AU2020103407A4 - Intention recognition method based on normal cloud generator-bayesian network - Google Patents
Intention recognition method based on normal cloud generator-bayesian network Download PDFInfo
- Publication number
- AU2020103407A4 AU2020103407A4 AU2020103407A AU2020103407A AU2020103407A4 AU 2020103407 A4 AU2020103407 A4 AU 2020103407A4 AU 2020103407 A AU2020103407 A AU 2020103407A AU 2020103407 A AU2020103407 A AU 2020103407A AU 2020103407 A4 AU2020103407 A4 AU 2020103407A4
- Authority
- AU
- Australia
- Prior art keywords
- variables
- bayesian network
- intention
- node
- continuous
- 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.)
- Ceased
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 abstract description 3
- 238000003786 synthesis reaction Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/257—Belief theory, e.g. Dempster-Shafer
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The present disclosure relates to an intention recognition method based on a normal cloud
generator-Bayesian network, in particular to a new intention recognition method combining
the normal cloud generator in a cloud model with a Bayesian network to overcome the
weakness of a single cloud model on an inference capability and the shortcoming of the
Bayesian network on a knowledge representation. According to the present disclosure, the
uncertainty of target information is avoided from affecting recognition on an overall intention
by means of repeated inference through a synthesis formula of a Dempster-Shafer (D-S)
evidence theory, so that accuracy of a result is improved.
Si
Acquire real-time node variables
S21 Normalize continuous real-time node
variables to obtain normalized Input discrete real-time node variables
continuous node variables to a Bayesian network system, andS2
infer the Bayesian network system by S22
means of a junction tree algorithm to
S31 Input the normalized continuous node obtain the probability of occurrence
of
variables to a normal cloud generator to an intention node
obtain accuracy of the variables
Repeat S1, S21-S31, and S22 to S4
obtain multiple groups of accuracy of
the variables and multiple groups of
probabilities of occurrence of the
intention node; and
Synthesize the multiple groups of S5
accuracy of the variables as well as
the multiple groups of probabilities of
occurrence of the intention node by
means of a D-S evidence theory to
obtain a recognized intention
Fig. 1
Description
Si Acquire real-time node variables
S21 Normalize continuous real-time node variables to obtain normalized Input discrete real-time node variables continuous node variables to a Bayesian network system, andS2 infer the Bayesian network system by S22 means of a junction tree algorithm to
S31 Input the normalized continuous node obtain the probability of occurrence of variables to a normal cloud generator to an intention node obtain accuracy of the variables
Repeat S1, S21-S31, and S22 to S4 obtain multiple groups of accuracy of the variables and multiple groups of probabilities of occurrence of the intention node; and
Synthesize the multiple groups of S5 accuracy of the variables as well as the multiple groups of probabilities of occurrence of the intention node by means of a D-S evidence theory to obtain a recognized intention
Fig. 1
TECHNICAL FIELD The present disclosure relates to the field of intention recognition, in particular to an intention recognition method based on a normal cloud generator-Bayesian network.
BACKGROUND There are a lot of uncertainties in intention recognition. With the continuous increase in data and continuous development of a semantic service, a large amount of uncertain data appears in the semantic Web, leading to a great difficulty in use of the semantic Web. Accordingly, it is more important to represent and deduce the uncertain data. Multi-entity Bayesian network methods indicate important development of Bayesian network inference technologies and make general Bayesian networks have expression capabilities of first-order predicate logic. The first-order predicate logic having a complete logical inference algorithm can guarantee logical consistency of old and new knowledge from knowledge bases as well as accuracy in deductive conclusions by means of logical inference, and is independent of any specific field as a formal inference method, thus having high universality. However, the first-order predicate logic is suitable for the representation of certain '0 knowledge, rather than the representation of uncertain knowledge, and has quite low inference efficiency. Cloud models reflect two uncertainties, namely randomness and fuzziness, of concepts in the objective world and fulfill uncertainty transformations between quantitative values and qualitative concepts; and moreover, the cloud models can take both the fuzziness and the randomness into account in terms of knowledge representations, thus well expressing the uncertainty of data as well as expert knowledge. Accordingly, the cloud models are superior to fuzzy set theories. Furthermore, people typically study the fuzziness and the randomness separately, but the closely correlated fuzziness and randomness are generally inseparable. The cloud models can provide reasonable explanations by means of fuzzy mathematics and probability theories and thus have great advantages on the knowledge representation; and moreover, the cloud models reflect both the uncertainty of concepts in natural languages and the correlation between the randomness and the fuzziness and thus achieve qualitative and quantitative mapping, thereby being widely used in research fields. Based on the above considerations, the present disclosure provides an intention recognition method combining a normal cloud generator in a cloud model with a Bayesian network to overcome the weakness of a single cloud model on an inference capability and the shortcoming of the Bayesian network on a knowledge representation.
SUMMARY The objective of the present disclosure is to provide an intention recognition method based on a normal cloud generator-Bayesian network to improve the accuracy and efficiency of recognition. To achieve the above objective, the present disclosure provides the following solutions: An intention recognition method based on a normal cloud generator-Bayesian network including: SI: acquiring real-time node variables which include an altitude, a speed, a distance, a motion trajectory, a course angle, environmental information, weather information, and geographic information and are classified as discrete real-time node variables and continuous real-time node variables; S21: normalizing the continuous real-time node variables to obtain normalized continuous node variables; S31: inputting the normalized continuous node variables to a normal cloud generator to obtain accuracy of the variables; S22: inputting the discrete real-time node variables to a Bayesian network system, and deducing the Bayesian network system by means of a junction tree algorithm to obtain the probability of occurrence of an intention node; S4: repeating Sl, S21-S31, and S22 to obtain multiple groups of accuracy of the variables and multiple groups of probabilities of occurrence of the intention node; and S5: synthesizing the multiple groups of accuracy of the variables as well as the multiple groups of probabilities of occurrence of the intention node by means of a Dempster-Shafer (D S) evidence theory to obtain a recognized intention. Optionally, the Bayesian network system is built through the following steps: acquiring influencing factors of nodes, enemy intention factors corresponding to the influencing factors of the nodes, and conditional probability densities at the nodes, where the influencing factors of the nodes include an enemy altitude, an enemy speed, an enemy distance, an enemy motion trajectory, an enemy course angle, enemy environmental information, enemy weather information, and enemy geographic information and are classified as discrete influencing factors and continuous influencing factors; training a network structure of a Bayesian network model by using the discrete influencing factors of the nodes as the input of the Bayesian network model as well as the enemy intention factors corresponding to the discrete influencing factors of the nodes as the output of a Bayesian network model to obtain a Bayesian network topology; and performing parameter learning by using the conditional probability densities at the nodes as the input of the Bayesian network topology to obtain the Bayesian network system. Optionally, the normal cloud generator is built through the following steps: acquiring the continuous influencing factors of the nodes; establishing a cloud family by means of the continuous influencing factors of the nodes; and building the normal cloud generator according to the cloud family. Optionally, the parameter learning is performed on the Bayesian network topology by means of GeNIe software. Optionally, a discrete node which cannot provide an exact value is also obtained by inputting the normalized continuous node variables to the normal cloud generator. A specific example of the present disclosure provides a new intention recognition method '0 combining the normal cloud generator in a cloud model with a Bayesian network to overcome the weakness of a single cloud model on an inference capability and the shortcoming of the Bayesian network on a knowledge representation. According to the present disclosure, the uncertainty of target information is avoided from affecting recognition on an overall intention by means of repeated inference through a synthesis formula of the D-S evidence theory, so that accuracy of a result is improved. The Bayesian network system is built by performing structure learning first and then performing parameter learning. By means of the structure learning, a Bayesian network model built based on priori knowledge can be adjusted to perform data fitting more fully and can achieve higher reliability.
BRIEF DESCRIPTION OF DRAWINGS In order to illustrate examples of the present disclosure or the technical solutions of the prior art more clearly, the accompanying drawing to be used in the examples will be described briefly below. Notably, the accompanying drawings merely illustrates some examples of the present disclosure, and other drawings illustrating other examples could be derived by those ordinarily skilled in the art. FIG. 1 is a flow chart of an intention recognition method based on a normal cloud generator-Bayesian network of the present disclosure.
DETAILED DESCRIPTION The technical solutions in the examples of the present disclosure are clearly and completely described below with reference to the accompanying drawings. Clearly, the examples in the following description are only illustrative ones, and are not all possible ones of the present disclosure. Other examples obtained by those ordinarily skilled in the art based on the examples of the present disclosure should also fall within the protection scope of the present disclosure. The objective of the present disclosure is to provide an intention recognition system based on a normal cloud generator-Bayesian network, which can accurately and quickly obtain an intention recognition result. To make the foregoing objective, features, and advantages of the present disclosure clearer and more comprehensible, the present disclosure is further described in detail below with reference to the accompanying drawings and specific examples. An intention recognition method based on a normal cloud generator-Bayesian network '0 includes: SI: Acquire real-time node variables which include an altitude, a speed, a distance, a motion trajectory, a course angle, environmental information, weather information, and geographic information and are classified as discrete real-time node variables and continuous real-time node variables; S21: Normalize the continuous real-time node variables to obtain normalized continuous node variables; S31: Input the normalized continuous node variables to a normal cloud generator to obtain accuracy of the variables; S22: Input the discrete real-time node variables to a Bayesian network system, and deduce the Bayesian network system by means of a junction tree algorithm to obtain the probability of occurrence of an intention node; S4: Repeat Sl, S21-S31, and S22 to obtain multiple groups of accuracy of the variables and multiple groups of probabilities of occurrence of the intention node; and
S5: Synthesize the multiple groups of accuracy of the variables as well as the multiple groups of probabilities of occurrence of the intention node by means of a D-S evidence theory to obtain a recognized intention. The present disclosure provides a new intention recognition method combining the normal cloud generator in a cloud model with a Bayesian network to overcome the weakness of a single cloud model on an inference capability and the shortcoming of the Bayesian network on a knowledge representation. A discrete node which cannot provide an exact value is also obtained by inputting the normalized continuous node variables to the normal cloud generator and serves as a soft evidence. Furthermore, a discrete node which can provide an exact value serves as a hard evidence. According to the present disclosure, to avoid the uncertainty of target information from affecting recognition on an overall intention, a final intention of a target is obtained by means of repeated inference through a synthesis formula of the D-S evidence theory, so that accuracy of a result is improved. The Bayesian network system is built by performing structure learning first and then performing parameter learning. By means of the structure learning, a Bayesian network model built based on priori knowledge can be adjusted to perform data fitting more fully and can achieve higher reliability. In a case of incomplete data, an approximation method such as an '0 expectation-maximization (EM) algorithm and a Gibbs sampling algorithm can be adopted to learn to obtain a network structure. A method for building the Bayesian network system particularly includes: Acquire influencing factors of the nodes, enemy intention factors corresponding to the influencing factors of the nodes, and conditional probability densities at the nodes, where the influencing factors of the nodes include an enemy altitude, an enemy speed, an enemy distance, an enemy motion trajectory, an enemy course angle, enemy environmental information, enemy weather information, and enemy geographic information and are classified as discrete influencing factors and continuous influencing factors; Train a network structure of the Bayesian network model by using the discrete influencing factors of the nodes as the input of the Bayesian network model as well as the enemy intention factors corresponding to the discrete influencing factors of the nodes as the output of the Bayesian network model to obtain a Bayesian network topology; and Perform the parameter learning by using the conditional probability densities at the nodes as the input of the Bayesian network topology to obtain the Bayesian network system, where the parameter learning can be performed on the Bayesian network topology by means of GeNIe software in the specific process. The normal cloud generator built according to a cloud family established by means of the continuous influencing factors of the nodes can take both fuzziness and randomness into account in terms of a knowledge representation, thus well expressing the uncertainty of data and expert knowledge. Accordingly, the normal cloud generator is superior to a fuzzy set theory. The above specific examples are used to explain the principle and implementations of the present disclosure, and the explanations of these examples are only used to assist in understanding the method and core concept of the present disclosure. In addition, those ordinarily skilled in the art can make various modifications on the specific implementations and scope of application in accordance with the concept of the present disclosure. In summary, the content of the specification should not be understood as a limit to the present disclosure.
Claims (5)
1. An intention recognition method based on a normal cloud generator-Bayesian network, comprising: Si: acquiring real-time node variables which include an altitude, a speed, a distance, a motion trajectory, a course angle, environmental information, weather information, and geographic information and are classified as discrete real-time node variables and continuous real-time node variables; S21: normalizing the continuous real-time node variables to obtain normalized continuous node variables; S31: inputting the normalized continuous node variables to a normal cloud generator to obtain accuracy of the variables; S22: inputting the discrete real-time node variables to a Bayesian network system, and deducing the Bayesian network system by means of a junction tree algorithm to obtain a probability of occurrence of an intention node; S4: repeating SI, S21-S31, and S22 to obtain multiple groups of accuracy of the variables and multiple groups of probabilities of occurrence of the intention node; and S5: synthesizing the multiple groups of accuracy of the variables as well as the multiple groups of probabilities of occurrence of the intention node by means of a Dempster-Shafer (D S) evidence theory to obtain a recognized intention.
2. An intention recognition method based on a normal cloud generator-Bayesian network according to claim 1, wherein the Bayesian network system is built through the following steps: acquiring influencing factors of nodes, enemy intention factors corresponding to the influencing factors of the nodes, and conditional probability densities at the nodes, wherein the influencing factors of the nodes include an enemy altitude, an enemy speed, an enemy distance, an enemy motion trajectory, an enemy course angle, enemy environmental information, enemy weather information, and enemy geographic information and are classified as discrete influencing factors and continuous influencing factors; training a network structure of a Bayesian network model by using the discrete influencing factors of the nodes as an input of the Bayesian network model as well as the enemy intention factors corresponding to the discrete influencing factors of the nodes as an output of the Bayesian network model to obtain a Bayesian network topology; and performing parameter learning by using the conditional probability densities at the nodes as an input of the Bayesian network topology to obtain the Bayesian network system.
3. An intention recognition method based on a normal cloud generator-Bayesian network according to claim 2, wherein the normal cloud generator is built through the following steps: acquiring the continuous influencing factors of the nodes; establishing a cloud family by means of the continuous influencing factors of the nodes; and building the normal cloud generator according to the cloud family.
4. An intention recognition method based on a normal cloud generator-Bayesian network according to claim 2 or claim 3, wherein the parameter learning can be performed on the Bayesian network topology by means of GeNIe software.
5. An intention recognition method based on a normal cloud generator-Bayesian network according to claim 1, wherein a discrete node which cannot provide an exact value is also obtained by inputting the normalized continuous node variables to the normal cloud generator.
S1 Acquire real-time node variables
S21 Normalize continuous real-time node variables to obtain normalized Input discrete real-time node variables continuous node variables to a Bayesian network system, and infer the Bayesian network system by S22 2020103407
means of a junction tree algorithm to Input the normalized continuous node obtain the probability of occurrence of S31 variables to a normal cloud generator to an intention node obtain accuracy of the variables
Repeat S1, S21-S31, and S22 to S4 obtain multiple groups of accuracy of the variables and multiple groups of probabilities of occurrence of the intention node; and
Synthesize the multiple groups of S5 accuracy of the variables as well as the multiple groups of probabilities of occurrence of the intention node by means of a D-S evidence theory to obtain a recognized intention
Fig. 1
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020103407A AU2020103407A4 (en) | 2020-11-12 | 2020-11-12 | Intention recognition method based on normal cloud generator-bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020103407A AU2020103407A4 (en) | 2020-11-12 | 2020-11-12 | Intention recognition method based on normal cloud generator-bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2020103407A4 true AU2020103407A4 (en) | 2021-01-28 |
Family
ID=74192063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020103407A Ceased AU2020103407A4 (en) | 2020-11-12 | 2020-11-12 | Intention recognition method based on normal cloud generator-bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2020103407A4 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139331A (en) * | 2021-03-29 | 2021-07-20 | 西北工业大学 | Air-to-air missile situation perception and decision method based on Bayesian network |
| CN113298006A (en) * | 2021-06-04 | 2021-08-24 | 西北工业大学 | Novel abnormal target detection method based on brain-machine fusion cognition and decision |
| CN113392579A (en) * | 2021-05-19 | 2021-09-14 | 中国电子科技集团公司电子科学研究院 | Method and equipment for analyzing main effect factors based on causal model |
| CN113792655A (en) * | 2021-09-14 | 2021-12-14 | 京东鲲鹏(江苏)科技有限公司 | Intention identification method and device, electronic equipment and computer readable medium |
| CN113887807A (en) * | 2021-10-08 | 2022-01-04 | 天津大学 | Robot game tactical prediction method based on machine learning and evidence theory |
| CN113919026A (en) * | 2021-10-09 | 2022-01-11 | 福州大学 | Rod system structure damage identification model and method based on Bayesian network |
| CN114092967A (en) * | 2021-11-19 | 2022-02-25 | 济南大学 | Real-time multi-mode accompanying robot intention understanding method and system |
| CN114444910A (en) * | 2022-01-14 | 2022-05-06 | 华北电力大学 | Electric power Internet of things-oriented edge network system health degree evaluation method |
| CN115757828A (en) * | 2022-11-16 | 2023-03-07 | 南京航空航天大学 | Radiation source knowledge graph-based aerial target intention identification method |
| CN116029379A (en) * | 2022-12-31 | 2023-04-28 | 中国电子科技集团公司信息科学研究院 | Method for constructing air target intention recognition model |
-
2020
- 2020-11-12 AU AU2020103407A patent/AU2020103407A4/en not_active Ceased
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139331A (en) * | 2021-03-29 | 2021-07-20 | 西北工业大学 | Air-to-air missile situation perception and decision method based on Bayesian network |
| CN113392579A (en) * | 2021-05-19 | 2021-09-14 | 中国电子科技集团公司电子科学研究院 | Method and equipment for analyzing main effect factors based on causal model |
| CN113298006B (en) * | 2021-06-04 | 2024-01-19 | 西北工业大学 | Novel abnormal target detection method based on brain-computer fusion cognition and decision |
| CN113298006A (en) * | 2021-06-04 | 2021-08-24 | 西北工业大学 | Novel abnormal target detection method based on brain-machine fusion cognition and decision |
| CN113792655A (en) * | 2021-09-14 | 2021-12-14 | 京东鲲鹏(江苏)科技有限公司 | Intention identification method and device, electronic equipment and computer readable medium |
| CN113887807A (en) * | 2021-10-08 | 2022-01-04 | 天津大学 | Robot game tactical prediction method based on machine learning and evidence theory |
| CN113887807B (en) * | 2021-10-08 | 2024-04-30 | 天津大学 | Robot game tactics prediction method based on machine learning and evidence theory |
| CN113919026A (en) * | 2021-10-09 | 2022-01-11 | 福州大学 | Rod system structure damage identification model and method based on Bayesian network |
| CN114092967A (en) * | 2021-11-19 | 2022-02-25 | 济南大学 | Real-time multi-mode accompanying robot intention understanding method and system |
| CN114444910A (en) * | 2022-01-14 | 2022-05-06 | 华北电力大学 | Electric power Internet of things-oriented edge network system health degree evaluation method |
| CN115757828B (en) * | 2022-11-16 | 2023-11-10 | 南京航空航天大学 | Aerial target intention recognition method based on radiation source knowledge graph |
| CN115757828A (en) * | 2022-11-16 | 2023-03-07 | 南京航空航天大学 | Radiation source knowledge graph-based aerial target intention identification method |
| CN116029379A (en) * | 2022-12-31 | 2023-04-28 | 中国电子科技集团公司信息科学研究院 | Method for constructing air target intention recognition model |
| CN116029379B (en) * | 2022-12-31 | 2024-01-02 | 中国电子科技集团公司信息科学研究院 | Method for constructing air target intention recognition model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020103407A4 (en) | Intention recognition method based on normal cloud generator-bayesian network | |
| CN110033101B (en) | Hydroelectric generating set fault diagnosis method and system based on knowledge graph of fusion features | |
| CN112613303B (en) | Knowledge distillation-based cross-modal image aesthetic quality evaluation method | |
| CN109934261B (en) | Knowledge-driven parameter propagation model and few-sample learning method thereof | |
| GB2537903B (en) | Device and method for a spoken dialogue system | |
| CN109933953B (en) | Power distribution network switch state identification method based on probability map model | |
| CN113780002A (en) | Knowledge reasoning method and device based on graph representation learning and deep reinforcement learning | |
| CN116150338A (en) | Intelligent customer service method and system based on multi-round dialogue | |
| EP3920048A1 (en) | Method and system for automated visual question answering | |
| CN117435715B (en) | Question answering method for improving time sequence knowledge graph based on auxiliary supervision signals | |
| CN115964459B (en) | Multi-hop reasoning question-answering method and system based on food safety cognition spectrum | |
| CN112463989B (en) | Knowledge graph-based information acquisition method and system | |
| CN115168443A (en) | Anomaly detection method and system based on GCN-LSTM and attention mechanism | |
| CN112860904B (en) | External knowledge-integrated biomedical relation extraction method | |
| CN117172413A (en) | Power grid equipment operation state monitoring method based on multi-mode data joint characterization and dynamic weight learning | |
| CN115936001A (en) | Power grid IT operation and maintenance entity identification method and system based on BERT-BilSTM-CRF model and attention | |
| CN114462607A (en) | Causal reasoning method and system for enhancing case map based on hyperbolic space | |
| CN117932065A (en) | Global hyperbolic embedding-based multi-intention detection and semantic slot filling method | |
| CN117093226A (en) | Homology analysis method and device for binary files, electronic equipment and medium | |
| CN116895386A (en) | Medical consultation dialogue system and method based on medical entity knowledge prediction and reasoning | |
| CN112579775B (en) | Method for classifying unstructured text and computer-readable storage medium | |
| Zhan et al. | Differential Convolutional Fuzzy Time Series Forecasting | |
| Vagin et al. | Inductive inference and argumentation methods in modern intelligent decision support systems | |
| CN114528223A (en) | Intelligent software code type inference method, system, equipment and storage medium | |
| Tang et al. | A score based approach towards improving bayesian network structure learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |