CN110543914A - Event data processing method and device, computing equipment and medium - Google Patents
Event data processing method and device, computing equipment and medium Download PDFInfo
- Publication number
- CN110543914A CN110543914A CN201910832430.2A CN201910832430A CN110543914A CN 110543914 A CN110543914 A CN 110543914A CN 201910832430 A CN201910832430 A CN 201910832430A CN 110543914 A CN110543914 A CN 110543914A
- Authority
- CN
- China
- Prior art keywords
- label
- event
- event data
- combined
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
the embodiment of the invention discloses a method, a device, computing equipment and a medium for processing event data. The method comprises the following steps: acquiring each event data; performing content identification on each event data to match one or more tags for the event data; for each combined label, counting the covering quantity of the combined label covering events according to the label of the event data; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more; and determining a characteristic combined label according to the event coverage quantity aiming at each combined label with the same preset label quantity, wherein the characteristic combined label is used for determining an event coping strategy. According to the technical scheme of the embodiment of the invention, the effect of effectively distinguishing the events by extracting the event characteristics in a labeling mode is achieved.
Description
Technical Field
The embodiment of the invention relates to a computer application technology, in particular to a method, a device, computing equipment and a medium for processing event data.
Background
The smart city is a high-level form of city informatization following a digital city and an intelligent city, and is a deep fusion of informatization, industrialization and urbanization. The smart city can change the living mode of residents and the urban production mode, and can ensure the sustainable development of the city, so that the development of the smart city is an important measure for improving the urbanization quality and relieving the current increasingly serious large urban diseases.
In the process of building a smart city, many city management problems such as fighting events, traffic jam events, fire events, theft events and the like can be exposed, and a decision maker needs to make reasonable judgment on the problems exposed in the city management process and provide reasonable solution measures.
Only by the decision maker himself/herself, it is difficult to make a comprehensive and correct judgment on the event and to provide the most effective and reasonable solution, so that there is a need for an event data processing method that can analyze the essence of the event occurrence, thereby giving a reasonable suggestion, helping the decision maker to provide the correct solution for the event itself, and thereby more accurately and effectively processing various urban events.
disclosure of Invention
the embodiment of the invention provides a method, a device, a computing device and a medium for processing event data, which are used for effectively processing the event data and accurately distinguishing events.
In a first aspect, an embodiment of the present invention provides a method for processing event data, where the method for processing event data includes:
Acquiring each event data;
Performing content identification on each event data to match one or more tags with the event data;
for each combined label, counting the covering quantity of the combined label covering events according to the label of the event data; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more;
and determining a characteristic combined label according to the event coverage quantity aiming at each combined label with the same preset label quantity, wherein the characteristic combined label is used for determining an event coping strategy.
in a second aspect, an embodiment of the present invention further provides an apparatus for processing event data, where the apparatus for processing event data includes:
The event data acquisition module is used for acquiring each event data;
The event tag matching module is used for performing content identification on each event data to match one or more tags for the event data;
the event coverage counting module is used for counting the coverage quantity of the combined label coverage events according to the label of the event data aiming at each combined label; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more;
And the characteristic tag determining module is used for determining characteristic combined tags according to the event coverage quantity and aiming at all the combined tags with the same preset tag quantity, wherein the characteristic combined tags are used for determining an event coping strategy.
In a third aspect, an embodiment of the present invention further provides a computing device, where the computing device includes:
one or more processors;
a storage device for storing one or more programs,
When the one or more programs are executed by the one or more processors, the one or more processors implement the method for processing event data provided by any embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the method for processing event data as provided in any embodiment of the present invention.
