CN113111302A - Information extraction method based on non-European space - Google Patents
Information extraction method based on non-European space Download PDFInfo
- Publication number
- CN113111302A CN113111302A CN202110431000.7A CN202110431000A CN113111302A CN 113111302 A CN113111302 A CN 113111302A CN 202110431000 A CN202110431000 A CN 202110431000A CN 113111302 A CN113111302 A CN 113111302A
- Authority
- CN
- China
- Prior art keywords
- space
- hyperbolic
- hyperbolic space
- extraction method
- information extraction
- 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.)
- Granted
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 30
- 238000013507 mapping Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000009826 distribution Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 13
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000012614 Monte-Carlo sampling Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 1
- 239000002994 raw material Substances 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012733 comparative method Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- RFHAOTPXVQNOHP-UHFFFAOYSA-N fluconazole Chemical compound C1=NC=NN1CC(C=1C(=CC(F)=CC=1)F)(O)CN1C=NC=N1 RFHAOTPXVQNOHP-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an information extraction method based on a non-European space, which comprises the steps of mapping a graph structure input by an European space to a hyperbolic space based on a basic algorithm of the hyperbolic space; by using
Addition and
multiplying to redefine a conditional strength function of a Hawkes process in the hyperbolic space; taking the curvature c as said functionAnd (3) iteratively updating the curvature c by one parameter of the number to obtain a trained hyperbolic space model and describe the distribution of future events. The method of the invention realizes that the future event is mapped into a hyperbolic space by combining the time and type information of the past event, so as to obtain a better hierarchical structure to predict the future event, and can well express large-scale hierarchical data in the aspect of application, so that the graph information is more accurate.
Description
Technical Field
The invention relates to the technical field of computer hyperbolic space, in particular to an information extraction method based on non-European space.
Background
To better describe the hyperbolic space, the basic concept of differential geometry, an n-dimensional manifold, required by the general principles of neural networks in euclidean space is briefly described herein
Is available locally
Space of approximation: it is a generalization of the 2D concept of two-dimensional curved surfaces in higher dimensions, for
Can be combined with
Cutting space at x
Is defined as
A first order linear approximation around x,
leemann measurement of
Is an inner product gx:
Set of (5), Riemann manifold
Is a manifold with Riemann measurement g
Although the choice of Riemann metric g seems to define the geometry only locally, it does so by integrating between two pointsThe length of the inter shortest path (the velocity vector existing in the tangent space) yields the global distance:
wherein,
and γ (0) ═ y (1) ═ y, the path of minimum length γ between two points x and y is called geodesic and can be considered as a generalization of a straight line in euclidean space, Px→y:TxM→TyM corresponds to a tangent vector moving along the geodesic line and defines a canonical method of connecting tangent spaces, exponentially mapping expxA method is provided for cutting a space
Is projected to a point on the manifold
Poincare sphere model, exp, as considered hereinxIn the full cutting space
The above definition is very good.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides an information extraction method based on a non-European space, which can solve the problems that a better node characteristic information and European space mapping distortion cannot be obtained.
In order to solve the technical problems, the invention provides the following technical scheme: mapping a graph structure input by an Euclidean space to a hyperbolic space based on a basic algorithm of the hyperbolic space; by using
Addition and
multiplying to redefine a conditional strength function of a Hawkes process in the hyperbolic space; and taking the curvature c as a parameter of the function, and iteratively updating the curvature c to obtain a trained hyperbolic space model to describe the distribution of future events.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: the method further comprises the steps of embedding graph information of the hyperbolic space, fusing information of the hyperbolic space, embedding category characteristics of the hyperbolic space, fusing information, predicting, training and fine-tuning.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: the embedding of the graph information of the hyperbolic space comprises the steps of mapping an adjacent matrix of a user node to the hyperbolic space, and then utilizing a GCN in the hyperbolic space to aggregate the adjacent matrix information of the graph structure.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: the information fusion of the hyperbolic space comprises mapping specific time intervals and occurrence time matrixes of past events to the hyperbolic space for aggregation.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: embedding the category characteristics of the hyperbolic space comprises mapping a category matrix of all past occurrence events into the hyperbolic space.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: and the information fusion comprises the steps of inputting the adjacency matrix and the characteristic matrix into the hyperbolic space GCN, and connecting the output of the GCN with the category matrix and the time matrix which are input into the hyperbolic space for mapping.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: the prediction comprises the steps of simulating and calling an inverse method and Monte Carlo sampling, and predicting the type and time of an event which occurs in the future.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: the training comprises the steps of dividing a data set, selecting 10 events as one-time training, predicting the event time and the category of the next event, and performing training through a cross entropy loss function.
As a preferred embodiment of the non-european space-based information extraction method according to the present invention, wherein: and the fine adjustment comprises the steps of selecting different batch sizes, different cyclic neural network models and learning rates to carry out a series of fine adjustments, and finishing the optimal output.
The invention has the beneficial effects that: the method of the invention realizes that the future event is mapped into a hyperbolic space by combining the time and type information of the past event, so as to obtain a better hierarchical structure to predict the future event, and can well express large-scale hierarchical data in the aspect of application, so that the graph information is more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic diagram of a Nostradamus model of a non-euro-space-based information extraction method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a Nostradamus model of a non-euro-space-based information extraction method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a root mean square error of a synthetic data set according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a root mean square error of a Stack Overflow data set of the information extraction method based on a non-european space according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a root mean square error of a fault data set of a self-service teller machine according to an embodiment of the invention;
fig. 6 is a schematic diagram of root mean square error of a financial transaction data set according to an embodiment of the non-european space-based information extraction method.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 and 2, a first embodiment of the present invention provides a non-european space-based information extraction method, including:
s1: and mapping the graph structure input by the Euclidean space to the hyperbolic space based on the basic algorithm of the hyperbolic space.
S2: by using
Addition and
the multiplication redefines the conditional strength function of the Hawkes process in the hyperbolic space.
S3: and (5) taking the curvature c as a parameter of the function, and updating the curvature c in an iterative manner to obtain a trained hyperbolic space model and describe the distribution of future events.
Preferably, the embodiment defines the graph convolution neural network and the recurrent neural network in the hyperbolic space, obtains the time and space information of the event occurring in the past by using the hox process, converts the conditional strength function with similar parameter shape into a nonparametric form by using the recurrent neural network approximate hox process, and improves the effect of predicting the future event by fine tuning the parameter.
Specifically, the information extraction method based on the non-european space provided in this embodiment specifically includes the following steps:
embedding graph information of a hyperbolic space, fusing information of the hyperbolic space, embedding category characteristics of the hyperbolic space, fusing information, predicting, training and fine-tuning;
(1) embedding graph information of the hyperbolic space comprises the steps of mapping an adjacent matrix of a user node to the hyperbolic space, and then utilizing a GCN (general packet network) in the hyperbolic space to aggregate the adjacent matrix information of the graph structure;
(2) the information fusion of the hyperbolic space comprises the steps of mapping specific time intervals and occurrence time matrixes of past events to the hyperbolic space for aggregation;
(3) embedding the category characteristics of the hyperbolic space comprises mapping category matrixes of all past occurrence events into the hyperbolic space;
(4) the information fusion comprises the steps of inputting an adjacent matrix and a characteristic matrix into a hyperbolic space GCN, and connecting the output of the GCN with a category matrix and a time matrix which are mapped by the hyperbolic space;
(5) the prediction comprises the steps of simulating and calling an inverse method and Monte Carlo sampling, and predicting the type and time of an event which occurs in the future;
(6) the training comprises the steps of dividing a data set, selecting 10 events as one-time training, predicting the event time and the category of the next event, and performing training through a cross entropy loss function;
(7) the fine tuning comprises selecting different batch sizes, different cyclic neural network models and learning rates to perform a series of fine tuning to complete the optimal output.
In this embodiment, in order to obtain a good graph embedding, that is, feature information of a node, and overcome mapping distortion of an euclidean space, so as to obtain a good time and type prediction effect of an event, a poincare sphere model, a graph convolution neural network, and a GRU are adopted for prediction, so that a basic idea of information extraction based on a non-euclidean space is as follows:
mapping a graph structure input by a Euclidean space to a hyperbolic space, and adopting a method of combining the hyperbolic space and a graph convolution neural network;
in order to solve the hyperbolic space of input mapping of the Euclidean space, the aggregation formula operation of the graph convolution neural network is replaced by a basic algorithm of the hyperbolic space;
in order to define the conditional strength function of the Hawkes process in the hyperbolic space, the operation of the function is used
Addition and
multiplying to redefine the conditional strength function;
in order to make each iteration have a hyperbolic space model with a proper curvature, the curvature c is taken as a parameter of a loss function, and the curvature c is continuously updated iteratively during model training so as to solve the second challenge, so that the model can better describe the distribution of future events.
Example 2
Referring to fig. 3 to 6, a second embodiment of the present invention, which is different from the first embodiment, provides an experimental verification of a non-european space-based information extraction method, specifically including:
for the euclidean space map feature, the conventional graph convolution neural network is used for capturing the aggregate information between nodes by constructing a filter in the fourier domain, and the specific operations are as follows:
in order to learn more valuable information from the hierarchical structure diagram, the present embodiment selects a graph convolution neural network defined in a hyperbolic space to obtain the spatial dependency, and the specific implementation method is shown as the following formula.
Therefore, for the input features of the euclidean space and the output of the model, the conversion between the euclidean space features and the hyperbolic space features is realized according to the Exponential mapping (Exponential) and the logarithmic mapping (logarithmic), and the following reasoning gives a closed derivation of the Exponential mapping and the logarithmic mapping:
for any point
When v ≠ 0, the exponent map
Can be given by:
logarithmic mapping when y ≠ x
Can be given by:
hyperbolic spatial curvature K given at different layers l-1 and l in a neural networkl-1,KlNonlinear activation functions using hyperbolic spaces of different curvatures
For the nonlinear activation function in the Euclidean space, the data is mapped to the Euclidean space by using logarithmic mapping for activation, and then is mapped back to the hyperbolic space by using the exponent, and the operation is as follows.
Wherein the superscript H represents a hyperbolic space.
When a graph of a Euclidean space is obtained, two layers of hyperbolic space graph convolutional neural networks are adopted to capture the space characteristics of the graph, wherein the definition of one layer of hyperbolic space graph convolutional neural network layer is shown as the following formula:
wherein, Kl-1And KlHyperbolic space curvature, W, of the convolution layers l-1 and l, respectivelylRepresenting the weight matrix of the l-1 layer, and the output hyperbolic space characteristic H of the last layer(l+1)The next phase is input as spatial information to predict the time and type of the next event.
During the Hawkes process stage of the hyperbolic space diagram nerve, when obtaining the output information H of the hyperbolic space diagram convolutional neural network (HGCN)(l+1)And the dynamic propagation sequence in the past
This example presents a HGNHP phase (Hyperbolic Graph Neural Hawkes Process Stage) based on a gated round-robin unit (GRU) and Poincare sphereThe following five steps are iterated to predict the type and time of occurrence of the next event.
Referring to FIG. 2, the information of the past event and the output of the previous stage include { yi-1,g,ti-1As a triplet, the first item is
Read thermal coding of middle node, the second item is graph embedding learned from the first stage and represents the aggregation information of corresponding nodes in hyperbolic space, and the last item is the occurrence time t of the current eventi-1。
Hidden layer status update, as shown in FIG. 1, the right side shows details of HGNHP cell, ht-1Represents ti-1Hidden state of moment rtAnd utIs reset gate and update gate of GRU, when current input sum h is receivedt-1After the hidden state, the calculation process of the hidden layer state update is shown as the following formula:
wherein,
representing an activation function, g representing node aggregation information captured by a graph convolution neural network defined in a hyperbolic space, k representing an event k embedding occurring at a current time, and t representing a time interval from a previous occurring eventW represents the weight and b represents the deviation, so the event propagation probability P (yn +1hn) and the conditional strength function approximating the Hawkes process can be calculated.
Event propagation probability given by hiDecoding the output of the hidden state to Euclidean space by exponential mapping and calculating
The specific calculation is as follows:
wherein N is a figure
The number of the nodes of (a) is,
is the deviation of the measured value,
k-th is the th row of matrix V.
Referring to FIGS. 3, 4, 5, and 6, in the artificially generated dataset, the RMSE of Nostradamus was 2.84, and over all comparative methods, in the automated teller machine failure dataset, the RMSE of the most advanced method was 2.256, Nostradamus was predicting RMSE 2.82, and Nostradamus was predicting RMSE 10.05 in the Stack overflow dataset, similar to the most advanced method, constructing a graph-based dataset to verify that adding graph information may improve the performance of timestamp prediction, and these results show that Nostradamus performs better than other prior methods when applied to the artificially synthesized dataset.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (9)
1. A non-Europe space based information extraction method is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
mapping a graph structure input by an Euclidean space to a hyperbolic space based on a basic algorithm of the hyperbolic space;
by using
Addition and
multiplying to redefine a conditional strength function of a Hawkes process in the hyperbolic space;
and taking the curvature c as a parameter of the function, and iteratively updating the curvature c to obtain a trained hyperbolic space model to describe the distribution of future events.
2. The non-european space-based information extraction method according to claim 1, wherein: the method further comprises the steps of embedding graph information of the hyperbolic space, fusing information of the hyperbolic space, embedding category characteristics of the hyperbolic space, fusing information, predicting, training and fine-tuning.
3. The non-european space-based information extraction method according to claim 2, wherein: the embedding of the graph information of the hyperbolic space comprises the steps of mapping an adjacent matrix of a user node to the hyperbolic space, and then utilizing a GCN in the hyperbolic space to aggregate the adjacent matrix information of the graph structure.
4. The non-ohmic space-based information extraction method according to claim 2 or 3, wherein: the information fusion of the hyperbolic space comprises mapping specific time intervals and occurrence time matrixes of past events to the hyperbolic space for aggregation.
5. The non-ohmic space-based information extraction method according to claim 4, wherein: embedding the category characteristics of the hyperbolic space comprises mapping a category matrix of all past occurrence events into the hyperbolic space.
6. The non-ohmic space-based information extraction method according to claim 5, wherein: and the information fusion comprises the steps of inputting the adjacency matrix and the characteristic matrix into the hyperbolic space GCN, and connecting the output of the GCN with the category matrix and the time matrix which are input into the hyperbolic space for mapping.
7. The non-ohmic space-based information extraction method of claim 6, wherein: the prediction comprises the steps of simulating and calling an inverse method and Monte Carlo sampling, and predicting the type and time of an event which occurs in the future.
8. The non-european space-based information extraction method according to claim 7, wherein: the training comprises the steps of dividing a data set, selecting 10 events as one-time training, predicting the event time and the category of the next event, and performing training through a cross entropy loss function.
9. The non-european space-based information extraction method according to claim 8, wherein: and the fine adjustment comprises the steps of selecting different batch sizes, different cyclic neural network models and learning rates to carry out a series of fine adjustments, and finishing the optimal output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110431000.7A CN113111302B (en) | 2021-04-21 | 2021-04-21 | Information extraction method based on non-European space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110431000.7A CN113111302B (en) | 2021-04-21 | 2021-04-21 | Information extraction method based on non-European space |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113111302A true CN113111302A (en) | 2021-07-13 |
| CN113111302B CN113111302B (en) | 2023-05-12 |
Family
ID=76719112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110431000.7A Active CN113111302B (en) | 2021-04-21 | 2021-04-21 | Information extraction method based on non-European space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111302B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947088A (en) * | 2021-09-15 | 2022-01-18 | 阿里巴巴达摩院(杭州)科技有限公司 | Emotion polarity representation method, emotion polarity representation device and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800504A (en) * | 2019-01-21 | 2019-05-24 | 北京邮电大学 | A kind of embedding grammar and device of heterogeneous information network |
| CN109857457A (en) * | 2019-01-29 | 2019-06-07 | 中南大学 | A kind of function level insertion representation method learnt in source code in the hyperbolic space |
| CN111782768A (en) * | 2020-06-30 | 2020-10-16 | 首都师范大学 | Fine-grained entity identification method based on hyperbolic space representation and label text interaction |
| CN112131490A (en) * | 2020-09-18 | 2020-12-25 | 东南大学 | Region-sensitive interest point recommendation method driven by knowledge graph |
| CN112287126A (en) * | 2020-12-24 | 2021-01-29 | 中国人民解放军国防科技大学 | Entity alignment method and device suitable for multi-mode knowledge graph |
| CN112328801A (en) * | 2020-09-28 | 2021-02-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Method for predicting group events by event knowledge graph |
-
2021
- 2021-04-21 CN CN202110431000.7A patent/CN113111302B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800504A (en) * | 2019-01-21 | 2019-05-24 | 北京邮电大学 | A kind of embedding grammar and device of heterogeneous information network |
| CN109857457A (en) * | 2019-01-29 | 2019-06-07 | 中南大学 | A kind of function level insertion representation method learnt in source code in the hyperbolic space |
| CN111782768A (en) * | 2020-06-30 | 2020-10-16 | 首都师范大学 | Fine-grained entity identification method based on hyperbolic space representation and label text interaction |
| CN112131490A (en) * | 2020-09-18 | 2020-12-25 | 东南大学 | Region-sensitive interest point recommendation method driven by knowledge graph |
| CN112328801A (en) * | 2020-09-28 | 2021-02-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Method for predicting group events by event knowledge graph |
| CN112287126A (en) * | 2020-12-24 | 2021-01-29 | 中国人民解放军国防科技大学 | Entity alignment method and device suitable for multi-mode knowledge graph |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947088A (en) * | 2021-09-15 | 2022-01-18 | 阿里巴巴达摩院(杭州)科技有限公司 | Emotion polarity representation method, emotion polarity representation device and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111302B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tencaliec et al. | Flexible semiparametric generalized Pareto modeling of the entire range of rainfall amount | |
| CN113672811B (en) | Hypergraph convolution collaborative filtering recommendation method and system based on topology information embedding and computer readable storage medium | |
| Kirshner | Modeling of multivariate time series using hidden Markov models | |
| CN107609648B (en) | Genetic algorithm combined with stacking noise reduction sparse automatic encoder | |
| CN113112004B (en) | Time-space prediction method based on Hox process and graph neural network | |
| CN113190688A (en) | Complex network link prediction method and system based on logical reasoning and graph convolution | |
| CN114611384A (en) | Medical knowledge graph node importance evaluation method based on graph neural network | |
| CN113111302A (en) | Information extraction method based on non-European space | |
| CN116340646A (en) | Recommendation method for optimizing multi-element user representation based on hypergraph motif | |
| CN113688253A (en) | Hierarchical perception temporal knowledge map representation learning method | |
| CN104657434A (en) | Construction method for social network structure | |
| CN113689052B (en) | Travel demand prediction method based on tensor product neural network | |
| CN113688974B (en) | Mobile application recommendation method based on lightweight graph convolutional network | |
| CN113205181A (en) | Graph combination optimization problem solving method based on deep graph learning | |
| CN114997476A (en) | Commodity prediction method fusing commodity incidence relation | |
| CN117077771B (en) | Causal association driven aviation traffic network sweep effect prediction method | |
| CN116306780B (en) | Dynamic graph link generation method | |
| CN113537613B (en) | Temporal network prediction method for die body perception | |
| CN116665809A (en) | Method, system and equipment for predicting material property based on graph neural network | |
| CN115794586A (en) | Cloud server software aging prediction method, device, equipment and medium | |
| CN114386600B (en) | Network characterization method based on self-adaptive structure and position coding | |
| CN116258923A (en) | Image recognition model training method, device, computer equipment and storage medium | |
| CN115936176A (en) | Load prediction method based on data enhancement strategy and residual self-correction learning model | |
| CN114611803A (en) | Switch device service life prediction method based on degradation characteristics | |
| CN113744023A (en) | Dual-channel collaborative filtering recommendation method based on graph convolution network |
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 |