CN116821374A - Event prediction method based on information - Google Patents
Event prediction method based on information Download PDFInfo
- Publication number
- CN116821374A CN116821374A CN202310932586.4A CN202310932586A CN116821374A CN 116821374 A CN116821374 A CN 116821374A CN 202310932586 A CN202310932586 A CN 202310932586A CN 116821374 A CN116821374 A CN 116821374A
- Authority
- CN
- China
- Prior art keywords
- event
- prediction
- text data
- target
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000013598 vector Substances 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000003058 natural language processing Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 8
- 238000005192 partition Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 7
- 230000002787 reinforcement Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06N3/092—Reinforcement learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an event prediction method based on information in the technical field of event analysis and processing, and aims to solve the technical problem of low interpretation of the existing event prediction. It comprises the following steps: acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through relevance among the key information; based on the event knowledge graph, encoding the event text data to obtain corresponding event codes, wherein the event codes are converted into corresponding digital vectors; inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of event text data, and providing a generation formula rule of a prediction basis for the prediction result. The method and the device can acquire the corresponding prediction result of the event text data, can also acquire the corresponding generation formula rule of the final prediction result, and improve the interpretability of the prediction result.
Description
Technical Field
The application relates to an event prediction method based on information, and belongs to the technical field of event analysis and processing.
Background
Prediction is a theory and method for regulating current actions by researching the future development trend of something according to the past development rule of something. Prediction learning (predictive learning) has been studied in many fields, and event prediction has been widely used in many scenarios. For example, the method can accurately predict time and space of target events such as war, epidemic situation, terrorist attack and the like, is helpful for maximally improving benefits related to future events, realizes minimum loss, and simultaneously provides huge benefits for key fields such as national security, disease prevention, disaster management and the like. Therefore, the prediction and early warning of the heavy event are performed, and sufficient preparation is made for the subsequent development of the event in advance. Prediction is a precondition for decision making, and any successful decision making is not a scientific prediction. The prediction method is various, and different prediction methods are applicable to different prediction objects. A wide variety of prediction methods are formed due to the difference in predicted objects, targets, content and deadlines.
In the present big data age, the event prediction technology has been rapidly developed, and a plurality of alternative methods for processing the event prediction problem based on the statistical technology are proposed at present, and the need of comprehensively exploring the potential mechanism of the event occurrence is avoided, however, the method of some black boxes is difficult to output as the decision basis of prediction, has low interpretability, and has great limitation on the applicability. In addition, the event prediction often needs to be performed based on a high-quality structured event library for analysis prediction, and most of open source information and closed source information in the existing information data are unstructured texts, so that it is difficult to construct an event library meeting the prediction requirement.
Disclosure of Invention
The application aims to overcome the defects in the prior art, provides an event prediction method based on information, and solves the technical problem that the existing event is difficult to make a prediction result with high interpretability.
In order to achieve the above purpose/solve the above technical problems, the present application is realized by adopting the following technical scheme:
in a first aspect, the present application provides an intelligence-based event prediction method, including:
acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through the relevance of each key information;
based on the event knowledge graph, encoding the event text data to obtain corresponding event codes, wherein the event codes are used for converting the event text data into corresponding digital vectors;
inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of event text data, and providing a generation formula rule of a prediction basis for the prediction result.
With reference to the first aspect, further, the process of constructing a knowledge graph includes:
detecting an event from the event text data, classifying the event, and identifying a target event;
extracting basic information and event attribute information of the target event;
and carrying out co-fingering analysis on the target event based on the basic information and the event attribute information, and associating different stories of the same target event to obtain the story number.
With reference to the first aspect, further, the extracted target event specifically includes:
the basic information at least comprises time, place, parties involved in the event and event types;
the event attribute information includes the duration of an event, the damage degree of a target, and the change of the scale of personnel or equipment;
the event attribute information is a quantization index of the target event.
With reference to the first aspect, further, the acquired event code includes: temporal segment coding, spatial partition coding, and event intensity coding.
With reference to the first aspect, further, the acquired event encoding process further includes:
encoding the occurrence time of the target event according to a certain time period to obtain a time segment code;
acquiring a key region of the target event, and coding the key region according to an extraction point or dividing the key region into a plurality of grids for coding to obtain a space partition code;
and inputting the target event into a pre-constructed event attribute information model, and acquiring an event intensity code corresponding to the target event.
With reference to the first aspect, further, the process of obtaining the predicted result of the event text data includes:
dividing each piece of key information into training set data and testing set data based on the relevance between each piece of key information in an event knowledge graph;
training by adopting a relation reinforcement learning framework according to the event codes corresponding to the training set data, the test set data and the event text data to obtain a trained event prediction model;
and inputting event codes corresponding to the event text data to be predicted at the current moment into a trained event prediction model, and obtaining the prediction results of time and space-time distribution of the current target event at the future moment.
With reference to the first aspect, further, the process of providing a prediction basis for the prediction result includes:
and extracting a generation rule of the current target event to obtain the prediction result based on the prediction result of the time and space-time distribution of the current target event at the future moment, and taking the generation rule as a prediction basis of the prediction result corresponding to the current target event.
In a second aspect, an intelligence-based event prediction apparatus includes:
the text analysis module is used for acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through the relevance among the key information;
the coding conversion module is used for coding the event text data based on the event knowledge graph to obtain corresponding event codes, and the event codes are used for converting the event text data into corresponding digital vectors;
the model prediction module is used for inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of the event text data and providing a generation formula rule of a prediction basis for the prediction result.
In a third aspect, an electronic terminal comprising a processor and a memory connected to the processor, in which memory a computer program is stored which, when executed by the processor, performs the steps of the method according to any of the first aspects.
In a fourth aspect, a computer readable storage medium has stored thereon a computer program, characterized in that the program when executed by a processor implements the steps of the method according to any of the first aspects.
Compared with the prior art, the application has the beneficial effects that:
the open source big data information and the closed source small data information form event text data, natural language processing is adopted to carry out semantic analysis on the event text data, so that key information in the time text data is determined, the relevance among the key information is analyzed, the construction of an event knowledge graph is facilitated, training set data and test set data are acquired from the event knowledge graph, the prediction requirement of an event prediction model can be met by combining the relevance among the key information, a required prediction result is obtained, a generation rule of a prediction basis is provided for the prediction result, and the interpretability of the prediction result is improved.
Drawings
FIG. 1 is a flow chart of an event prediction method based on information provided by an embodiment of the present application;
FIG. 2 is a flow chart of a construction process of an event knowledge graph provided by an embodiment of the application;
FIG. 3 is a flow chart of a get event encoding process provided by an embodiment of the present application;
FIG. 4 is a flowchart of an acquisition event prediction model provided by an embodiment of the present application;
fig. 5 is a flow chart of event coding corresponding to event text data to be predicted at the current moment provided by the embodiment of the application;
FIG. 6 is a schematic diagram of an event prediction apparatus according to an embodiment of the present application;
fig. 7 is an internal structure diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following detailed description of the technical solutions of the present application will be given by way of the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and that the embodiments and technical features of the embodiments of the present application may be combined with each other without conflict.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Example 1
Fig. 1 is a flowchart of an event prediction method according to a first embodiment of the present application. The flow chart merely shows the logical sequence of the method according to the present embodiment, and the steps shown or described may be performed in a different order than shown in fig. 1 in other possible embodiments of the application without mutual conflict.
The event prediction method provided in this embodiment may be applied to a terminal, and may be performed by an event prediction apparatus, where the apparatus may be implemented by software and/or hardware, and the apparatus may be integrated in the terminal, for example: any smart phone, tablet computer or computer device with communication function. Referring to fig. 1, the method of the present embodiment specifically includes the following steps:
acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through the relevance among the key information;
specifically, the open source big data information and the closed source small data information together form event text data, and after the event knowledge graph is constructed, the event knowledge graph can analyze and collect event text data of various sources to form a structured event knowledge graph, so that the construction of training set data and test set data is facilitated.
It should be noted that, natural language processing (english abbreviated as NLP, which is called Natural Language Process in its entirety) is used for performing intelligent semantic analysis on open-source big data information and closed-source small data information of the internet to form an event knowledge graph of a structured target event, so as to facilitate extraction of quantized representation of the target event, for example: information such as event duration, target damage level, change in personnel or equipment scale, etc., report propagation amount of event, etc.
Based on the event knowledge graph, encoding the event text data to obtain corresponding event codes, wherein the event codes are used for converting the event text data into corresponding digital vectors;
specifically, based on the constructed event knowledge graph, the received event text data is encoded, and the target event is converted into a corresponding digital vector in a manner of encoding the target event, so that the corresponding digital vector is conveniently provided for a relationship reinforcement learning framework as an input end, and subsequent event prediction model training and prediction are performed.
Inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of event text data, and providing a generation formula rule of a prediction basis for the prediction result.
Specifically, the event prediction model adopts a relation reinforcement learning framework, and is obtained based on a large number of digital vectors of event text data, training set data and test set data.
It should be noted that, the relationship reinforcement learning framework is abbreviated as "RRL" or "Relational Reinforcement Learning" and is used for combining the key information and the correlation between the key information, providing a rule representation and learning framework, and has performance advantages compared with the conventional decision tree method.
Referring to fig. 2, the process of constructing the event knowledge graph is as follows:
events are detected from the event text data and classified to identify target events, i.e., accent events, such as identifying and reading national military operations, identifying terrorist attack events, crowd events, etc.
Extracting basic information and event attribute information of the target event;
the basic information comprises target event occurrence time, place, event involved party, event type and the like; the event attribute information is a quantitative index in the target event, such as the duration of the event, the damage degree of the target, and the change of the personnel or equipment scale.
It should be noted that open source big data information usually uses the duration of an event and the propagation amount of the event to quantify the event; closed source small data intelligence typically quantifies events with information about the extent of damage to the target, as well as changes in personnel or equipment size.
And carrying out co-fingering analysis on the target event based on the basic information and the event attribute information, and associating different stories of the same target event to obtain the story number.
In an embodiment of the present application, the acquired-based event codes include, but are not limited to, time segment codes, spatial partition codes, and event intensity codes.
The time segment coding is obtained by segmenting a target event according to a certain time period; the space partition coding is to code according to points after acquiring key areas or divide the key areas into grids for coding; the event intensity code is obtained by coding quantization indexes in event attribute information.
Referring to fig. 3, the acquired event encoding process further includes:
the target event is encoded according to a certain time period, in the embodiment of the application, the first segment of the time period is used for research, and the other segments refer to the encoding mode of the first segment, so that the corresponding time segment codes are obtained, and the same time interval exists between the corresponding time segments.
It should be noted that the time segment coding also includes various segment modes according to days, weeks, months, quarters, years, and the like. For example: the method comprises the steps of taking 1 month and 1 day in 1900 as reference time points, calculating the difference of days between the current time and the reference time points, and obtaining the coded values of week, month, quarter and year respectively, wherein the coded values are expressed by the coded values coded by days, namely, one coded value is given every other day, and the cycle number difference between the current time and the reference time points, the month number difference between the current time and the reference time points, the quarter difference between the current time and the reference time points and the year number difference between the current time and the reference time points are calculated in the same way.
Acquiring a key region of the target event, and coding the key region according to an extraction point or dividing the key region into a plurality of grids for coding to obtain a space partition code;
it should be noted that, the encoding of the key area according to the abstract points is a point encoding mode, each area position is expressed as an infinitely small abstract point, and a coding value is given to each infinitely small abstract point as a space partition encoding; the method comprises the steps of dividing an important area into a plurality of grids for coding, extracting coordinate information such as longitude and latitude of the important area, dividing the area into a plurality of grids, and assigning a coding value to each grid.
The target event is input into a pre-constructed event attribute information model, namely modeling is carried out through personnel change, equipment change, target damage degree, event quantity change, event type change and other variables, so that an event intensity code corresponding to the target event is obtained, and preparation is carried out for inputting the event intensity code into an event prediction model subsequently.
Referring to fig. 4, before an event code corresponding to a target event is input to a prediction model, test set data and training set data are required to be constructed, and the test set data and the training set data are acquired through correlation between key information extracted from an event knowledge graph, so that a relation reinforcement learning framework (RRL) is used for training, and thus an event prediction model with interpretability is acquired.
The test set data and the training set data comprise, but are not limited to, various data sets such as time prediction, space prediction, time-space joint prediction and the like.
In practical application, referring to fig. 5, before performing event prediction, first, event text data at a current moment is acquired, and in the embodiment of the present application, a first time period is taken as an example, that is, first event text data in a first time period is acquired, and a corresponding first event is detected from the first event text data; and classifying the plurality of first events to obtain a first target event in the text data of the first event, and encoding the target event to obtain a first event code, namely an event code corresponding to the text data of the event to be predicted at the current moment.
And encoding the event corresponding to the event text data to be predicted at the current moment into a trained event prediction model, and obtaining the prediction results of the time and space-time distribution of the current target event at the future moment. Taking the first event segment as an example, after the first event is encoded and input into the event prediction model, the time and space-time distribution of the first target event at the second moment is predicted.
Before the event code corresponding to the event text data to be predicted at the current moment is input into the event prediction model, the event code is organized according to a specific time sequence and a specific space sequence to form a corresponding event vector, and then the event vector is input into the interpretable event prediction model for prediction, so that a required prediction result is obtained.
Referring to fig. 6, based on the prediction results of the time and space distribution of the future time of the current target event, a generation rule of the prediction result obtained by the current target event is extracted and used as a prediction basis of the prediction result corresponding to the current target event, and the obtained prediction result and the generation rule enable the prediction result of the whole event to have excellent interpretability.
Example two
An embodiment of the present application provides an intelligence-based event prediction apparatus, referring to fig. 7, which may be used to implement the method described in the first embodiment, where the apparatus includes:
the text analysis module 710 is configured to obtain event text data, perform semantic analysis on the event text data by using natural language processing, determine key information in the event text data, and construct an event knowledge graph according to the relevance of each key information;
the code conversion module 720 is configured to encode the event text data based on the event knowledge graph, and obtain a corresponding event code, where the event code is used to convert the event text data into a corresponding digital vector;
the model prediction module 730 is configured to input the digital vector into a pre-constructed event prediction model, obtain a prediction result of the event text data, and provide a generating rule of a prediction basis for the prediction result.
For other technical features which are not the best of this embodiment, reference may be made to embodiment one.
Example III
The embodiment of the application also provides an electronic terminal, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method of embodiment one.
Example IV
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of embodiment one.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present application, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present application, and such modifications and variations should also be regarded as being within the scope of the application.
Claims (10)
1. An intelligence-based event prediction method, comprising:
acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through the relevance of each key information;
based on the event knowledge graph, encoding the event text data to obtain corresponding event codes, wherein the event codes are used for converting the event text data into corresponding digital vectors;
inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of event text data, and providing a generation formula rule of a prediction basis for the prediction result.
2. The intelligence-based event prediction method according to claim 1, wherein the constructing a knowledge-graph process includes:
detecting an event from the event text data, classifying the event, and identifying a target event;
extracting basic information and event attribute information of the target event;
and carrying out co-fingering analysis on the target event based on the basic information and the event attribute information, and associating different stories of the same target event to obtain the story number.
3. The intelligence-based event prediction method according to claim 2, wherein the extracted target event specifically comprises:
the basic information at least comprises time, place, parties involved in the event and event types;
the event attribute information includes the duration of an event, the damage degree of a target, and the change of the scale of personnel or equipment;
the event attribute information is a quantization index of the target event.
4. The intelligence-based event prediction method according to claim 1, wherein the acquired event codes include: temporal segment coding, spatial partition coding, and event intensity coding.
5. The intelligence-based event prediction method according to any one of claims 1 to 2, wherein the acquired event coding process further includes:
encoding the occurrence time of the target event according to a certain time period to obtain a time segment code;
acquiring a key region of the target event, and coding the key region according to an extraction point or dividing the key region into a plurality of grids for coding to obtain a space partition code;
and inputting the target event into a pre-constructed event attribute information model, and acquiring an event intensity code corresponding to the target event.
6. The intelligence-based event prediction method according to claim 1, wherein the process of obtaining the predicted result of the event text data comprises:
dividing each piece of key information into training set data and testing set data based on the relevance among the pieces of key information extracted from the event knowledge graph;
training by adopting a relation reinforcement learning framework according to the event codes corresponding to the training set data, the test set data and the event text data to obtain a trained event prediction model;
and inputting event codes corresponding to the event text data to be predicted at the current moment into a trained event prediction model, and obtaining the prediction results of time and space-time distribution of the current target event at the future moment.
7. The intelligence-based event prediction method according to claim 6, wherein the process of providing the predictive result with the generated rule of the prediction basis comprises:
and extracting a generation rule of the current target event to obtain the prediction result based on the prediction result of the time and space-time distribution of the current target event at the future moment, and taking the generation rule as a prediction basis of the prediction result corresponding to the current target event.
8. An intelligence-based event prediction apparatus, comprising:
the text analysis module is used for acquiring event text data, carrying out semantic analysis on the event text data by adopting natural language processing, determining key information in the event text data, and constructing an event knowledge graph through the relevance among the key information;
the coding conversion module is used for coding the event text data based on the event knowledge graph to obtain corresponding event codes, and the event codes are used for converting the event text data into corresponding digital vectors;
the model prediction module is used for inputting the digital vector into a pre-constructed event prediction model, obtaining a prediction result of the event text data and providing a generation formula rule of a prediction basis for the prediction result.
9. An electronic terminal comprising a processor and a memory coupled to the processor, wherein a computer program is stored in the memory, which, when executed by the processor, performs the steps of the method according to any of claims 1-8.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310932586.4A CN116821374A (en) | 2023-07-27 | 2023-07-27 | Event prediction method based on information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310932586.4A CN116821374A (en) | 2023-07-27 | 2023-07-27 | Event prediction method based on information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116821374A true CN116821374A (en) | 2023-09-29 |
Family
ID=88114577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310932586.4A Pending CN116821374A (en) | 2023-07-27 | 2023-07-27 | Event prediction method based on information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116821374A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109643323A (en) * | 2016-07-15 | 2019-04-16 | 谷歌有限责任公司 | Content item is selected using intensified learning |
| CN112183881A (en) * | 2020-10-19 | 2021-01-05 | 中国人民解放军国防科技大学 | Public opinion event prediction method and device based on social network and storage medium |
| CN113283589A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Updating method and device of event prediction system |
| CN113326381A (en) * | 2020-02-28 | 2021-08-31 | 拓尔思天行网安信息技术有限责任公司 | Semantic and knowledge graph analysis method, platform and equipment based on dynamic ontology |
| 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 |
| CN114896387A (en) * | 2022-01-18 | 2022-08-12 | 厦门渊亭信息科技有限公司 | Military intelligence analysis visualization method and device and computer readable storage medium |
| CN115333778A (en) * | 2022-07-15 | 2022-11-11 | 中国地质大学（武汉） | Network attack behavior prediction method based on attack mode |
| CN116383399A (en) * | 2023-03-01 | 2023-07-04 | 武汉大学 | Event public opinion risk prediction method and system |
| CN116485777A (en) * | 2023-05-04 | 2023-07-25 | 广西壮族自治区人民医院 | Medical image interpretability analysis system and analysis method |
-
2023
- 2023-07-27 CN CN202310932586.4A patent/CN116821374A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109643323A (en) * | 2016-07-15 | 2019-04-16 | 谷歌有限责任公司 | Content item is selected using intensified learning |
| CN113326381A (en) * | 2020-02-28 | 2021-08-31 | 拓尔思天行网安信息技术有限责任公司 | Semantic and knowledge graph analysis method, platform and equipment based on dynamic ontology |
| CN112183881A (en) * | 2020-10-19 | 2021-01-05 | 中国人民解放军国防科技大学 | Public opinion event prediction method and device based on social network and storage medium |
| CN113283589A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Updating method and device of event prediction system |
| 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 |
| CN114896387A (en) * | 2022-01-18 | 2022-08-12 | 厦门渊亭信息科技有限公司 | Military intelligence analysis visualization method and device and computer readable storage medium |
| CN115333778A (en) * | 2022-07-15 | 2022-11-11 | 中国地质大学（武汉） | Network attack behavior prediction method based on attack mode |
| CN116383399A (en) * | 2023-03-01 | 2023-07-04 | 武汉大学 | Event public opinion risk prediction method and system |
| CN116485777A (en) * | 2023-05-04 | 2023-07-25 | 广西壮族自治区人民医院 | Medical image interpretability analysis system and analysis method |
Non-Patent Citations (1)
| Title |
|---|
| CHRISTOPHE RODRIGUES 等: "Collaborative decision in multi-agent learning of action models", 《2016 IEEE 28TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE》, 31 December 2016 (2016-12-31), pages 640 - 641 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111581983B (en) | Method for predicting social concern hotspots in online public opinion event based on group analysis | |
| CN110348622B (en) | Temperature prediction method and system based on machine learning and electronic equipment | |
| CN112966714B (en) | Edge time sequence data anomaly detection and network programmable control method | |
| CN113505583B (en) | Emotion reason clause pair extraction method based on semantic decision graph neural network | |
| CN116822803B (en) | Carbon emission data graph construction method, device and equipment based on intelligent algorithm | |
| US20240086731A1 (en) | Knowledge-graph extrapolating method and system based on multi-layer perception | |
| CN117035073B (en) | Future meteorological event prediction method based on hierarchical event development mode induction | |
| CN115168443A (en) | Anomaly detection method and system based on GCN-LSTM and attention mechanism | |
| CN113076545A (en) | Deep learning-based kernel fuzzy test sequence generation method | |
| CN117523418B (en) | Multisource remote sensing image analysis method and system | |
| Zhong et al. | Reduced-order digital twin and latent data assimilation for global wildfire prediction | |
| CN115204171A (en) | Document-level event extraction method and system based on hypergraph neural network | |
| CN117725592A (en) | Intelligent contract vulnerability detection method based on directed graph annotation network | |
| CN117149996A (en) | Man-machine interface digital conversation mining method and AI system for artificial intelligence application | |
| CN110852066A (en) | Multi-language entity relation extraction method and system based on confrontation training mechanism | |
| CN116861373A (en) | Query selectivity estimation method, system, terminal equipment and storage medium | |
| CN116821374A (en) | Event prediction method based on information | |
| CN111638926A (en) | Method for realizing artificial intelligence in Django framework | |
| CN115410642A (en) | Biological relation network information modeling method and system | |
| CN114036319A (en) | Power knowledge extraction method, system, device and storage medium | |
| CN112685314A (en) | JavaScript engine security test method and test system | |
| De Fausti et al. | Multilayer perceptron models for the estimation of the attained level of education in the Italian Permanent Census | |
| Wang | Big Data-Based Analysis and Prediction of International Events | |
| Liu et al. | OD demand forecasting for the large-scale dockless sharing bike system: a deep learning approach | |
| CN116383883B (en) | Big data-based data management authority processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |