WO2020134684A1 - 信息检索方法、装置、设备和介质 - Google Patents

信息检索方法、装置、设备和介质 Download PDF

Info

Publication number
WO2020134684A1
WO2020134684A1 PCT/CN2019/118929 CN2019118929W WO2020134684A1 WO 2020134684 A1 WO2020134684 A1 WO 2020134684A1 CN 2019118929 W CN2019118929 W CN 2019118929W WO 2020134684 A1 WO2020134684 A1 WO 2020134684A1
Authority
WO
WIPO (PCT)
Prior art keywords
event
search
information
sentence
standard
Prior art date
Application number
PCT/CN2019/118929
Other languages
English (en)
French (fr)
Inventor
火玺彩
王新宇
王海啸
荣佑宝
Original Assignee
苏州龙信信息科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 苏州龙信信息科技有限公司 filed Critical 苏州龙信信息科技有限公司
Publication of WO2020134684A1 publication Critical patent/WO2020134684A1/zh

Links

Images

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

Definitions

  • the embodiments of the present invention relate to the technical field of data processing, for example, to an information retrieval method, device, device, and medium.
  • the present application provides an information retrieval method, device, equipment, and medium to achieve efficient retrieval of related feature information described in an event.
  • an embodiment of the present invention provides an information retrieval method.
  • the method includes:
  • an embodiment of the present invention further provides an information retrieval device, which includes:
  • the event attribute determination module is configured to obtain event description information of the event to be checked, and determine the corresponding event attribute according to the event description information;
  • the standard sentence acquisition module is configured to acquire at least one standard retrieval sentence corresponding to the event attribute based on the retrieval associated data table, wherein the retrieval associated data table is obtained according to a generation module set with a retrieval sentence generation strategy;
  • a target sentence determination module configured to determine the acquired standard search sentence as the target search sentence of the event to be checked
  • the feature information search module is configured to retrieve the selected material information library using the target search sentence to obtain feature information of the event to be detected.
  • an embodiment of the present invention further provides a device, the device including:
  • One or more processors are One or more processors;
  • Memory used to store one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the information retrieval method according to any one of the embodiments of the present invention.
  • an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the information retrieval method described in any of the embodiments.
  • This application obtains the event description information of the event to be checked, and determines the corresponding event attribute according to the event description information; based on the search associated data table, obtains at least one standard search sentence corresponding to the event attribute, wherein the search associated data table is based on Obtain a certain search sentence generation strategy; determine the obtained standard search sentence as the target search sentence of the event to be checked; use the target search sentence to search the selected material information library to obtain the characteristic information of the event to be checked; solve the information retrieval process
  • the problem of low reuse rate of retrieval sentences improves the information retrieval efficiency of the characteristic information associated with the event, and thus improves the user experience of information-based case handling.
  • FIG. 1 is a flowchart of steps of the information retrieval method provided in Embodiment 1 of the present invention
  • FIG. 1b is a flow chart of implementation of generating a search-related data table provided in Embodiment 1 of the present invention
  • Embodiment 2 is a flowchart of steps of the information retrieval method provided by Embodiment 2 of the present invention.
  • Embodiment 3 is a schematic structural diagram of an information retrieval device provided in Embodiment 3 of the present invention.
  • FIG. 4 is a schematic structural diagram of a device according to Embodiment 4 of the present invention.
  • FIG. 1 is a flowchart of steps of an information retrieval method according to Embodiment 1 of the present invention. This embodiment can be applied to the case of feature information retrieval.
  • the method can be executed by an information retrieval device and can include the following steps:
  • Step 101 Obtain event description information of an event to be checked, and determine a corresponding event attribute according to the event description information.
  • the event to be checked can be an event that needs to obtain characteristic information based on the event-related data
  • the description information can be a simple description of the event to be checked, which can be generated by the user based on experience or using automated tools based on the content of the event, for example, the event
  • the description can be input by the police handling the case according to the circumstances of the incident as the occurrence of an item loss event
  • the event attribute can be used to reflect the type of the event to be inspected, which can include theft cases, environmental protection cases, security cases and robbery cases.
  • the corresponding description information of the event to be detected can be obtained, and the character type of the event to be detected can be determined by using character matching or a neural network algorithm according to the description information.
  • the event attributes can include theft cases and environmental protection cases. , Security cases and robbery cases, etc.
  • the event attributes can also be generated by analyzing the event-related data by sub-word data, synonymous word data and part-of-speech corpus.
  • the method of acquisition can be to preprocess the event-related data first, including To filter the meaningless content, such as ".#@%##%$2423" and other text, delete the stop words of event-related data, such as carriage returns and spaces, etc.
  • the pre-processing also includes emoticons or images in the relevant data Translate emoji characters, such as emoji characters Can be translated as "crying", and then the event attributes can be extracted from the pre-processed event-related data.
  • the process can divide the words in the event-related data into single words according to the word-separation data pair. If there are similar synonyms in the word, the hash result corresponding to the synonyms in the synonymous words is used as the hash operation result of the word. The word frequency of each word is counted separately, and the weight of each word is calculated.
  • the weight of the key words can be weighted, such as stealing and
  • the key words related to the nature of the incident such as robbery can be weighted using the calculation method of log (total words/key word frequency) to ensure that the key words are determined as event attributes, and finally the hash calculation results and weights using each word can be formed into a vector ,
  • the vector is used as the input of the convolutional neural network, and the convolutional neural network generates the event attributes of the corresponding event.
  • Step 102 Acquire at least one standard retrieval sentence corresponding to the event attribute based on the retrieval associated data table, wherein the retrieval associated data table is obtained according to the set retrieval sentence generation strategy.
  • the search-related data table may be a data table that stores event attributes and standard search sentences corresponding to the event attributes, and the correspondence between event attributes and standard search sentences may include one-to-one, one-to-many, and many-to-many, etc.
  • the search related data table can be obtained according to the set search sentence generation strategy;
  • the standard search sentence can be a preset template query sentence for event feature search, which can be based on the case time of the event to be checked, search keywords, special numbers and And/or data sources to adjust.
  • the standard search statement for retrieving the event to be checked can be found in the data table storing the event attribute and the corresponding standard search statement according to the event attribute corresponding to the event to be checked, where the The number can be one or more.
  • Step 103 Determine the obtained standard search sentence as the target search sentence of the event to be checked.
  • the target search sentence may be a standard search sentence as a template, a query sentence generated after adjustment according to the information of the event to be checked, or a query sentence to retrieve the event to be checked.
  • the obtained standard search sentence may be adjusted according to the relevant information of the event to be checked, and the adjustment method may include changing the search range, search keyword, and case time of the standard search sentence, and may also be included in Based on the standard search sentence, new query conditions are added, such as removing takeaway calls; the adjusted standard search sentence is used as the target search sentence for the event to be checked.
  • the standard search sentence may not be adjusted, and the obtained standard search sentence may be directly used as the target search sentence.
  • Step 104 Use the target search sentence to search the selected material information library to obtain the feature information of the event to be checked.
  • the material information library may be a database that stores information related to the event to be checked, and its acquisition method may include downloading from a software server such as WeChat, QQ, and Fetion or connecting to a smart terminal related to the event to be detected to obtain the information stored in the smart terminal All the information, the characteristic information of the event to be checked may be the iconic information used to characterize the event to be checked, and may include: the occupation, gender, name, physical condition, marital status, common contact person and event details of the person involved in the event.
  • the obtained target search sentence may be used to search in the material information, and the events used to characterize the event to be detected may be obtained by involving the occupation, gender, name, physical condition, marital status, frequently used contacts and characters of the person involved in the event. Event details and other information.
  • the description information of the event to be checked is obtained, and the description information is analyzed to determine the event attribute of the event to be checked.
  • the corresponding standard search statement is obtained in the search-related data table, and the standard statement is used.
  • Determine the target search sentence for retrieving the event to be checked use the target search sentence to search the material information database corresponding to the event to be checked, and obtain the characteristic information of the event to be checked, which solves the problem of low reuse rate of the search sentence in the search process and improves the waiting time Retrieval efficiency of event feature information.
  • this embodiment modifies the retrieval related data table obtained according to the set retrieval sentence generation strategy.
  • the generation of the search-related data table may include the following steps:
  • Step 110 Obtain historical event description information of each historical event in the historical event set.
  • the historical event set may be a set of events that have been searched based on a standard search statement, where the historical event set may be associated with corresponding historical event description information and standard feature information.
  • the description information of each historical event may be read in a stored historical event set using traversal at intervals.
  • the corresponding historical event description information may be read.
  • Step 111 Determine corresponding historical event attributes based on the historical event description information, and record each of the historical event attributes as standard attributes.
  • the historical event attribute may be information used to identify the category to which the historical event belongs, and may include theft cases, environmental protection cases, public security cases, and robbery cases;
  • the standard attributes may be attribute information used to generate the search-related data table, It can be the historical event attribute of the unified text description. For example, if the historical event attribute is theft, then the corresponding standard attribute is the theft case.
  • character matching or a neural network algorithm may be used to determine the historical event attributes of the historical event set based on the descriptions of all historical events in the acquired historical event set, and the historical event attribute information may be merged to generate correspondence Standard attributes of each historical event.
  • the historical event attributes of each historical event may be directly used as their corresponding standard attributes without processing the historical event attributes.
  • Step 112 Based on the standard feature information corresponding to each historical event, determine at least one standard search sentence required to obtain each of the standard feature information.
  • the standard feature information can be the final result of historical event retrieval, and can be stored in the historical event set in association with the historical event attributes.
  • the standard search statement can be generated based on the standard feature information, for example, the feature information is the ID number, then the corresponding The search statement may be a query statement of an ID number.
  • the standard feature information corresponding to each historical event stored in the historical event set can be obtained, and the corresponding standard search sentence can be generated according to the historical feature information.
  • the target search sentence used in the historical event retrieval process can also be stored. Match the stored target search sentences according to the historical feature information, and use the matched storage target search sentences as standard search sentences.
  • Step 113 associatively store each of the standard attributes and corresponding standard search sentences to form a search-related data table.
  • search-related data table may be a data table that stores event attributes and standard search sentences corresponding to the event attributes, and the correspondence between event attributes and standard search sentences may include one-to-one, one-to-many, and many-to-many, etc. .
  • the standard attribute can be used as the primary key for storage, and the standard search statement can be stored according to the standard attribute to generate a search-related data table, where the form of the search-related data table can include files, tables, and databases.
  • FIG. 2 is a flowchart of steps of the information retrieval method provided by Embodiment 2 of the present invention; this embodiment is an embodiment provided on the basis of the above-mentioned embodiment, see FIG. 2, an information provided by the embodiment of the present invention
  • the search methods include:
  • Step 201 Obtain description information of the event to be checked, and extract keywords in the description information.
  • the keyword may be a word used to characterize the category of the event to be detected, such as theft, loss, and injury.
  • a neural network algorithm may be used to extract words used to characterize the event to be detected in the description information of the event to be detected, and the acquired words may be used as keywords.
  • keywords used to extract keywords
  • the neural network algorithm cited in this embodiment is only an example.
  • Step 202 Use the keyword to search for a corresponding event attribute in a preset attribute relationship table, and determine the query result as the event attribute of the event to be checked.
  • the attribute relationship table may be a data table of the correspondence between keywords and event attributes preset in advance, for example, the keyword is lost, the corresponding event attribute is a theft case, and the keyword and event attributes may be a pair 1.
  • One-to-many and many-to-many, that is, one keyword can correspond to one case attribute or multiple case attributes.
  • the corresponding stored event attributes may be searched in the preset attribute relationship table according to the obtained keywords, and the found event attributes are used as the event attributes of the event to be checked.
  • a neural network classification algorithm can be used, and the keywords are used as input to the neural network classification algorithm, and the corresponding output result can be the case attributes of the case to be checked.
  • Step 203 Acquire at least one standard search sentence corresponding to the event attribute based on the search associated data table, wherein the search associated data table is obtained according to the set search sentence generation strategy.
  • Step 204 Obtain the case time, search keyword, special number and/or data source information of the event to be checked.
  • the search keyword can be an automatically generated word or a word determined by the user according to his own experience
  • the special number can be a number directly related to the event.
  • phone number or ID card number the special number can also be the number of interference information that is not related to the event, such as the phone number of takeaway or express delivery
  • the data source can be the data source of the data related to the event, such as from WeChat, SMS, MMS , QQ and household registration information.
  • data such as case time, search keywords, special numbers, and/or data source information input by the user related to the event to be checked can be obtained.
  • the user can add the corresponding parameter information by selecting a label by providing a data label with selectable case time, search keywords, special numbers and/or data source information.
  • Step 205 Generate a corresponding adjustment search sentence based on the case time, search keyword, special number, and/or data source information, and add the adjustment search sentence to the standard search sentence to generate the target search for the event to be checked Statement.
  • the adjustment statement may be a query statement generated according to the obtained case time, search keywords, special numbers, and/or data source information, etc., or may be a supplement to the standard search statement, for example, enter a case Time, you can generate the corresponding query sentence according to the input case time.
  • a corresponding adjustment sentence may be generated based on the acquired case time, search keywords, special numbers, and/or data source information, and the obtained adjustment sentence may be added to a standard search sentence, and the adjusted standard The search sentence is used as the target search sentence.
  • Step 206 Obtain the event data stored in the material information library, and segment the event data to generate an event segmentation set.
  • the event data may be data related to the content of the event to be checked, which may include WeChat messages, SMS messages, MMS messages, QQ messages, transcripts, and usage records of smart terminals, etc.
  • the event segmentation set may be to disconnect the event data After the word is divided into a data set of words.
  • all data related to the event to be detected in the material information library can be obtained, and the connected words of the acquired data can be removed and segmented into words to form an event segmentation set.
  • Step 207 Use the target search sentence to search the event segmentation set to obtain feature information of the event to be detected.
  • the characteristic information may be iconic information used to characterize the event to be checked, and may include: the occupation, gender, name, physical condition, marital status, common contact person and event details of the person involved in the event.
  • the determined target search sentence can be used to query the event segmentation set, and the queried events related to the character's occupation, gender, name, physical condition, marital status, common contacts and event details, etc. Check the characteristic information of the event.
  • the corresponding case attribute is determined by the keyword extracted from the description information of the event to be checked, and the standard search statement is obtained in the search-related data table according to the case attribute.
  • the obtained user's case time and search key Parameters such as words, special numbers and data source information adjust the standard search sentence to determine the target search sentence, use the target search sentence to retrieve the event segmentation set to obtain the corresponding feature information, and improve the search sentence by adjusting the standard search sentence to the target search sentence Accuracy, use the target search sentence to search the event segmentation set, effectively improve the search efficiency.
  • the information retrieval device provided by the embodiment of the present invention can execute the information retrieval method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.
  • the information retrieval device provided by an embodiment of the present invention includes: an event attribute determination module 301, a standard sentence acquisition module 302, a target sentence determination module 303, and a feature information search module 304.
  • the event attribute determination module 301 is configured to obtain event description information of the event to be checked, and determine the corresponding event attribute according to the event description information.
  • the standard sentence acquisition module 302 is configured to acquire at least one standard search sentence corresponding to the event attribute based on a search-related data table, wherein the search-related data table is obtained according to a generation module set with a search sentence generation strategy.
  • the target sentence determination module 303 is configured to determine the acquired standard search sentence as the target search sentence of the to-be-checked event.
  • the feature information search module 304 is configured to retrieve the selected material information library using the target search sentence to obtain feature information of the event to be detected.
  • the description information of the event to be checked is obtained through the event attribute determination module, and the event attribute of the event to be checked is determined according to the description information.
  • the standard statement acquisition module obtains the corresponding standard search statement from the associated data table according to the event attribute.
  • the target sentence determination module determines the target retrieval sentence for retrieval according to the standard retrieval sentence, and the feature information search module uses the target retrieval sentence to retrieve the material information library corresponding to the event to be checked, to obtain the feature information of the event to be checked, and improves the retrieval sentence in event retrieval
  • the repeated utilization rate in the system can effectively improve the retrieval efficiency of feature information.
  • the generation module includes:
  • the description information acquiring unit is configured to acquire historical event description information of each historical event in the historical event set.
  • the standard attribute acquisition unit is configured to determine a corresponding historical event attribute based on each historical event description information, and respectively record each of the historical event attributes as a standard attribute.
  • the standard sentence acquiring unit is configured to determine at least one standard search sentence required to obtain each of the standard feature information based on the standard feature information corresponding to each historical event.
  • the search-related data table generating unit is configured to store each of the standard attributes and corresponding standard search sentences in an associated manner to form a search-related data table.
  • the target sentence determination module 303 includes:
  • the information acquisition unit is configured to acquire the case time, search keywords, special numbers and/or data source information of the event to be checked.
  • the search sentence adjustment unit is configured to generate a corresponding adjustment search sentence based on the case time, search keyword, special number and/or data source information, add the adjustment search sentence to the standard search sentence to generate the pending Check the target search statement of the event.
  • the feature information search module 304 includes:
  • the event attribute determination module 301 includes:
  • FIG. 4 is a schematic structural diagram of a device according to Embodiment 4 of the present invention.
  • the device includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the device may be One or more, one processor 70 is taken as an example in FIG. 4; the processor 70, the memory 71, the input device 72, and the output device 73 in the device may be connected through a bus or other means, and FIG. 4 is taken as an example through a bus connection .
  • the memory 71 as a computer-readable storage medium can be used to store software programs, computer executable programs, and modules, such as program instructions/modules corresponding to the information retrieval method in the embodiments of the present invention (for example, the information retrieval device includes: event attributes The determination module 301, the standard sentence acquisition module 302, the target sentence determination module 303, and the feature information search module 304).
  • the processor 70 executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in the memory 71, that is, implementing the above-mentioned information retrieval method.
  • the memory 71 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system and application programs required for at least one function; the storage data area may store data created according to the use of the terminal, and the like.
  • the memory 71 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device.
  • the memory 71 may include memories remotely provided with respect to the processor 70, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 72 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the device.
  • the output device 73 may include a display device such as a display screen.
  • Embodiment 5 of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor are used to execute an information retrieval method, the method including:
  • a storage medium containing computer-executable instructions provided by an embodiment of the present invention can also perform relevant operations in the information retrieval method provided by any embodiment of the present application.

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

一种信息检索方法、装置、设备和介质。该方法包括：获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性（101）；基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句（102），其中，所述检索关联数据表根据设定的检索语句生成策略获得；将获取的所述标准检索语句确定为所述待检事件的目标检索语句（103）；采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息（104）。

Description

信息检索方法、装置、设备和介质
本公开要求在2018年12月27日提交中国专利局、申请号为201811610513.9的中国专利申请的优先权，以上申请的全部内容通过引用结合在本公开中。
技术领域
本发明实施例涉及数据处理技术领域，例如涉及一种信息检索方法、装置、设备和介质。
背景技术
随着社会的进步和经济的发展，传统的公安办案方法已经不能满足当前打击犯罪、预防犯罪和社会治安管理的要求，急需科技手段来提高民警的办案效率，例如，通过报案人的案件描述，通过信息检索，很快检索确定出案件涉及犯案人员的特征信息。
加强信息化建设，有助于提高公安机关对犯罪份子的打击，有效预防犯罪发生，但是相关技术中的公安信息检索系统，各案件检索过程独立，检索过程中使用的检索条件无法重复利用，存在办案效率较低的问题。
发明内容
本申请提供一种信息检索方法、装置、设备和介质，以实现事件所述关联特征信息的高效检索。
第一方面，本发明实施例提供了一种信息检索方法，该方法包括：
获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；
基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定的检索语句生成策略获得；
将获取的所述标准检索语句确定为所述待检事件的目标检索语句；
采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
第二方面，本发明实施例还提供了信息检索装置，该装置包括：
事件属性确定模块，被设置为获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；
标准语句获取模块，被设置为基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定有检索语句生成策略的生成模块获得；
目标语句确定模块，被设置为将获取的所述标准检索语句确定为所述待检事件的目标检索语句；
特征信息搜索模块，被设置为采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
第三方面，本发明实施例还提供了一种设备，所述设备包括：
一个或多个处理器；
存储器，用于存储一个或多个程序；
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如本发明实施例中任一所述的信息检索方法。
第四方面，本发明实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现实施例中任一所述的信息检索方法。
本申请通过获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；基于检索关联数据表，获取该事件属性对应的至少一条标准检索语句，其中，检索关联数据表根据设定的检索语句生成策略获得；将获取的标准检索语句确定为待检事件的目标检索语句；采用目标检索语句检索选定的素材信息库，获得待检事件的特征信息；解决了信息检索过程中检索语句重复使用率低的问题，提高了事件所关联特征信息的信息检索效率，进而提升了信息化办案的用户体验。
附图说明
图1是本发明实施例一提供的信息检索方法的步骤流程图；
图1b是本发明实施例一提供的生成检索关联数据表的实现流程图；
图2是本发明实施例二提供的信息检索方法的步骤流程图；
图3是本发明实施例三提供的信息检索装置的结构示意图；
图4是本发明实施例四提供的一种设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此 处所描述的具体实施例仅仅用于解释本申请，而非对本申请的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
实施例一
图1是本发明实施例一提供的信息检索方法的步骤流程图，本实施例可适用于特征信息检索的情况，该方法可以由信息检索装置来执行，可以包括如下步骤：
步骤101、获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性。
需要说明的是，待检事件可以是需要根据事件相关数据获取特征信息的事件；描述信息可以是对待检事件的简单描述，可以由用户根据经验生成或使用自动化工具根据事件内容生成，例如，事件描述可以由办案民警根据事件的案情输入为发生了物品丢失事件；事件属性可以是用于反映待检事件所属类型的信息，可以包括偷盗案件、环保案件、治安案件和抢劫案件等。
在一些实施例中，可以获取待检事件的对应的描述信息，根据描述信息采用字符匹配或者神经网络算法确定待检事件的所属的事件类型，示例性的，事件属性可以包括偷盗案件、环保案件、治安案件和抢劫案件等，可选的，事件属性还可以由分词语料、近义词语料和词性语料共同分析事件相关的数据生成，获取的方式可以是先对事件相关数据进行预处理，包括中的无意义内容进行过滤，例如过滤“.#@％##％$2423”等文字，删除事件相关数据的停用词，如回车和空格等，预处理还包括将相关数据中的表情图像或者表情字符进行翻译，例如表情字符
Figure PCTCN2019118929-appb-000001
可以翻译成“哭泣”，然后可以在经过预处理后的事件相关数据中提取事件属性，其过程可以根据分词语料对将事件相关数据内的词语分割为单个的词语，该词语若在近义词语料中存在相近的近义词，则使用近义词语料中近义词对应的哈希结果作为该词语的哈希运算结果，分别统计各词语的词频，计算各词语的权重，可以对重点词语的权重加权，例如偷盗和抢劫等与事件性质相关的重点词语可以使用log(词语总数/重点词语词频)的计算方式进行加权，确保重点词语被确定为事件属性，最后可以将使用各词语的哈希计算结果和权重形成向量，将该向量作为卷积神经网络的输入，由卷积神经网络生成对应事件的事件属性。
步骤102、基于检索关联数据表，获取所述事件属性对应的至少一条标准检 索语句，其中，所述检索关联数据表根据设定的检索语句生成策略获得。
需要说明的是，检索关联数据表可以是存储有事件属性和事件属性对应的标准检索语句的数据表，事件属性和标准检索语句的对应关系可以包括一对一、一对多和多对多等，检索关联数据表可以根据设定的检索语句生成策略获得；标准检索语句可以是预设的用于事件特征检索的模板查询语句，可以依据待检事件的案件时间、搜索关键字、特殊号码和/或数据来源进行调整。
在一些实施例中，可以根据待检事件对应的事件属性在存储有事件属性和对应标准检索语句的数据表中查找用于检索待检事件的标准检索语句，其中，查询到对应待检事件的条数可以为一条或多条。
步骤103、将获取的所述标准检索语句确定为所述待检事件的目标检索语句。
需要说明的是，目标检索语句可以是以标准检索语句为模板，依据待检事件的信息调整后生成的查询语句，可以是进行检索待检事件的查询语句。
在一些实施例中，可以依据待检事件的相关信息对获取到的标准检索语句进行调整，调整的方式可以包括改变标准检索语句的检索范围、检索关键字和案件时间等信息，还可以包括在标准检索语句的基础上增加新的查询条件，例如去除外卖电话；将调整后的标准检索语句作为待检事件的目标检索语句。
一种可选的实施方式，可以不对标准检索语句进行调整，直接将获取到的标准检索语句作为目标检索语句。
步骤104、采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
需要说明的是，素材信息库可以是存储有待检事件相关信息的数据库，其获取的方式可以包括从微信、QQ和飞信等软件服务器下载或连接待检事件相关的智能终端获取智能终端中存储的所有信息，待检事件的特征信息可以是用于表征待检事件标志性的信息，可以包括：事件涉及人物的职业、性别、姓名、身体状况、婚姻状况、常用联系人和事件详细情况等。
在一些实施例中，可以使用获取到的目标检索语句在素材信息中进行检索，获取用于表征待检事件特征的事件涉及人物的职业、性别、姓名、身体状况、婚姻状况、常用联系人和事件详细情况等信息。
本实施例的技术方案，通过获取到待检事件的描述信息，对描述信息进行分析确定待检事件的事件属性，根据事件属性在检索关联数据表中获取到对应的标准检索语句，使用标准语句确定用于检索待检事件的目标检索语句，使用 目标检索语句检索待检事件对应的素材信息库，获取待检事件的特征信息，解决了搜索过程中检索语句重复利用率低问题，提高了待检事件特征信息的检索效率。
在上述技术方案的基础上，本实施例对根据设定的检索语句生成策略获得检索关联数据表，进行了改动，图1b是本发明实施例一提供的生成检索关联数据表的实现流程图，如图1b所示，检索关联数据表的生成可以包括以下步骤：
步骤110、获取历史事件集中各历史事件的历史事件描述信息。
需要说明的是，历史事件集可以是基于标准检索语句进行过检索的事件的集合，其中，历史事件集中可关联存储有对应的历史事件描述信息和标准特征信息。
在一些实施例中，可以每隔一段时间在存储的历史事件集中使用遍历的方式读取各历史事件的描述信息。一种可选的实施方式，可以每当有新的历史事件产生时读取其对应的历史事件描述信息。
步骤111、基于各所述历史事件描述信息确定对应的历史事件属性，并分别记各所述历史事件属性为标准属性。
需要说明的是，历史事件属性可以是用于标识历史事件所属类别的信息，可以包括偷盗案件、环保案件、治安案件和抢劫案件等；标准属性可以是用于生成检索关联数据表的属性信息，可以是统一文字描述的历史事件属性，例如，历史事件属性为偷窃，那么其对应的标准属性为偷盗案件。
在一些实施例中，可以使用字符匹配或者神经网络算法根据获取到的历史事件集中所有的各历史事件的描述确定历史事件集的历史事件属性，可以对各历史事件属性信息进行合并整理，生成对应各历史事件的标准属性。一种可选的实施方式，可以不对历史事件属性进行处理，直接将获取到的各历史事件的历史事件属性作为其对应的标准属性。
步骤112、基于各所述历史事件对应的标准特征信息，确定至少一条获得各所述标准特征信息所需的标准检索语句。
需要说明的是，标准特征信息可以是历史事件检索的最终结果，可以和历史事件属性关联存储于历史事件集，标准检索语句可以是根据标准特征信息生成，例如特征信息为身份证号，则对应检索语句可以是身份证号的查询语句。
在一些实施例中，可以获取历史事件集存储的对应各历史事件的标准特征信息，根据历史特征信息生成对应的标准检索语句，可选的，还可以存储历史 事件检索过程使用的目标检索语句，根据历史特征信息在存储的目标检索语句进行匹配，将匹配到的存储目标检索语句作为标准检索语句。
步骤113、关联存储各所述标准属性及对应的标准检索语句，形成检索关联数据表。
需要说明的是，检索关联数据表可以是存储有事件属性和事件属性对应的标准检索语句的数据表，事件属性和标准检索语句的对应关系可以包括一对一、一对多和多对多等。
在一些实施例中，可以将标准属性作为存储的主键，标准检索语句可以依据标准属性进行存储，生成检索关联数据表，其中，检索关联数据表的形式可以包括文件、表格和数据库等。
实施例二
图2是本发明实施例二提供的信息检索方法的步骤流程图；本实施例是在上述实施例的基础上，提供的一种实施例，参见图2，本发明实施例提供的一种信息检索方法包括：
步骤201、获取待检事件的描述信息，提取所述描述信息中的关键字。
需要说明的是，关键字可以是用于表征待检事件所属类别特征的词语，如偷盗、丢失和伤害等。
在一些实施例中，可以使用神经网络算法在待检事件的描述信息中提取用于表征待检事件特征的词语，将获取到的词语作为关键字，可以理解的提取关键字方法具有多种，本实施方式举出的神经网络算法仅为示例。
步骤202、使用所述关键字在预设的属性关系表查找对应的事件属性，将查询结果确定为所述待检事件的事件属性。
需要说明的是，属性关系表可以提前预设的关键字与事件属性之间对应关系的数据表，例如，关键字为丢失，其对应的事件属性为偷盗案件，关键字和事件属性可以一对一、一对多和多对多，也就是一个关键字可以对应一个案件属性也可以对应多个案件属性。
在一些实施例中，可以根据获取到的关键字在预设的属性关系表中查找其对应存储的事件属性，将查找到的事件属性作为待检事件的事件属性，在一些实施例中，为了获取关键字与案件属性之间的对应关系，可以采用神经网络分类算法，将关键字作为神经网络分类算法的输入，其对应得输出结果可以为待检案件得案件属性。
步骤203、基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定的检索语句生成策略获得。
步骤204、获取所述待检事件的案件时间、搜索关键字、特殊号码和/或数据来源信息。
需要说明的是，案件时间可以是待检事件发生的时间或者报警时间，搜索关键字可以是自动生成的字词或用户根据自身经验确定的字词，特殊号码可以是有事件直接相关的号码，例如电话号码或身份证号码等，特殊号码还可以是与事件不相关的干扰信息的号码，例如外卖或者快递的电话号码，数据来源可以是事件涉及数据的数据来源，例如来自微信、短信、彩信、QQ和户籍信息等。
在一些实施例中，可以获取用户输入的与待检事件相关的案件时间、搜索关键字、特殊号码和/或数据来源信息等数据。在一些实施例中，可以通过提供可选的案件时间、搜索关键字、特殊号码和/或数据来源信息的数据标签，由用户通过选择标签的形式添加对应的参数信息。
步骤205、根据所述案件时间、搜索关键字、特殊号码和/或数据来源信息生成对应的调整检索语句，将所述调整检索语句添加进所述标准检索语句生成所述待检事件的目标检索语句。
需要说明的是，调整语句可以是根据获取到的案件时间、搜索关键字、特殊号码和/或数据来源信息等数据对应生成的查询语句，可以是标准检索语句的补充内容，例如，输入一个案件时间，可以根据输入案件时间生成对应的查询语句。
在一些实施例中，可以根据获取到的案件时间、搜索关键字、特殊号码和/或数据来源信息生成对应的调整语句，将获取到的调整语句补充进标准检索语句，将进行调整后的标准检索语句作为目标检索语句。
步骤206、获取所述素材信息库存储的事件数据，分割所述事件数据生成事件分词集。
需要说明的是，事件数据可以是待检事件相关内容的数据，可以包括微信消息、短信消息、彩信消息、QQ消息、笔录和智能终端的使用记录等，事件分词集可以是将事件数据去除连接词后分割为单词的数据集合。
在一些实施例中，可以获取素材信息库中与待检事件相关的所有数据，可以去除获取到数据的连接词并分割成单词，形成事件分词集。
步骤207、使用所述目标检索语句对所述事件分词集进行检索获取所述待检 事件的特征信息。
需要说明的是，特征信息可以是用于表征待检事件标志性的信息，可以包括：事件涉及人物的职业、性别、姓名、身体状况、婚姻状况、常用联系人和事件详细情况等。
在一些实施例中，可以使用确定的目标检索语句对事件分词集进行查询，将查询到的事件涉及人物的职业、性别、姓名、身体状况、婚姻状况、常用联系人和事件详细情况等作为待检事件的特征信息。
本发明实施例的技术方案，通过在待检事件描述信息中提取的关键字确定对应的案件属性，根据案件属性在检索关联数据表中获取标准检索语句，获取到的用户的案件时间、搜索关键字、特殊号码和数据来源信息等参数对标准检索语句进行调整确定目标检索语句，使用目标检索语句检索事件分词集获取对应的特征信息，通过将标准检索语句调整为目标检索语句提高了检索语句的准确度，使用目标检索语句对事件分词集进行检索，有效提高检索效率。
实施例三
图3是本发明实施例三提供的信息检索装置的结构示意图。本发明实施例所提供的信息检索装置可执行本申请任意实施例所提供的信息检索方法，具备执行方法相应的功能模块和有益效果。参见图3，本发明实施例提供的信息检索装置包括：事件属性确定模块301、标准语句获取模块302、目标语句确定模块303和特征信息搜索模块304。
其中，事件属性确定模块301，被设置为获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性。
标准语句获取模块302，被设置为基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定有检索语句生成策略的生成模块获得。
目标语句确定模块303，被设置为将获取的所述标准检索语句确定为所述待检事件的目标检索语句。
特征信息搜索模块304，被设置为采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
本实施例的技术方案，通过事件属性确定模块获取待检事件的描述信息，根据描述信息确定待检事件的事件属性，标准语句获取模块根据事件属性在检索关联数据表获取对应的标准检索语句，目标语句确定模块根据标准检索语句 确定用于检索的目标检索语句，特征信息搜索模块使用目标检索语句检索待检事件对应的素材信息库，获取待检事件的特征信息，提高了检索语句在事件检索中的重复利用率，有效提高特征信息的检索效率。
在一些实施例中，所述生成模块包括:
描述信息获取单元，被设置为获取历史事件集中各历史事件的历史事件描述信息。
标准属性获取单元，被设置为基于各所述历史事件描述信息确定对应的历史事件属性，并分别记各所述历史事件属性为标准属性。
标准语句获取单元，被设置为基于各所述历史事件对应的标准特征信息，确定至少一条获得各所述标准特征信息所需的标准检索语句。
检索关联数据表生成单元，被设置为关联存储各所述标准属性及对应的标准检索语句，形成检索关联数据表。
在一些实施例中，所述目标语句确定模块303包括：
信息获取单元，被设置为获取所述待检事件的案件时间、搜索关键字、特殊号码和/或数据来源信息。
搜索语句调整单元，被设置为根据所述案件时间、搜索关键字、特殊号码和/或数据来源信息生成对应的调整检索语句，将所述调整检索语句添加进所述标准检索语句生成所述待检事件的目标检索语句。
在一些实施例中，所述特征信息搜索模块304包括：
获取所述素材信息库存储的事件数据，分割所述事件数据生成事件分词集。
使用所述目标检索语句对所述事件分词集进行检索获取所述待检事件的特征信息。
在一些实施例中，所述事件属性确定模块301，包括：
获取所述待检事件的描述信息，提取所述描述信息中的关键字。
使用所述关键字在预设的属性关系表查找对应的事件属性，将查询结果确定为所述待检事件的事件属性。
实施例四
图4是本发明实施例四提供的一种设备的结构示意图，如图4所示，该设备包括处理器70、存储器71、输入装置72和输出装置73；设备中处理器70的数量可以是一个或多个，图4中以一个处理器70为例；设备中的处理器70、存储器71、输入装置72和输出装置73可以通过总线或其他方式连接，图4中以 通过总线连接为例。
存储器71作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序以及模块，如本发明实施例中的信息检索方法对应的程序指令/模块(例如，信息检索装置包括：事件属性确定模块301、标准语句获取模块302、目标语句确定模块303和特征信息搜索模块304)。处理器70通过运行存储在存储器71中的软件程序、指令以及模块，从而执行设备的各种功能应用以及数据处理，即实现上述的信息检索方法。
存储器71可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器71可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器71可包括相对于处理器70远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例包括互联网、企业内部网、局域网、移动通信网及其组合。
输入装置72可用于接收输入的数字或字符信息，以及产生与设备的用户设置以及功能控制有关的键信号输入。输出装置73可包括显示屏等显示设备。
实施例五
本发明实施例五还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种信息检索方法，该方法包括：
获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；
基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定的检索语句生成策略获得；
将获取的所述标准检索语句确定为所述待检事件的目标检索语句；
采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
当然,本发明实施例所提供的一种包含计算机可执行指令的存储介质,其计算机可执行指令，还可以执行本申请任意实施例所提供的信息检索方法中的相关操作。
通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到， 本申请可借助软件及必需的通用硬件来实现，当然也可以通过硬件实现，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、闪存(FLASH)、硬盘或光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
值得注意的是，上述信息检索装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的名称也只是为了便于相互区分，并不用于限制本申请的保护范围。

Claims (10)

  1. 一种信息检索方法，包括：
    获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；
    基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定的检索语句生成策略获得；
    将获取的所述标准检索语句确定为所述待检事件的目标检索语句；
    采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
  2. 根据权利要求1所述的方法，其中，所述根据设定的检索语句生成策略获得检索关联数据表，包括：
    获取历史事件集中每个历史事件的历史事件描述信息；
    基于每个所述历史事件描述信息确定对应的历史事件属性，并分别记每个所述历史事件属性为标准属性；
    基于每个所述历史事件对应的标准特征信息，确定至少一条获得每个所述标准特征信息所需的标准检索语句；
    关联存储每个所述标准属性及对应的标准检索语句，形成检索关联数据表。
  3. 根据权利要求1所述的方法，其中，所述将获取的所述标准检索语句确定为所述待检事件的目标检索语句，包括：
    获取所述待检事件的案件时间、搜索关键字、特殊号码和数据来源信息中至少之一；根据所述案件时间、搜索关键字、特殊号码和数据来源信息中至少之一生成对应的调整检索语句，将所述调整检索语句添加进所述标准检索语句生成所述待检事件的目标检索语句。
  4. 根据权利要求1所述的方法，其中，所述采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息，包括：
    获取所述素材信息库存储的事件数据，分割所述事件数据生成事件分词集；
    使用所述目标检索语句对所述事件分词集进行检索获取所述待检事件的特征信息。
  5. 根据权利要求1所述的方法，其中，所述获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性，包括：
    获取所述待检事件的描述信息，提取所述描述信息中的关键字；
    使用所述关键字在预设的属性关系表查找对应的事件属性，将查询结果确 定为所述待检事件的事件属性。
  6. 一种信息检索装置，包括：
    事件属性确定模块，被设置为获取待检事件的事件描述信息，根据所述事件描述信息确定对应的事件属性；
    标准语句获取模块，被设置为基于检索关联数据表，获取所述事件属性对应的至少一条标准检索语句，其中，所述检索关联数据表根据设定有检索语句生成策略的生成模块获得；
    目标语句确定模块，被设置为将获取的所述标准检索语句确定为所述待检事件的目标检索语句；
    特征信息搜索模块，被设置为采用所述目标检索语句检索选定的素材信息库，获得所述待检事件的特征信息。
  7. 根据权利要求6所述的装置，其中，所述生成模块包括：
    描述信息获取单元，被设置为获取历史事件集中每个历史事件的历史事件描述信息；
    标准属性获取单元，被设置为基于每个所述历史事件描述信息确定对应的历史事件属性，并分别记每个所述历史事件属性为标准属性；
    标准语句获取单元，被设置为基于每个所述历史事件对应的标准特征信息，确定至少一条获得每个所述标准特征信息所需的标准检索语句；
    检索关联数据表生成单元，被设置为关联存储每个所述标准属性及对应的标准检索语句，形成检索关联数据表。
  8. 根据权利要求6所述的装置，其中，所述目标语句确定模块包括：
    信息获取单元，被设置为获取所述待检事件的案件时间、搜索关键字、特殊号码和数据来源信息中至少之一；
    搜索语句调整单元，被设置为根据所述案件时间、搜索关键字、特殊号码和数据来源信息中至少之一生成对应的调整检索语句，将所述调整检索语句添加进所述标准检索语句生成所述待检事件的目标检索语句。
  9. 一种设备，所述设备包括：
    一个或多个处理器；
    存储器，用于存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-5中任一所述的信息检索方法。
  10. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如权利要求1-5中任一所述的信息检索方法。
PCT/CN2019/118929 2018-12-27 2019-11-15 信息检索方法、装置、设备和介质 WO2020134684A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811610513.9 2018-12-27
CN201811610513.9A CN109739963A (zh) 2018-12-27 2018-12-27 信息检索方法、装置、设备和介质

Publications (1)

Publication Number Publication Date
WO2020134684A1 true WO2020134684A1 (zh) 2020-07-02

Family

ID=66360160

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/118929 WO2020134684A1 (zh) 2018-12-27 2019-11-15 信息检索方法、装置、设备和介质

Country Status (2)

Country Link
CN (1) CN109739963A (zh)
WO (1) WO2020134684A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109739963A (zh) * 2018-12-27 2019-05-10 苏州龙信信息科技有限公司 信息检索方法、装置、设备和介质
CN111046130B (zh) * 2019-11-08 2023-05-23 杭州安恒信息技术股份有限公司 结合ElasticSearch和FSM的关联检索方法
CN110866091B (zh) * 2019-11-19 2023-07-11 杭州数梦工场科技有限公司 一种数据检索方法及装置
CN111126073B (zh) * 2019-12-23 2023-07-04 中国建设银行股份有限公司 语义检索方法和装置
CN111488430B (zh) * 2020-04-07 2023-08-04 百度在线网络技术（北京）有限公司 事件的数据处理的方法、装置、设备以及存储介质
CN111475732B (zh) * 2020-04-13 2023-07-14 深圳市雅阅科技有限公司 一种信息处理方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577420A (zh) * 2012-07-23 2014-02-12 中国移动通信集团上海有限公司 一种用户信息动态查询方法及装置
CN104598445A (zh) * 2013-11-01 2015-05-06 腾讯科技（深圳）有限公司 自动问答系统和方法
US20160378851A1 (en) * 2015-06-25 2016-12-29 International Business Machines Corporation Knowledge Canvassing Using a Knowledge Graph and a Question and Answer System
CN107766483A (zh) * 2017-10-13 2018-03-06 华中科技大学 一种基于知识图谱的交互式问答方法及系统
CN107885844A (zh) * 2017-11-10 2018-04-06 南京大学 基于分类检索的自动问答方法及系统
CN109739963A (zh) * 2018-12-27 2019-05-10 苏州龙信信息科技有限公司 信息检索方法、装置、设备和介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2779349C (en) * 2012-06-06 2019-05-07 Ibm Canada Limited - Ibm Canada Limitee Predictive analysis by example
US9965474B2 (en) * 2014-10-02 2018-05-08 Google Llc Dynamic summary generator
CN104657439B (zh) * 2015-01-30 2019-12-13 欧阳江 用于自然语言精准检索的结构化查询语句生成系统及方法
CN104809254A (zh) * 2015-05-19 2015-07-29 郑州悉知信息技术有限公司 一种数据查询方法及装置
US10691685B2 (en) * 2017-06-03 2020-06-23 Apple Inc. Converting natural language input to structured queries
CN107885874B (zh) * 2017-11-28 2020-09-29 上海智臻智能网络科技股份有限公司 数据查询方法和装置、计算机设备及计算机可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577420A (zh) * 2012-07-23 2014-02-12 中国移动通信集团上海有限公司 一种用户信息动态查询方法及装置
CN104598445A (zh) * 2013-11-01 2015-05-06 腾讯科技（深圳）有限公司 自动问答系统和方法
US20160378851A1 (en) * 2015-06-25 2016-12-29 International Business Machines Corporation Knowledge Canvassing Using a Knowledge Graph and a Question and Answer System
CN107766483A (zh) * 2017-10-13 2018-03-06 华中科技大学 一种基于知识图谱的交互式问答方法及系统
CN107885844A (zh) * 2017-11-10 2018-04-06 南京大学 基于分类检索的自动问答方法及系统
CN109739963A (zh) * 2018-12-27 2019-05-10 苏州龙信信息科技有限公司 信息检索方法、装置、设备和介质

Also Published As

Publication number Publication date
CN109739963A (zh) 2019-05-10

Similar Documents

Publication Publication Date Title
WO2020134684A1 (zh) 信息检索方法、装置、设备和介质
CN109670163B (zh) 信息识别方法、信息推荐方法、模板构建方法及计算设备
US10127453B2 (en) Automatically detecting an event and determining whether the event is a particular type of event
CN109582861B (zh) 一种数据隐私信息检测系统
WO2017097231A1 (zh) 话题处理方法及装置
WO2021120627A1 (zh) 数据搜索匹配方法、装置、计算机设备和存储介质
WO2019148712A1 (zh) 钓鱼网站检测方法、装置、计算机设备和存储介质
CN107832440B (zh) 一种数据挖掘方法、装置、服务器及计算机可读存储介质
CN109947903B (zh) 一种成语查询方法及装置
CN114722137A (zh) 基于敏感数据识别的安全策略配置方法、装置及电子设备
US10250550B2 (en) Social message monitoring method and apparatus
CN114547257B (zh) 类案匹配方法、装置、计算机设备及存储介质
CN112492606A (zh) 垃圾短信的分类识别方法、装置、计算机设备及存储介质
CN113971210B (zh) 一种数据字典生成方法、装置、电子设备及存储介质
US20160246794A1 (en) Method for entity-driven alerts based on disambiguated features
CN110019763B (zh) 文本过滤方法、系统、设备及计算机可读存储介质
CN110399464B (zh) 一种相似新闻判别方法、系统及电子设备
WO2021103594A1 (zh) 一种默契度检测方法、设备、服务器及可读存储介质
CN111984797A (zh) 客户身份识别装置及方法
CN111752922A (zh) 一种建立知识数据库、实现知识查询的方法及装置
CN108875050B (zh) 面向文本的数字取证分析方法、装置和计算机可读介质
CN114461763B (zh) 一种基于突发词聚类的网络安全事件抽取方法
CN115544214A (zh) 一种事件处理方法、设备及计算机可读存储介质
WO2017143979A1 (zh) 图像的检索方法及装置
CN115129864A (zh) 文本分类方法、装置、计算机设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19905734

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19905734

Country of ref document: EP

Kind code of ref document: A1