CN114611816B - Potential event prediction method, device, equipment and storage medium - Google Patents
Potential event prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114611816B CN114611816B CN202210281274.7A CN202210281274A CN114611816B CN 114611816 B CN114611816 B CN 114611816B CN 202210281274 A CN202210281274 A CN 202210281274A CN 114611816 B CN114611816 B CN 114611816B
- Authority
- CN
- China
- Prior art keywords
- event
- map
- scene
- nodes
- neural network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003062 neural network model Methods 0.000 claims abstract description 98
- 239000013598 vector Substances 0.000 claims abstract description 71
- 238000012545 processing Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 23
- 238000003058 natural language processing Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 3
- 230000001149 cognitive effect Effects 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 230000004807 localization Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Abstract
The disclosure provides a potential event prediction method, a device, equipment and a storage medium, and relates to the technical field of machine learning cognitive computing. The method comprises the following steps: obtaining a rational map of a target event scene, wherein the rational map comprises: the event nodes and the node connection relations among the event nodes are provided, and each event node corresponds to one event in the target event scene; determining a feature vector of the rational atlas by using the graph neural network model; inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and corresponding node connection relations in the event map; and determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations. The method and the device can improve the accuracy of predicting the event based on the event text.
Description
Technical Field
The disclosure relates to the technical field of machine learning cognitive computing, and in particular relates to a potential event prediction method, a device, equipment and a storage medium.
Background
In the context of the information age, events that have occurred are recorded as documents for storage, for use in a scenario such as message distribution or event analysis. However, in the process of summarizing the events into the text, the situation of losing, missing or vague key information is unavoidable, and the effectiveness of the information in the text is seriously affected.
Algorithms based on natural language processing are used in the related art to predict missing events. By taking the text itself describing the events as input, the relation of each event in the text is modeled by means of the complexity of the model, but the prediction result is completely dependent on the normalization of the input, so that the reliability of the output result is not stable enough.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The present disclosure provides a method, an apparatus, an electronic device, and a storage medium for predicting a potential event, which overcome, at least to some extent, the problem that the output result of the method for predicting a missing event provided in the related art is unreliable. In the related art, a method for predicting an event based on an event text has the technical problem that a prediction result is inaccurate.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to one aspect of the present disclosure, there is provided a potential event prediction method, comprising: obtaining a rational map of a target event scene, wherein the rational map comprises: a plurality of event nodes and node connection relations among the event nodes, wherein each event node corresponds to one event in the target event scene; determining a feature vector of the rational atlas using a graph neural network model; inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and corresponding node connection relations in the event map; and determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations.
In one embodiment of the present disclosure, determining feature vectors of the rational atlas using a graph neural network model includes: determining the feature vector of each event node in the event map by using a graph neural network model; and determining the feature vector of the event map according to the feature vector of each event node in the event map.
In one embodiment of the disclosure, before inputting the feature vector of the event map into the pre-trained neural network model, predicting the missing event node and the corresponding node connection relationship in the event map, the method further includes: acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; and training the neural network model by taking the plurality of complete event map and the corresponding missing event map as training data to obtain a trained neural network model.
In one embodiment of the present disclosure, obtaining a plurality of complete rational atlases includes: acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; and generating a complete event map under each event scene according to the plurality of event nodes and the corresponding node connection relations under each event scene.
In one embodiment of the disclosure, inputting the feature vector of the event map into a pre-trained neural network model, predicting the missing event node and the corresponding node connection relationship in the event map, including: based on a pre-trained neural network model, adopting a multi-layer attention mechanism to predict missing event nodes and corresponding node connection relations in the event map layer by layer.
In one embodiment of the present disclosure, based on a pre-trained neural network model, a multi-layer attention mechanism is adopted to predict event nodes missing in the event map and corresponding node connection relations layer by layer, including: inputting the feature vector of the event map to a pre-trained neural network model, and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting missing event node content; inputting the type of the missing event node and the content of the missing event node into a pre-trained neural network model, and outputting the missing event node and the corresponding node connection relation in the event map.
In one embodiment of the present disclosure, obtaining a rational map of a target event scene includes: acquiring a plurality of events in a target scene; performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene; inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene; and generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
According to another aspect of the present disclosure, there is provided a potential event prediction apparatus, comprising: the event map acquisition module is used for acquiring an event map of a target event scene, wherein the event map comprises: a plurality of event nodes and node connection relations among the event nodes, wherein each event node corresponds to one event in the target event scene; the feature vector determining module is used for determining the feature vector of the rational atlas by using the graph neural network model; the neural network input module is used for inputting the feature vector of the event map into a pre-trained neural network model and predicting the missing event nodes and the corresponding node connection relations in the event map; and the potential event determining module is used for determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations.
According to still another aspect of the present disclosure, there is provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the potential event prediction method described above via execution of the executable instructions.
According to yet another aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the potential event prediction method described above.
According to the potential event prediction method provided by the embodiment of the disclosure, the feature vector of the event map of the target event scene is calculated by acquiring the event map of the target event scene and is input into the pre-trained neural network model to obtain the missing event nodes and the corresponding node connection relations in the event map of the target event scene, and the potential event in the target event scene is determined according to the missing event nodes and the corresponding node connection relations in the event map. In the embodiment of the disclosure, a situation map is constructed based on the event text, and the event represented by the natural language is abstracted into the event node and the connection relation, so that the potential event is accurately predicted.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 illustrates a flow chart of a method of potential event prediction in an embodiment of the present disclosure;
FIG. 2 illustrates a feature vector determination flow diagram in an embodiment of the present disclosure;
FIG. 3 illustrates a neural network model training flow diagram in an embodiment of the present disclosure;
FIG. 4 illustrates a complete event map acquisition flow diagram in an embodiment of the present disclosure;
FIG. 5 illustrates a neural network model layer-by-layer prediction flow diagram in an embodiment of the present disclosure;
FIG. 6 illustrates a neural network model layer-by-layer prediction flow diagram in an embodiment of the present disclosure;
FIG. 7 illustrates a process map acquisition flow diagram for a target event scenario in an embodiment of the present disclosure;
FIG. 8 illustrates a schematic diagram of a potential event prediction device in an embodiment of the present disclosure;
FIG. 9 shows a block diagram of an electronic device in an embodiment of the disclosure;
fig. 10 shows a schematic diagram of a computer-readable storage medium in an embodiment of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
The present exemplary embodiment will be described in detail below with reference to the accompanying drawings and examples.
First, in an embodiment of the present disclosure, a method for predicting a potential event is provided, which may be performed by any electronic device having computing processing capabilities.
Fig. 1 shows a flowchart of a potential event prediction method in an embodiment of the present disclosure, and as shown in fig. 1, the potential event prediction method provided in the embodiment of the present disclosure includes the following steps:
s102, acquiring a rational map of a target event scene, wherein the rational map comprises: the system comprises a plurality of event nodes and node connection relations among the event nodes, wherein each event node corresponds to one event in a target event scene.
It should be noted that the target event scenario may be any event scenario, where the target event scenario includes a plurality of events and a logical relationship between the plurality of events. Optionally, the target event scenario in the embodiments of the present disclosure may be any target event scenario to be predicted, such as a medical scenario, an industrial scenario, a financial scenario, and the like. The event map may be a map formed by a plurality of event nodes and connection relations between event nodes, each event node in the map corresponds to an event, and the connection relations between the event nodes represent logical relations between the corresponding events.
S104, determining the feature vector of the rational atlas by using the graph neural network model.
The graph neural network model may be a network model obtained by training a graph neural network (Graph Neural Networks, GNN). The feature vector of a certain event map refers to the feature vector of each event node in the event map forming a matrix.
S106, inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and the corresponding node connection relations in the event map.
The neural network model may be a model obtained through machine learning training. Alternatively, the neural network model in the embodiments of the present disclosure may be a model capable of predicting, from the feature vector of the input rational atlas, the missing event node and the corresponding node connection relationship in the rational atlas. The missing event node may be a node of an event in the event map, which itself lacks a literal record.
S108, determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations.
It should be noted that the potential event may be an event that may be missing in the event map.
In specific implementation, each event included in a target event scene is generalized to be an event node, the event scene is represented in a manner of a event map, and compared with a method for directly processing a text, the method and the device can explicitly represent an event structure through the event map, reduce dependence on model complexity and accurately predict potential events.
In one embodiment of the present disclosure, as shown in fig. 2, the potential event prediction method provided in the embodiment of the present disclosure may determine feature vectors of a rational map using a graph neural network model by:
s202, determining the feature vector of each event node in the event map by using the graph neural network model.
In specific implementation, each event node in the event map is respectively formed into a corresponding matrix, then the matrices are respectively input into a graph neural network model, and the graph neural network model respectively outputs one or more characteristic vectors of the matrices.
S204, determining the feature vector of the event map according to the feature vector of each event node in the event map.
In the implementation, an adjacent matrix of the event map is constructed according to the node connection relation among the event nodes, and feature extraction is carried out on the feature vectors of the event nodes and the adjacent matrix through the graph attention network model to obtain the feature vectors of the event map.
According to the method and the device, the feature vector is calculated through each event node in the event map, so that the feature vector of the event map is accurately determined.
In one embodiment of the present disclosure, as shown in fig. 3, before the feature vector of the event map is input to the pre-trained neural network model to predict the missing event node and the corresponding node connection relationship in the event map, the potential event prediction method provided in the embodiment of the present disclosure further includes the following steps:
s302, acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene.
It should be noted that the complete event map may be a directed graph formed by all event nodes included in one event and node connection relationships between the event nodes. The event scene can be any event scene with complete text records, such as a medical scene, an industrial scene, a financial scene and the like.
S304, deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain the missing event map of each complete event map.
And S306, training the neural network model by taking the plurality of complete event map and the corresponding missing event map as training data to obtain a trained neural network model.
In the specific implementation, the event nodes in the complete event map and the node connection relation between the event nodes are partially deleted, and the deleted complete event map is the missing event map and is used as training data of the neural network. According to the method and the device, the node connection relation between part of event nodes in the complete event map is deleted, so that the neural network model is trained by taking the node connection relation as training data, and the prediction accuracy of the neural network model is improved.
In one embodiment of the present disclosure, as shown in fig. 4, the potential event prediction method provided in the embodiment of the present disclosure may obtain a plurality of complete event maps by:
s402, acquiring a plurality of events in each event scene.
In a specific implementation, a plurality of events with complete text records of any one of a medical scene, an industrial scene, a financial scene and the like are acquired. For example, fault alarm events, field investigation events, fault localization events and fault removal events in an industrial scenario are acquired.
S404, performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene.
In one embodiment, a fault alarm event, a field investigation event, a fault location event and a fault removal event in an industrial scenario are subjected to generalization processing to obtain a plurality of event nodes of the fault alarm event, a plurality of event nodes of the field investigation event, a plurality of event nodes of the fault location event and a plurality of event nodes of the fault removal event. The generalization refers to expanding a specific and individual event to a general event, and the generalization process may be expanding a specific event to a representative node.
S406, inputting a plurality of events in each event scene into the natural language processing model, and outputting the node connection relation among a plurality of event nodes in each event scene.
In one embodiment, the fault alarm event, the site investigation event, the fault location event and the fault removal event in the industrial scene are respectively input into a natural language processing model to obtain the logic relationship among the events in the fault alarm event, the logic relationship among the events in the site investigation event, the logic relationship among the events in the fault location event and the logic relationship among the events in the fault removal event, and the logic relationship is used as the connection relationship of the event nodes.
S408, generating a complete event map under each event scene according to the plurality of event nodes and the corresponding node connection relations under each event scene.
In one embodiment, the complete rational map of the fault alarm event, the complete rational map of the field investigation event, the complete rational map of the fault localization event, and the complete rational map of the fault removal event are generated from a plurality of event nodes of the fault alarm event, a plurality of event nodes of the field investigation event, a plurality of event nodes of the fault localization event, a plurality of event nodes of the fault removal event, and a logical relationship between each event in the fault alarm event (corresponding to the connection relationship), a logical relationship between each event in the field investigation event (corresponding to the connection relationship), a logical relationship between each event in the fault localization event, and a logical relationship between each event in the fault removal event (corresponding to the connection relationship).
In one embodiment of the present disclosure, as shown in fig. 5, in inputting the feature vector of the event map into the pre-trained neural network model, and predicting the missing event node and the corresponding node connection relationship in the event map, the potential event prediction method provided in the embodiment of the present disclosure further includes the following steps:
s502, based on a pre-trained neural network model, predicting missing event nodes and corresponding node connection relations in a case map layer by adopting a multi-layer attention mechanism.
It should be noted that, the multi-layer attention mechanism may take the output of the previous layer attention mechanism (including the output vector and the manually set weight parameter) as the input of the next layer attention, and in this way, the information of the previous layer is used to guide the prediction of the next layer.
To further illustrate the use of a multi-layer attention mechanism layer-by-layer prediction, in one embodiment of the present disclosure, as shown in fig. 6, S502 may specifically include the steps of:
s602, inputting the feature vector of the event map into a pre-trained neural network model, and outputting the missing event node type.
It should be noted that the event node type may be an attribute indicating a feature of an event. For example, in an industrial scenario, a fault alarm event type, a field survey event type, a fault localization event type, and a fault removal event type.
S604, inputting the missing event node type into a pre-trained neural network model, and outputting the missing event node content.
The content of the event node may be a node representing the event feature.
The field investigation content is more relevant to the fault alarm condition, and then the model pays more attention to the fault alarm node when predicting a specific field investigation event, so that the node content of the missing node is predicted.
S606, inputting the types of the missing event nodes and the content of the missing event nodes into a pre-trained neural network model, and outputting the missing event nodes and the corresponding node connection relations in the event map.
For example, a target event scenario is a device maintenance record, and a event map of the target event includes a fault alarm event, a field investigation event, a fault location event and a fault removal event, and a plurality of event nodes exist in each event. First layer prediction: inputting the feature vector of the event map into a pre-trained neural network model, and the neural network model presumes that the event of the on-site investigation is missing in the event map according to the trained event structure (fault alarm event, on-site investigation event, fault positioning event and fault removal event), namely, the first layer attribute of the missing node is determined: node type. Second layer prediction: in the fault alarm event, the field investigation event, the fault positioning event and the fault removal event, as the field investigation event is most relevant to the fault alarm event, when the node type of the first layer prediction output is input into the neural network model for prediction, the neural network model can allocate high weight to the node of the fault alarm event, and output the second layer attribute of the missing node: node content (corresponding to the nodes of the above-mentioned live investigation event). Third layer prediction: the node type of the first layer of prediction output and the node content of the second layer of prediction output are input into a neural network model, and the event logic relationship (equivalent to the connection relationship) between the node with higher correlation with the missing node and the related node is output, such as which fault alarm event is caused by the field investigation event and which fault location event should be linked.
The method and the device have the advantages that a multi-layer attention structure is introduced in a potential event prediction method, event texts are generalized to event nodes with multi-layer attribute information, and an attention mechanism based on a front-layer prediction result is used in the process of predicting the node attributes layer by layer, so that the reliability and the interpretability of the prediction result are improved.
In one embodiment of the present disclosure, as shown in fig. 7, in acquiring a rational map of a target event scene, the potential event prediction method provided in the embodiment of the present disclosure further includes the following steps:
s702, acquiring a plurality of events in a target scene;
s704, performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene;
s706, inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene;
s708, generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
In specific implementation, event texts are generalized into event nodes, event scenes are represented in a manner of a rational map, and compared with a method for directly processing the texts, the method and the device can explicitly represent event structures through the rational map, reduce dependence on model complexity and accurately predict potential events.
Based on the same inventive concept, a potential event prediction apparatus is also provided in the embodiments of the present disclosure, as described in the following embodiments. Since the principle of solving the problem of the embodiment of the device is similar to that of the embodiment of the method, the implementation of the embodiment of the device can be referred to the implementation of the embodiment of the method, and the repetition is omitted.
Fig. 8 shows a schematic diagram of a potential event prediction apparatus according to an embodiment of the disclosure, as shown in fig. 8, the apparatus includes: a rational map acquisition module 801, a feature vector determination module 802, a neural network input module 803, and a potential event determination module 804.
The event map obtaining module 801 is configured to obtain an event map of a target event scene, where the event map includes: the event nodes and the node connection relations among the event nodes are provided, and each event node corresponds to one event in the target event scene; a feature vector determination module 802, configured to determine a feature vector of a rational map using the graph neural network model; the neural network input module 803 is configured to input a feature vector of the event map to a neural network model trained in advance, and predict event nodes missing in the event map and corresponding node connection relations; the potential event determining module 804 is configured to determine a potential event in the target event scene according to the missing event node in the event map and the corresponding node connection relationship.
In one embodiment of the present disclosure, the feature vector determining module 802 is further configured to: determining the feature vector of each event node in the event map by using a graph neural network model; and determining the feature vector of the event map according to the feature vector of each event node in the event map.
In one embodiment of the present disclosure, the potential event predicting apparatus further includes: the neural network model training module 805 is configured to obtain a plurality of complete event maps, where each complete event map corresponds to an event scenario; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; and training the neural network model by taking the plurality of complete event maps and the corresponding missing event maps as training data to obtain a trained neural network model.
In one embodiment of the present disclosure, the neural network model training module 805 is further configured to: acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; and generating a complete event map under each event scene according to the plurality of event nodes and the corresponding node connection relations under each event scene.
In one embodiment of the present disclosure, the neural network input module 803 is further configured to: based on a pre-trained neural network model, adopting a multi-layer attention mechanism to predict event nodes missing in a event map and corresponding node connection relations layer by layer.
In one embodiment of the present disclosure, the neural network input module 803 is further configured to: inputting the feature vector of the event map into a pre-trained neural network model, and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting the missing event node content; inputting the types of the missing event nodes and the content of the missing event nodes into a pre-trained neural network model, and outputting the missing event nodes and the corresponding node connection relations in the event map.
In one embodiment of the present disclosure, the aforementioned rational map acquisition module 801 is further configured to: acquiring a plurality of events in a target scene; performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene; inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene; and generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
Those skilled in the art will appreciate that the various aspects of the present disclosure may be implemented as a system, method, or program product. Accordingly, various aspects of the disclosure may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 900 according to such an embodiment of the present disclosure is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.
As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, and a bus 930 connecting the different system components (including the storage unit 920 and the processing unit 910).
Wherein the storage unit stores program code that is executable by the processing unit 910 such that the processing unit 910 performs steps according to various exemplary embodiments of the present disclosure described in the above-described "exemplary methods" section of the present specification.
For example, the processing unit 910 may perform the following steps of the method embodiment described above: obtaining a rational map of a target event scene, wherein the rational map comprises: the event nodes and the node connection relations among the event nodes are provided, and each event node corresponds to one event in the target event scene; determining a feature vector of the rational atlas by using the graph neural network model; inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and corresponding node connection relations in the event map; and determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations.
In one embodiment, the processing unit 910 may perform the following steps of the method embodiments described above to determine feature vectors of a rational atlas using a graph neural network model: determining the feature vector of each event node in the event map by using a graph neural network model; and determining the feature vector of the event map according to the feature vector of each event node in the event map.
In one embodiment, the processing unit 910 performs the method, and before inputting the feature vector of the event map into the pre-trained neural network model, and predicting the missing event node and the corresponding node connection relationship in the event map, the following steps of the method embodiment may be performed: acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; and training the neural network model by taking the plurality of complete event maps and the corresponding missing event maps as training data to obtain a trained neural network model.
In one embodiment, the processing unit 910 may perform the following steps of the method embodiment described above to obtain a plurality of complete rational maps: acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; and generating a complete event map under each event scene according to the plurality of event nodes and the corresponding node connection relations under each event scene.
In one embodiment, the processing unit 910 may perform the following steps of the above method embodiment to predict missing event nodes and corresponding node connection relationships in the event map: based on a pre-trained neural network model, adopting a multi-layer attention mechanism to predict event nodes missing in a event map and corresponding node connection relations layer by layer.
In one embodiment, the processing unit 910 may perform the following steps of the above method embodiment to predict the missing event nodes and corresponding node connection relations in the event map layer by layer: inputting the feature vector of the event map into a pre-trained neural network model, and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting the missing event node content; inputting the types of the missing event nodes and the content of the missing event nodes into a pre-trained neural network model, and outputting the missing event nodes and the corresponding node connection relations in the event map.
In one embodiment, the processing unit 910 may perform the following steps of the above method embodiment to obtain a rational map of the target event scene: acquiring a plurality of events in a target scene; performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene; inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene; and generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
The storage unit 920 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 9201 and/or cache memory 9202, and may further include Read Only Memory (ROM) 9203.
The storage unit 920 may also include a program/utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The bus 930 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 900 may also communicate with one or more external devices 940 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 900, and/or any devices (e.g., routers, modems, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 950. Also, electronic device 900 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 over the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 900, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium, which may be a readable signal medium or a readable storage medium, is also provided. Fig. 10 illustrates a schematic diagram of a computer-readable storage medium in an embodiment of the present disclosure, as shown in fig. 10, on which a program product capable of implementing the method of the present disclosure is stored 1000. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
For example, a program product in an embodiment of the disclosure, when executed by a processor, performs a method of: obtaining a rational map of a target event scene, wherein the rational map comprises: the event nodes and the node connection relations among the event nodes are provided, and each event node corresponds to one event in the target event scene; determining a feature vector of the rational atlas by using the graph neural network model; inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and corresponding node connection relations in the event map; and determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: determining the feature vector of each event node in the event map by using a graph neural network model; and determining the feature vector of the event map according to the feature vector of each event node in the event map.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; and training the neural network model by taking the plurality of complete event maps and the corresponding missing event maps as training data to obtain a trained neural network model.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; and generating a complete event map under each event scene according to the plurality of event nodes and the corresponding node connection relations under each event scene.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: based on a pre-trained neural network model, adopting a multi-layer attention mechanism to predict event nodes missing in a event map and corresponding node connection relations layer by layer.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: inputting the feature vector of the event map into a pre-trained neural network model, and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting the missing event node content; inputting the types of the missing event nodes and the content of the missing event nodes into a pre-trained neural network model, and outputting the missing event nodes and the corresponding node connection relations in the event map.
In some embodiments, the program product in the embodiments of the present disclosure may further implement a method of: acquiring a plurality of events in a target scene; performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene; inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene; and generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
More specific examples of the computer readable storage medium in the present disclosure may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In this disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Alternatively, the program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
In particular implementations, the program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the description of the above embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (7)
1. A method of predicting a potential event, comprising:
obtaining a rational map of a target event scene, wherein the rational map comprises: a plurality of event nodes and node connection relations among the event nodes, wherein each event node corresponds to one event in the target event scene;
determining a feature vector of the rational atlas using a graph neural network model;
inputting the feature vector of the event map into a pre-trained neural network model, and predicting the missing event nodes and corresponding node connection relations in the event map;
determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations;
Before the feature vector of the event map is input to a pre-trained neural network model, and the missing event nodes and the corresponding node connection relations in the event map are predicted, the method further comprises: acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; taking the plurality of complete event management maps and the corresponding missing event management maps as training data, and training the neural network model to obtain a trained neural network model;
acquiring a plurality of complete rational atlases, including: acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; generating a complete event map under each event scene according to a plurality of event nodes and corresponding node connection relations under each event scene;
Based on a pre-trained neural network model, predicting event nodes missing in the event map and corresponding node connection relations layer by adopting a multi-layer attention mechanism, wherein the method comprises the following steps of: inputting the feature vector of the event map to a pre-trained neural network model, and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting missing event node content; inputting the type of the missing event node and the content of the missing event node into a pre-trained neural network model, and outputting the missing event node and the corresponding node connection relation in the event map.
2. The method of claim 1, wherein determining feature vectors of the rational atlas using a graph neural network model comprises:
determining the feature vector of each event node in the event map by using a graph neural network model;
and determining the feature vector of the event map according to the feature vector of each event node in the event map.
3. The method for predicting potential events according to claim 1, wherein inputting the feature vector of the event map into a pre-trained neural network model, predicting the missing event nodes and the corresponding node connection relations in the event map comprises:
Based on a pre-trained neural network model, adopting a multi-layer attention mechanism to predict missing event nodes and corresponding node connection relations in the event map layer by layer.
4. The method of claim 1, wherein obtaining a rational map of a target event scene comprises:
acquiring a plurality of events in a target scene;
performing generalization processing on a plurality of events in a target scene to obtain a plurality of event nodes in the target scene;
inputting a plurality of events in a target scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in the target scene;
and generating a rational map of the target event scene according to the plurality of event nodes and the corresponding node connection relations in the target scene.
5. A potential event prediction apparatus, comprising:
the event map acquisition module is used for acquiring an event map of a target event scene, wherein the event map comprises: a plurality of event nodes and node connection relations among the event nodes, wherein each event node corresponds to one event in the target event scene;
the feature vector determining module is used for determining the feature vector of the rational atlas by using the graph neural network model;
The neural network input module is used for inputting the feature vector of the event map into a pre-trained neural network model and predicting the missing event nodes and the corresponding node connection relations in the event map;
the potential event determining module is used for determining potential events in the target event scene according to the missing event nodes in the event map and the corresponding node connection relations;
the neural network model training module: the method comprises the steps of acquiring a plurality of complete event maps, wherein each complete event map corresponds to an event scene; deleting the event nodes in each complete event map and the node connection relation between the event nodes in proportion to obtain a missing event map of each complete event map; taking the plurality of complete event management maps and the corresponding missing event management maps as training data, and training the neural network model to obtain a trained neural network model;
the neural network model training module is further used for acquiring a plurality of events under each event scene; performing generalization processing on a plurality of events in each event scene to obtain a plurality of event nodes in each event scene; inputting a plurality of events in each event scene into a natural language processing model, and outputting node connection relations among a plurality of event nodes in each event scene; generating a complete event map under each event scene according to a plurality of event nodes and corresponding node connection relations under each event scene;
The neural network input module is also used for inputting the feature vector of the event map to a pre-trained neural network model and outputting the missing event node type; inputting the missing event node type into a pre-trained neural network model, and outputting missing event node content; inputting the type of the missing event node and the content of the missing event node into a pre-trained neural network model, and outputting the missing event node and the corresponding node connection relation in the event map.
6. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the potential event prediction method of any one of claims 1 to 4 via execution of the executable instructions.
7. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the potential event prediction method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210281274.7A CN114611816B (en) | 2022-03-21 | 2022-03-21 | Potential event prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210281274.7A CN114611816B (en) | 2022-03-21 | 2022-03-21 | Potential event prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114611816A CN114611816A (en) | 2022-06-10 |
| CN114611816B true CN114611816B (en) | 2024-02-27 |
Family
ID=81864940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210281274.7A Active CN114611816B (en) | 2022-03-21 | 2022-03-21 | Potential event prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114611816B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363449A (en) * | 2019-07-25 | 2019-10-22 | 中国工商银行股份有限公司 | A kind of Risk Identification Method, apparatus and system |
| CN110688489A (en) * | 2019-09-09 | 2020-01-14 | 中国电子科技集团公司电子科学研究院 | Knowledge graph deduction method and device based on interactive attention and storage medium |
| CN110968699A (en) * | 2019-11-01 | 2020-04-07 | 数地科技(北京)有限公司 | Logic map construction and early warning method and device based on event recommendation |
| CN111881219A (en) * | 2020-05-19 | 2020-11-03 | 杭州中奥科技有限公司 | Dynamic knowledge graph completion method and device, electronic equipment and storage medium |
| CN112819164A (en) * | 2021-02-02 | 2021-05-18 | 京东数科海益信息科技有限公司 | Inference method and device of affair map and computer equipment |
| CN113822494A (en) * | 2021-10-19 | 2021-12-21 | 平安科技（深圳）有限公司 | Risk prediction method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11379733B2 (en) * | 2019-07-10 | 2022-07-05 | International Business Machines Corporation | Detecting and predicting object events from images |
-
2022
- 2022-03-21 CN CN202210281274.7A patent/CN114611816B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363449A (en) * | 2019-07-25 | 2019-10-22 | 中国工商银行股份有限公司 | A kind of Risk Identification Method, apparatus and system |
| CN110688489A (en) * | 2019-09-09 | 2020-01-14 | 中国电子科技集团公司电子科学研究院 | Knowledge graph deduction method and device based on interactive attention and storage medium |
| CN110968699A (en) * | 2019-11-01 | 2020-04-07 | 数地科技(北京)有限公司 | Logic map construction and early warning method and device based on event recommendation |
| CN111881219A (en) * | 2020-05-19 | 2020-11-03 | 杭州中奥科技有限公司 | Dynamic knowledge graph completion method and device, electronic equipment and storage medium |
| CN112819164A (en) * | 2021-02-02 | 2021-05-18 | 京东数科海益信息科技有限公司 | Inference method and device of affair map and computer equipment |
| CN113822494A (en) * | 2021-10-19 | 2021-12-21 | 平安科技（深圳）有限公司 | Risk prediction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114611816A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11487539B2 (en) | Systems and methods for automating and monitoring software development operations | |
| CN108491320A (en) | Exception analysis method, device, computer equipment and the storage medium of application program | |
| WO2022116322A1 (en) | Method and apparatus for generating anomaly detection model, and anomaly event detection method and apparatus | |
| CN109408105A (en) | Acquisition method, device, computing device and the storage medium of user behavior data | |
| US8917853B2 (en) | Enhanced customer experience through speech detection and analysis | |
| US11037674B2 (en) | Dashboard usage tracking and generation of dashboard recommendations | |
| CN109144879B (en) | Test analysis method and device | |
| CN111258832B (en) | Interface parameter verification method, device, equipment and medium | |
| CN115827436A (en) | Data processing method, device, equipment and storage medium | |
| CN114491037A (en) | Fault diagnosis method, device, equipment and medium based on knowledge graph | |
| CN113110843A (en) | Contract generation model training method, contract generation method and electronic equipment | |
| CN114611816B (en) | Potential event prediction method, device, equipment and storage medium | |
| CN109684207B (en) | Method and device for packaging operation sequence, electronic equipment and storage medium | |
| CN110515758A (en) | A kind of Fault Locating Method, device, computer equipment and storage medium | |
| CN116805012A (en) | Quality assessment method and device for multi-mode knowledge graph, storage medium and equipment | |
| CN111176944A (en) | Block chain intelligent contract calling record analysis method, device, terminal and storage medium | |
| CN115964701A (en) | Application security detection method and device, storage medium and electronic equipment | |
| CN114500075B (en) | User abnormal behavior detection method and device, electronic equipment and storage medium | |
| CN114238128A (en) | Test case generation method and device, electronic equipment and computer readable medium | |
| CN117033318B (en) | Method and device for generating data to be tested, storage medium and electronic equipment | |
| CN113434193B (en) | Root cause change positioning method and device | |
| CN111435452A (en) | Model training method, device, equipment and medium | |
| CN113821436B (en) | Method and device for generating test script | |
| CN116467178B (en) | Database detection method, apparatus, electronic device and computer readable medium | |
| CN117331548B (en) | Low-code development system based on intelligent building software |
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 |