According to the embodiment of the invention, the content of the event data is firstly identified, the labels are matched according to the content of the event data, the labels are combined, the covering quantity of the combined label covering the event is counted, and then the characteristic combined label is determined according to the event covering quantity in the combined labels with the same preset label quantity. The feature combination label can be used for matching an event coping strategy and providing the strategy for a decision maker to refer, so that the problem that the proposed solution is unreasonable because the decision maker cannot make accurate judgment on the event in the event processing process is solved. The event data is labeled, the event characteristics are extracted by analyzing the combined label, the essence of the event occurrence is found, the processing efficiency of the event is improved, and the effect that the matched suggested measures are more accurate and effective is realized.
drawings
FIG. 1 is a flowchart of a method for processing event data according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a method for processing event data according to a second embodiment of the present invention;
FIG. 3 is a block diagram of an event data processing apparatus according to a third embodiment of the present invention;
Fig. 4 is a schematic structural diagram of a computing device in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
fig. 1 is a flowchart of an event data processing method according to an embodiment of the present invention, where this embodiment is applicable to a case where a decision maker obtains tag information capable of characterizing the nature of an event through processing event data, and the method may be executed by an event data processing apparatus, where the event data processing apparatus may be implemented by software and/or hardware, and the event data processing apparatus may be configured on a computing device, and specifically includes the following steps:
and step 110, acquiring the data of each event.
in the above steps, the event data is description content of an event, the original data may be text content, or may be image content, audio/video content, and the like, the above contents may be converted into text content, and the event may include: fire events, theft events, robbery events, fighting events, traffic congestion events, kidnapping events, and the like. The acquisition source of the event data can be reported by a public security system, reported by the public or published by multimedia. The event data may be retrieved on a case-by-case basis or may be retrieved periodically from a database, such as a police system.
And 120, performing content identification on each event data to match one or more tags for the event data.
In the operation, keywords can be extracted through semantic analysis to identify the content of each event data, the keywords are matched with a preset tag library, one event can be matched with one or more tags, the tags comprise at least one level, and the lower level tags are refined tags of the upper level tags. For example: aiming at fighting events, the content of event data is taken as ZhouSanjio, students Zhang Sanyi have serious fighting events in one, and keywords are extracted according to semantic analysis, wherein the keyword comprises the following steps: wednesday, Jiu Dian, Zhang San, Yizhong and Severe;
according to the difference of the suggested granularity needed by the client, matching the keywords with a preset tag library, wherein Wednesday and nine points are time tags, counting in the following steps, and if the suggested granularity needed by the client is on a relatively wide level of a principal person and/or a place of affairs, a tag matched by Zhang III is a student, a tag matched in the first step is a school, and a tag matched severely is a severe one;
If the suggested granularity needed by the client is at the level of a specific person and/or a specific place, the school, the student and the severity are set as tags, step 130 and step 140 are executed, the tags are combined and then counted to obtain a feature combination tag, then the specific examples of Zhang III and Zhang III in the feature combination tag are set as lower-level tags, and then step 130 and step 140 are executed. Zhang three is the subordinate label of the student label, and one is the subordinate label of the school label.
and step 130, counting the covering number of the combined label covering events according to the label of the event data for each combined label.
the combined label is a label combined with the keyword, the combined label is determined according to the label at the lowest level, the label in each label combination belongs to different label types, the label types are classified according to different dimensions, and different types of events can have different label types. The tag type may be manually preset. For example, for a public security type event, the tag types may include principal, time of issue, location of issue characteristics and severity, etc., and each combination tag does not include a time tag.
If the number of the preset tags simultaneously adopted for one event data is one, two or three, at least three tag types are included, for example, for three tags including students and schools and the weight, three combined tags including one tag are provided, namely, the students, the schools and the weight; the number of the tags of two tags is three, namely student + school, school + severe, student + severe; one label combination of three labels is formed, namely student + school + severe; or the preset number of the tags adopted at the same time is one, two, three, four and five, and at least five tag types are included. The combined label is determined in a manner similar to that described above. And presetting the combination of all the labels of the number of the labels and the natural numbers below the number of the labels as combined labels.
the event data processing method includes the steps that one or more combined labels with the same number of labels are used, the labels of the event data include all the labels in the combined labels, the event data are determined to be covered by the combined labels, and the total number of the event data covered by the combined labels is counted to determine the event data to be covered by the event data.
and 140, determining characteristic combination labels according to the event coverage quantity aiming at the combination labels with the same preset label quantity, and determining an event coping strategy through the characteristic combination labels.
