CN109739963A - Information retrieval method, device, equipment and medium - Google Patents
Information retrieval method, device, equipment and medium Download PDFInfo
- Publication number
- CN109739963A CN109739963A CN201811610513.9A CN201811610513A CN109739963A CN 109739963 A CN109739963 A CN 109739963A CN 201811610513 A CN201811610513 A CN 201811610513A CN 109739963 A CN109739963 A CN 109739963A
- Authority
- CN
- China
- Prior art keywords
- event
- retrieval
- sentence
- information
- standard
- 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 38
- 239000000463 material Substances 0.000 claims abstract description 18
- 230000015654 memory Effects 0.000 claims description 17
- 238000007689 inspection Methods 0.000 claims description 6
- 239000012141 concentrate Substances 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of information retrieval method, device, equipment and media.The event description information for obtaining event to be checked determines corresponding event attribute according to the event description information；Based on retrieval associated data table, the corresponding at least one standard retrieval sentence of the event attribute is obtained, wherein the retrieval associated data table is obtained according to the retrieval sentence generation strategy of setting；The standard retrieval sentence that will acquire is determined as the target retrieval sentence of the event to be checked；The material information bank selected using the target retrieval sentence retrieval obtains the characteristic information of the event to be checked.The present invention implements the method provided, by obtaining standard retrieval sentence according to event attribute, increases the reusability of retrieval sentence, recall precision can be improved.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of information retrieval method, device, equipment and
Medium.
Background technique
With the progress of society and economic development, traditional public security method of handling a case is no longer satisfied the current criminal of strike
Guilty, crime prevention and social security management requirement is badly in need of technological means to improve the case handling efficiency of people's police, for example, passing through report
The case of case people describes, and by information retrieval, retrieval determines that case is related to the characteristic information for the personnel of committing a crime quickly.
To reinforce informatization, helps to improve strike of the public security organ to crime one's share of expenses for a joint undertaking, effective crime prevention occurs, but
It is existing Police Information searching system, each case retrieving is independent, and search condition used in retrieving can not repeat benefit
With there is a problem of that case handling efficiency is lower.
Summary of the invention
The present invention provides a kind of information retrieval method, device, equipment and medium, with linked character information described in realization event
Efficient retrieval.
In a first aspect, the embodiment of the invention provides a kind of information retrieval methods, this method comprises:
The event description information for obtaining event to be checked determines corresponding event attribute according to the event description information；
Based on retrieval associated data table, the corresponding at least one standard retrieval sentence of the event attribute is obtained, wherein institute
Retrieval associated data table is stated to be obtained according to the retrieval sentence generation strategy of setting；
The standard retrieval sentence that will acquire is determined as the target retrieval sentence of the event to be checked；
The material information bank selected using the target retrieval sentence retrieval obtains the characteristic information of the event to be checked.
Second aspect, the embodiment of the invention also provides information indexing device, which includes:
Event attribute determining module, for obtaining the event description information of event to be checked, according to the event description information
Determine corresponding event attribute；
Standard sentence obtains module, for obtaining the event attribute corresponding at least one based on retrieval associated data table
Standard retrieval sentence, wherein the retrieval associated data table is obtained according to the generation module for retrieving sentence generation strategy is set with
?；
Object statement determining module, the standard retrieval sentence for will acquire are determined as the target of the event to be checked
Retrieve sentence；
Characteristic information search module, the material information bank for being selected using the target retrieval sentence retrieval, obtains institute
State the characteristic information of event to be checked.
The third aspect, the embodiment of the invention also provides a kind of equipment, the equipment includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the information retrieval method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes any information retrieval method in embodiment when the program is executed by processor.
The present invention determines corresponding thing according to the event description information by the event description information of acquisition event to be checked
Part attribute；Based on retrieval associated data table, the corresponding at least one standard retrieval sentence of the event attribute is obtained, wherein retrieval
Associated data table is obtained according to the retrieval sentence generation strategy of setting；The standard retrieval sentence that will acquire is determined as event to be checked
Target retrieval sentence；The material information bank selected using target retrieval sentence retrieval, obtains the characteristic information of event to be checked；It solves
The low problem of retrieval sentence reuse rate, improves the information retrieval of characteristic information associated by event in information retrieval process
Efficiency, and then improve the information-based user experience handled a case.
Detailed description of the invention
Fig. 1 is the step flow chart for the information retrieval method that the embodiment of the present invention one provides；
Fig. 1 b is the implementation flow chart for the generation retrieval associated data table that the embodiment of the present invention one provides；
Fig. 2 is the step flow chart of information retrieval method provided by Embodiment 2 of the present invention；
Fig. 3 is the structural schematic diagram for the information indexing device that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the step flow chart for the information retrieval method that the embodiment of the present invention one provides, and the present embodiment is applicable to spy
The case where levying information retrieval, this method can be executed by information indexing device, be specifically comprised the following steps:
Step 101, the event description information for obtaining event to be checked, determine corresponding event according to the event description information
Attribute.
Wherein, event to be checked can be the event for needing that characteristic information is obtained according to event related data；Description information can
To be that event to be checked is briefly described, it is raw according to event content that automation tools can be rule of thumb generated or used by user
At for example, event description can lose event according to the input of the merit of event by policeman in charge of the case for article has occurred；Event attribute
Can be the information for reflecting the affiliated type of event to be checked, can specifically include steal case, environmentally friendly case, case involving public security and
Robbery etc..
Specifically, the corresponding description information of available event to be checked, according to description information using character match or
Neural network algorithm determines the affiliated event type of event to be checked, and illustratively, event attribute may include stealing case, ring
Case, case involving public security and robbery etc. are protected, optionally, event attribute can also be by participle corpus, near synonym corpus and part of speech
Corpus is analyzed the relevant data of event jointly and is generated, and the mode specifically obtained can be first locates event related data in advance
Reason, the meaningless content including in are filtered, such as the texts such as filtering " .#@%##% $ 2423 ", deletion event related data
Stop words, such as carriage return and space, pretreatment further include by related data facial expression image or expression character turn over
It translates, such as expression character " ┭ ┮ ﹏ ┭ ┮ " can translate into " sobbing ", it then can be related by pretreated event
Extract event attribute in data, detailed process can be according to participle corpus to being single by the word segmentation in event related data
Word, if the word near synonym corpus there are similar near synonym, it is corresponding using near synonym near synonym corpus
Hash result as the word Hash operation as a result, count the word frequency of each word respectively, calculate the weight of each word, can be right
The Weight of emphasis word, such as the emphasis word relevant to event property such as steal and plunder and log can be used (word is total
Number/heavy duty word words and phrases frequency) calculation be weighted, it is ensured that emphasis word is confirmed as event attribute, can will finally make
Vector is formed with the Hash calculation result and weight of each word, using the vector as the input of convolutional neural networks, by convolution mind
The event attribute of corresponding event is generated through network.
Step 102 is based on retrieval associated data table, obtains the corresponding at least one standard retrieval language of the event attribute
Sentence, wherein the retrieval associated data table is obtained according to the retrieval sentence generation strategy of setting.
Wherein, retrieval associated data table, which can be, is stored with event attribute and the corresponding standard retrieval sentence of event attribute
The corresponding relationship of tables of data, event attribute and standard retrieval sentence may include one-to-one, one-to-many and multi-to-multi etc., and retrieval is closed
Connection tables of data can be obtained according to the retrieval sentence generation strategy of setting；Standard retrieval sentence can be preset special for event
The template query sentence for levying retrieval, can be according to case time, search key, special number and/or the data of event to be checked
Source is adjusted.
Specifically, event attribute and corresponding standard retrieval language can be stored with according to the corresponding event attribute of event to be checked
The standard retrieval sentence for retrieving event to be checked is searched in the tables of data of sentence, wherein inquire the item number of corresponding event to be checked
It can be one or more.
Step 103, the standard retrieval sentence that will acquire are determined as the target retrieval sentence of the event to be checked.
Wherein, target retrieval sentence can be using standard retrieval sentence as template, after the information adjustment of event to be checked
The query statement of generation can be the query statement for carrying out retrieving event to be checked.
Specifically, can be adjusted according to the relevant information of event to be checked to the standard retrieval sentence got, adjust
Mode may include changing the information such as range of search, search key and case time of standard retrieval sentence, can also wrap
It includes and increases new querying condition on the basis of standard retrieval sentence, such as phone is taken out in removal；By standard retrieval adjusted
Target retrieval sentence of the sentence as event to be checked.
A kind of optional embodiment can not be adjusted standard retrieval sentence, the standard inspection that directly will acquire
Rope sentence is as target retrieval sentence.
Step 104, the material information bank selected using the target retrieval sentence retrieval, obtain the spy of the event to be checked
Reference breath.
Wherein, material information bank can be the database for being stored with information concerning events to be checked, and the mode obtained can be with
It is obtained in intelligent terminal including downloading or connecting the relevant intelligent terminal of event to be checked from software servers such as wechat, QQ and Fetions
All information of storage, the characteristic information of event to be checked can be the information for characterizing event flag to be checked, may include:
Event is related to occupation, gender, name, physical condition, marital status, frequent contact and event details of personage etc..
It is retrieved, is obtained for characterizing in material information specifically, the target retrieval sentence got can be used
The event of affair character to be checked is related to occupation, gender, name, physical condition, marital status, frequent contact and the event of personage
The information such as details.
The technical solution of the present embodiment analyze really to description information by getting the description information of event to be checked
The event attribute of fixed event to be checked gets corresponding standard retrieval sentence in retrieval associated data table according to event attribute,
The target retrieval sentence for retrieving event to be checked is determined using standard sentence, uses target retrieval sentence retrieval event pair to be checked
The material information bank answered, obtains the characteristic information of event to be checked, solves in search process retrieval sentence recycling rate of waterused is low and ask
Topic, improves the recall precision of affair character information to be checked.
Based on the above technical solution, the present embodiment is specifically examined to according to the retrieval sentence generation strategy of setting
Rope associated data table, is optimized, and Fig. 1 b is the realization stream for the generation retrieval associated data table that the embodiment of the present invention one provides
Cheng Tu, as shown in Figure 1 b, retrieve associated data table generation specifically includes the following steps:
Step 110 obtains the historical events description information that historical events concentrates each historical events.
Wherein, historical events collection can be the set that the event of retrieval was carried out based on standard retrieval sentence, wherein history
In event set can associated storage have corresponding historical events description information and standard feature information.
Specifically, each history thing can be read in the mode that the historical events of storage is concentrated use in traversal at regular intervals
The description information of part.A kind of optional embodiment can read its corresponding history whenever having new historical events to generate
Event description information.
Step 111 determines corresponding historical events attribute based on each historical events description information, and remembers each institute respectively
Stating historical events attribute is standard attribute.
Wherein, historical events attribute can be the information for identifying historical events generic, can specifically include steathily
Theft case part, environmentally friendly case, case involving public security and robbery etc.；Standard attribute can be the category for generating retrieval associated data table
Property information, can be the historical events attribute of unified verbal description, for example, historical events attribute is stealing, then its is corresponding
Standard attribute is to steal case.
Specifically, can be used character match or neural network algorithm concentrated according to the historical events got it is all
The description of each historical events determines the historical events attribute of historical events collection, can merge to each historical events attribute information
It arranges, generates the standard attribute of corresponding each historical events.A kind of optional embodiment can not carry out historical events attribute
Processing, the historical events attribute for each historical events that directly will acquire is as its corresponding standard attribute.
Step 112 is based on the corresponding standard feature information of each historical events, determines each mark of at least one acquisition
Standard retrieval sentence needed for quasi- characteristic information.
Wherein, standard feature information can be the final result of historical events retrieval, can be with historical events Attribute Association
It is stored in historical events collection, standard retrieval sentence can be to be generated according to standard feature information, such as characteristic information is identity card
Number, then corresponding retrieval sentence can be the query statement of identification card number.
Specifically, the standard feature information of each historical events of correspondence of available historical events collection storage, according to history
Characteristic information generates corresponding standard retrieval sentence, optionally, can also store the target inspection that historical events retrieving uses
Rope sentence, the target retrieval sentence according to history feature information in storage are matched, the storage target retrieval language that will match to
Sentence is used as standard retrieval sentence.
Each standard attribute of step 113, associated storage and corresponding standard retrieval sentence form retrieval associated data
Table.
Wherein, retrieval associated data table, which can be, is stored with event attribute and the corresponding standard retrieval sentence of event attribute
The corresponding relationship of tables of data, event attribute and standard retrieval sentence may include one-to-one, one-to-many and multi-to-multi etc..
Specifically, can be using standard attribute as the major key of storage, standard retrieval sentence can be carried out with establishing criteria attribute
Storage generates retrieval associated data table, wherein the concrete form of retrieval associated data table may include file, table and data
Library etc..
Embodiment two
Fig. 2 is the step flow chart of information retrieval method provided by Embodiment 2 of the present invention；The present embodiment is in above-mentioned reality
On the basis of applying example, a kind of embodiment provided, referring to fig. 2, a kind of information retrieval method provided in an embodiment of the present invention includes:
Step 201, the description information for obtaining event to be checked, extract the keyword in the description information.
Wherein, keyword can be the word for characterizing event generic feature to be checked, such as steals, loses and injures
Deng.
It is extracted in the description information of event to be checked for characterizing event to be checked specifically, neural network algorithm can be used
The word of feature, the word that will acquire is as keyword, it is possible to understand that extraction keyword specific method have a variety of, this reality
The merely illustrative rather than restriction to embodiment of the neural network algorithm that the mode of applying is enumerated.
Step 202 searches corresponding event attribute in preset relation on attributes table using the keyword, by query result
It is determined as the event attribute of the event to be checked.
Wherein, relation on attributes table can be with the tables of data of corresponding relationship between the keyword and event attribute of preset in advance, example
Such as, keyword is to lose, and corresponding event attribute is to steal case, and keyword and event attribute can be one-to-one, one-to-many
And multi-to-multi, that is, a keyword can correspond to a case attribute or correspond to multiple case attributes.
Specifically, its event for corresponding to storage can be searched in preset relation on attributes table according to the keyword got
Attribute, using the event attribute found as the event attribute of event to be checked, further, in order to obtain keyword and case category
Property between corresponding relationship, neural network classification algorithm can be used, using keyword as the input of neural network classification algorithm,
It can obtain case attribute to deserved output result for case to be checked.
Step 203 is based on retrieval associated data table, obtains the corresponding at least one standard retrieval language of the event attribute
Sentence, wherein the retrieval associated data table is obtained according to the retrieval sentence generation strategy of setting.
Step 204, the case time for obtaining the event to be checked, search key, special number and/or data source letter
Breath.
Wherein, the case time can be the time or time of fire alarming that event to be checked occurs, and search key can be certainly
The words that the dynamic words generated or user determine according to experience, special number can be the directly related number of event,
Such as telephone number or ID card No. etc., special number can also be the number with the incoherent interference information of event, such as
It takes out or the telephone number of express delivery, data source can be event and be related to the data source of data, such as from wechat, short
Letter, multimedia message, QQ and household register information etc..
Specifically, the case time relevant to event to be checked of available user's input, search key, special number
And/or the data such as data origin information.It further, can be by providing optional case time, search key, special number
The data label of code and/or data origin information, adds corresponding parameter information by user by way of selecting label.
Step 205 generates correspondence according to the case time, search key, special number and/or data origin information
Adjustment retrieve sentence, the adjustment retrieval sentence is added to the target that the standard retrieval sentence generates the event to be checked
Retrieve sentence.
Wherein, adjustment sentence can be according to case time, search key, special number and/or the data got
The corresponding query statement generated of the data such as source-information, can be the supplemental content of standard retrieval sentence, for example, one case of input
The part time can generate corresponding query statement according to the input case time.
Specifically, can be according to case time, search key, special number and/or the data origin information got
Corresponding adjustment sentence is generated, the adjustment sentence that will acquire is supplemented in standard retrieval sentence, the standard inspection after being adjusted
Rope sentence is as target retrieval sentence.
Step 206, the event data for obtaining the material information bank storage divide the event data and generate event participle
Collection.
Wherein, event data can be the data of event related content to be checked, may include wechat message, short message,
Multimedia message, QQ message, notes and usage record of intelligent terminal etc., event participle collection, which can be to remove event data, to be connected
The data acquisition system of word is divided into after word.
Specifically, all data relevant to event to be checked in available material information bank, can remove and get number
According to conjunction and be divided into word, formed event participle collection.
Step 207 carries out the retrieval acquisition event to be checked to event participle collection using the target retrieval sentence
Characteristic information.
Wherein, characteristic information can be the information for characterizing event flag to be checked, may include: that event is related to personage
Occupation, gender, name, physical condition, marital status, frequent contact and event details etc..
Event participle collection is inquired specifically, determining target retrieval sentence can be used, the event that will be inquired
It is related to occupation, gender, name, physical condition, marital status, frequent contact and event details of personage etc. as to be checked
The characteristic information of event.
The technical solution of the embodiment of the present invention is determined corresponding by the keyword extracted in event description information to be checked
Case attribute obtains standard retrieval sentence in retrieval associated data table according to case attribute, when the case of the user got
Between, the parameters such as search key, special number and data origin information determining target retrieval is adjusted to standard retrieval sentence
Sentence segments collection using target retrieval sentence retrieval event and obtains corresponding characteristic information, by adjusting standard retrieval sentence
The accuracy that retrieval sentence is improved for target retrieval sentence is retrieved event participle collection using target retrieval sentence, is had
Effect improves recall precision.
Embodiment three
Fig. 3 is the structural schematic diagram for the information indexing device that the embodiment of the present invention three provides.The embodiment of the present invention is provided
Information indexing device information retrieval method provided by any embodiment of the invention can be performed, have the corresponding function of execution method
It can module and beneficial effect.Referring to Fig. 3, the information indexing device that the present invention implements to provide includes: event attribute determining module
301, standard sentence obtains module 302, object statement determining module 303 and characteristic information search module 304.
Wherein, event attribute determining module 301, for obtaining the event description information of event to be checked, according to the event
Description information determines corresponding event attribute.
Standard sentence obtains module 302, for it is corresponding at least to obtain the event attribute based on retrieval associated data table
One standard retrieval sentence, wherein the retrieval associated data table is according to the generation module for being set with retrieval sentence generation strategy
It obtains.
Object statement determining module 303, the standard retrieval sentence for will acquire are determined as the event to be checked
Target retrieval sentence.
Characteristic information search module 304, the material information bank for being selected using the target retrieval sentence retrieval, is obtained
The characteristic information of the event to be checked.
The technical solution of the present embodiment obtains the description information of event to be checked by event attribute determining module, according to retouching
The event attribute that information determines event to be checked is stated, standard sentence obtains module and obtains according to event attribute in retrieval associated data table
Corresponding standard retrieval sentence, object statement determining module determine the target retrieval language for retrieval according to standard retrieval sentence
Sentence, characteristic information search module use the corresponding material information bank of target retrieval sentence retrieval event to be checked, obtain event to be checked
Characteristic information, improve recycling rate of waterused of the retrieval sentence in fact retrieval, effectively improve the recall precision of characteristic information.
Further, the generation module includes:
Description information acquiring unit concentrates the historical events description information of each historical events for obtaining historical events.
Standard attribute acquiring unit, for determining corresponding historical events category based on each historical events description information
Property, and remember that each historical events attribute is standard attribute respectively.
Standard sentence acquiring unit determines at least one for being based on the corresponding standard feature information of each historical events
Standard retrieval sentence needed for item obtains each standard feature information.
Associated data table generation unit is retrieved, each standard attribute of associated storage and corresponding standard retrieval language are used for
Sentence forms retrieval associated data table.
Further, the object statement determining module 303 includes:
Information acquisition unit, for obtain case time of the event to be checked, search key, special number and/or
Data origin information.
Search statement adjustment unit, for according to the case time, search key, special number and/or data come
Source information generates corresponding adjustment and retrieves sentence, and adjustment retrieval sentence is added to described in the standard retrieval sentence generation
The target retrieval sentence of event to be checked.
Further, the characteristic information search module 304 includes:
The event data for obtaining the material information bank storage divides the event data and generates event participle collection.
The feature letter that retrieval obtains the event to be checked is carried out to event participle collection using the target retrieval sentence
Breath.
Further, the event attribute determining module 301, comprising:
The description information for obtaining the event to be checked, extracts the keyword in the description information.
Corresponding event attribute is searched in preset relation on attributes table using the keyword, query result is determined as institute
State the event attribute of event to be checked.
Example IV
Fig. 4 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides, as shown in figure 4, the equipment includes place
Manage device 70, memory 71, input unit 72 and output device 73；The quantity of processor 70 can be one or more in equipment,
In Fig. 4 by taking a processor 70 as an example；Processor 70, memory 71, input unit 72 and output device 73 in equipment can be with
It is connected by bus or other modes, in Fig. 4 for being connected by bus.
Memory 71 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of the information retrieval method in the embodiment of the present invention is (for example, information retrieval fills
Set includes: event attribute determining module 301, standard sentence acquisition module 302, object statement determining module 303 and characteristic information
Search module 304).Software program, instruction and the module that processor 70 is stored in memory 71 by operation, thereby executing
The various function application and data processing of equipment, that is, realize above-mentioned information retrieval method.
Memory 71 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 71 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 71 can be further
Including the memory remotely located relative to processor 70, these remote memories can pass through network connection to equipment.It is above-mentioned
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 72 can be used for receiving the number or character information of input, and generate with the user setting of equipment and
The related key signals input of function control.Output device 73 may include that display screen etc. shows equipment.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction is used to execute a kind of information retrieval method when being executed by computer processor, this method comprises:
The event description information for obtaining event to be checked determines corresponding event attribute according to the event description information；
Based on retrieval associated data table, the corresponding at least one standard retrieval sentence of the event attribute is obtained, wherein institute
Retrieval associated data table is stated to be obtained according to the retrieval sentence generation strategy of setting；
The standard retrieval sentence that will acquire is determined as the target retrieval sentence of the event to be checked；
The material information bank selected using the target retrieval sentence retrieval obtains the characteristic information of the event to be checked.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed information retrieval provided by any embodiment of the invention
Relevant operation in method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, included each unit and module are only pressed in the embodiment of above- mentioned information retrieval device
It is divided, but is not limited to the above division according to function logic, as long as corresponding functions can be realized；In addition,
The specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of information retrieval method characterized by comprising
The event description information for obtaining event to be checked determines corresponding event attribute according to the event description information；
Based on retrieval associated data table, the corresponding at least one standard retrieval sentence of the event attribute is obtained, wherein the inspection
Rope associated data table is obtained according to the retrieval sentence generation strategy of setting；
The standard retrieval sentence that will acquire is determined as the target retrieval sentence of the event to be checked；
The material information bank selected using the target retrieval sentence retrieval obtains the characteristic information of the event to be checked.
2. the method according to claim 1, wherein described examined according to the retrieval sentence generation strategy of setting
Rope associated data table, comprising:
Obtain the historical events description information that historical events concentrates each historical events；
Corresponding historical events attribute is determined based on each historical events description information, and remembers each historical events category respectively
Property is standard attribute；
Based on the corresponding standard feature information of each historical events, each standard feature information institute of at least one acquisition is determined
The standard retrieval sentence needed；
Each standard attribute of associated storage and corresponding standard retrieval sentence form retrieval associated data table.
3. the method according to claim 1, wherein the standard retrieval sentence that will acquire is determined as institute
State the target retrieval sentence of event to be checked, comprising:
Obtain case time, search key, special number and/or the data origin information of the event to be checked；According to described
Case time, search key, special number and/or data origin information generate corresponding adjustment and retrieve sentence, by the tune
Whole retrieval sentence is added to the target retrieval sentence that the standard retrieval sentence generates the event to be checked.
4. the method according to claim 1, wherein the element selected using the target retrieval sentence retrieval
Material information bank obtains the characteristic information of the event to be checked, comprising:
The event data for obtaining the material information bank storage divides the event data and generates event participle collection；
The characteristic information that retrieval obtains the event to be checked is carried out to event participle collection using the target retrieval sentence.
5. according to the method described in claim 1, the event description information for obtaining event to be checked, according to the event description
Information determines corresponding event attribute, comprising:
The description information for obtaining the event to be checked, extracts the keyword in the description information；
Search corresponding event attribute in preset relation on attributes table using the keyword, by query result be determined as it is described to
The event attribute of inspection event.
6. a kind of information indexing device characterized by comprising
Event attribute determining module is determined for obtaining the event description information of event to be checked according to the event description information
Corresponding event attribute；
Standard sentence obtains module, for obtaining corresponding at least one mark of the event attribute based on retrieval associated data table
Quasi- retrieval sentence, wherein the retrieval associated data table is obtained according to the generation module for being set with retrieval sentence generation strategy；
Object statement determining module, the standard retrieval sentence for will acquire are determined as the target retrieval of the event to be checked
Sentence；
Characteristic information search module, the material information bank for being selected using the target retrieval sentence retrieval, obtain it is described to
The characteristic information of inspection event.
7. device according to claim 6, which is characterized in that the generation module includes:
Description information acquiring unit concentrates the historical events description information of each historical events for obtaining historical events；
Standard attribute acquiring unit, for determining corresponding historical events attribute based on each historical events description information, and
Remember that each historical events attribute is standard attribute respectively；
Standard sentence acquiring unit determines that at least one obtains for being based on the corresponding standard feature information of each historical events
Standard retrieval sentence needed for obtaining each standard feature information；
Associated data table generation unit is retrieved, each standard attribute of associated storage and corresponding standard retrieval sentence, shape are used for
At retrieval associated data table.
8. device according to claim 6, which is characterized in that the object statement determining module includes:
Information acquisition unit, for obtaining case time, search key, special number and/or the data of the event to be checked
Source-information；
Search statement adjustment unit, for being believed according to the case time, search key, special number and/or data source
Breath generates corresponding adjustment and retrieves sentence, and it is described to be checked that adjustment retrieval sentence is added to the standard retrieval sentence generation
The target retrieval sentence of event.
9. a kind of equipment, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs, when one or more of programs are by one or more of processors
It executes, so that one or more of processors realize such as information retrieval method as claimed in any one of claims 1 to 5.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as information retrieval method as claimed in any one of claims 1 to 5 is realized when execution.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811610513.9A CN109739963A (en) | 2018-12-27 | 2018-12-27 | Information retrieval method, device, equipment and medium |
| PCT/CN2019/118929 WO2020134684A1 (en) | 2018-12-27 | 2019-11-15 | Information retrieval method, apparatus, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811610513.9A CN109739963A (en) | 2018-12-27 | 2018-12-27 | Information retrieval method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109739963A true CN109739963A (en) | 2019-05-10 |
Family
ID=66360160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811610513.9A Pending CN109739963A (en) | 2018-12-27 | 2018-12-27 | Information retrieval method, device, equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109739963A (en) |
| WO (1) | WO2020134684A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866091A (en) * | 2019-11-19 | 2020-03-06 | 杭州数梦工场科技有限公司 | Data retrieval method and device |
| CN111046130A (en) * | 2019-11-08 | 2020-04-21 | 杭州安恒信息技术股份有限公司 | Association retrieval method combining ElasticSearch and FSM |
| CN111126073A (en) * | 2019-12-23 | 2020-05-08 | 中国建设银行股份有限公司 | Semantic retrieval method and device |
| WO2020134684A1 (en) * | 2018-12-27 | 2020-07-02 | 苏州龙信信息科技有限公司 | Information retrieval method, apparatus, device and medium |
| CN111475732A (en) * | 2020-04-13 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN111488430A (en) * | 2020-04-07 | 2020-08-04 | 百度在线网络技术（北京）有限公司 | Event data processing method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2779349A1 (en) * | 2012-06-06 | 2013-12-06 | Ibm Canada Limited - Ibm Canada Limitee | Predictive analysis by example |
| CN103577420A (en) * | 2012-07-23 | 2014-02-12 | ***通信集团上海有限公司 | Method and device for inquiring user information dynamically |
| CN104657439A (en) * | 2015-01-30 | 2015-05-27 | 欧阳江 | Generation system and method for structured query sentence used for precise retrieval of natural language |
| CN104809254A (en) * | 2015-05-19 | 2015-07-29 | 郑州悉知信息技术有限公司 | Data query method and device |
| CN105488096A (en) * | 2014-10-02 | 2016-04-13 | 谷歌公司 | Dynamic summary generator |
| CN107766483A (en) * | 2017-10-13 | 2018-03-06 | 华中科技大学 | The interactive answering method and system of a kind of knowledge based collection of illustrative plates |
| CN107885844A (en) * | 2017-11-10 | 2018-04-06 | 南京大学 | Automatic question-answering method and system based on systematic searching |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| US20180349377A1 (en) * | 2017-06-03 | 2018-12-06 | Apple Inc. | Converting natural language input to structured queries |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598445B (en) * | 2013-11-01 | 2019-05-10 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| US10586156B2 (en) * | 2015-06-25 | 2020-03-10 | International Business Machines Corporation | Knowledge canvassing using a knowledge graph and a question and answer system |
| CN109739963A (en) * | 2018-12-27 | 2019-05-10 | 苏州龙信信息科技有限公司 | Information retrieval method, device, equipment and medium |
-
2018
- 2018-12-27 CN CN201811610513.9A patent/CN109739963A/en active Pending
-
2019
- 2019-11-15 WO PCT/CN2019/118929 patent/WO2020134684A1/en active Application Filing
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2779349A1 (en) * | 2012-06-06 | 2013-12-06 | Ibm Canada Limited - Ibm Canada Limitee | Predictive analysis by example |
| CN103577420A (en) * | 2012-07-23 | 2014-02-12 | ***通信集团上海有限公司 | Method and device for inquiring user information dynamically |
| CN105488096A (en) * | 2014-10-02 | 2016-04-13 | 谷歌公司 | Dynamic summary generator |
| CN104657439A (en) * | 2015-01-30 | 2015-05-27 | 欧阳江 | Generation system and method for structured query sentence used for precise retrieval of natural language |
| CN104809254A (en) * | 2015-05-19 | 2015-07-29 | 郑州悉知信息技术有限公司 | Data query method and device |
| US20180349377A1 (en) * | 2017-06-03 | 2018-12-06 | Apple Inc. | Converting natural language input to structured queries |
| CN107766483A (en) * | 2017-10-13 | 2018-03-06 | 华中科技大学 | The interactive answering method and system of a kind of knowledge based collection of illustrative plates |
| CN107885844A (en) * | 2017-11-10 | 2018-04-06 | 南京大学 | Automatic question-answering method and system based on systematic searching |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
Non-Patent Citations (3)
| Title |
|---|
| 万乐 等: ""类别特征词权重加权文本分类方法"", 《军民两用技术与产品》 * |
| 台德艺 等: ""文本分类特征权重改进算法"", 《计算机工程》 * |
| 董慧: ""基于多元权重特征加权的中文文本分类算法"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020134684A1 (en) * | 2018-12-27 | 2020-07-02 | 苏州龙信信息科技有限公司 | Information retrieval method, apparatus, device and medium |
| CN111046130A (en) * | 2019-11-08 | 2020-04-21 | 杭州安恒信息技术股份有限公司 | Association retrieval method combining ElasticSearch and FSM |
| CN111046130B (en) * | 2019-11-08 | 2023-05-23 | 杭州安恒信息技术股份有限公司 | Correlation retrieval method combining elastic search and FSM |
| CN110866091A (en) * | 2019-11-19 | 2020-03-06 | 杭州数梦工场科技有限公司 | Data retrieval method and device |
| CN110866091B (en) * | 2019-11-19 | 2023-07-11 | 杭州数梦工场科技有限公司 | Data retrieval method and device |
| CN111126073A (en) * | 2019-12-23 | 2020-05-08 | 中国建设银行股份有限公司 | Semantic retrieval method and device |
| CN111126073B (en) * | 2019-12-23 | 2023-07-04 | 中国建设银行股份有限公司 | Semantic retrieval method and device |
| CN111488430A (en) * | 2020-04-07 | 2020-08-04 | 百度在线网络技术（北京）有限公司 | Event data processing method, device, equipment and storage medium |
| CN111488430B (en) * | 2020-04-07 | 2023-08-04 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for processing data of event |
| CN111475732A (en) * | 2020-04-13 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Information processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020134684A1 (en) | 2020-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109739963A (en) | Information retrieval method, device, equipment and medium | |
| CN109446513B (en) | Extraction method of events in text based on natural language understanding | |
| US9495345B2 (en) | Methods and systems for modeling complex taxonomies with natural language understanding | |
| WO2020057022A1 (en) | Associative recommendation method and apparatus, computer device, and storage medium | |
| CN108171073B (en) | Private data identification method based on code layer semantic parsing drive | |
| AU2008339587B2 (en) | Data normalisation for investigative data mining | |
| US8868609B2 (en) | Tagging method and apparatus based on structured data set | |
| CN109508458B (en) | Legal entity identification method and device | |
| Nasridinov et al. | A decision tree-based classification model for crime prediction | |
| CN111209411B (en) | Document analysis method and device | |
| CN110929125A (en) | Search recall method, apparatus, device and storage medium thereof | |
| CN110245239A (en) | A kind of construction method and system towards automotive field knowledge mapping | |
| CN114896305A (en) | Smart internet security platform based on big data technology | |
| Nesi et al. | Ge (o) Lo (cator): Geographic information extraction from unstructured text data and Web documents | |
| CN110880142A (en) | Risk entity acquisition method and device | |
| CN113971210B (en) | Data dictionary generation method and device, electronic equipment and storage medium | |
| CN103226601A (en) | Method and device for image search | |
| CN110727764A (en) | Phone operation generation method and device and phone operation generation equipment | |
| Chardonnens et al. | Mining user queries with information extraction methods and linked data | |
| KR20150122855A (en) | Distributed processing system and method for real time question and answer | |
| CN109660621A (en) | A kind of content delivery method and service equipment | |
| KR20220168062A (en) | Article writing soulution using artificial intelligence and device using the same | |
| CN107004002A (en) | According to the set of structural data generation unstructured searching inquiry | |
| CN111752922A (en) | Method and device for establishing knowledge database and realizing knowledge query | |
| CN109960752B (en) | Query method and device in application program, 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 |
Application publication date: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |