CN116701610A - Effective alarm condition identification method and device based on emergency multisource alarm - Google Patents
Effective alarm condition identification method and device based on emergency multisource alarm Download PDFInfo
- Publication number
- CN116701610A CN116701610A CN202310968949.XA CN202310968949A CN116701610A CN 116701610 A CN116701610 A CN 116701610A CN 202310968949 A CN202310968949 A CN 202310968949A CN 116701610 A CN116701610 A CN 116701610A
- Authority
- CN
- China
- Prior art keywords
- alarm
- information
- sequence
- layer
- labels
- 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 47
- 238000012545 processing Methods 0.000 claims abstract description 27
- 239000013598 vector Substances 0.000 claims description 14
- 230000006399 behavior Effects 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
Abstract
The application relates to the technical field of automatic police management, in particular to an effective alarm condition identification method and device based on emergency multisource alarm. According to the technical scheme provided by the embodiment of the application, the alarm information is converted into the text language by constructing the recognition model for information recognition, the key text features in the text language are queried based on the multi-source data, whether the same event occurs in the time period is determined, and the authenticity of the alarm information is determined in a short time based on the occurrence frequency of the event, so that the alarm information is checked and falsified on the premise of not carrying out manual processing, the processing efficiency of the alarm information is improved, and the problem of resource waste caused by false alarm conditions is directly avoided.
Description
Technical Field
The application relates to the technical field of automatic police management, in particular to an effective alarm condition identification method and device based on emergency multisource alarm.
Background
Along with the acceleration of the urban process in China, the intelligent fire-fighting alarm receiving and processing system applies a natural language processing technology to realize key information in alarm information according to alarm receiving and processing data, and the intelligent fire-fighting alarm receiving and processing system is used for adapting and coping with the requirements of 'full disaster variety and large emergency' as soon as possible, and simultaneously is also used for adapting to the alarm receiving and processing requirements in the current informatization and intelligent age, and comprises the following steps: police condition sources (telephone/WeChat/APP/SMS), police condition addresses, police condition types, police condition categories, police condition descriptions, combustion objects, building structures, floor levels, combustion levels, personnel trapped amount, police condition positions, alarm telephones and other elements. And the method is combined with the information retrieval technology, big data and other technologies, so that firefighters can quickly locate useful cases, and the quick response capability and the combat capability of the firefighting department are improved. The emergency management basic capability and level are improved to enhance the urban toughness, and the emergency management method is a great demand for urban safety in a new period.
Moreover, false alarm conditions and actions of exaggerating alarm conditions always occur under actual operation conditions, and the current receiving of alarm conditions is mainly based on manual work, and under the condition of large quantity of alarm conditions, the authenticity of the alarm conditions and the actual conditions of the alarm conditions are difficult to accurately and rapidly acquire in a short time by manual work, so that the alarm condition resource is wasted and abused.
Disclosure of Invention
In order to solve the problems, the application provides the method and the device for identifying the effective alarm condition of the emergency multi-source alarm, which can realize automatic identification of alarm information, and realize the evaluation of the authenticity of the identified alarm condition information in a mode of carrying out secondary verification according to multi-source data, thereby reducing the problems of resource waste and abuse caused by alarm condition errors or exaggeration.
In order to achieve the above purpose, the technical scheme adopted by the embodiment of the application is as follows:
in a first aspect, a method for identifying effective alarm conditions based on emergency multi-source alarm is provided, and is applied to a server, and the method comprises the following steps: acquiring alarm information, inputting the alarm information into a trained recognition model to obtain a text entity information optimal mark sequence, namely recognized text information, wherein corresponding labels are configured in the most marked sequence, and the labels comprise event type labels, behavior labels and position labels; searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the label, determining the overlapping degree of text information in the corresponding label, and determining the true degree of the alarm information based on the overlapping degree.
Further, before the alarm information is input into the trained recognition model, the sequence processing is further carried out on the alarm information, and the alarm information is processed into a sequence text.
Further, the recognition model comprises a preprocessing layer, a neural network processing layer and a decoding layer which are sequentially connected.
Furthermore, the preprocessing layer is used for representing word representation vectors corresponding to words in the sequence text after semantic information in the universal field is fused, the neural network processing layer is used for obtaining semantic codes, and the decoding layer is used for decoding and obtaining text entity information optimal marking sequences according to rationality relations.
Further, the pretreatment layer is an ALBERT structure.
Further, the neural network processing layer comprises a forgetting gate structure, a memory gate structure and an output structure, wherein the forgetting gate structure inputs the state of the hidden layer at the previous moment of the current moment and the current input sequence; the memory gate structure inputs the cell state at the moment before the current moment and outputs the cell state at the current moment; the output structure inputs the word representation vector at the current moment and the state of the unit at the current moment, and outputs the word representation vector at the current moment and the state of the unit at the current moment as a value of an output gate and a current hiding state.
Further, the hidden layer comprises a forward hidden layer and a backward hidden layer, and the forward hidden layer and the backward hidden layer are respectively connected to the same output layer to obtain the spliced word vector.
Further, the decoding layer is a CRF layer, and the CRF layer obtains the optimal marking sequence based on the following formula:； wherein ,/>Representing the slave tag->To tag->Transition probability of->Output for the ith position is +>Is a probability of (2).
Further, X in the formula is an unordered character sequence, namelyY represents the tag sequence of a sentence +.>。
In a second aspect, there is provided an emergency multisource alarm-based effective alarm condition recognition device for performing the method of any one of the above, the device comprising: the text information acquisition module is used for inputting alarm information into the trained recognition model to obtain a text entity information optimal mark sequence, namely recognized text information, wherein corresponding labels are configured in the optimal mark sequence, and the labels comprise event type labels, behavior labels and position labels; and the authenticity identification module is used for searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the tag, determining the coincidence degree of text information in the corresponding tag, and determining the authenticity degree of the alarm information based on the coincidence degree.
In a third aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program which, when executed by a processor, implements the method of any one of the above.
According to the technical scheme provided by the embodiment of the application, the alarm information is converted into the text language by constructing the recognition model for information recognition, the key text features in the text language are queried based on the multi-source data, whether the same event occurs in the time period is determined, and the authenticity of the alarm information is determined in a short time based on the occurrence frequency of the event, so that the alarm information is checked and falsified on the premise of not carrying out manual processing, the processing efficiency of the alarm information is improved, and the problem of resource waste caused by false alarm conditions is directly avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
The methods, systems, and/or programs in the accompanying drawings will be described further in terms of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein the exemplary numbers represent like mechanisms throughout the various views of the drawings.
Fig. 1 is a schematic flow chart of an effective alarm condition recognition method based on emergency multi-source alarm provided by an embodiment of the application.
Fig. 2 is a block diagram of an effective alarm condition recognition device based on emergency multi-source alarm provided by an embodiment of the application.
Fig. 3 is a schematic structural diagram of an effective alarm condition recognition device based on emergency multi-source alarm provided by an embodiment of the application.
Detailed Description
In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present application is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the 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 the technical features of the embodiments and the embodiments of the present application may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. It will be apparent, however, to one skilled in the art that the application can be practiced without these details. In other instances, well known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.
The present application uses a flowchart to illustrate the execution of a system according to an embodiment of the present application. It should be clearly understood that the execution of the flowcharts may be performed out of order. Rather, these implementations may be performed in reverse order or concurrently. Additionally, at least one other execution may be added to the flowchart. One or more of the executions may be deleted from the flowchart.
Before describing embodiments of the present application in further detail, the terms and terminology involved in the embodiments of the present application will be described, and the terms and terminology involved in the embodiments of the present application will be used in the following explanation.
(1) In response to a condition or state that is used to represent the condition or state upon which the performed operation depends, the performed operation or operations may be in real-time or with a set delay when the condition or state upon which it depends is satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
(2) Based on the conditions or states that are used to represent the operations that are being performed, one or more of the operations that are being performed may be in real-time or with a set delay when the conditions or states that are being relied upon are satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
The application scene of the embodiment of the application is that text information of the alarm call is identified in the alarm information receiving process, and searching is carried out in the area and time domain through the identified key characteristic information, so that the alarm receiving personnel is assisted in determining the information authenticity. It should be noted that the technical solution disclosed in the embodiment of the present application is mainly aimed at providing the alarm personnel with an estimate of the authenticity of the information, but cannot be directly used as a final estimate. In other embodiments, the technical scheme provided by the embodiment of the application can be combined with a knowledge graph or an expert system to add a query mechanism, namely, the corresponding query questions are set according to the estimated authenticity to assist the alarm receiving personnel to quickly give questions to the alarm personnel, and the answers of the questions are identified secondarily and checked pseudo in real time, so that the authenticity of the information reported by the alarm personnel is finally determined. It is noted that in the process of question query, the computing system performs recognition of answers to questions and simultaneously performs synchronous reconfirmation of the initial alarm information in parallel, because the reason for alarm hysteresis can cause hysteresis of data acquired by multiple paths in a certain period of time.
Therefore, the technical scheme provided by the embodiment of the application is used as an auxiliary scheme for assisting the alarm receiving personnel in judging the authenticity of the alarm information.
In order to solve the problems in the prior art, the embodiment of the application provides an emergency alert acceptance information identification method, which specifically comprises the following steps:
s110, acquiring alarm information, and inputting the alarm information into the trained recognition model to obtain an optimal marking sequence of the text entity information, namely the recognized text information.
In the embodiment of the application, corresponding labels are configured in the optimal marking sequence, wherein the labels are event features used for representing the optimal marking sequence. Wherein the tags include event type tags, behavior tags, and location tags. The event type labels are labels for specifying specific event types, such as ignition, leakage, collapse, rescue and the like. The behavior labels are labels for explaining specific behaviors to be processed in the event of floor fire, forest fire, gas leakage, natural gas leakage and the like. The position label is a specific geographic information label and is used for explaining the occurrence place of the event and the behavior.
The recognition model is used for assisting the police to collect and sort complex text information, and can be independently configured, namely unmanned automation is realized.
Specifically, for the recognition model which is a trained model, processing logic of the model is to sort text information into sequences, rationally associate words in the sequences to obtain a final recognized sequence, and convert the sequence into text information to be output. Therefore, the received alarm information needs to be converted into the text information before being converted into the sequence, and the alarm information needs to be converted into the voice information because the alarm information is received by an alarm person through telephone or other voice modes, the process is not the protection object of the embodiment of the application, the voice recognition scheme in the prior scheme can be adopted for conversion, the prior voice recognition model is adopted for processing, and the accumulation is not carried out.
The text information acquired by the voice recognition needs to be converted into the sequence text, and the specific scheme can be performed by adopting the existing scheme without detailed description.
The recognition model provided by the embodiment of the application is a preprocessing layer, a neural network processing layer and a decoding layer which are sequentially connected. The method comprises the steps of obtaining a word representation vector representation of a word corresponding to a word in a sequence text after semantic information in a general field is fused, wherein the word representation vector representation is used for a preprocessing layer, the neural network processing layer is used for obtaining semantic codes, and the decoding layer is used for decoding and obtaining a text entity information optimal marking sequence according to a rationality relation.
The method is characterized in that an ALBERT structure is adopted for a preprocessing layer, and N-gram is adopted to mask text data, wherein the N-gram is a probability-based discriminant language model in the field of natural language processing, so that the association between texts is realized.
The processing layer comprises a forgetting gate structure, a memory gate structure and an output structure, wherein the forgetting gate structure inputs the state of the hidden layer at the previous moment and the current input sequence; the memory gate structure inputs the cell state at the moment before the current moment and outputs the cell state at the current moment; the output structure inputs the word representation vector at the current moment and the state of the unit at the current moment, and outputs the word representation vector at the current moment and the state of the unit at the current moment as a value of an output gate and a current hiding state. The word vector comprises a front hidden layer and a rear hidden layer, wherein the front hidden layer and the rear hidden layer are respectively connected to the same output layer, so that a spliced word vector is obtained.
The decoding layer is a CRF layer, and the CRF layer obtains an optimal marking sequence based on the following formula:
；
wherein ,representing the slave tag->To tag->Transition probability of->Output for the ith position is +>X is the probability of unordered character sequence +.>Y represents the tag sequence of a sentence +.>. Wherein the score calculation formula for all possible tag sequences y is:
, wherein />Representing the set of all possible sequence observations for the input sequence X, +.>Representing the actual true mark value.
Through the step, the text information obtained by recognition after the alarm information can be obtained, and the text information is basic data for subsequent alarm condition recognition.
And S120, searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the label, determining the superposition degree of text information in the corresponding label, and determining the true degree of the alarm information based on the superposition degree.
In the embodiment of the present application, the processing of the optimal tag sequences for the plurality of alarm information is performed by the scheme provided in step S110, that is, the plurality of alarm information is processed by the identification model in step S110 to obtain a plurality of optimal tag sequences, and tags are configured in the plurality of optimal tag sequences, where the tags are event type tags, behavior tags, and location tags in the optimal tag sequences.
And extracting a plurality of text messages corresponding to the same label in the plurality of optimal label sequences, and comparing the plurality of text messages to determine the coincidence degree.
In the embodiment of the application, the text information is compared based on the optimal mark sequence, at least two optimal mark sequences to be compared are traversed, the repeated word pairs are found, namely, for the first optimal mark sequence and the second optimal mark sequence to be compared, any adjacent words in the two optimal mark sequences are sequentially selected and the positions of the adjacent words are interchanged, finally, the adjacent words are combined into a single word form, namely, mutual matching is performed, the adjacent words between the two optimal mark sequences form phrases and are matched with each other continuously until the matching of the last two phrases of the two sequences is finished, and the completely matched phrases in the matching process are selected as the repeated word pairs.
In another embodiment of the present application, a scheme for overlap ratio may adopt different tag alignment schemes, and firstly, words in two optimal tag sequences with position tags are aligned, and when the alignment results are different, no alignment is required for the words of other tags. When the comparison result is the same result, comparing the words corresponding to the event type labels to determine whether the words are the same, if the words are the same, comparing the behavior labels, if the words are different, not performing specific mismatching, storing the two optimal mark sequences as independent text information, and sending the independent text information to a manual end for manual verification.
In the embodiment of the application, the normalization processing is performed on the words corresponding to the position labels in the two schemes, wherein the normalization processing is performed by searching the words corresponding to the position labels in the alarm information in the geographic database according to the words corresponding to the position labels, so as to obtain the standard geographic information.
Therefore, in another embodiment of the present application, the first comparison of the location tag is based on the standard geographic information, so that the comparison efficiency is improved. The geographic database in the embodiment of the application is constructed according to the building and road names corresponding to the specific geographic coordinate points, namely subdirectories of the building and the road names are arranged in the specific geographic coordinate points, and the standard geographic information is determined by comparing the sub-catalogs of the words based on the acquisition of the standard geographic information to determine the geographic coordinate points corresponding to the subdirectories. Or, the standard geographic information is acquired through voice rule setting in the process of acquiring the alarm information, and the process is not described in detail in the embodiment of the application.
And setting the coincidence degree based on label comparison, and when the words corresponding to the position labels and the words corresponding to the event type labels are identical through judgment, recognizing that the coincidence degree of the alarm information is 100% as effective information.
And when the words corresponding to the position tags are the same, the coincidence degree of the event type tag corresponding words and the behavior tag corresponding words in different periods is 50%, and the information is determined to be confirmed.
And when the words corresponding to the position coordinates are different, the overlap ratio is 0, and the secondary screening is manually performed.
Referring to fig. 2, an apparatus 200 for identifying an effective alarm condition based on emergency multi-source alarm is provided, including:
the text information obtaining module 210 is configured to input the alarm information to the trained recognition model to obtain the text entity information optimal tag sequence, i.e. the recognized text information.
The authenticity identifying module 220 searches a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the tag, determines the coincidence degree of text information in the corresponding tag, and determines the authenticity degree of the alarm information based on the coincidence degree.
Referring to fig. 3, the emergency multi-source alert enabled alert condition recognition apparatus 300 may include one or more processors 301 and memory 302, where the memory 302 may store one or more stored applications or data, which may vary widely depending on configuration or performance. Wherein the memory 302 may be transient storage or persistent storage. The application program stored in memory 302 may include one or more modules (not shown in the figures) each of which may include a series of computer-executable instructions for identifying an active alarm condition based on an emergency multi-source alarm. Still further, the processor 401 may be configured to communicate with the memory 302 to execute a series of computer executable instructions in the memory 302 on the emergency multi-source alert enabled alert condition recognition device. The emergency multi-source based alert enabled alert condition recognition device may also include one or more power sources 303, one or more wired or wireless network interfaces 304, one or more input/output interfaces 305, one or more keyboards 306, and the like.
In one particular embodiment, an emergency multi-source alarm-based active alarm condition identification device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the emergency multi-source alarm-based active alarm condition identification device, and configured to be executed by one or more processors, the one or more programs comprising computer-executable instructions for:
acquiring alarm information, and inputting the alarm information into a trained recognition model to obtain an optimal marking sequence of the text entity information, namely recognized text information;
searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the label, determining the overlapping degree of text information in the corresponding label, and determining the true degree of the alarm information based on the overlapping degree.
The following describes each component of the processor in detail:
wherein in this embodiment the processor is a specific integrated circuit (application specific integrated circuit, ASIC), or one or more integrated circuits configured to implement embodiments of the present application, such as: one or more microprocessors (digital signal processor, DSPs), or one or more field programmable gate arrays (field programmable gate array, FPGAs).
Alternatively, the processor may perform various functions, such as performing the method shown in fig. 1 described above, by running or executing a software program stored in memory, and invoking data stored in memory.
In a particular implementation, the processor may include one or more microprocessors, as one embodiment.
The memory is configured to store a software program for executing the scheme of the present application, and the processor is used to control the execution of the software program, and the specific implementation manner may refer to the above method embodiment, which is not described herein again.
Alternatively, the memory may be read-only memory (ROM) or other type of static storage device that can store static information and instructions, random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, but may also be, without limitation, electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), compact disc read-only memory (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be integrated with the processor or may exist separately and be coupled to the processing unit through an interface circuit of the processor, which is not particularly limited by the embodiment of the present application.
It should be noted that the structure of the processor shown in this embodiment is not limited to the apparatus, and an actual apparatus may include more or less components than those shown in the drawings, or may combine some components, or may be different in arrangement of components.
In addition, the technical effects of the processor may refer to the technical effects of the method described in the foregoing method embodiments, which are not described herein.
It should be appreciated that the processor in embodiments of the application may be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example but not limitation, many forms of random access memory (random access memory, RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An effective alarm condition identification method based on emergency multisource alarm is characterized by being applied to a server, and comprises the following steps:
acquiring alarm information, and inputting the alarm information into a trained recognition model to obtain a text entity information optimal mark sequence, namely recognized text information, wherein corresponding labels are configured in the optimal mark sequence, and the labels comprise event type labels, behavior labels and position labels;
searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the label, determining the overlapping degree of text information in the corresponding label, and determining the true degree of the alarm information based on the overlapping degree.
2. The method for identifying effective alarm conditions based on emergency multi-source alarm according to claim 1, wherein the step of inputting the alarm information into the trained identification model is preceded by the step of performing sequence processing on the alarm information and processing the alarm information into sequence text.
3. The method for identifying the effective alarm condition based on the emergency multi-source alarm according to claim 2, wherein the identification model comprises a preprocessing layer, a neural network processing layer and a decoding layer which are sequentially connected.
4. The method for identifying effective warning conditions based on emergency multi-source warning according to claim 3, wherein the preprocessing layer is used for representing word representation vectors after semantic information in a general field is fused corresponding to words in a sequence text, the neural network processing layer is used for obtaining semantic codes, and the decoding layer is used for decoding and obtaining text entity information optimal marking sequences according to rationality relations.
5. The method for identifying effective alarm conditions based on emergency multi-source alarm according to claim 4, wherein the preprocessing layer is an ALBERT structure.
6. The method for identifying the effective alarm condition based on the emergency multi-source alarm according to claim 5, wherein the neural network processing layer comprises a forgetting gate structure, a memory gate structure and an output structure, wherein the forgetting gate structure inputs the state of a hidden layer at the moment before the moment and the current input sequence; the memory gate structure inputs the cell state at the moment before the current moment and outputs the cell state at the current moment; the output structure inputs the word representation vector at the current moment and the state of the unit at the current moment, and outputs the word representation vector at the current moment and the state of the unit at the current moment as a value of an output gate and a current hiding state.
7. The method for identifying effective warning conditions based on emergency multi-source warning according to claim 6, wherein the hidden layers comprise a forward hidden layer and a backward hidden layer, and the forward hidden layer and the backward hidden layer are respectively connected to the same output layer to obtain the spliced word vector.
8. The method for identifying the effective alarm condition based on the emergency multi-source alarm according to claim 7, wherein the decoding layer is a CRF layer, and the CRF layer obtains the optimal marking sequence based on the following formula:
；
wherein ,representing the slave tag->To tag->Transition probability of->Output for the ith position is +>Where X is a disordered character sequence and y represents a tag sequence of a sentence.
9. The method for identifying effective alarm condition based on emergency multi-source alarm according to claim 8, wherein X in the formula is a disordered character sequence, namelyY represents the tag sequence of a sentence +.>。
10. An effective alarm condition recognition device based on emergency multi-source alarm, which is used for executing the method of any one of claims 1-9, and comprises:
the text information acquisition module is used for inputting alarm information into the trained recognition model to obtain a text entity information optimal mark sequence, namely recognized text information, wherein corresponding labels are configured in the optimal mark sequence, and the labels comprise event type labels, behavior labels and position labels;
and the authenticity identification module is used for searching a plurality of optimal mark sequences in a plurality of alarm information processed in a preset time period based on the tag, determining the coincidence degree of text information in the corresponding tag, and determining the authenticity degree of the alarm information based on the coincidence degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310968949.XA CN116701610A (en) | 2023-08-03 | 2023-08-03 | Effective alarm condition identification method and device based on emergency multisource alarm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310968949.XA CN116701610A (en) | 2023-08-03 | 2023-08-03 | Effective alarm condition identification method and device based on emergency multisource alarm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116701610A true CN116701610A (en) | 2023-09-05 |
Family
ID=87832478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310968949.XA Pending CN116701610A (en) | 2023-08-03 | 2023-08-03 | Effective alarm condition identification method and device based on emergency multisource alarm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116701610A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117238294A (en) * | 2023-11-13 | 2023-12-15 | 成都大成均图科技有限公司 | Automatic local fire control voice recognition method and device based on artificial intelligence |
| CN117251493A (en) * | 2023-11-14 | 2023-12-19 | 成都大成均图科技有限公司 | Multi-source comprehensive positioning method and device based on police map |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104764979A (en) * | 2015-03-30 | 2015-07-08 | 国网河南省电力公司经济技术研究院 | Virtual information fusion power grid alarming method based on probabilistic reasoning |
| CN108010289A (en) * | 2017-12-28 | 2018-05-08 | 深圳市永达电子信息股份有限公司 | A kind of internet alarm method and system based on Application on Voiceprint Recognition |
| CN108074381A (en) * | 2016-11-10 | 2018-05-25 | 杭州海康威视系统技术有限公司 | Alarm method, apparatus and system |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微系统与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| CN109410509A (en) * | 2018-10-25 | 2019-03-01 | 华翔翔能电气股份有限公司 | Subregion alarm method, terminal and the storage medium of fire-fighting link net broadcast system |
| CN110298043A (en) * | 2019-07-03 | 2019-10-01 | 吉林大学 | A kind of vehicle name entity recognition method and system |
| CN111429889A (en) * | 2019-01-08 | 2020-07-17 | 百度在线网络技术（北京）有限公司 | Method, apparatus, device and computer readable storage medium for real-time speech recognition based on truncated attention |
| CN113222433A (en) * | 2021-05-21 | 2021-08-06 | 马鑫海 | Enterprise safety intelligent management system |
| CN113938649A (en) * | 2021-09-24 | 2022-01-14 | 成都智元汇信息技术股份有限公司 | Alarm message duplicate removal method and device |
| CN114726589A (en) * | 2022-03-17 | 2022-07-08 | 南京科技职业学院 | Alarm data fusion method |
| CN115758908A (en) * | 2022-11-29 | 2023-03-07 | 中国地质大学（武汉） | Alarm online prediction method under alarm flooding condition based on deep learning |
| CN115909692A (en) * | 2022-10-25 | 2023-04-04 | 长威信息科技发展股份有限公司 | Management method, platform, equipment and medium for expressway alarm event |
-
2023
- 2023-08-03 CN CN202310968949.XA patent/CN116701610A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104764979A (en) * | 2015-03-30 | 2015-07-08 | 国网河南省电力公司经济技术研究院 | Virtual information fusion power grid alarming method based on probabilistic reasoning |
| CN108074381A (en) * | 2016-11-10 | 2018-05-25 | 杭州海康威视系统技术有限公司 | Alarm method, apparatus and system |
| CN108010289A (en) * | 2017-12-28 | 2018-05-08 | 深圳市永达电子信息股份有限公司 | A kind of internet alarm method and system based on Application on Voiceprint Recognition |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微系统与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| CN109410509A (en) * | 2018-10-25 | 2019-03-01 | 华翔翔能电气股份有限公司 | Subregion alarm method, terminal and the storage medium of fire-fighting link net broadcast system |
| CN111429889A (en) * | 2019-01-08 | 2020-07-17 | 百度在线网络技术（北京）有限公司 | Method, apparatus, device and computer readable storage medium for real-time speech recognition based on truncated attention |
| CN110298043A (en) * | 2019-07-03 | 2019-10-01 | 吉林大学 | A kind of vehicle name entity recognition method and system |
| CN113222433A (en) * | 2021-05-21 | 2021-08-06 | 马鑫海 | Enterprise safety intelligent management system |
| CN113938649A (en) * | 2021-09-24 | 2022-01-14 | 成都智元汇信息技术股份有限公司 | Alarm message duplicate removal method and device |
| CN114726589A (en) * | 2022-03-17 | 2022-07-08 | 南京科技职业学院 | Alarm data fusion method |
| CN115909692A (en) * | 2022-10-25 | 2023-04-04 | 长威信息科技发展股份有限公司 | Management method, platform, equipment and medium for expressway alarm event |
| CN115758908A (en) * | 2022-11-29 | 2023-03-07 | 中国地质大学（武汉） | Alarm online prediction method under alarm flooding condition based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 陈娜等: "结合注意力机制BERT-BiGRU-CRF 中文电子病历命名实体识别", 小型微型计算机系统, pages 1 - 10 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117238294A (en) * | 2023-11-13 | 2023-12-15 | 成都大成均图科技有限公司 | Automatic local fire control voice recognition method and device based on artificial intelligence |
| CN117251493A (en) * | 2023-11-14 | 2023-12-19 | 成都大成均图科技有限公司 | Multi-source comprehensive positioning method and device based on police map |
| CN117251493B (en) * | 2023-11-14 | 2024-02-02 | 成都大成均图科技有限公司 | Multi-source comprehensive positioning method and device based on police map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021004333A1 (en) | Knowledge graph-based event processing method and apparatus, device, and storage medium | |
| CN116701610A (en) | Effective alarm condition identification method and device based on emergency multisource alarm | |
| CN108170859B (en) | Voice query method, device, storage medium and terminal equipment | |
| CN112632230B (en) | Event joint extraction method and device based on multi-level graph network | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN115203440B (en) | Event map construction method and device for time-space dynamic data and electronic equipment | |
| CN107679035A (en) | A kind of information intent detection method, device, equipment and storage medium | |
| CN111460783B (en) | Data processing method and device, computer equipment and storage medium | |
| CN115221332A (en) | Construction method and system of dangerous chemical accident event map | |
| CN110851608A (en) | Infringement detection method, device and equipment based on block chain and storage medium | |
| CN113779190B (en) | Event causal relationship identification method, device, electronic equipment and storage medium | |
| Madani et al. | Fake news detection using deep learning integrating feature extraction, natural language processing, and statistical descriptors | |
| WO2014047309A2 (en) | Method and system for creating and managing a verified online profile | |
| CN112069324A (en) | Classified label adding method, device, equipment and storage medium | |
| US20210051123A1 (en) | Systems and methods for automatically identifying spam in social media comments | |
| CN111209750A (en) | Internet of vehicles threat intelligence modeling method, device and readable storage medium | |
| Shiri et al. | Toward the automated construction of probabilistic knowledge graphs for the maritime domain | |
| CN115563296A (en) | Fusion detection method and system based on content semantics | |
| CN116722992A (en) | Fraud website identification method and device based on multi-mode fusion | |
| CN115883218A (en) | Composite attack chain completion method, system and medium based on multi-mode data model | |
| Johnson et al. | Extraction of expanded entity phrases | |
| CN117251493B (en) | Multi-source comprehensive positioning method and device based on police map | |
| CN113468307A (en) | Text processing method and device, electronic equipment and storage medium | |
| EP4075320A1 (en) | A method and device for improving the efficiency of pattern recognition in natural language | |
| US11870933B2 (en) | Emergency dispatch command information management system, device, and method capable of providing relevant emergency dispatch command information |
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 |