The feature combination tags reflect main influence factors of events, and at least one combination tag with the total quantity meeting a set total quantity lower limit condition and the difference meeting a set difference lower limit condition is selected as a feature combination tag corresponding to the number of the preset tags according to the event coverage number of each combination tag with the same number of the preset tags, and corresponding measure suggestions are matched on the feature combination tags. That is, it is necessary to select a significantly larger number of combination tags as feature combination tags, which are relatively meaningful for the event.
And after determining the feature combination label, the method may further include: and for each event data corresponding to each feature combination label, performing distribution statistics on the time labels in each event data according to a preset time period to determine the time distribution feature of the event data of the feature combination label. The preset time period includes a natural day and/or a week. And respectively matching the feature combination labels of the introduced event distribution features with corresponding measure suggestions.
according to the technical scheme, the content of event data is firstly identified, the labels are matched according to the content of the event data, the labels are combined, the covering quantity of the combined label covering events is counted, then the feature combined labels are determined according to the event covering quantity in the combined labels with the same preset label quantity, the feature combined labels are matched with the event coping strategies, and the strategies are provided for a decision maker to refer to, so that the problem that the decision maker cannot make accurate judgment on the events in the event processing process, and the proposed solution is unreasonable is solved. The event data is labeled, the event characteristics are extracted by analyzing the combined label, the essence of the event occurrence is found, the processing efficiency of the event is improved, and the effect that the matched suggested measures are more accurate is realized.
On the basis of the above technical solution, in step 120, the content of the time data is identified, the keyword is extracted, and the keyword is matched with one or more tags, so that the key information of the event data is matched with the tag, information without analysis value can be removed, information with analysis value is retained, not only the nature of the event occurrence can be found, but also the analysis efficiency of the event data is improved.
In step 130, the tags in each of the tag combinations are classified into different tag types. The combined label has the advantages that different types of labels are combined, namely different event characteristics are contained in each label combination, the key information of the event can be more fully embodied in the label combination, and the matched measures can be more accurately matched.
Example two
fig. 2 is a flowchart of an event data processing method according to a second embodiment of the present invention, which is embodied on the basis of the foregoing embodiments. As shown in fig. 2, the method specifically includes:
and step 210, acquiring the data of each event.
For example, the acquired event data is a fire event, and two event data are taken: 1. fifty o 'clock in week, staff are in a serious fire incident in department stores, 2, twenty-eight o' clock in week, and five wang students are in a light fire incident in one.
And step 220, when the recommendation level required by the client is wider, performing content identification on each event data to match one or more tags for the event data.
According to the difference of the client on the granularity of the required suggestions, the event data is matched with the labels, if the client requires the suggestions on a wider level such as a chief responsible person and/or a place of affairs, the client matches with the label of a staff member for liquan, matches with the label of a department store for department stores, matches with the label of a student for king five, matches with the label of a school for one, and is signed to be heavy, and the label of a slight match is signed to be light, and then the steps 230-270 are executed.
step 221, when the recommendation level required by the client is more specific, identifying the content of each event data, and matching one or more tags with the event data.
if the client needs to recommend a specific level, such as a specific employee and/or a specific mall, the event data is first matched with the tags according to the above steps, and the steps 230 to 240 are executed, and the tags are combined and counted to obtain a feature tag combination, such as the obtained feature tag combination is: staff + mall + heavy, if the customer wants to get the suggestion of which mall, the specific mall name under the mall, such as department store, is set as the next-level label, and the other labels are unchanged; similarly, friday and ten are time labels, statistics is performed in subsequent steps, and the label with serious content matching is still serious because of no next level, and then step 230-step 270 are executed.
Step 230, combining the tags to obtain one or more combined tags.
Four tag types are included in the event data, namely: time of incident, principal person, incident location and severity;
when the matched label is: staff, market, severe, student, school and when slight, except time tag, will belong to the label of different grade type and make up, the label combination that obtains includes: a type 1 label combination, a type 2 label combination and a type 3 label combination;
there are 6 class 1 tag combinations, including: staff, mall, severe, student, school, and mild;
There are 12 class 2 tag combinations, including: staff + mall, staff + school, staff + heavy, staff + light, mall + heavy, mall + light, student + mall, student + school, student + heavy, student + light, school + heavy, and school + light;
There are 8 label combinations of 3 types, including: staff + mall + severe, staff + mall + mild, staff + school + severe, staff + school + mild, student + mall + severe, student + mall + mild, student + school + severe, and student + school + mild.
When the user needs a more specific suggestion, the above-mentioned tags are combined and executed in step 240 to obtain a feature combination tag, such as staff + mall + heavy, and if the user needs a suggestion of a specific mall, the event data under the tag combination is matched with a subordinate tag of the mall, which may further include, in addition to department stores: clothing market and case and bag market make up staff, department store market, clothing market, case and bag market and the label of severe different grade type, and 3 types of label combinations that obtain equally include:
the label combination of type 1 comprises: staff, department stores, clothing stores, luggage stores and the severity;
the class 2 label combination comprises: staff + department store, staff + clothing store, staff + luggage store, staff + heavy, department store + heavy, clothing store + heavy, and luggage store + heavy;
The 3 types of label combinations comprise: staff + department store + heavy, staff + clothing store + heavy, and staff bag store + heavy;
And 240, counting the covering quantity of the combined label covering events according to the labels of the event data for each combined label.
and matching the event data with the label combination, if the labels of the event data comprise all the labels in the combined labels, determining that the combined labels cover the event data, wherein the number of the combined labels is +1, and determining the number of the event data covered by each combined label.
and step 250, determining feature combination labels according to the event coverage quantity aiming at the combination labels with the same preset label quantity, and determining an event coping strategy through the feature combination labels.
The feature combination tags reflect main influence factors of events, and at least one combination tag with the total quantity meeting a set total quantity lower limit condition and the difference meeting a set difference lower limit condition is selected as a feature combination tag corresponding to the number of the preset tags according to the event coverage number of each combination tag with the same number of the preset tags, and corresponding measure suggestions are matched on the feature combination tags. For example, the number of fire events is 1000, and through statistics, if the number of event data meeting the combination of staff, market and heavy label is 500, which accounts for half of the total number of events and is far larger than the number of event data meeting other label combinations, the staff, market and heavy label are determined as feature combination labels and matched with suggestions, such as: strengthening fire-fighting knowledge training of staff in a shopping mall; if the number of event data conforming to the combination of staff, shopping mall and heavy label is 300, the number of event data conforming to student, school and light is 300 and is far greater than the number of event data conforming to other label combinations, the two combined labels are determined as feature combined labels, and matching suggestions are provided, such as: and the fire-fighting knowledge training of staff in a shopping mall and students in a school is enhanced.
step 260, after determining the event handling strategy determination feature combination label through the event data time distribution feature of the feature combination label, performing distribution statistics on the time labels in each event data according to a preset time period to determine the time distribution feature of the event data of the feature combination label, where the preset time period includes a natural day and/or a week. For example, the time labels are counted, the statistical result shows that the number of event data conforming to the label of Wednesday is the largest, and if the combination of the feature labels is student + school + slight degree, the matched suggestion is to carry out fire fighting inspection on the school in Wednesday and remind the student of preventing fire; when the combination of the feature labels is student + first moderate and mild, the matched suggestion is that Wednesday carries out fire-fighting inspection on first moderate and moderate, and reminds students to pay attention to fire prevention; when the feature tag combination is: when the student + school + mild and the staff + market + severe, the suggestion of matching is: wednesday carries out fire control inspection to school and reminds students to pay attention to the prevention conflagration to and Wednesday carries out strict fire control inspection to market, and repeated warning market staff pay attention to the prevention conflagration.
And step 270, determining an event coping strategy by introducing additional factors on the basis of the feature combination label containing the time features.
For example: relevant factors affecting a fire event include: the number of smokers or the temperature is high, whether the additional factors and the number of fire events have a linear relation or not is analyzed, if the additional factors and the number of fire events have the linear relation, suggestions are given, and if the additional factors and the number of fire events have the linear relation, the suggestions are given, such as: the linear relation between the number of smokers and the number of fighting events exists, and as the number of smokers increases, the number of fire events also increases, and then the matching suggestions are shown, such as: smoking is prohibited in schools, and fire checks in schools and fire reminders to students are enhanced on wednesday.
The method for processing event data includes the steps of firstly obtaining event data, identifying content of the event data, matching tags according to the content of the event data, combining the tags to obtain one or more combined tags, counting the number of the combined tags covering events, then determining a feature combined tag according to the event coverage number in the combined tags with the same preset number of tags, matching an event handling strategy to the feature combined tag, after determining the feature combined tag, performing distribution statistics on time tags in the event data according to a preset time period to determine a time distribution feature of the event data of the feature combined tag, matching the event handling strategy, and introducing additional factors on the basis of the feature combined tag containing the time feature to determine the event handling strategy. The strategy is provided for the decision maker to refer, so that the problem that the proposed solution is unreasonable because the decision maker cannot make accurate judgment on the event in the event processing process is solved. The event data is labeled, the event characteristics are extracted by analyzing the combined label, the essence of the event occurrence is found, the processing efficiency of the event is improved, and the effect that the matched suggested measures are more accurate is realized.
EXAMPLE III
fig. 3 is a structural diagram of an event data processing apparatus according to a third embodiment of the present invention, where the event data processing apparatus includes: an event data acquisition module 310, an event tag matching module 320, an event coverage statistics module 330, and a feature tag determination module 340.
The event data acquiring module 310 is configured to acquire event data; an event tag matching module 320, configured to perform content identification on each event data to match one or more tags to the event data; an event coverage counting module 330, configured to count, for each combined tag, a coverage number of the combined tag coverage event according to a tag included in the event data; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more; the feature tag determining module 340 is configured to determine, according to the event coverage number, a feature combination tag for each combination tag having the same preset number of tags, where the feature combination tag is used to determine an event handling policy.
In the technical solution of the above embodiment, the event data acquired by the event data acquiring module includes a fire event, a theft event, a robbery event, a fighting event, a traffic jam event, a kidnapping event, and the like.
In the technical solution of the above embodiment, the event tag matching module is specifically configured to identify the content of each event data by extracting keywords through semantic analysis, and match the keywords with a preset tag library, where an event may match one or more tags, where the tags include at least one level, and a lower level tag is a refined tag of a higher level tag.
In the technical solution of the foregoing embodiment, the event coverage statistics module is configured to count the number of covered combined tags covering an event, where the tags in the combined tags belong to different tag types, the tag types include a person in charge, event time, an event location, characteristics and severity of the event location, and each combined tag does not include a time tag.
optionally, if the number of preset tags simultaneously adopted for one event data is one, two, or three, at least three tag types are included;
At least five tag types are included if the number of preset tags simultaneously employed is one, two, three, four, and five.
In the technical solution of the above embodiment, the feature tag determining module is specifically configured to select, for the event coverage number of each combined tag with the same preset tag number, at least one combined tag whose total amount meets a set total amount lower limit condition and whose gap meets a set difference lower limit condition, as the feature combined tag corresponding to the preset tag number, and suggest a corresponding measure for matching the feature combined tag.
And after determining the feature combination label, the method further comprises the following steps: and for each event data corresponding to each feature combination label, performing distribution statistics on the time labels in each event data according to a preset time period to determine the time distribution feature of the event data of the feature combination label. The preset time period includes a natural day and/or a week. And respectively matching the feature combination labels of the introduced event distribution features with corresponding measure suggestions.
The technical scheme of the embodiment solves the problem that a decision maker cannot make accurate judgment on an event in the process of processing the event, so that the proposed solution is unreasonable. The event data is labeled, the event characteristics are extracted by analyzing the combined label, the essence of the event occurrence is found, the processing efficiency of the event is improved, and the effect that the matched suggested measures are more accurate is realized.
The event data processing device provided by the embodiment of the invention can execute the event data processing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
fig. 4 is a schematic structural diagram of a computing apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the computing apparatus includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the computing device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, memory 420, input device 430, and output device 440 in the computing device may be connected by a bus or other means, such as by a bus in fig. 4.
The memory 420 serves as a computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the event data processing method in the embodiment of the present invention (for example, the event data acquisition module 310, the event tag matching module 320, the event coverage statistics module 330, and the feature tag determination module 340 in the event data processing device). The processor 410 executes various functional applications of the computing device and data processing, i.e., implements the above-described event data processing method, by executing software programs, instructions, and modules stored in the memory 420.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to a computing device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computing device. The output device 440 may include a display device such as a display screen.
EXAMPLE five
Embodiment 5 of the present invention also provides a computer-readable storage medium, where the computer-executable instructions, when executed by a computer processor, are configured to perform a method for processing event data, the method including:
Acquiring each event data;
Performing content identification on each event data to match one or more tags with the event data;
For each combined label, counting the covering quantity of the combined label covering events according to the label of the event data; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more;
and determining a characteristic combined label according to the event coverage quantity aiming at each combined label with the same preset label quantity, wherein the characteristic combined label is used for determining an event coping strategy.
of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in a method for processing event data provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (15)
1. A method for processing event data, the method comprising:
Acquiring each event data;
Performing content identification on each event data to match one or more tags with the event data;
For each combined label, counting the covering quantity of the combined label covering events according to the label of the event data; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more;
And determining a characteristic combined label according to the event coverage quantity aiming at each combined label with the same preset label quantity, wherein the characteristic combined label is used for determining an event coping strategy.
2. the method of claim 1, wherein content identifying each of the event data to match one or more tags to the event data comprises:
Extracting keywords of each event data through semantic analysis;
and matching each keyword with a preset label library to match one or more labels for the event data.
3. The method according to claim 1, wherein for each combined label, counting the number of covered events covered by the combined label according to the label of the event data comprises:
For each combined label, if the label of the event data comprises all labels in the combined label, determining that the combined label covers the event data;
and counting the total number of the event data covered by the combined label to determine the event covered number.
4. the method of claim 1, wherein determining the feature combination labels according to the event coverage number for each combination label having the same preset label number comprises:
And selecting at least one combined label with the total amount meeting a set total amount lower limit condition and the difference meeting a set difference lower limit condition as a characteristic combined label corresponding to the preset label quantity according to the event coverage quantity of each combined label with the same preset label quantity.
5. the method according to claim 4, wherein the condition of setting the total lower limit is that the number of event coverage is maximum or that a total threshold is set; the set difference lower limit condition is that the difference between the event coverage quantity of the combined label and the event coverage quantity of other combined labels is maximum or the difference meets a set threshold value.
6. the method according to claim 1 or 5, characterized in that:
the number of the preset labels adopted at the same time is one, two or three, and at least three label types are included; or
The number of the preset tags adopted at the same time is one, two, three, four and five, and at least five tag types are included.
7. The method of claim 6, wherein: the number of the feature combination labels corresponding to the preset label number is the same as or different from the preset label number.
8. The method of claim 1, wherein each combination tag does not include a time tag, and wherein determining the feature combination tag further comprises:
And for each event data corresponding to each feature combination label, performing distribution statistics on the time labels in each event data according to a preset time period to determine the time distribution feature of the event data of the feature combination label.
9. The method of claim 8, wherein the preset time period comprises a natural day and/or a week.
10. The method of claim 1, wherein the event comprises at least one of a fire event, a fighting event, and a theft event.
11. The method of claim 1, wherein the tag types include principal, time of issue, and location of issue.
12. the method of claim 1, wherein the tags include at least one level, lower level tags are refinement tags of upper level tags, and the combined tag is determined according to a lowest level tag.
13. An apparatus for processing event data, comprising:
The event data acquisition module is used for acquiring each event data;
the event tag matching module is used for performing content identification on each event data to match one or more tags for the event data;
The event coverage counting module is used for counting the coverage quantity of the combined label coverage events according to the label of the event data aiming at each combined label; each combined label comprises labels with preset label quantity, the labels in each label combination belong to different label types, the preset label quantity is a natural number, and the quantity of the combined labels with the same preset label quantity is one or more;
and the characteristic tag determining module is used for determining characteristic combined tags according to the event coverage quantity and aiming at all the combined tags with the same preset tag quantity, wherein the characteristic combined tags are used for determining an event coping strategy.
14. A computing device, wherein the computing device comprises:
One or more processors;
A storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of processing event data as recited in any of claims 1-12.
15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of processing event data according to any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910832430.2A CN110543914B (en) | 2019-09-04 | 2019-09-04 | Event data processing method and device, computing equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910832430.2A CN110543914B (en) | 2019-09-04 | 2019-09-04 | Event data processing method and device, computing equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110543914A true CN110543914A (en) | 2019-12-06 |
| CN110543914B CN110543914B (en) | 2022-06-24 |
Family
ID=68711240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910832430.2A Active CN110543914B (en) | 2019-09-04 | 2019-09-04 | Event data processing method and device, computing equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543914B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739254B1 (en) * | 2005-09-30 | 2010-06-15 | Google Inc. | Labeling events in historic news |
| CN103455611A (en) * | 2013-09-06 | 2013-12-18 | 北京邮电大学 | Data processing method for RFID (Radio Frequency Identification) middleware |
| CN103699663A (en) * | 2013-12-27 | 2014-04-02 | 中国科学院自动化研究所 | Hot event mining method based on large-scale knowledge base |
| US9251530B1 (en) * | 2012-08-31 | 2016-02-02 | Sprinklr, Inc. | Apparatus and method for model-based social analytics |
| CN105589950A (en) * | 2015-12-18 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Event attribute statement determination method, early warning method and apparatus based on event attribute statement |
| CN106776933A (en) * | 2016-12-01 | 2017-05-31 | 厦门市美亚柏科信息股份有限公司 | A kind of processing method and system that polymerization is analyzed to similar case information |
| CN107196910A (en) * | 2017-04-18 | 2017-09-22 | 国网山东省电力公司电力科学研究院 | Threat early warning monitoring system, method and the deployment framework analyzed based on big data |
| CN107748803A (en) * | 2017-11-20 | 2018-03-02 | 中国运载火箭技术研究院 | A kind of roomage state characteristic event database design method |
| CN108446296A (en) * | 2018-01-24 | 2018-08-24 | 北京奇艺世纪科技有限公司 | A kind of information processing method and device |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109815481A (en) * | 2018-12-17 | 2019-05-28 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer storage medium of event extraction are carried out to text |
| CN109858869A (en) * | 2018-12-21 | 2019-06-07 | 厦门市美亚柏科信息股份有限公司 | Method and apparatus for handling event information |
| CN110020807A (en) * | 2019-04-11 | 2019-07-16 | 软通动力信息技术有限公司 | A kind of Urban Event allocates method of disposal, system, electronic equipment and storage medium |
| CN110033092A (en) * | 2019-01-31 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Data label generation, model training, event recognition method and device |
| CN110162518A (en) * | 2019-04-16 | 2019-08-23 | 平安科技（深圳）有限公司 | Data grouping method, apparatus, electronic equipment and storage medium |
-
2019
- 2019-09-04 CN CN201910832430.2A patent/CN110543914B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739254B1 (en) * | 2005-09-30 | 2010-06-15 | Google Inc. | Labeling events in historic news |
| US9251530B1 (en) * | 2012-08-31 | 2016-02-02 | Sprinklr, Inc. | Apparatus and method for model-based social analytics |
| CN103455611A (en) * | 2013-09-06 | 2013-12-18 | 北京邮电大学 | Data processing method for RFID (Radio Frequency Identification) middleware |
| CN103699663A (en) * | 2013-12-27 | 2014-04-02 | 中国科学院自动化研究所 | Hot event mining method based on large-scale knowledge base |
| CN105589950A (en) * | 2015-12-18 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Event attribute statement determination method, early warning method and apparatus based on event attribute statement |
| CN106776933A (en) * | 2016-12-01 | 2017-05-31 | 厦门市美亚柏科信息股份有限公司 | A kind of processing method and system that polymerization is analyzed to similar case information |
| CN107196910A (en) * | 2017-04-18 | 2017-09-22 | 国网山东省电力公司电力科学研究院 | Threat early warning monitoring system, method and the deployment framework analyzed based on big data |
| CN107748803A (en) * | 2017-11-20 | 2018-03-02 | 中国运载火箭技术研究院 | A kind of roomage state characteristic event database design method |
| CN108446296A (en) * | 2018-01-24 | 2018-08-24 | 北京奇艺世纪科技有限公司 | A kind of information processing method and device |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109815481A (en) * | 2018-12-17 | 2019-05-28 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer storage medium of event extraction are carried out to text |
| CN109858869A (en) * | 2018-12-21 | 2019-06-07 | 厦门市美亚柏科信息股份有限公司 | Method and apparatus for handling event information |
| CN110033092A (en) * | 2019-01-31 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Data label generation, model training, event recognition method and device |
| CN110020807A (en) * | 2019-04-11 | 2019-07-16 | 软通动力信息技术有限公司 | A kind of Urban Event allocates method of disposal, system, electronic equipment and storage medium |
| CN110162518A (en) * | 2019-04-16 | 2019-08-23 | 平安科技（深圳）有限公司 | Data grouping method, apparatus, electronic equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| ANDREAS WEILER 等: "Survey and Experimental Analysis of Event Detection Techniques for Twitter", 《THE COMPUTER JOURNAL 》 * |
| LIANG-CHIH YU 等: "Mining association language patterns using a distributional semantic model for negative life event classification", 《JOURNAL OF BIOMEDICAL INFORMATICS》 * |
| 周志恒: "基于事件社会网络群组发现及推荐策略", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 李昕: "新闻事件识别系统的研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110543914B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101708444B1 (en) | Method for evaluating relation between keyword and asset value and Apparatus thereof | |
| US8601494B2 (en) | Multi-event type monitoring and searching | |
| Balduini et al. | Models and practices in urban data science at scale | |
| CN102902960B (en) | Leave-behind object detection method based on Gaussian modelling and target contour | |
| Oosterloo et al. | The politics and biases of the ‘crime anticipation system’of the Dutch police | |
| CN112487208A (en) | Network security data association analysis method, device, equipment and storage medium | |
| Liu et al. | Detecting global and local topics via mining twitter data | |
| CA3169417A1 (en) | Method of and system for appraising risk | |
| CN112511855A (en) | Cloud computing-based electronic commerce platform live video intelligent management system | |
| CN111125344A (en) | Related word recommendation method and device | |
| Brown-Liburd et al. | Measuring with exogenous data (MED), and government economic monitoring (GEM) | |
| CN111028087A (en) | Information display method, device and equipment | |
| CN117273429A (en) | Event monitoring method, system, electronic equipment and storage medium | |
| CN108984514A (en) | Acquisition methods and device, storage medium, the processor of word | |
| CN112464670A (en) | Recognition method, recognition model training method, device, equipment and storage medium | |
| Morshed et al. | Viscrimepredict: a system for crime trajectory prediction and visualisation from heterogeneous data sources | |
| CN115514558A (en) | Intrusion detection method, device, equipment and medium | |
| CN110543914B (en) | Event data processing method and device, computing equipment and medium | |
| CN111435435A (en) | Method, device, server and system for identifying pedestrians | |
| CN112925899B (en) | Ordering model establishment method, case clue recommendation method, device and medium | |
| CN111291029B (en) | Data cleaning method and device | |
| JP2021185485A (en) | Time value detection system in disaster information and display method | |
| di Bella et al. | Smart Security: Integrated systems for security policies in urban environments | |
| CN115809256B (en) | Public security management integrated information system and visual display method | |
| CN114386415A (en) | Method for constructing digital-image fusion library and related equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 300308 402, building 7, Zhongxing Industrial base, No.2, East 7th Road, Tianjin pilot free trade zone (Airport Economic Zone), Binhai New Area, Tianjin Applicant after: Softcom smart Information Technology Co.,Ltd. Address before: 300308 402, building 7, Zhongxing Industrial base, No.2, East 7th Road, Tianjin pilot free trade zone (Airport Economic Zone), Binhai New Area, Tianjin Applicant before: ISOFTSTONE INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |