CN110532292A - Alert string and method, apparatus, equipment and storage medium - Google Patents
Alert string and method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN110532292A CN110532292A CN201910767708.2A CN201910767708A CN110532292A CN 110532292 A CN110532292 A CN 110532292A CN 201910767708 A CN201910767708 A CN 201910767708A CN 110532292 A CN110532292 A CN 110532292A
- Authority
- CN
- China
- Prior art keywords
- alert
- characteristic information
- information
- important feature
- current
- 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 59
- 238000004590 computer program Methods 0.000 claims description 28
- 230000002123 temporal effect Effects 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 7
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 14
- 210000000056 organ Anatomy 0.000 description 16
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012216 screening Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 210000004218 nerve net Anatomy 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
- G06F16/24554—Unary operations; Data partitioning operations
- G06F16/24556—Aggregation; Duplicate elimination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of alert string and method, apparatus, equipment and storage mediums, belong to field of computer technology.The described method includes: obtaining the corresponding characteristic information set of current alert, this feature information aggregate includes at least one characteristic information, and each this feature information is used to indicate the alert feature of corresponding alert;Obtain pending string and the corresponding characteristic information set of target histories alert, and obtain according to the corresponding characteristic information set of current alert characteristic information set corresponding with the target histories alert similarity of the current alert and the target histories alert;When the similarity is greater than or equal to default similarity threshold, the current alert and the target histories alert are gone here and there simultaneously.Technical solution provided by the embodiments of the present application can solve the problems, such as policeman's wasting of resources to a certain extent.
Description
Technical field
This application involves field of computer technology, and more particularly to a kind of alert string and method, apparatus, equipment and storage are situated between
Matter.
Background technique
In practical application, when there is alert, the people associated with the alert often selects to alarm, wherein
What so-called alert referred to be handled by public security organ is related to the event broken laws and commit crime or endangered public security, for example,
Alert can be the event of fighting, event of fire and swindle event etc., and the people associated with alert refers to
Witness or victim etc..
Under normal conditions, after receiving people's alarm, public security organ can send policeman's responding to handle related police
Feelings.However, in many cases, for same alert, public security organ may receive the alarm of multiple people, example
Such as, for the event of fighting, witness may have multidigit, and multidigit witness may select alarm, meanwhile, it fights
The victim having a fist fight may also select to alarm.After public security organ receives alarm of multiple people for same alert,
If it is for same alert, then public security organ may can send multiple groups that public security organ, which can not tell multiple alarm,
Policeman goes to handle the same alert, this will cause the waste of policeman's resource.
In the related technology, public security organ can identify the alarm call of alarm personnel, when recognizing not homogeneous report
When alert alarm personnel's phone is identical, public security organ can determine that the corresponding alert of homogeneous alarm is not same alert for this, then,
Public security organ can the corresponding alert of homogeneous alarm not be gone here and there simultaneously to this.
However, the relevant technologies provide alert string and method can go here and there simultaneously alert it is very limited, can not efficiently solve
The problem of policeman's wasting of resources.
Summary of the invention
Based on this, it is necessary to aiming at the problem that simultaneously method can not efficiently solve policeman's wasting of resources to existing alert string, mention
For a kind of alert string and method, apparatus, equipment and storage medium.
In a first aspect, a kind of alert string and method are provided, this method comprises:
The corresponding characteristic information set of current alert is obtained, this feature information aggregate includes at least one characteristic information, respectively
This feature information is used to indicate the alert feature of corresponding alert;Obtain the corresponding feature of target histories alert of pending string simultaneously
Information aggregate, and according to the corresponding characteristic information set of current alert characteristic information set corresponding with the target histories alert
Obtain the similarity of the current alert and the target histories alert;When the similarity is greater than or equal to default similarity threshold,
The current alert and the target histories alert are gone here and there simultaneously.
The corresponding characteristic information set of current alert is obtained in one of the embodiments, comprising:
The alert information for obtaining the current alert carries out feature extraction to the alert information of the current alert, obtains at least
One characteristic information, the alert information of the current alert include the description content to the current alert;According to this, at least one is special
Reference ceases to obtain the corresponding characteristic information set of the current alert.
This feature information aggregate includes alert property information in one of the embodiments, obtains the mesh of pending string simultaneously
Mark the corresponding characteristic information set of history alert, comprising:
According to the alert property information query history alert database of the current alert, which is obtained by inquiry
The corresponding characteristic information set of alert;Wherein, the alert of the alert property information of the target histories alert and the current alert
Matter information matches, and the corresponding characteristic information set of at least one history alert is stored in the history alert database.
In one of the embodiments, according to the current corresponding characteristic information set of alert and the target histories alert pair
The characteristic information set answered obtains the similarity of the current alert and the target histories alert, comprising:
Each characteristic information in the corresponding characteristic information set of the current alert is input to important feature identification nerve net
In network, the probabilistic information of important feature identification neural network output is obtained, which is used to indicate the current alert pair
Each characteristic information is the probability of important characteristic information in the characteristic information set answered;According to the probabilistic information from the current alert pair
Important feature information is obtained in the characteristic information set answered, and obtains the corresponding important feature information aggregate of the current alert;According to
Important feature information aggregate characteristic information set corresponding with the target histories alert obtains the current alert and the target is gone through
The similarity of history alert.
Believed in one of the embodiments, according to important feature information aggregate feature corresponding with the target histories alert
Breath set obtains the similarity of the current alert and the target histories alert, comprising:
From in the corresponding characteristic information set of the target histories alert obtain with respectively this is heavy in the important feature information aggregate
Want the corresponding characteristic information of characteristic information institute;For each important feature information in the important feature information aggregate, obtain
Similarity between important feature information characteristic information corresponding with the important feature;According to the respectively important feature information and respectively
Similarity between the corresponding characteristic information of the important feature, obtains the similarity of the current alert and the target histories alert.
It is obtained between important feature information characteristic information corresponding with the important feature in one of the embodiments,
Similarity, comprising:
When the important feature information be temporal information, and, characteristic information corresponding with the important feature is also temporal information
When, obtain the time difference information between the important feature information and characteristic information corresponding with the important feature;According to the time
Poor information obtains the similarity between important feature information characteristic information corresponding with the important feature.
It is obtained between important feature information characteristic information corresponding with the important feature in one of the embodiments,
Similarity, comprising:
When the important feature information is geographical location information, and, characteristic information corresponding with the important feature is also geographical
When location information, the distance between the important feature information and characteristic information corresponding with the important feature information are obtained;According to
The range information obtains the similarity between important feature information characteristic information corresponding with the important feature.
It is obtained between important feature information characteristic information corresponding with the important feature in one of the embodiments,
Similarity, comprising:
Obtain the corresponding text vector of the important feature information and characteristic information corresponding with important feature institute;Meter
Calculate between the text vector of the text vector sum characteristic information corresponding with the important feature of the important feature information to span
From;According to the vector distance, the similarity between important feature information characteristic information corresponding with the important feature is obtained.
This method in one of the embodiments, further include: when the similarity is less than default similarity threshold, forbid pair
The current alert and the target histories alert are gone here and there simultaneously.
Second aspect provides a kind of alert string and device, which is characterized in that the device includes:
First obtains module, and for obtaining the corresponding characteristic information set of current alert, this feature information aggregate includes extremely
A few characteristic information, each this feature information are used to indicate the alert feature of corresponding alert;
Second obtains module, for obtaining the corresponding characteristic information set of target histories alert of pending string simultaneously, and root
The current police is obtained according to the corresponding characteristic information set of current alert characteristic information set corresponding with the target histories alert
The similarity of feelings and the target histories alert;
String and module are used for when the similarity is greater than or equal to default similarity threshold, to the current alert and the mesh
Mark history alert is gone here and there simultaneously.
The first acquisition module in one of the embodiments, is specifically used for:
The alert information for obtaining the current alert carries out feature extraction to the alert information of the current alert, obtains at least
One characteristic information, the alert information of the current alert include the description content to the current alert;According to this, at least one is special
Reference ceases to obtain the corresponding characteristic information set of the current alert.
This feature information aggregate includes alert property information in one of the embodiments, the second acquisition module, specifically
For:
According to the alert property information query history alert database of the current alert, which is obtained by inquiry
The corresponding characteristic information set of alert;Wherein, the alert of the alert property information of the target histories alert and the current alert
Matter information matches, and the corresponding characteristic information set of at least one history alert is stored in the history alert database.
The second acquisition module in one of the embodiments, is specifically used for:
Each characteristic information in the corresponding characteristic information set of the current alert is input to important feature identification nerve net
In network, the probabilistic information of important feature identification neural network output is obtained, which is used to indicate the current alert pair
Each characteristic information is the probability of important characteristic information in the characteristic information set answered;According to the probabilistic information from the current alert pair
Important feature information is obtained in the characteristic information set answered, and obtains the corresponding important feature information aggregate of the current alert;According to
Important feature information aggregate characteristic information set corresponding with the target histories alert obtains the current alert and the target is gone through
The similarity of history alert.
The second acquisition module in one of the embodiments, is specifically used for:
From in the corresponding characteristic information set of the target histories alert obtain with respectively this is heavy in the important feature information aggregate
Want the corresponding characteristic information of characteristic information institute;For each important feature information in the important feature information aggregate, obtain
Similarity between important feature information characteristic information corresponding with the important feature;According to the respectively important feature information and respectively
Similarity between the corresponding characteristic information of the important feature, obtains the similarity of the current alert and the target histories alert.
The second acquisition module in one of the embodiments, is specifically used for:
When the important feature information be temporal information, and, characteristic information corresponding with the important feature is also temporal information
When, obtain the time difference information between the important feature information and characteristic information corresponding with the important feature;According to the time
Poor information obtains the similarity between important feature information characteristic information corresponding with the important feature.
The second acquisition module in one of the embodiments, is specifically used for:
When the important feature information is geographical location information, and, characteristic information corresponding with the important feature is also geographical
When location information, the distance between the important feature information and characteristic information corresponding with the important feature information are obtained;According to
The range information obtains the similarity between important feature information characteristic information corresponding with the important feature.
The second acquisition module in one of the embodiments, is specifically used for:
Obtain the corresponding text vector of the important feature information and characteristic information corresponding with important feature institute;Meter
Calculate between the text vector of the text vector sum characteristic information corresponding with the important feature of the important feature information to span
From;According to the vector distance, the similarity between important feature information characteristic information corresponding with the important feature is obtained.
The device can also include disabled module in one of the embodiments,;
Wherein, the disabled module, for when the similarity is less than default similarity threshold, forbidding to the current alert and
The target histories alert is gone here and there simultaneously.
The third aspect, provides a kind of computer equipment, including memory and processor, which is stored with computer
Program, the computer program realize any alert string of above-mentioned first aspect and method when being executed by the processor.
Fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, which is located
Reason device realizes any alert string of above-mentioned first aspect and method when executing.
Technical solution bring beneficial effect provided by the embodiments of the present application includes at least:
It is corresponding by obtaining the target histories alert of the corresponding characteristic information set of current alert and pending string simultaneously
Characteristic information set, according to the corresponding characteristic information set of the current alert and the corresponding characteristic information collection of target histories alert
The similarity for obtaining current alert and target histories alert is closed, then, is greater than or equal to default similarity threshold in the similarity
When, current alert and target histories alert are gone here and there simultaneously, due to alert string provided by the embodiments of the present application and method being capable of root
Determine whether to go here and there alert according to the similarity of alert simultaneously, therefore, can be gone here and there simultaneously compared to being expanded for the relevant technologies
Alert range, the problem of policeman's wasting of resources can be efficiently solved to a certain extent.
Detailed description of the invention
Fig. 1 is the schematic diagram of implementation environment involved by a kind of alert string provided by the embodiments of the present application and method;
Fig. 2 is the flow chart of a kind of alert string provided by the embodiments of the present application and method;
Fig. 3 is the flow chart of another alert string provided by the embodiments of the present application and method;
Fig. 4 is the flow chart of another alert string provided by the embodiments of the present application and method;
Fig. 5 is the flow chart of another alert string provided by the embodiments of the present application and method;
Fig. 6 is the block diagram of a kind of alert string provided by the embodiments of the present application and device;
Fig. 7 is the block diagram of a kind of alert string provided by the embodiments of the present application and device;
Fig. 8 is a kind of block diagram of computer equipment provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
In order to avoid the waste of policeman's resource, it is necessary to alarm corresponding alert in not homogeneous as same alert for public security organ
When, to this, the corresponding alert of homogeneous alarm is not gone here and there simultaneously.
In the related technology, public security organ can go here and there simultaneously alert according to the alarm call of alarm personnel, specifically, if
When the alarm call of the alarm personnel of homogeneous alarm is identical, public security organ can to this not homogeneous alarm corresponding alert into
Row string is simultaneously.
It is gone here and there simultaneously however, the relevant technologies are only capable of the corresponding alert of not homogeneous alarm to Same Alarm personnel, and can not
The corresponding alert of not homogeneous alarm of different alarm personnel is gone here and there simultaneously, therefore, the alert simultaneously that can go here and there is very limited, nothing
Method efficiently solves the problem of policeman's wasting of resources.
The embodiment of the present application provides a kind of alert string and method, can effectively solve policeman's resource wave to a certain extent
The problem of taking.In the alert string and in method, the corresponding characteristic information set of the available current alert of server and into
Row string and the corresponding characteristic information set of target histories alert, and according to the corresponding characteristic information set of the current alert and
The corresponding characteristic information set of target histories alert obtains the similarity of current alert and target histories alert, then, server
Can when the similarity is greater than or equal to default similarity threshold, to current alert and target histories alert gone here and there simultaneously, by
In alert string provided by the embodiments of the present application, simultaneously method can determine whether to go here and there simultaneously alert according to the similarity of alert,
Therefore, simultaneously method can not only be to the corresponding police of the not homogeneous of Same Alarm personnel alarm for alert string provided by the embodiments of the present application
Feelings are gone here and there simultaneously, and the corresponding alert that can alarm the not homogeneous of different alarm personnel is gone here and there simultaneously, so, compared to phase
Expanded for the technology of pass can go here and there and alert range, policeman's wasting of resources can be efficiently solved to a certain extent
Problem.
In the following, by being carried out briefly to implementation environment involved by alert string provided by the embodiments of the present application and method
It is bright.
Fig. 1 is a kind of schematic diagram of implementation environment provided by the embodiments of the present application.As shown in Figure 1, the implementation environment can be with
Including server 101 and at least one terminal 102 (illustrating only a terminal 102 in Fig. 1), wherein server 101 and terminal
It can be communicated by wired or wireless mode between 102.
Terminal 102 can be the corresponding terminal of the personnel that receive a crime report of public security organ, and the personnel that receive a crime report are receiving alarm personnel's
After alarm, the corresponding alert of the alarm can be input in terminal 102 in the form of text or image etc., by terminal 102
The alert is sent to server 101.Server 101 can use the application after the alert for receiving the transmission of terminal 102
The alert string and method that embodiment provides go here and there simultaneously the alert and history alert.
Referring to FIG. 2, it illustrates a kind of alert string provided by the embodiments of the present application and the flow chart of method, the alert string
And method can be applied in server 101 shown in FIG. 1.As shown in Fig. 2, simultaneously method may include following step to the alert string
It is rapid:
Step 201, server obtain the corresponding characteristic information set of current alert.
Wherein, so-called " current alert " refer to need with history alert go here and there and alert, for example, the current alert
It can be the newest alert that server receives, alternatively, the current alert can be one section of server before current time
The alert received in the preset time.
The corresponding characteristic information set of a certain alert may include at least one characteristic information, wherein this feature information collection
Each characteristic information that conjunction includes is used to indicate the alert feature of the alert.Then according to the above description, current alert is corresponding
Characteristic information set may include at least one characteristic information, wherein each characteristic information that this feature information aggregate includes
It is used to indicate the alert feature of the current alert.
Optionally, " characteristic information " in the embodiment of the present application may include temporal information, geographical location information, personage/
Company's information, alert property information and alert attribute information etc., wherein alert property information is used to indicate alert property, example
Such as, alert property can be fire, swindle or theft etc., and alert attribute information is used to indicate alert attribute, for example, alert category
Property can for loss the amount of money or object on fire etc..
Step 202, server obtain the corresponding characteristic information set of target histories alert of pending string simultaneously.
According to the above description, the corresponding characteristic information set of target histories alert may include at least one feature letter
Breath, wherein each characteristic information that this feature information aggregate includes is used to indicate the alert feature of the target histories alert.
In practical application, can go here and there and the alert property of alert must be identical, for example, alert property is all fire
Alert is possible to be gone here and there simultaneously, and alert property is fire and alert property is that two alerts swindled obviously can not
Therefore string can not be can be carried out simultaneously for same alert.
In view of above situation, in one embodiment of the application, it is alert from history that server can use alert property
In feelings preliminary screening obtain may with current alert string and target histories alert, and determined whether really using subsequent technology process
It is real to need to go here and there simultaneously the current alert and target histories alert.By preliminary screening, subsequent technology mistake can be greatly reduced
The calculation amount of server in journey.
Optionally, history alert database can have been safeguarded in server, be stored at least in the history alert database
The corresponding characteristic information set of one history alert, wherein so-called history alert refers to depositing before current alert here
Enter the alert in server.Optionally, server can be according to the alert property in the corresponding characteristic information set of current alert
Information query history alert database obtains the corresponding characteristic information set of target histories alert by inquiry, wherein target is gone through
The alert property information of alert property information and current alert in the corresponding characteristic information set of history alert matches.Generically
For, server preliminary screening can obtain alert property phase of the alert property with current alert from history alert database
The history alert matched, and the history alert screened is determined as the target histories alert of pending string simultaneously.
In addition, the difference between the time for the alert generation that can be gone here and there simultaneously is usually not too large, for example, working as in practical application
Preceding alert can be to occur in ten two points of noon of fire alert on January 5, obviously can not be with generation in morning three January 4
The fire alert of point is gone here and there simultaneously.
In view of above situation, in one embodiment of the application, server can simultaneously using alert property and
Alert occur time difference from history alert preliminary screening obtain may with current alert string and target histories alert, thus
The calculation amount of server during reduction subsequent technology.
As described above, history alert database can have been safeguarded in server, be stored in the history alert database
The corresponding characteristic information set of at least one history alert.Optionally, server can be believed according to the corresponding feature of current alert
Alert property information and temporal information query history alert database in breath set, obtain target histories alert by inquiry
Corresponding characteristic information set, wherein alert property information in the corresponding characteristic information set of target histories alert and current
The alert property information of alert matches, and, the difference for the time that the time and current alert that target histories alert occurs occur
Less than or equal to the poor threshold value of alert time of origin.For generically, server can from history alert database preliminary screening
It obtains alert property and the alert property of current alert matches, and, the time difference that alert occurs is less than or equal to alert
The history alert of time difference threshold value, and the history alert screened is determined as the target histories alert of pending string simultaneously.
It should be pointed out that the different corresponding alert time of origin difference threshold values of alert property can be different, for example, fire
The corresponding alert time of origin difference threshold value of this alert property can be 2 hours, swindle the corresponding alert hair of this alert property
Raw time difference threshold value can be 30 days.
By the way that different alert time of origin difference threshold values is arranged to different alert properties, so that the screening of target histories alert
It is more accurate, in this way, can not only reduce the calculation amount of server during subsequent technology, subsequent technology process can also be improved
The accuracy of middle similarity calculation.
Step 203, server are according to the corresponding characteristic information set of current alert and the corresponding feature of target histories alert
Information aggregate obtains the similarity of current alert and target histories alert.
Wherein, the similarity of current alert and target histories alert is used to indicate the phase of current alert and target histories alert
Like degree.
Step 204, when the similarity of current alert and target histories alert is greater than or equal to default similarity threshold, clothes
Business device goes here and there simultaneously current alert and target histories alert.
It if the similarity of current alert and target histories alert is larger, that is to say, be greater than or equal to default similarity threshold,
Server can go here and there simultaneously current alert and target histories alert, and optionally, server can be by current alert and target
History alert is sent to the corresponding terminal of the personnel that receive a crime report of public security organ, to be confirmed whether pair by the personnel of receiving a crime report of the public security organ
Current alert and target histories alert are gone here and there simultaneously.
Optionally, it if the similarity of current alert and target histories alert is smaller, that is to say, be less than default similarity threshold
Value, server can be forbidden going here and there simultaneously current alert and target histories alert.
In alert string provided by the embodiments of the present application and method, by obtaining the corresponding characteristic information set of current alert
And pending string and the corresponding characteristic information set of target histories alert, according to the corresponding characteristic information collection of the current alert
Conjunction and the corresponding characteristic information set of target histories alert obtain the similarity of current alert and target histories alert, then,
When the similarity is greater than or equal to default similarity threshold, current alert and target histories alert are gone here and there simultaneously, due to this
Application embodiment provide alert string and method can be determined whether to go here and there alert according to the similarity of alert simultaneously, because
This, compared to expanded for the relevant technologies can go here and there and alert range, police can be efficiently solved to a certain extent
The problem of member's wasting of resources.
Referring to FIG. 3, server can execute step as steps described below on the basis of embodiment described above
201 technical process:
Step 2011, server obtain the alert information of current alert, and carry out feature to the alert information of current alert
It extracts, obtains at least one characteristic information.
Wherein, the alert information of the current alert includes the description content to current alert, optionally, to current alert
Description content may include the descriptive text to current alert, for example, the description content to current alert can be " January 5
At unity South Road and scientific and technological road interface port collective's fighting incident occurs for 12 noon ".The alert information of the current alert can be with
It is that the corresponding terminal of the personnel that receive a crime report of public security organ is sent to server.
Server can extract after getting the alert information of current alert from the alert information of the current alert
Effective field and data are cleaned out, to obtain the alert information after data cleansing, then, server can use Entity recognition
Algorithm extracts at least one characteristic information from the alert information after the data cleansing.
Step 2012, server obtain the corresponding characteristic information collection of current alert according at least one above-mentioned characteristic information
It closes.
Feature extraction is carried out in the alert information to current alert, after obtaining at least one characteristic information, server can
At least one characteristic information is combined into the corresponding characteristic information set of current alert.Optionally, current alert is being obtained
After corresponding characteristic information set, server can be stored the corresponding characteristic information set of the current alert to described above
History alert database in.
Referring to FIG. 4, server can execute step as steps described below on the basis of embodiment described above
203 technical process:
Each characteristic information in the corresponding characteristic information set of current alert is input to important spy by step 2031, server
In sign identification neural network, the probabilistic information of important feature identification neural network output is obtained.
Wherein, it is corresponding to be used to indicate current alert for the probabilistic information probabilistic information of important feature identification neural network output
Each characteristic information is the probability of important characteristic information in characteristic information set.
In practical application, the certain characteristic informations for including in the corresponding characteristic information set of current alert may be than heavier
It wants, and other characteristic information may be so-called here " important " to refer to when calculating similarity so unimportant
Percentage contribution is larger.In other words, " the important feature information " in the embodiment of the present application refers to the contribution when calculating similarity
More characteristic information.Such as: the alert property of current alert is that network swindles property, corresponding characteristic information set
Including characteristic information have " XX investment platform " " loss 2000 yuan ", wherein " XX investment platform " is contributed when calculating similarity
Degree is larger, and " loss 2000 yuan " when calculating similarity, percentage contribution is smaller, therefore, " XX investment platform " is important feature
Information.
Since percentage contribution is larger when calculating similarity for important feature information, from the corresponding feature of current alert
Important feature information is extracted in information aggregate, and calculates similarity using the important feature information, and similarity meter can be improved
The accuracy of calculation.In order to extract important feature information from the corresponding characteristic information set of current alert, implement in the application
In example, each characteristic information in the corresponding characteristic information set of current alert can be input to important feature identification mind by server
Through in network, so that obtain important feature identification neural network output is used to indicate the corresponding characteristic information set of current alert
In each characteristic information be important characteristic information probability probabilistic information.
Step 2032, server identify that the probabilistic information of neural network output is corresponding from current alert according to important feature
Important feature information is obtained in characteristic information set, obtains the corresponding important feature information aggregate of current alert.
Server probability indicated by acquisition probability information can be greater than from current alert corresponding characteristic information set
The characteristic information of predetermined probabilities threshold value, and the characteristic information that will acquire is determined as important feature information, then, server can be with
The corresponding important feature information aggregate of current alert is formed using determining important feature information.
Step 2033, server are obtained according to important feature information aggregate and the corresponding characteristic information set of target histories alert
Take the similarity of current alert and target histories alert.
Referring to FIG. 5, server can execute step as steps described below on the basis of embodiment described above
2033 technical process:
Step 20331, server obtain and important feature information from the corresponding characteristic information set of target histories alert
The corresponding characteristic information of each important feature information institute in set.
Wherein, spy identical with the type of important feature information is referred to characteristic information corresponding to important feature information
Reference breath.For example, server can be from the corresponding characteristic information of target histories alert if important feature information is temporal information
Acquisition time information in set, the temporal information of acquisition are characteristic information corresponding with important feature information, in another example, if
Important feature information is geographical location information, then server can be obtained from the corresponding characteristic information set of target histories alert
Geographical location information, the geographical location information of acquisition are characteristic information corresponding with important feature information.
Step 20332, for each important feature information in important feature information aggregate, server obtains the important feature
Similarity between information characteristic information corresponding with the important feature.
In other words, in step 20332, the corresponding feature letter of the available each important feature information of server
Similarity between breath.
In the following, the embodiment of the present application obtains important feature letter to server for according to the different type of important feature information
The several ways for ceasing the similarity between corresponding characteristic information are briefly described.
The first, when important feature information be temporal information, and, characteristic information corresponding with the important feature is also the time
Time difference letter when information, between the available important feature information of server and characteristic information corresponding with the important feature
Breath, then, server can obtain important feature information feature letter corresponding with the important feature according to the time difference information
Similarity between breath.
Second, when the important feature information be geographical location information, and, characteristic information corresponding with the important feature
When for geographical location information, between the available important feature information of server and characteristic information corresponding with the important feature
Range information, then, server can information according to this distance, it is corresponding with the important feature to obtain the important feature information
Similarity between characteristic information.
The third, server obtain important feature information and characteristic information corresponding with the important feature institute it is corresponding
Text vector, then, server calculate the text vector sum characteristic information corresponding with the important feature of the important feature information
Text vector between vector distance, then, it is important with this to obtain the important feature information according to the vector distance for server
Similarity between the corresponding characteristic information of feature.
Step 20333, server are according to the phase between each important feature information characteristic information corresponding with each important feature
Like degree, the similarity of current alert and target histories alert is obtained.
Referring to FIG. 6, it illustrates a kind of alert string provided by the embodiments of the present application and the block diagram of device 600, the alert
It goes here and there and device 600 can be configured in server described above.As shown in fig. 6, simultaneously device 600 may include: the alert string
First, which obtains module 601, second, obtains module 602 and string and module 603.
The first acquisition module 601, for obtaining the corresponding characteristic information set of current alert, this feature information aggregate packet
At least one characteristic information is included, each this feature information is used to indicate the alert feature of corresponding alert.
The second acquisition module 602, for obtaining the corresponding characteristic information set of target histories alert of pending string simultaneously,
And deserved according to the characteristic information set acquisition corresponding with the target histories alert of the corresponding characteristic information set of the current alert
The similarity of preceding alert and the target histories alert.
The string and module 603, for when the similarity is greater than or equal to default similarity threshold, to the current alert and
The target histories alert is gone here and there simultaneously.
In one embodiment of the application, which is specifically used for: obtaining the police of the current alert
Feelings information carries out feature extraction to the alert information of the current alert, obtains at least one characteristic information, the police of the current alert
Feelings information includes the description content to the current alert;The corresponding spy of the current alert is obtained according at least one characteristic information
Levy information aggregate.
In one embodiment of the application, this feature information aggregate includes alert property information, the second acquisition module
602, it is specifically used for: according to the alert property information query history alert database of the current alert, which is obtained by inquiry
Mark the corresponding characteristic information set of history alert;Wherein, the alert property information of the target histories alert and the current alert
Alert property information matches, and the corresponding characteristic information collection of at least one history alert is stored in the history alert database
It closes.
In one embodiment of the application, which is specifically used for: the current alert is corresponding
Each characteristic information in characteristic information set is input in important feature identification neural network, obtains important feature identification nerve
The probabilistic information of network output, the probabilistic information are used to indicate each characteristic information in the corresponding characteristic information set of the current alert
For the probability of important characteristic information;Important spy is obtained from the corresponding characteristic information set of the current alert according to the probabilistic information
Reference breath obtains the corresponding important feature information aggregate of the current alert;It is gone through according to the important feature information aggregate and the target
The corresponding characteristic information set of history alert obtains the similarity of the current alert and the target histories alert.
In one embodiment of the application, which is specifically used for: from the target histories alert pair
It is obtained in the characteristic information set answered and each corresponding feature of important feature information institute in the important feature information aggregate
Information;For each important feature information in the important feature information aggregate, the important feature information and the important feature are obtained
Similarity between corresponding characteristic information;According to respectively important feature information characteristic information corresponding with the respectively important feature it
Between similarity, obtain the similarity of the current alert and the target histories alert.
In one embodiment of the application, which is specifically used for: when the important feature information is
Temporal information, and, when characteristic information corresponding with the important feature is also temporal information, obtain the important feature information and with this
Time difference information between the corresponding characteristic information of important feature;According to the time difference information, obtain the important feature information with
Similarity between the corresponding characteristic information of the important feature.
In one embodiment of the application, which is specifically used for: when the important feature information is
Geographical location information, and, when characteristic information corresponding with the important feature is also geographical location information, obtain important feature letter
The distance between breath and characteristic information corresponding with the important feature information;Information according to this distance obtains important feature letter
Cease the similarity between characteristic information corresponding with the important feature.
In one embodiment of the application, which is specifically used for: obtaining the important feature information
Text vector corresponding with characteristic information institute corresponding with the important feature;Calculate the text vector of the important feature information
Vector distance between the text vector of characteristic information corresponding with the important feature;According to the vector distance, it is heavy to obtain this
Want the similarity between characteristic information characteristic information corresponding with the important feature.
Referring to FIG. 7, the embodiment of the present application also provides another alert string and device 700, the alert string and device
700 other than including alert string each module that simultaneously device 600 includes, and optionally, simultaneously device 700 can also include prohibiting to the alert string
Only module 604.
Wherein, disabled module 604, for forbidding to deserving when the similarity is less than the default similarity threshold
Preceding alert and the target histories alert are gone here and there simultaneously.
Alert string provided by the embodiments of the present application and device, may be implemented above method embodiment, realization principle and skill
Art effect is similar, and details are not described herein.
About alert string and the specific of device limits the restriction that may refer to above for alert string and method, herein not
It repeats again.Modules in above-mentioned alert string and device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment of the application, a kind of computer equipment is provided, internal structure chart can be such as Fig. 8 institute
Show.The computer equipment includes the processor and memory connected by system bus.Wherein, the processor of the computer equipment
For providing calculating and control ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.This is non-
Volatile storage medium is stored with operating system and computer program.The built-in storage is the operation in non-volatile memory medium
The operation of system and computer program provides environment.To realize a kind of alert string and square when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment of the application, a kind of computer equipment is provided, which can be server,
The computer equipment includes memory and processor, is stored with computer program in memory, which executes computer journey
It is performed the steps of when sequence
The corresponding characteristic information set of current alert is obtained, this feature information aggregate includes at least one characteristic information, respectively
This feature information is used to indicate the alert feature of corresponding alert;Obtain the corresponding feature of target histories alert of pending string simultaneously
Information aggregate, and according to the corresponding characteristic information set of current alert characteristic information set corresponding with the target histories alert
Obtain the similarity of the current alert and the target histories alert;When the similarity is greater than or equal to default similarity threshold,
The current alert and the target histories alert are gone here and there simultaneously.
In one embodiment of the application, processor, which also performs the steps of acquisition when executing computer program, to deserve
The alert information of preceding alert carries out feature extraction to the alert information of the current alert, obtains at least one characteristic information, deserve
The alert information of preceding alert includes the description content to the current alert;The current police is obtained according at least one characteristic information
The corresponding characteristic information set of feelings.
This feature information aggregate includes alert property information, and in one embodiment of the application, processor executes calculating
The alert property information query history alert database according to the current alert is also performed the steps of when machine program, by looking into
Inquiry obtains the corresponding characteristic information set of the target histories alert;Wherein, the alert property information of the target histories alert with should
The alert property information of current alert matches, and is stored with the corresponding spy of at least one history alert in the history alert database
Levy information aggregate.
In one embodiment of the application, processor also performs the steps of this is current when executing computer program
Each characteristic information in the corresponding characteristic information set of alert is input in important feature identification neural network, obtains the important spy
The probabilistic information of sign identification neural network output, the probabilistic information are used to indicate in the corresponding characteristic information set of the current alert
Each characteristic information is the probability of important characteristic information;According to the probabilistic information from the corresponding characteristic information set of the current alert
Important feature information is obtained, the corresponding important feature information aggregate of the current alert is obtained;According to the important feature information aggregate
Characteristic information set corresponding with the target histories alert obtains the similarity of the current alert and the target histories alert.
In one embodiment of the application, processor is also performed the steps of when executing computer program from the target
It is obtained in the corresponding characteristic information set of history alert and each important feature information institute difference in the important feature information aggregate
Corresponding characteristic information;For each important feature information in the important feature information aggregate, obtain the important feature information with
Similarity between the corresponding characteristic information of the important feature;It is corresponding with the respectively important feature according to the respectively important feature information
Similarity between characteristic information obtains the similarity of the current alert and the target histories alert.
In one embodiment of the application, processor is also performed the steps of when executing computer program when this is important
Characteristic information is temporal information, and, when characteristic information corresponding with the important feature is also temporal information, obtain the important feature
Time difference information between information and characteristic information corresponding with the important feature;According to the time difference information, it is important to obtain this
Similarity between characteristic information characteristic information corresponding with the important feature.
In one embodiment of the application, processor is also performed the steps of when executing computer program when this is important
Characteristic information is geographical location information, and, when characteristic information corresponding with the important feature is also geographical location information, obtaining should
The distance between important feature information and characteristic information corresponding with the important feature information;Information according to this distance, obtaining should
Similarity between important feature information characteristic information corresponding with the important feature.
In one embodiment of the application, processor also performs the steps of acquisition when executing computer program this is heavy
Want the corresponding text vector of characteristic information and characteristic information corresponding with important feature institute;Calculate the important feature information
Text vector sum characteristic information corresponding with the important feature text vector between vector distance;According to this to span
From obtaining the similarity between important feature information characteristic information corresponding with the important feature.
In one embodiment of the application, processor is also performed the steps of when executing computer program when this is similar
When degree is less than default similarity threshold, forbid going here and there simultaneously the current alert and the target histories alert.
Computer equipment provided by the embodiments of the present application, implementing principle and technical effect and above method embodiment class
Seemingly, details are not described herein.
In one embodiment of the application, a kind of computer readable storage medium is provided, computer is stored thereon with
Program performs the steps of when computer program is executed by processor
The corresponding characteristic information set of current alert is obtained, this feature information aggregate includes at least one characteristic information, respectively
This feature information is used to indicate the alert feature of corresponding alert;Obtain the corresponding feature of target histories alert of pending string simultaneously
Information aggregate, and according to the corresponding characteristic information set of current alert characteristic information set corresponding with the target histories alert
Obtain the similarity of the current alert and the target histories alert;When the similarity is greater than or equal to default similarity threshold,
The current alert and the target histories alert are gone here and there simultaneously.
Also performing the steps of acquisition in one embodiment of the application, when computer program is executed by processor should
The alert information of current alert carries out feature extraction to the alert information of the current alert, obtains at least one characteristic information, should
The alert information of current alert includes the description content to the current alert;It is current that this is obtained according at least one characteristic information
The corresponding characteristic information set of alert.
This feature information aggregate includes alert property information, and in one embodiment of the application, computer program is located
Reason device also performs the steps of the alert property information query history alert database according to the current alert when executing, pass through
Inquiry obtains the corresponding characteristic information set of the target histories alert;Wherein, the alert property information of the target histories alert with
The alert property information of the current alert matches, and it is corresponding to be stored at least one history alert in the history alert database
Characteristic information set.
In one embodiment of the application, also performing the steps of when computer program is executed by processor will deserve
Each characteristic information in the corresponding characteristic information set of preceding alert is input in important feature identification neural network, and it is important to obtain this
Feature identifies that the probabilistic information of neural network output, the probabilistic information are used to indicate the corresponding characteristic information set of the current alert
In each characteristic information be important characteristic information probability;According to the probabilistic information from the corresponding characteristic information set of the current alert
Middle acquisition important feature information obtains the corresponding important feature information aggregate of the current alert;According to the important feature information collection
Close the similarity that characteristic information set corresponding with the target histories alert obtains the current alert and the target histories alert.
It also performs the steps of when computer program is executed by processor in one of the embodiments, and is gone through from the target
Obtained in the corresponding characteristic information set of history alert in the important feature information aggregate respectively important feature information it is right respectively
The characteristic information answered;For each important feature information in the important feature information aggregate, obtain the important feature information with should
Similarity between the corresponding characteristic information of important feature;According to respectively important feature information spy corresponding with the respectively important feature
Similarity between reference breath, obtains the similarity of the current alert and the target histories alert.
It is also performed the steps of in one embodiment of the application, when computer program is executed by processor when this is heavy
Wanting characteristic information is temporal information, and, when characteristic information corresponding with the important feature is also temporal information, obtain the important spy
Time difference information between reference breath and characteristic information corresponding with the important feature;According to the time difference information, it is heavy to obtain this
Want the similarity between characteristic information characteristic information corresponding with the important feature.
It is also performed the steps of in one embodiment of the application, when computer program is executed by processor when this is heavy
Wanting characteristic information is geographical location information, and, when characteristic information corresponding with the important feature is also geographical location information, obtain
The distance between the important feature information and characteristic information corresponding with the important feature information;Information according to this distance obtains
Similarity between important feature information characteristic information corresponding with the important feature.
Also performing the steps of acquisition in one embodiment of the application, when computer program is executed by processor should
The corresponding text vector of important feature information and characteristic information corresponding with important feature institute;Calculate important feature letter
Vector distance between the text vector of the text vector sum of breath characteristic information corresponding with the important feature;According to this to span
From obtaining the similarity between important feature information characteristic information corresponding with the important feature.
In one embodiment of the application, also perform the steps of when computer program is executed by processor when the phase
When being less than default similarity threshold like degree, forbid going here and there simultaneously the current alert and the target histories alert.
Computer readable storage medium provided in this embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
The limitation to claim therefore cannot be interpreted as.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (12)
1. a kind of alert string and method, which is characterized in that the described method includes:
The corresponding characteristic information set of current alert is obtained, the characteristic information set includes at least one characteristic information, each institute
State the alert feature that characteristic information is used to indicate corresponding alert;
Obtain pending string and the corresponding characteristic information set of target histories alert, and according to the corresponding spy of the current alert
It levies information aggregate and the corresponding characteristic information set of the target histories alert obtains the current alert and the target histories
The similarity of alert;
When the similarity is greater than or equal to default similarity threshold, to the current alert and the target histories alert into
Row string is simultaneously.
2. the method according to claim 1, wherein described obtain the corresponding characteristic information set of current alert,
Include:
The alert information for obtaining the current alert carries out feature extraction to the alert information of the current alert, obtains at least
One characteristic information, the alert information of the current alert include the description content to the current alert;
The corresponding characteristic information set of the current alert is obtained according at least one described characteristic information.
3. the method according to claim 1, wherein the characteristic information set includes alert property information, institute
It states and obtains the corresponding characteristic information set of target histories alert of pending string simultaneously, comprising:
According to the alert property information query history alert database of the current alert, the target histories are obtained by inquiry
The corresponding characteristic information set of alert;
Wherein, the alert property information of the target histories alert and the alert property information of the current alert match, institute
It states and is stored with the corresponding characteristic information set of at least one history alert in history alert database.
4. the method according to claim 1, wherein described according to the corresponding characteristic information collection of the current alert
Close the phase that characteristic information set corresponding with the target histories alert obtains the current alert and the target histories alert
Like degree, comprising:
Each characteristic information in the corresponding characteristic information set of the current alert is input to important feature identification neural network
In, the probabilistic information of the important feature identification neural network output is obtained, the probabilistic information is used to indicate the current police
Each characteristic information is the probability of important characteristic information in the corresponding characteristic information set of feelings;
Important feature information is obtained from the corresponding characteristic information set of the current alert according to the probabilistic information, obtains institute
State the corresponding important feature information aggregate of current alert;
It is obtained according to the important feature information aggregate and the corresponding characteristic information set of the target histories alert described current
The similarity of alert and the target histories alert.
5. according to the method described in claim 4, it is characterized in that, described according to the important feature information aggregate and the mesh
The corresponding characteristic information set of mark history alert obtains the similarity of the current alert and the target histories alert, comprising:
It is each described from acquisition in the corresponding characteristic information set of the target histories alert and the important feature information aggregate
The corresponding characteristic information of important feature information institute;
For the important feature information each in the important feature information aggregate, obtain the important feature information with it is described heavy
Want the similarity between the corresponding characteristic information of feature;
According to the similarity between each important feature information characteristic information corresponding with each important feature, described in acquisition
The similarity of current alert and the target histories alert.
6. according to the method described in claim 5, it is characterized in that, described obtain the important feature information and the important spy
Levy the similarity between corresponding characteristic information, comprising:
When the important feature information be temporal information, and, characteristic information corresponding with the important feature is also temporal information
When, obtain the time difference information between the important feature information and characteristic information corresponding with the important feature;
According to the time difference information, obtain between important feature information characteristic information corresponding with the important feature
Similarity.
7. according to the method described in claim 5, it is characterized in that, described obtain the important feature information and the important spy
Levy the similarity between corresponding characteristic information, comprising:
When the important feature information is geographical location information, and, characteristic information corresponding with the important feature is also geographical
When location information, the distance between the important feature information and characteristic information corresponding with the important feature information are obtained;
According to the range information, the phase between important feature information characteristic information corresponding with the important feature is obtained
Like degree.
8. according to the method described in claim 5, it is characterized in that, described obtain the important feature information and the important spy
Levy the similarity between corresponding characteristic information, comprising:
Obtain the corresponding text vector of the important feature information and characteristic information corresponding with important feature institute;
Calculate the text vector sum characteristic information corresponding with the important feature of the important feature information text vector it
Between vector distance;
According to the vector distance, the phase between important feature information characteristic information corresponding with the important feature is obtained
Like degree.
9. method according to any one of claims 1 to 8, which is characterized in that the method also includes:
When the similarity is less than the default similarity threshold, forbid to the current alert and the target histories alert
It is gone here and there simultaneously.
10. a kind of alert string and device, which is characterized in that described device includes:
First obtains module, and for obtaining the corresponding characteristic information set of current alert, the characteristic information set includes at least
One characteristic information, each characteristic information are used to indicate the alert feature of corresponding alert;
Second obtains module, for obtaining the corresponding characteristic information set of target histories alert of pending string simultaneously, and according to institute
It states the corresponding characteristic information set of current alert and the corresponding characteristic information set acquisition of the target histories alert is described current
The similarity of alert and the target histories alert;
It goes here and there and module, for when the similarity is greater than or equal to default similarity threshold, to the current alert and described
Target histories alert is gone here and there simultaneously.
11. a kind of computer equipment, which is characterized in that including memory and processor, the memory is stored with computer journey
Sequence, which is characterized in that the computer program realizes police as described in any one of claim 1 to 9 when being executed by the processor
Feelings string and method.
12. a kind of computer readable storage medium, which is characterized in that be stored thereon with computer program, which is characterized in that the journey
Alert string as described in any one of claim 1 to 9 and method are realized when sequence is executed by processor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910767708.2A CN110532292A (en) | 2019-08-20 | 2019-08-20 | Alert string and method, apparatus, equipment and storage medium |
PCT/CN2020/076986 WO2021031547A1 (en) | 2019-08-20 | 2020-02-27 | Police situation combining method and apparatus, device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910767708.2A CN110532292A (en) | 2019-08-20 | 2019-08-20 | Alert string and method, apparatus, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110532292A true CN110532292A (en) | 2019-12-03 |
Family
ID=68663700
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910767708.2A Pending CN110532292A (en) | 2019-08-20 | 2019-08-20 | Alert string and method, apparatus, equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110532292A (en) |
WO (1) | WO2021031547A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111291150A (en) * | 2020-03-09 | 2020-06-16 | 北京明略软件系统有限公司 | Method and device for determining information to be searched and readable storage medium |
CN111311908A (en) * | 2020-02-18 | 2020-06-19 | 青岛海信网络科技股份有限公司 | Method and device for identifying and processing repeated traffic information |
CN111382779A (en) * | 2019-12-31 | 2020-07-07 | 清华大学 | Alarm condition similarity recognition method, device and equipment |
WO2021031547A1 (en) * | 2019-08-20 | 2021-02-25 | 深圳追一科技有限公司 | Police situation combining method and apparatus, device, and storage medium |
CN112860844A (en) * | 2021-01-13 | 2021-05-28 | 广东省公安厅 | Case clue processing system, method and device and computer equipment |
CN115525803A (en) * | 2022-09-16 | 2022-12-27 | 深圳市海邻科信息技术有限公司 | Alarm handling method, alarm handling system, vehicle-mounted equipment and computer readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010108233A (en) * | 2008-10-30 | 2010-05-13 | Panasonic Corp | Non-detector notification device, non-detector notification system and non-detector notification method |
CN106095967A (en) * | 2016-06-17 | 2016-11-09 | 武汉烽火众智数字技术有限责任公司 | A kind of repetition of alarms recognition methods based on search engine and system |
CN106338975A (en) * | 2016-09-21 | 2017-01-18 | 浙江中控技术股份有限公司 | Alarm merging method and alarm merging system |
CN110008362A (en) * | 2019-03-05 | 2019-07-12 | 青岛海信网络科技股份有限公司 | A kind of case classifying method and device |
CN110019374A (en) * | 2019-03-26 | 2019-07-16 | 杭州数梦工场科技有限公司 | Data item processing method, device, storage medium and computer equipment based on feature |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107908742A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN109165243A (en) * | 2018-08-15 | 2019-01-08 | 武汉烽火众智数字技术有限责任公司 | Similar case recommender system and its method based on the customized rule of combining related cases of user |
CN110532292A (en) * | 2019-08-20 | 2019-12-03 | 深圳追一科技有限公司 | Alert string and method, apparatus, equipment and storage medium |
-
2019
- 2019-08-20 CN CN201910767708.2A patent/CN110532292A/en active Pending
-
2020
- 2020-02-27 WO PCT/CN2020/076986 patent/WO2021031547A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010108233A (en) * | 2008-10-30 | 2010-05-13 | Panasonic Corp | Non-detector notification device, non-detector notification system and non-detector notification method |
CN106095967A (en) * | 2016-06-17 | 2016-11-09 | 武汉烽火众智数字技术有限责任公司 | A kind of repetition of alarms recognition methods based on search engine and system |
CN106338975A (en) * | 2016-09-21 | 2017-01-18 | 浙江中控技术股份有限公司 | Alarm merging method and alarm merging system |
CN110008362A (en) * | 2019-03-05 | 2019-07-12 | 青岛海信网络科技股份有限公司 | A kind of case classifying method and device |
CN110019374A (en) * | 2019-03-26 | 2019-07-16 | 杭州数梦工场科技有限公司 | Data item processing method, device, storage medium and computer equipment based on feature |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021031547A1 (en) * | 2019-08-20 | 2021-02-25 | 深圳追一科技有限公司 | Police situation combining method and apparatus, device, and storage medium |
CN111382779A (en) * | 2019-12-31 | 2020-07-07 | 清华大学 | Alarm condition similarity recognition method, device and equipment |
WO2021136455A1 (en) * | 2019-12-31 | 2021-07-08 | 清华大学 | Method and apparatus for recognizing police emergency similarity, and device |
CN111382779B (en) * | 2019-12-31 | 2024-04-30 | 清华大学 | Police condition similarity recognition method, device and equipment |
CN111311908A (en) * | 2020-02-18 | 2020-06-19 | 青岛海信网络科技股份有限公司 | Method and device for identifying and processing repeated traffic information |
CN111291150A (en) * | 2020-03-09 | 2020-06-16 | 北京明略软件系统有限公司 | Method and device for determining information to be searched and readable storage medium |
CN111291150B (en) * | 2020-03-09 | 2023-08-25 | 北京明智和术科技有限公司 | Method and device for determining information to be searched and readable storage medium |
CN112860844A (en) * | 2021-01-13 | 2021-05-28 | 广东省公安厅 | Case clue processing system, method and device and computer equipment |
CN115525803A (en) * | 2022-09-16 | 2022-12-27 | 深圳市海邻科信息技术有限公司 | Alarm handling method, alarm handling system, vehicle-mounted equipment and computer readable storage medium |
CN115525803B (en) * | 2022-09-16 | 2024-02-23 | 深圳市海邻科信息技术有限公司 | Alarm processing method, system, vehicle-mounted equipment and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2021031547A1 (en) | 2021-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110532292A (en) | Alert string and method, apparatus, equipment and storage medium | |
CN113094758B (en) | Gradient disturbance-based federated learning data privacy protection method and system | |
US10438308B2 (en) | Systems and methods for identifying entities using geographical and social mapping | |
CN111860147B (en) | Pedestrian re-identification model optimization processing method and device and computer equipment | |
US7458508B1 (en) | System and method for identity-based fraud detection | |
US9412141B2 (en) | Systems and methods for identifying entities using geographical and social mapping | |
CN108876133A (en) | Risk assessment processing method, device, server and medium based on business information | |
CN109829776A (en) | Trade company's methods of risk assessment, device, computer equipment and storage medium | |
CN111369342A (en) | Loan approval method, device, equipment and storage medium based on machine learning | |
WO2022095434A1 (en) | Auto-encoder-based data anomaly identification method and apparatus and computer device | |
WO2014150987A1 (en) | Systems and methods for identifying entites using geographical and social mapping | |
CN113240505B (en) | Method, apparatus, device, storage medium and program product for processing graph data | |
CN111860865B (en) | Model construction and analysis method, device, electronic equipment and medium | |
CN109063984B (en) | Method, apparatus, computer device and storage medium for risky travelers | |
CN106909821A (en) | The control method of terminal, device and terminal device | |
CN108449514A (en) | Information processing method and device | |
CN110717758B (en) | Abnormal transaction identification method and device | |
CN110135943A (en) | Products Show method, apparatus, computer equipment and storage medium | |
CN110046548A (en) | Tracking, device, computer equipment and the readable storage medium storing program for executing of face | |
CN111885181B (en) | Monitoring data reporting method and device, computer equipment and storage medium | |
CN116205726B (en) | Loan risk prediction method and device, electronic equipment and storage medium | |
CN116881967A (en) | Privacy protection method, device and equipment | |
CN111178339A (en) | User identity identification method, device, equipment and medium | |
CN108460811B (en) | Face image processing method and device and computer equipment | |
CN109471852A (en) | Medical data base method for building up, device, computer equipment and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |