors of function descriptions of all command functions specified in advance.
S130, acquiring an objective function description and an objective function definition according to the objective description feature vector.
S200, inputting the objective function description and the natural language text request of the user into a second natural language model interface to obtain response data; the response data includes a function parameter.
S300, filtering the response data to obtain function parameters.
S400, calling the definition of the target function through the EDA command interface according to the function parameters and executing the target function to obtain an execution result.
S500, inputting the execution result, the natural language text request and the target description feature vector into a second natural language model to obtain a final natural language response result, and feeding back the final natural language response result to the user through a man-machine interaction session window.
The invention has at least the following beneficial effects:
the invention provides a command interaction system based on natural language, which automatically executes commands and feeds back results after a user inputs a natural language text request in a session window, specifically obtains objective function description and objective function definition according to the natural language text request, and inputs the objective function description and the natural language text request of the user into a second natural language model interface to obtain function parameters; and finally, automatically feeding back a response result after the command is executed in a natural language mode, wherein the user does not need to input a corresponding command preset by the EDA tool in the whole process, so that the learning cost of the user is reduced, and the usability of the EDA tool is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a command interaction step based on natural language according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The invention provides a command interaction system based on natural language, which comprises a man-machine interaction session window, an EDA command interface, a first natural language model interface and a second natural language model interface.
Referring to fig. 1, when a user inputs a natural language text request to designate EDA to execute a designation command in a man-machine interaction session window, the following steps are performed:
s100, acquiring an objective function description and an objective function definition according to a natural language text request input by a user.
Wherein the user-entered natural language text request is a user intent, e.g., the user-entered natural language text request is "set component a to red".
It should be noted that a large number of command functions are preset in the EDA tool, and each command function is a function of an associated command in the EDA tool. The command function corresponds to a layer of translation of the command.
Wherein, what type of return value of the command function, input parameters and output parameters, and which commands are executed by the function body are specifically defined in the function definition of the command function.
Wherein the function description is a pre-specified natural language description of the command function.
As a preferred embodiment, the function description includes a function name field, a function description field, a parameter field, and a parameter description field.
As one example, wherein the function of pick_on_canvas is defined as: the input parameters are x-coordinate, y-coordinate, and the function body is an external interface function pick (x, y). The function description of pick_on_canvas includes: function name field: pick_on_canvas. Function description field: the x-coordinate and y-coordinate positions specified on the canvas, the mouse left click operation. Parameter field: x and y. Parameter description field: "x", the data type is a digital type, and the description of x is the abscissa position; "y", the data type is a digital type, and the description of y is the ordinate position.
Further, S100 includes the following steps:
s110, inputting the natural language text request into a first natural language model interface to obtain a request feature vector.
Optionally, the first natural language model is a text embedding model, a word embedding model or a large language model based on deep learning, and other models capable of converting natural language into feature vectors in the prior art fall within the protection scope of the present invention. The word embedding model may be a text embedding model. The large language model based on deep learning can be a chatGPT model, etc.
Preferably, the text embedding model is a text-embedding-ada-002 model.
Wherein the first natural language model is a trained model. The first natural language model converts a natural language text request into a request feature vector as a set of fixed feature vectors.
S120, inquiring a description feature vector library according to the request feature vector to obtain a target description feature vector matched with the request feature vector; wherein the descriptive feature vector library includes descriptive feature vectors of function descriptions of all command functions specified in advance.
Alternatively, the description feature vector library is saved as a database, or the description feature vector library is saved as a file.
As a preferred embodiment, the step of obtaining each description feature vector in the description feature vector library in S120 includes:
s121, acquiring command functions and function descriptions of different commands in the EDA.
S122, inputting the function description of each command function into the first natural language model interface to obtain a description feature vector of the function description of each command function.
It should be noted that, the first natural language model interface generates the request feature vector and the description feature vector library respectively, and the models for generating the feature vectors are the same.
Optionally, the matching algorithm is a euclidean distance, cosine similarity or clustering algorithm between the request feature vector and each description feature vector, and the target description feature vector is the description feature vector with the highest matching degree with the request feature vector. The highest matching degree means: when the Euclidean distance is adopted, the matching degree of the description feature vector with the minimum Euclidean distance with the request feature vector is highest; when cosine similarity is adopted, the matching degree of the description feature vector with the maximum similarity with the request feature vector is the highest; when a clustering algorithm is adopted, the matching degree of the description feature vectors which are in the same type with the request feature vectors is highest; if there are multiple description feature vectors in the same class, the Euclidean distance between each description feature vector and the request feature vector is calculated, and the matching degree between the Euclidean distance between each description feature vector and the description feature vector with the minimum Euclidean distance of the request feature vector is the highest. Other algorithms in the prior art capable of calculating the similarity between two feature vectors fall within the scope of the present invention.
Preferably, the algorithm of the similarity is cosine similarity.
S130, acquiring an objective function description and an objective function definition according to the objective description feature vector.
As a preferred embodiment, S120 further includes:
and S123, storing the function description and the description feature vector of each command function as a description mapping relation to obtain a description feature vector library. Then:
the step of obtaining the objective function description in S130 further includes: and inquiring the description feature vector library according to the target description feature vector, acquiring a target description mapping relation, and extracting target function description in the target description mapping relation.
As a preferred embodiment, the step of obtaining the objective function definition in S130 further includes:
s131, storing the function definition of each function name and the command function thereof as a mapping relation to obtain a function mapping relation table.
S132, extracting a function name field in the objective function description to obtain an objective function name field, and searching a mapping relation in a mapping relation table according to the objective function name field to obtain an objective mapping relation.
S133, extracting an objective function definition in the objective mapping relation.
As another preferred embodiment, in order to further improve the query efficiency, S120 further includes:
s124, storing the function name, function definition, function description and description feature vector of each command function as global mapping relation to obtain description feature vector library. Then:
the step of obtaining the objective function description and the objective function definition in S130 further comprises the steps of inquiring a description feature vector library according to the objective description feature vector to obtain an objective global mapping relation; and extracting the target function description and the target function definition in the target global mapping relation.
According to the embodiment, the target description feature vector can be queried once and the target function description and the target function definition can be extracted, and compared with the mode that the description mapping relation table and the function mapping relation table are queried twice respectively and data are extracted twice, the query efficiency is greatly improved.
S200, inputting the objective function description and the natural language text request of the user into a second natural language model interface to obtain response data; the response data includes a function parameter.
Preferably, the second natural language model is a deep learning-based large language model. The large language model based on deep learning can be a chatGPT model, and other models capable of understanding natural language semantics in the prior art also fall into the protection scope of the invention.
It should be noted that, the second natural language model is a trained large-scale language model, and after the second natural language model receives the description of the objective function, the function parameters necessary for the objective function are learned. When the natural language text request input by the user does not comprise the function parameters in the objective function description or the necessary function parameters are not complete, the second natural language model carries out conversation with the user through the conversation window, and the user is guided to input the corresponding parameters. After the necessary function parameters are acquired, the acquired function parameters are taken as response data.
Alternatively, the first natural language model and the second natural language model may use the same model capable of implementing both functions at the same time. For example, a chatGPT model.
S300, filtering the response data to obtain function parameters.
S400, calling the definition of the target function through the EDA command interface according to the function parameters and executing the target function to obtain an execution result.
It should be noted that, the execution result is returned for the format specified by the system.
S500, inputting the execution result, the natural language text request and the target description feature vector into a second natural language model to obtain a final natural language response result, and feeding back the final natural language response result to the user through a man-machine interaction session window.
It should be noted that, the execution result, the natural language text request and the target description feature vector are input into the natural language model again, and the natural language model can respond to the result through the session window by using the logic feedback of the natural language.
As an example, when the user inputs a natural language text request "set the color of the component U1 to green" in the conversation window, after the corresponding command is executed through the above-described method, the result fed back to the user in the conversation window is "the color of the current component U1 is originally black, and has been set to green". Details of the automatic execution include: after the execution of the step S100, a target command function assignment_color ()' closest to the natural language text request input by the user can be obtained; after the execution of S200 and S300, the function parameters of the target command function assignment_color () can be obtained; after the execution of S300, the result of the target command function call execution can be obtained; after S500 is performed, the result of the execution can be fed back to the user in natural language.
In the executing process of the method, after the user inputs the natural language text request in the conversation window, the method automatically executes and automatically feeds back the response result after executing the command in a natural language mode, the user does not need to input the command, the learning cost of the user is reduced, and the usability of the EDA tool is improved.
Embodiments of the present invention also provide a non-transitory computer readable storage medium that may be provided in an electronic device to store at least one instruction or at least one program related to implementing one of the method embodiments, the at least one instruction or the at least one program being loaded and executed by the processor to implement steps S100-S500 provided by the above embodiments.
Embodiments of the present invention also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present invention also provide a computer program product comprising program code for causing an electronic device to carry out the steps according to the various exemplary embodiments of the invention as described in the specification, when said program product is run on the electronic device.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (7)
1. A command interaction system based on natural language, which is characterized by comprising a man-machine interaction session window, an EDA command interface, a first natural language model interface and a second natural language model interface; when a user inputs a natural language text request in a man-machine interaction session window to specify EDA to execute a specified command, the following steps are executed:
s100, acquiring an objective function description and an objective function definition according to a natural language text request input by a user, wherein the method comprises the following steps:
s110, inputting a natural language text request into a first natural language model interface to obtain a request feature vector;
s120, inquiring a description feature vector library according to the request feature vector to obtain a target description feature vector matched with the request feature vector; the description feature vector library comprises description feature vectors of function descriptions of all pre-specified command functions;
s130, acquiring an objective function description and an objective function definition according to the objective description feature vector;
s200, inputting the objective function description and the natural language text request of the user into a second natural language model interface to obtain response data; the response data includes a function parameter;
s300, filtering the response data to obtain function parameters;
s400, calling an objective function definition through an EDA command interface according to the function parameters and executing the objective function definition to obtain an execution result;
s500, inputting the execution result, the natural language text request and the target description feature vector into a second natural language model to obtain a final natural language response result, and feeding back the final natural language response result to the user through a man-machine interaction session window;
the step of obtaining each description feature vector in the description feature vector library in S120 includes:
s121, acquiring command functions and function descriptions of different commands in the EDA;
s122, inputting the function description of each command function into the first natural language model interface to obtain a description feature vector of the function description of each command function.
2. The system of claim 1, wherein the function description includes a function name field, a function description field, a parameter field, and a parameter description field.
3. The system of claim 2, wherein S120 further comprises:
s123, storing function description and description feature vectors of each command function as description mapping relations to obtain a description feature vector library; then:
the step of obtaining the objective function description in S130 further includes: and inquiring the description feature vector library according to the target description feature vector, acquiring a target description mapping relation, and extracting target function description in the target description mapping relation.
4. A system according to claim 3, wherein the step of obtaining the objective function definition in S130 further comprises:
s131, storing function definitions of each function name and command functions thereof as a mapping relation to obtain a function mapping relation table;
s132, extracting a function name field in the objective function description to obtain an objective function name field, and searching a mapping relation in a mapping relation table according to the objective function name field to obtain an objective mapping relation;
s133, extracting an objective function definition in the objective mapping relation.
5. The system of claim 1, wherein S120 further comprises:
s124, storing the function name, function definition, function description and description feature vector of each command function as global mapping relation to obtain description feature vector library; then:
the step of obtaining the objective function description and the objective function definition in S130 further comprises the steps of inquiring a description feature vector library according to the objective description feature vector to obtain an objective global mapping relation; and extracting the target function description and the target function definition in the target global mapping relation.
6. The system of claim 1, wherein the matching algorithm in S120 is a euclidean distance, cosine similarity, or clustering algorithm between the requested feature vector and each of the descriptive feature vectors, and the target descriptive feature vector is the descriptive feature vector having the highest degree of matching with the requested feature vector.
7. The system of claim 1, wherein the first natural language model is a text embedding model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311334126.8A CN117094260B (en) | 2023-10-16 | 2023-10-16 | Command interaction system based on natural language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311334126.8A CN117094260B (en) | 2023-10-16 | 2023-10-16 | Command interaction system based on natural language |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117094260A CN117094260A (en) | 2023-11-21 |
| CN117094260B true CN117094260B (en) | 2024-01-19 |
Family
ID=88771971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311334126.8A Active CN117094260B (en) | 2023-10-16 | 2023-10-16 | Command interaction system based on natural language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094260B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902248A (en) * | 2013-09-06 | 2014-07-02 | 王柳 | Intelligent WeChat bank system based on natural language automatic scheduler and intelligent scheduling method for computer system through natural language |
| US8983823B1 (en) * | 2005-12-29 | 2015-03-17 | The Mathworks, Inc. | Verification harness for automatically generating a text-based representation of a graphical model |
| CN114386425A (en) * | 2022-03-24 | 2022-04-22 | 天津思睿信息技术有限公司 | Big data system establishing method for processing natural language text content |
| CN115858404A (en) * | 2023-03-01 | 2023-03-28 | 上海合见工业软件集团有限公司 | EDA-based graphical user interface test system |
| CN116108790A (en) * | 2023-04-12 | 2023-05-12 | 广州智慧城市发展研究院 | Analog circuit layout structural characteristic representation method and related components |
| CN116663491A (en) * | 2023-07-26 | 2023-08-29 | 北京云枢创新软件技术有限公司 | Method, equipment and medium for covering group condition constraint statement based on BDD solving function |
| CN116775442A (en) * | 2022-03-10 | 2023-09-19 | 上海合见工业软件集团有限公司 | Software debugging system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003271389A (en) * | 2002-03-19 | 2003-09-26 | Shuichi Araki | Method for operating software object in natural language and its program |
| US20140156282A1 (en) * | 2012-11-15 | 2014-06-05 | Maxwell Worthington, Llc | Method and system for controlling target applications based upon a natural language command string |
| US11113430B2 (en) * | 2014-05-09 | 2021-09-07 | Autodesk, Inc. | Techniques for using controlled natural language to capture design intent for computer-aided design |
| US10242139B2 (en) * | 2016-03-30 | 2019-03-26 | Synopsys, Inc. | Scheme and design markup language for interoperability of electronic design application tool and browser |
| US10783287B2 (en) * | 2017-06-14 | 2020-09-22 | International Business Machines Corporation | Employing natural language processing to facilitate geospatial analysis |
| EP3625699A1 (en) * | 2017-10-25 | 2020-03-25 | Google LLC | Natural language processing with an n-gram machine |
| EP3857330A1 (en) * | 2018-09-27 | 2021-08-04 | Google LLC | Automatic navigation of interactive web documents |
| US10853398B2 (en) * | 2018-11-13 | 2020-12-01 | Adobe Inc. | Generating three-dimensional digital content from natural language requests |
| US20230214583A1 (en) * | 2019-01-08 | 2023-07-06 | Paperless Parts, Inc. | Systems and methods for generating textual instructions for manufacturers from hybrid textual and image data |
| US20210150270A1 (en) * | 2019-11-19 | 2021-05-20 | International Business Machines Corporation | Mathematical function defined natural language annotation |
| TWI798513B (en) * | 2019-12-20 | 2023-04-11 | 國立清華大學 | Training method of natural language corpus for the decision making model of machine learning |
| US20230148108A1 (en) * | 2021-11-10 | 2023-05-11 | Graf Research Corporation | Computer-implemented verification of a hardware design implementation against a natural language description of the hardware design or software code against a natural language description of a software application |
-
2023
- 2023-10-16 CN CN202311334126.8A patent/CN117094260B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8983823B1 (en) * | 2005-12-29 | 2015-03-17 | The Mathworks, Inc. | Verification harness for automatically generating a text-based representation of a graphical model |
| CN103902248A (en) * | 2013-09-06 | 2014-07-02 | 王柳 | Intelligent WeChat bank system based on natural language automatic scheduler and intelligent scheduling method for computer system through natural language |
| CN116775442A (en) * | 2022-03-10 | 2023-09-19 | 上海合见工业软件集团有限公司 | Software debugging system |
| CN114386425A (en) * | 2022-03-24 | 2022-04-22 | 天津思睿信息技术有限公司 | Big data system establishing method for processing natural language text content |
| CN115858404A (en) * | 2023-03-01 | 2023-03-28 | 上海合见工业软件集团有限公司 | EDA-based graphical user interface test system |
| CN116108790A (en) * | 2023-04-12 | 2023-05-12 | 广州智慧城市发展研究院 | Analog circuit layout structural characteristic representation method and related components |
| CN116663491A (en) * | 2023-07-26 | 2023-08-29 | 北京云枢创新软件技术有限公司 | Method, equipment and medium for covering group condition constraint statement based on BDD solving function |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117094260A (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110888897B (en) | Method and device for generating SQ L statement according to natural language | |
| JP5538363B2 (en) | System and method for changing geometric relationship in solid model, and computer program | |
| US8346773B2 (en) | Product classification system | |
| CN106649503A (en) | Query method and system based on sql | |
| CN111210005B (en) | Equipment operation method and device, storage medium and electronic equipment | |
| CN109710220B (en) | Relational database query method, relational database query device, relational database query equipment and storage medium | |
| CN110146080B (en) | SLAM loop detection method and device based on mobile robot | |
| CN115878003B (en) | Method and system for automating RPA webpage operation based on Transformer | |
| WO2024098524A1 (en) | Text and video cross-searching method and apparatus, model training method and apparatus, device, and medium | |
| CN113434699A (en) | Pre-training method of BERT model, computer device and storage medium | |
| CN112988873A (en) | Data processing method and device | |
| CN114995729A (en) | Voice drawing method and device and computer equipment | |
| WO2018076971A1 (en) | Xml data manipulation method and apparatus | |
| CN117094260B (en) | Command interaction system based on natural language | |
| US6633836B1 (en) | Design system, design method, and storage medium storing design program for structural analysis after amendment of model form | |
| CN110286901B (en) | CAD-based script generation method, system and storage medium | |
| Meixner et al. | Udit–a graphical editor for task models | |
| AU2016100156A4 (en) | Data Structure, Model for Populating a Data Structure and Method of Programming a Processing Device Utilising a Data Structure | |
| CN112987653B (en) | Method and device for converting Chinese program into G code | |
| JP2018206074A (en) | Histogram generation method, histogram generation device, and histogram generation program | |
| CN110428814B (en) | Voice recognition method and device | |
| CN116402090B (en) | Processing method, device and equipment of neural network calculation graph | |
| CN116610298A (en) | Automatic modeling method, device, equipment and medium | |
| CN110047137B (en) | Paraboloid drawing method, device, equipment and storage medium | |
| CN117851443B (en) | SQL rule tag generation method based on artificial intelligence and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |