CN117194648B - Intelligent charging pile management platform software method and system - Google Patents
Intelligent charging pile management platform software method and system Download PDFInfo
- Publication number
- CN117194648B CN117194648B CN202311470069.6A CN202311470069A CN117194648B CN 117194648 B CN117194648 B CN 117194648B CN 202311470069 A CN202311470069 A CN 202311470069A CN 117194648 B CN117194648 B CN 117194648B
- Authority
- CN
- China
- Prior art keywords
- control
- management platform
- charging pile
- semantics
- training
- 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
- 238000012549 training Methods 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010195 expression analysis Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000014509 gene expression Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent charging pile management platform software method and system, wherein the method comprises the following steps of; collecting control instructions of the default charging pile by the management platform at the management platform, grouping the control instructions according to the corresponding relation between the control instructions of the default charging pile and control semantics to obtain original grouping instruction sets, wherein each group of instruction sets comprises a plurality of control instructions and one control semantics; training a first large language model by adopting the original grouping instruction set; according to the invention, the accurate training of the first large language model is realized by collecting the instructions of the management platform, then the training of the second large language model is completed, the control instructions of the management platform can be converted into control semantics, and then the control instructions of the newly added charging piles are converted into the control instructions of the newly added charging piles by the second large language model, so that the control of the newly added charging piles of different types is realized.
Description
Technical Field
The invention relates to the technical field of charging pile management platforms, in particular to an intelligent charging pile management platform software method and system.
Background
The charging pile management platform is used for realizing management platform between the charging pile and the user, and comprises functions of charging pile control, charging and charging, user charging and the like, and can realize management and operation of the charging pile. The existing large charging station is provided with a charging pile management platform and a charging pile, so that branding operation can be realized. But there are also a number of private charging piles that are smaller. The charging piles are initially set up to meet the charging requirements of enterprises or individuals. The private charging piles are in an idle state for a long time, and operation requirements exist, so that the social service capability of the charging piles can be fully exerted. Because of the decentralized nature of these proprietary charging posts, proprietary charging post owners do not have the ability to develop a management platform alone. Therefore, a unified charging pile management platform is needed to realize access and management of the private charging piles. The access comprises hardware access, and a communication module is to be installed on the charging pile, so that an instruction of the management platform can be issued to the charging pile, and data of the charging pile can be sent to the management platform. However, the existing problem is that the charging piles of each family adopt respective protocols, if the charging piles are accessed to the management platform, the charging piles are subjected to one-to-one manual adaptation, the workload of the early adaptation is large, and the period is long.
Disclosure of Invention
Therefore, an intelligent charging pile management platform software method and system are needed to be provided, and the problem that the existing management platform has large access adaptation workload to different charging piles is solved.
In order to achieve the above purpose, the invention provides an intelligent charging pile management platform software method, which comprises the following steps:
collecting control instructions of the default charging pile by the management platform at the management platform, grouping the control instructions according to the corresponding relation between the control instructions of the default charging pile and control semantics to obtain original grouping instruction sets, wherein each group of instruction sets comprises a plurality of control instructions and one control semantics;
training a first large language model by adopting the original grouping instruction set, wherein a control instruction is used as input and control semantics are used as output during training, and the first large language model is used for obtaining the control semantics according to the control instruction;
grouping the control instructions of the newly added charging piles according to the corresponding relation between the control instructions and the control semantics of the preset newly added charging piles to obtain newly added grouping instruction sets, wherein each group of instruction sets comprises at least one control instruction and one control semantics;
training a second large language model by adopting the newly added grouping instruction set, wherein the training takes control semantics as input and takes control instructions as output, and the second large language model is used for obtaining the control instructions according to the control semantics;
the management platform is provided with a first large language model and a plurality of second large language models, the management platform is provided with a corresponding relation between the second large language models and the types of the newly added charging piles and a charging pile address, when the management platform controls the newly added charging piles, a control instruction is sent to the first large language model to obtain control semantics, the control semantics are sent to the corresponding second large language models to obtain generated control instructions, and the generated control instructions are sent to the charging pile address.
Further, the method further comprises the steps of:
the control instruction contains variable parameters, and the step of obtaining the original grouping instruction set further comprises the following steps:
and extracting the variable parameters of the control instruction, supplementing the variable parameters serving as a part of control semantics to the control semantics, and obtaining a supplemented grouping instruction set.
Further, the training the second largest language model further comprises the steps of:
designating a certain newly added charging pile as a training charging pile, accessing the address of the training charging pile to a management platform, after the second large language model outputs a control instruction in training, sending the control instruction to the training charging pile by the management platform, acquiring a result returned by the training charging pile by the management platform, and feeding the result back to the second large language model correctly or not, wherein the second large language model completes training according to the feedback.
Further, the method further comprises the steps of:
and the management platform acquires a result returned by the charging pile address, and carries out regular expression analysis and prompt on the result.
Further: the management platform is used for acquiring the relation between the online applet, the APP, the payment bank or the WeChat user and the newly added charging pile, and the management platform is used for receiving the control instruction of the user and controlling the newly added charging pile according to the control instruction of the user.
Further, the method further comprises the steps of:
the management platform acquires all control semantics in an original grouping instruction set; and the management platform sequentially sends all the control semantics to the second large language model, judges whether a control instruction is obtained, and records the control semantics and prompts the control semantics to be missing if the control instruction is not obtained.
Further: the management platform comprises a management background and an untrained second large language model, the management background is used for inputting the corresponding relation between the control instruction and the control semantic of the newly-added charging pile, and the management platform carries out automatic training according to the input corresponding relation and stores the corresponding relation as a unique newly-added charging pile type identification code.
The invention provides an intelligent charging pile management platform software system which comprises a memory and a processor, wherein a computer program is stored in the memory, and the computer program realizes the steps of the method according to any one of the embodiments of the invention when being executed by the processor.
Compared with the prior art, the technical scheme realizes accurate training of the first large language model by collecting the instructions of the management platform, then also completes training of the second large language model, can convert the control instructions of the management platform into control semantics, and then converts the control instructions of the management platform into the control instructions of the newly added charging piles by the second large language model, thereby realizing control of the newly added charging piles of different types.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 is a schematic diagram of a system structure according to the present invention.
Detailed Description
In order to describe the technical content, constructional features, achieved objects and effects of the technical solution in detail, the following description is made in connection with the specific embodiments in conjunction with the accompanying drawings.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of the phrase "in various places in the specification are not necessarily all referring to the same embodiment, nor are they particularly limited to independence or relevance from other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the technical features mentioned in the embodiments may be combined in any manner to form a corresponding implementable technical solution.
Unless defined otherwise, technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application pertains; the use of related terms herein is for the description of specific embodiments only and is not intended to limit the present application.
In the description of the present application, the term "and/or" is a representation for describing a logical relationship between objects, which means that there may be three relationships, e.g., a and/or B, representing: there are three cases, a, B, and both a and B. In addition, the character "/" herein generally indicates that the front-to-back associated object is an "or" logical relationship.
In this application, terms such as "first" and "second" are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual number, order, or sequence of such entities or operations.
Without further limitation, the use of the terms "comprising," "including," "having," or other like terms in this application is intended to cover a non-exclusive inclusion, such that a process, method, or article of manufacture that comprises a list of elements does not include additional elements but may include other elements not expressly listed or inherent to such process, method, or article of manufacture.
As understood in the patent prosecution guidelines, in the present application, the expressions "greater than", "less than", "exceeding" and the like are understood to not include the present number; the expressions "above", "below", "within" and the like are understood to include this number. Furthermore, in the description of the embodiments of the present application, the meaning of "a plurality of" is two or more (including two), and similarly, the expression "a plurality of" is also to be understood as such, for example, "a plurality of groups", "a plurality of" and the like, unless specifically defined otherwise.
In the description of the embodiments of the present application, spatially relative terms such as "center," "longitudinal," "transverse," "length," "width," "thickness," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counter-clockwise," "axial," "radial," "circumferential," etc., are used herein as terms of orientation or positional relationship based on the specific embodiments or figures, and are merely for convenience of description of the specific embodiments of the present application or ease of understanding of the reader, and do not indicate or imply that the devices or components referred to must have a particular position, a particular orientation, or be configured or operated in a particular orientation, and therefore are not to be construed as limiting of the embodiments of the present application.
Unless specifically stated or limited otherwise, in the description of the embodiments of the present application, the terms "mounted," "connected," "affixed," "disposed," and the like are to be construed broadly. For example, the "connection" may be a fixed connection, a detachable connection, or an integral arrangement; the device can be mechanically connected, electrically connected and communicated; it can be directly connected or indirectly connected through an intermediate medium; which may be a communication between two elements or an interaction between two elements. The specific meanings of the above terms in the embodiments of the present application can be understood by those skilled in the art to which the present application pertains according to the specific circumstances.
Referring to fig. 1 to 2, the present invention provides an intelligent charging pile management platform software method, which includes the following steps: step S101, collecting control instructions of a default charging pile by a management platform in the management platform, and grouping the control instructions according to the corresponding relation between the control instructions of the default charging pile and control semantics to obtain original grouping instruction sets, wherein each group of instruction sets comprises a plurality of control instructions and one control semantics; the default charging pile refers to a charging pile which is accessed by the management platform first, and is generally an own charging pile. The correspondence relationship here can be obtained from the actual charging pile specifications. The collection is to preset automatic collection software at the management platform to collect, and divide the same control function in the instructions, namely one control semantic, into a group, so that a plurality of control instructions of one semantic can be received, and training is facilitated.
Step S102, training a first large language model by adopting the original grouping instruction set, wherein a control instruction is used as input and control semantics are used as output during training, and the first large language model is used for obtaining the control semantics according to the control instruction; this completes the training of the first large language model.
Specifically, when the first large language model is trained, the subsequent second large language model can be set by reference, and the following steps can be adopted:
1. data collection and labeling: and collecting a default charging pile control instruction and an original grouping instruction set of corresponding control semantic descriptions. These samples may include control instructions (typically english and symbols) and control semantics associated therewith (typically natural language descriptions, such as chinese descriptions, which are typically found in the charging stake description). Of course, it is also ensured that the data samples are sufficiently diverse and representative, such as insufficient needs to be manually replenished.
2. Pre-training a large language model:
the original group instruction set is pre-trained using a large pre-trained language model (e.g., GPT-3, BERT, or the like), mainly comprising pre-training of language understanding and generating tasks, so that the training large language model knows grammar, semantics, and context.
3.Fine-Tuning：
Fine-Tuning (Fine-Tuning) of the pre-trained model is performed using control instructions and control semantic association data of the data collection. During the fine tuning process, the large language model will learn how to relate protocol commands to semantic descriptions.
4. Inputting a control instruction:
control instructions are input into the large language model, for example, the instructions are "turn on charging".
5. Generating control semantics:
the large language model maps the charging stake protocol command inputs to the corresponding natural language. The semantic description of natural language is obtained by: "start charging".
6. Experiment and verification:
experiments and verifications were performed to evaluate the performance of the model for different unknown protocols. Ensuring that the generated control command works normally when being executed on the actual charging pile.
7. Iteration and improvement:
the model is continuously improved, more control instructions and control semantic association data are collected, iterative training is carried out, accuracy and generalization capability of the model are improved, and training is completed.
Step S103, grouping control instructions of the newly added charging piles according to the corresponding relation between the control instructions and control semantics of the preset newly added charging piles to obtain newly added grouping instruction sets, wherein each group of instruction sets comprises at least one control instruction and one control semantics; the correspondence is obtained according to the technical manual of the newly added charging pile. The technical manual or the charging pile specification contains the description, and if the description is incomplete, the manual supplement is needed to be completed.
Step S104, training a second large language model by adopting the newly added grouping instruction set, wherein the training takes control semantics as input and takes control instructions as output, and the second large language model is used for obtaining the control instructions according to the control semantics; this completes the training of the second largest language model.
Step 105, a first large language model and a plurality of second large language models are arranged on a management platform, the corresponding relation between the second large language models and the types of the newly-added charging piles and the addresses of the charging piles are arranged on the management platform, when the management platform controls the newly-added charging piles, a control instruction is sent to the first large language model to obtain control semantics, the control semantics are sent to the corresponding second large language models to obtain generated control instructions, and the generated control instructions are sent to the addresses of the charging piles. The charging pile address is the address of the control hardware connected to the charging pile, and the management platform sends the command to the control hardware by sending the command to the control hardware, and the control hardware sends the command to the charging pile. The second large language model is associated with a charging stake type, and charging stakes of the same type may share one large language model. By designating the charging pile type on the management platform, instruction conversion can be performed according to the corresponding relation between the charging pile type and the second large language model.
Therefore, by collecting the instructions of the management platform, the accurate training of the first large language model is realized, the training of the second large language model is completed, the control instructions of the management platform can be converted into control semantics, and then the second large language model is converted into the control instructions of the newly added charging piles, so that the control of the newly added charging piles of different types is realized.
Further, the method further comprises the steps of: the control instruction contains variable parameters, and the step of obtaining the original grouping instruction set further comprises the following steps: and extracting the variable parameters of the control instruction, supplementing the variable parameters serving as a part of control semantics to the control semantics, and obtaining a supplemented grouping instruction set.
The charging pile instruction comprises control on data size or time and the like, the same control instruction can be different in data size or time, the data size or time can be variable parameters, and the control instruction with different parameters can be realized by changing the parameters. Thus, the control semantics can embody the parameters, and then the parameters can be transferred to the second large language model through the control semantics, so that the transfer of the parameters is realized.
In some embodiments, the training the second largest language model further comprises the steps of: designating a certain newly added charging pile as a training charging pile, accessing the address of the training charging pile to a management platform, after the second large language model outputs a control instruction in training, sending the control instruction to the training charging pile by the management platform, acquiring a result returned by the training charging pile by the management platform, and feeding the result back to the second large language model correctly or not, wherein the second large language model completes training according to the feedback. Through inserting training fills electric pile for the big language model of second can have the feedback ground to train, improves the precision of training. The training charging pile can be a common charging pile which is not actually executed (namely, can not actually perform operations such as charging, and can be in a debugging mode) but can feed back data, so that the safety of the charging pile is ensured, and the training can be completed.
In order to obtain the result on the management platform, the method further comprises the steps of: and the management platform acquires a result returned by the charging pile address, and carries out regular expression analysis and prompt on the result. Because the result instruction is simpler, the regular expression can be directly adopted to obtain, and thus, a user or a manager can see the result on the platform.
Further: the management platform is used for acquiring the relation between the online applet, the APP, the payment bank or the WeChat user and the newly added charging pile, and the management platform is used for receiving the control instruction of the user and controlling the newly added charging pile according to the control instruction of the user. The invention can also accept the control of users, such as the starting and closing of users, reservation, and the like, and realize the automatic control of the newly added charging pile through the response to the control of users.
Further, the method further comprises the steps of:
the management platform acquires all control semantics in an original grouping instruction set; and the management platform sequentially sends all the control semantics to the second large language model, judges whether a control instruction is obtained, and records the control semantics and prompts the control semantics to be missing if the control instruction is not obtained. Therefore, the control semantics can be prompted to be missing during training, and the control semantics can be supplemented and trained in a targeted manner, so that the condition of semantic missing is avoided.
In order to realize automatic training, the management platform comprises a management background and an untrained second large language model, wherein the management background is used for inputting the corresponding relation between the control instruction and the control semantic of the newly added charging pile, and the management platform carries out automatic training according to the input corresponding relation and stores the corresponding relation as a unique newly added charging pile type identification code. Thus, through inputting the corresponding relation, automatic training can be realized, the automatic effect is improved, and automatic control of the newly added charging pile is realized.
The invention provides an intelligent charging pile management platform software system 200, which comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory, and the computer program realizes the steps of the method according to any one of the embodiments of the invention when being executed by the processor. The storage medium of the present embodiment may be a storage medium provided in an electronic device, and the electronic device may read the content of the storage medium and realize the effects of the present invention. The storage medium may also be a separate storage medium, which is connected to the electronic device, which may read the content in the storage medium and implement the method steps of the invention. The system realizes accurate training of the first large language model by collecting the instructions of the management platform, then also completes training of the second large language model, can convert the control instructions of the management platform into control semantics, and then converts the control instructions of the management platform into the control instructions of the newly added charging piles by the second large language model, thereby realizing control of the newly added charging piles of different types.
It should be noted that, although the foregoing embodiments have been described herein, the scope of the present invention is not limited thereby. Therefore, based on the innovative concepts of the present invention, alterations and modifications to the embodiments described herein, or equivalent structures or equivalent flow transformations made by the present description and drawings, apply the above technical solution, directly or indirectly, to other relevant technical fields, all of which are included in the scope of the invention.
Claims (8)
1. An intelligent charging pile management platform software method is characterized by comprising the following steps:
collecting control instructions of the default charging pile by the management platform at the management platform, grouping the control instructions according to the corresponding relation between the control instructions of the default charging pile and control semantics to obtain original grouping instruction sets, wherein each group of instruction sets comprises a plurality of control instructions and one control semantics;
training a first large language model by adopting the original grouping instruction set, wherein a control instruction is used as input and control semantics are used as output during training, and the first large language model is used for obtaining the control semantics according to the control instruction;
grouping the control instructions of the newly added charging piles according to the corresponding relation between the control instructions and the control semantics of the preset newly added charging piles to obtain newly added grouping instruction sets, wherein each group of instruction sets comprises at least one control instruction and one control semantics;
training a second large language model by adopting the newly added grouping instruction set, wherein the training takes control semantics as input and takes control instructions as output, and the second large language model is used for obtaining the control instructions according to the control semantics;
the management platform is provided with a first large language model and a plurality of second large language models, the management platform is provided with a corresponding relation between the second large language models and the types of the newly added charging piles and a charging pile address, when the management platform controls the newly added charging piles, a control instruction is sent to the first large language model to obtain control semantics, the control semantics are sent to the corresponding second large language models to obtain generated control instructions, and the generated control instructions are sent to the charging pile address.
2. The intelligent charge pile management platform software method of claim 1, further comprising the steps of:
the control instruction contains variable parameters, and the step of obtaining the original grouping instruction set further comprises the following steps:
and extracting the variable parameters of the control instruction, supplementing the variable parameters serving as a part of control semantics to the control semantics, and obtaining a supplemented grouping instruction set.
3. The intelligent charge stake management platform software method as recited in claim 1, wherein the training the second large language model further comprises the steps of:
designating a certain newly added charging pile as a training charging pile, accessing the address of the training charging pile to a management platform, after the second large language model outputs a control instruction in training, sending the control instruction to the training charging pile by the management platform, acquiring a result returned by the training charging pile by the management platform, and feeding the result back to the second large language model correctly or not, wherein the second large language model completes training according to the feedback.
4. The intelligent charge pile management platform software method of claim 1, further comprising the steps of:
and the management platform acquires a result returned by the charging pile address, and carries out regular expression analysis and prompt on the result.
5. The intelligent charging pile management platform software method according to claim 1, wherein: the management platform is used for acquiring the relation between the online applet, the APP, the payment bank or the WeChat user and the newly added charging pile, and the management platform is used for receiving the control instruction of the user and controlling the newly added charging pile according to the control instruction of the user.
6. The intelligent charge pile management platform software method of claim 1, further comprising the steps of:
the management platform acquires all control semantics in an original grouping instruction set; and the management platform sequentially sends all the control semantics to the second large language model, judges whether a control instruction is obtained, and records the control semantics and prompts the control semantics to be missing if the control instruction is not obtained.
7. The intelligent charging pile management platform software method according to claim 1, wherein: the management platform comprises a management background and an untrained second large language model, the management background is used for inputting the corresponding relation between the control instruction and the control semantic of the newly-added charging pile, and the management platform carries out automatic training according to the input corresponding relation and stores the corresponding relation as a unique newly-added charging pile type identification code.
8. An intelligent charging pile management platform software system, which is characterized in that: comprising a memory, a processor, said memory having stored thereon a computer program which, when executed by the processor, implements the steps of the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311470069.6A CN117194648B (en) | 2023-11-07 | 2023-11-07 | Intelligent charging pile management platform software method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311470069.6A CN117194648B (en) | 2023-11-07 | 2023-11-07 | Intelligent charging pile management platform software method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117194648A CN117194648A (en) | 2023-12-08 |
| CN117194648B true CN117194648B (en) | 2024-03-26 |
Family
ID=88996493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311470069.6A Active CN117194648B (en) | 2023-11-07 | 2023-11-07 | Intelligent charging pile management platform software method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194648B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115019776A (en) * | 2022-06-09 | 2022-09-06 | 内蒙古科技大学 | Voice recognition model, training method thereof, voice recognition method and device |
| CN115910066A (en) * | 2022-09-15 | 2023-04-04 | 平湖市通用电气安装有限公司 | Intelligent dispatching command and operation system for regional power distribution network |
| CN116150698A (en) * | 2022-09-08 | 2023-05-23 | 天津大学 | Automatic DRG grouping method and system based on semantic information fusion |
| CN116452280A (en) * | 2022-12-30 | 2023-07-18 | 南京邮电大学 | Clearing and settling method and device for electric vehicle charging pile order abnormality |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4323940A2 (en) * | 2021-04-16 | 2024-02-21 | Strong Force VCN Portfolio 2019, LLC | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
-
2023
- 2023-11-07 CN CN202311470069.6A patent/CN117194648B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115019776A (en) * | 2022-06-09 | 2022-09-06 | 内蒙古科技大学 | Voice recognition model, training method thereof, voice recognition method and device |
| CN116150698A (en) * | 2022-09-08 | 2023-05-23 | 天津大学 | Automatic DRG grouping method and system based on semantic information fusion |
| CN115910066A (en) * | 2022-09-15 | 2023-04-04 | 平湖市通用电气安装有限公司 | Intelligent dispatching command and operation system for regional power distribution network |
| CN116452280A (en) * | 2022-12-30 | 2023-07-18 | 南京邮电大学 | Clearing and settling method and device for electric vehicle charging pile order abnormality |
Non-Patent Citations (1)
| Title |
|---|
| 基于多融合模型的图像语义描述研究;王媛华;《河南科技》;20190731(第14期);第34-36页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117194648A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106992001B (en) | Voice instruction processing method, device and system | |
| CN109933653A (en) | Question and answer querying method, system and the computer equipment of question answering system | |
| CN102880468B (en) | Code intelligent prompting method and system for electronic control unit (ECU) program development | |
| CN108446321B (en) | Automatic question answering method based on deep learning | |
| CA2646362A1 (en) | Report generation with integrated quality management | |
| CN109324960A (en) | Automatic test approach and terminal device based on big data analysis | |
| CN110377892A (en) | A kind of government intelligence form templat designing system | |
| CN103902677A (en) | Cross-platform database access method | |
| CN115630146A (en) | Method and device for automatically generating demand document based on human-computer interaction and storage medium | |
| CN113051011A (en) | RPA and AI combined image information extraction method and device | |
| CN117194648B (en) | Intelligent charging pile management platform software method and system | |
| KR102081273B1 (en) | Cloud-AI server for generating function control protocols of IOT devices | |
| CN110321882A (en) | A kind of education resource acquisition methods, device, learning terminal and storage medium | |
| CN109543772A (en) | Data set automatic matching method, device, equipment and computer readable storage medium | |
| CN117216547A (en) | Model training method, language processing method, device and computer equipment | |
| CN111931503A (en) | Information extraction method and device, equipment and computer readable storage medium | |
| CN110032587A (en) | Data summarization method, device, computer equipment and storage medium | |
| CN114511393B (en) | Financial data processing method and system | |
| CN110674275B (en) | Knowledge question answering method and device | |
| WO2023038868A1 (en) | Methods and systems for codeless chatbot development | |
| CN113962213A (en) | Multi-turn dialog generation method, terminal and computer readable storage medium | |
| CN108415983B (en) | Intelligent problem solving method and device based on interaction | |
| CN110942139A (en) | Deep learning neural network deployment system and method thereof | |
| CN117744630B (en) | Model access method and device and electronic equipment | |
| CN111369005A (en) | Crowdsourcing marking system |
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 |