WO2021063087A1 - 数据处理方法、装置、存储介质及电子设备 - Google Patents

数据处理方法、装置、存储介质及电子设备 Download PDF

Info

Publication number
WO2021063087A1
WO2021063087A1 PCT/CN2020/103211 CN2020103211W WO2021063087A1 WO 2021063087 A1 WO2021063087 A1 WO 2021063087A1 CN 2020103211 W CN2020103211 W CN 2020103211W WO 2021063087 A1 WO2021063087 A1 WO 2021063087A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
task
question
knowledge base
processing
Prior art date
Application number
PCT/CN2020/103211
Other languages
English (en)
French (fr)
Inventor
葛婷
Original Assignee
北京国双科技有限公司
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 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Publication of WO2021063087A1 publication Critical patent/WO2021063087A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2455Query execution
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/45Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • G06N5/022Knowledge engineering; Knowledge acquisition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02Agriculture; Fishing; Forestry; Mining

Definitions

  • the present invention relates to data processing technology, and more specifically, to a data processing method, device, storage medium and electronic equipment.
  • the oil and gas field is an important sub-field in the industrial field. How to conduct more efficient and high-quality exploitation of the discovered oil fields is one of the goals that those skilled in the art are always committed to.
  • a data processing method including:
  • problem data does not include a problem task, directly retrieve the basic data corresponding to the problem data in the knowledge base and return;
  • the problem data includes a problem task
  • corresponding task processing is performed on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task, and the task processing result is obtained and returned.
  • the method before determining whether the problem data includes a problem task, the method further includes:
  • the direct search and return of the basic data corresponding to the question data in the knowledge base includes:
  • the basic data corresponding to the question data is directly retrieved from the entry of the knowledge base and returned.
  • the method further includes:
  • the determined task processing is performed on the basic data.
  • the task processing includes at least one of the following: combination, inference, and calculation.
  • the calculation is completed according to the preset calculation formula, wherein the preset formula is passed Historical knowledge accumulation and expert summary methods collect and enter the calculation formulas in the knowledge base.
  • a data processing device includes:
  • Problem acquisition module used to acquire problem data
  • the problem decomposition module is used to decompose the problem data
  • the task judgment module is used for judging whether the problem data contains problem tasks based on the result of decomposition
  • the first processing module is configured to directly retrieve and return basic data corresponding to the problem data in the knowledge base when the problem data does not include a problem task;
  • the second processing module is used to perform corresponding task processing on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task when the problem data includes a problem task, to obtain a task Process the result and return.
  • An electronic device including:
  • a memory for storing executable instructions of the processor
  • executable instructions include:
  • problem data does not include a problem task, directly retrieve the basic data corresponding to the problem data in the knowledge base and return;
  • the problem data includes a problem task
  • corresponding task processing is performed on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task, and the task processing result is obtained and returned.
  • the embodiments of the present invention disclose a data processing method, device, storage medium, and electronic equipment, including: obtaining problem data; decomposing the problem data; based on decomposition After the result, it is judged whether the question data contains a question task; if the question data does not contain a question task, directly retrieve the basic data corresponding to the question data in the knowledge base and return it; if the question data contains The problem task, according to the content of the problem task, perform corresponding task processing on the basic data corresponding to the problem task in the knowledge base, and obtain the task processing result and return it.
  • the data processing method, device, storage medium and electronic equipment can not only automatically search for the corresponding answer based on the question data, but also automatically perform the corresponding task processing on the searched basic data when the question data includes the question task. It can better serve users, save users the time of manually processing tasks, and greatly improve the user experience.
  • Fig. 1 is a flowchart of a data processing method disclosed in an embodiment of the present invention
  • FIG. 3 is a flowchart of another data processing method disclosed in an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a data processing device disclosed in an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another data processing device disclosed in an embodiment of the present invention.
  • Fig. 6 is a schematic structural diagram of a second processing module disclosed in an embodiment of the present invention.
  • Fig. 7 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention.
  • Fig. 1 is a flowchart of a data processing method disclosed in an embodiment of the present invention.
  • the data processing method may include:
  • Step 101 Obtain problem data.
  • the execution subject of the data processing method described in this embodiment may be an intelligent question-and-answer tool or the processor of the system.
  • the user first inputs question data through an input device, such as a keyboard, a voice acquisition device, etc., and the system obtains the question.
  • the problem data can be processed and searched accordingly.
  • the knowledge base may be a knowledge base in a specific field, such as an oil and gas field knowledge base, in which knowledge of industry knowledge, industry data, physical models, industry laws, etc. can be integrated and stored.
  • Step 102 Decompose the problem data.
  • Sentence decomposition of the problem data is for more accurate task identification. For example, if the problem data is "Which is the discovery well in Shinan Oilfield?", then sentence decomposition is performed. The decomposition results include “Shinan Oilfield” and “ “Of”, “discovery well”, “which is it”.
  • Step 103 Based on the result of the decomposition, determine whether the problem data includes a problem task.
  • the category of the question data may include task questions and non-task questions, and the category of the question data is determined by whether the question data contains the question task.
  • the task question contains the question task, and the task question means that to answer the question data, not only the data needs to be searched in the knowledge base, but also the searched data needs to be further processed to complete the task requirements.
  • the processing can include, but is not limited to, calculation, combination and other processing.
  • the non-task question that does not contain the question task is a non-task question.
  • the non-task question or the answer does not require additional processing. It is directly searched and retrieved in the knowledge base based on the question data, and the found data is directly returned as the answer. .
  • Step 104 If the question data does not include a question task, directly search for the basic data corresponding to the question data in the knowledge base and return it.
  • the question data is "Which plain is the Daqing Oilfield located?"
  • This knowledge point has long been included in the oil and gas domain knowledge base. Therefore, the answer can be obtained by searching directly in the knowledge base, that is, the basic data.
  • Step 105 If the problem data includes a problem task, perform corresponding task processing on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task, and obtain the task processing result and return it.
  • the task processing can be, but is not limited to, any one or a combination of combination, reasoning, and calculation.
  • the task processing performed on the basic data corresponding to the problem task in the knowledge base is calculation
  • the calculation is completed according to the preset calculation formula, wherein the preset formula is the accumulation of historical knowledge and
  • the expert summary method collects the calculation formulas entered into the knowledge base.
  • the question data is "What is the number of oil production wells in the Tokyo oil and gas field?"
  • this question is a statistical question.
  • Oil and gas fields include oil and gas reservoirs, and there is no attribute of the number of oil production wells in the stored information of the oil and gas field nodes. Therefore, to answer this question, you need to inquire about the oil and gas reservoirs contained in the oil and gas field, and make statistics based on the number of oil production wells in each oil and gas reservoir, and finally get the total number of oil production wells contained in the oil and gas field. So the whole process involves query, combination, and calculation.
  • the answer can include the basic knowledge in the knowledge base, or it can be an answer obtained by combining and calculating a variety of basic knowledge.
  • the data processing method can not only automatically search for the corresponding answer based on the question data, but also automatically perform the corresponding task processing on the searched basic data when the question data includes the question task, so as to better Serving users, saving users the time to manually process tasks, and greatly improving the user experience.
  • FIG. 2 is a flowchart of another data processing method disclosed in an embodiment of the present invention.
  • the data processing method may include:
  • Step 201 Obtain problem data.
  • Step 202 Decompose the problem data.
  • Step 203 Determine whether the decomposed question data contains subject words, if not, go to step 204; if it contains, go to step 205.
  • Subject terms can be divided into categories such as oil and gas fields, reservoirs, basins, and geological explorations according to the business needs of the oil and gas field. For example, in the above “Which is the discovery well of Shinan Oilfield?", "Shinan Oilfield” is the subject term, which is classified under the oil and gas field classification.
  • Step 204 Determine that the question data is a term search, and directly search for basic data corresponding to the question data in the term of the knowledge base and return it.
  • the question data does not contain subject terms, it is determined that the question data is a term search.
  • the term can be defined by some terms in the field. For example, the question data is "What is perforation?". There is no oil and gas subject in the question data, so it belongs to term search, where "perforation" is the term.
  • search where "perforation" is the term.
  • the interpretation of "perforating” can be obtained as: after cementing, the perforating gun is lowered to the specified interval in the oil and gas well, and the casing, cement ring and formation are perforated to make oil and gas flow from the reservoir. Wellbore operations.
  • Step 205 Based on the result of the decomposition, determine whether the question data includes a question task, if it does, go to step 206, if not, go to step 207.
  • Step 206 According to the content of the problem task, perform corresponding task processing on the basic data corresponding to the problem task in the knowledge base, and obtain the task processing result and return it.
  • the question data contains subject words and question tasks
  • Step 207 Directly retrieve the basic data corresponding to the question data in the knowledge base and return it.
  • the specific subject question and answer may be a query on basic entity, attribute, relationship and other data. Take “Which is the discovery well of Shinan Oilfield?" as an example. In this question, the basic entity (subject term) involved is Shinan Oilfield.
  • the discovery well may be a certain attribute or a certain relationship of the entity, so Query through the attributes and relationships of the entity.
  • the data processing method may further include: determining from the decomposed question data Subject words; query the attributes and relationships corresponding to the question data within the subject range corresponding to the subject words.
  • the attributes and relationships corresponding to the question data can be queried within the subject range corresponding to the subject words. In this way, compared to querying the attributes and relationships corresponding to the question data in the entire knowledge base data center The relationship greatly reduces the scope of the query, and improves the query speed and query accuracy.
  • FIG. 3 is a flowchart of yet another data processing method disclosed in an embodiment of the present invention.
  • the data processing method may include:
  • Step 301 Obtain problem data.
  • Step 302 Decompose the problem data.
  • Step 303 Determine whether the decomposed question data contains subject words, if it does not, go to step 304; if it does, go to step 305.
  • Step 304 Determine that the question data is a term search, and directly search for the basic data corresponding to the question data in the term of the knowledge base and return it.
  • Step 305 Based on the decomposed result, determine whether the question data contains a question task, if it does, go to step 306, if not, go to step 308.
  • Step 306 Determine subject words from the decomposed question data.
  • Step 307 Query the basic data corresponding to the question data within the subject range corresponding to the subject word, and determine the task processing that needs to be performed by identifying the content of the question task; The task processing.
  • Step 308 Directly retrieve the basic data corresponding to the question data in the knowledge base and return it.
  • the above embodiment introduces the realization of a complete data processing method.
  • the data processing method is based on a relatively complete oil and gas field knowledge base established through intention recognition, knowledge retrieval, task execution, and answer combination of question sentences. Process, return to the question the knowledge and answers based on the basic knowledge in the knowledge base.
  • the searched basic data can be automatically processed corresponding to the task, so as to better serve the user and save the user manual processing
  • the task time greatly improves the user experience.
  • performing corresponding task processing on the basic data corresponding to the problem task in the knowledge base to obtain and return the task processing result may include: according to preset The calculation formula of Calculates the basic data corresponding to the problem task in the knowledge base, and returns the calculated result.
  • the preset calculation formula may be a calculation formula collected and entered into the knowledge base through historical knowledge accumulation and expert summary.
  • the problem task can include the combination and reasoning of basic relationships, and the calculation of basic attribute values.
  • Specific calculations will involve different formulas according to different tasks in the problem. For example, some are formulas with physical meaning in actual production, and some are summation, average, etc.
  • FIG. 4 is a schematic structural diagram of a data processing device disclosed in an embodiment of the present invention.
  • the data processing device 40 may include:
  • the question obtaining module 401 is used to obtain question data.
  • the execution body of the data processing device in this embodiment may be a smart question and answer tool or the processor of the system.
  • the user first inputs question data through an input device, such as a keyboard, a voice acquisition device, etc., and the system obtains the question.
  • the problem data can be processed and searched accordingly.
  • the knowledge base may be a knowledge base in a specific field, such as an oil and gas domain knowledge base, in which knowledge of industry knowledge, industry data, physical models, and industry laws can be integrated and stored.
  • the problem decomposition module 402 is used to decompose the problem data.
  • the sentence decomposition of the question data is for more accurate task identification.
  • the task judgment module 403 is used for judging whether the problem data includes a problem task based on the decomposed result.
  • the category of the question data may include task questions and non-task questions, and the category of the question data is determined by whether the question data contains the question task.
  • the task question contains the question task, and the task question means that to answer the question data, not only the data needs to be searched in the knowledge base, but also the searched data needs to be further processed to complete the task requirements.
  • the processing can include, but is not limited to, calculation, combination and other processing.
  • the non-task question that does not contain the question task is a non-task question.
  • the non-task question or the answer does not require additional processing. It is directly searched and retrieved in the knowledge base based on the question data, and the found data is directly returned as the answer .
  • the first processing module 404 is configured to directly retrieve and return basic data corresponding to the problem data in the knowledge base when the problem data does not include a problem task.
  • the second processing module 405 is configured to perform corresponding task processing on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task when the problem data includes a problem task, to obtain Task processing result and return.
  • the task processing can be, but is not limited to, any one or a combination of combination, reasoning, and calculation.
  • the task processing performed on the basic data corresponding to the problem task in the knowledge base is calculation
  • the calculation is completed according to the preset calculation formula, wherein the preset formula is the accumulation of historical knowledge and
  • the expert summary method collects the calculation formulas entered into the knowledge base.
  • the answer can include the basic knowledge in the knowledge base, or it can be an answer obtained by combining and calculating a variety of basic knowledge.
  • the data processing device can not only automatically search for the corresponding answer based on the question data, but also automatically perform the corresponding task processing on the searched basic data when the question data includes the question task, so as to better Serving users, saving users the time to manually process tasks, and greatly improving the user experience.
  • FIG. 5 is a schematic structural diagram of another data processing device disclosed in an embodiment of the present invention. As shown in FIG. 5, the data processing device 50 may include:
  • the question obtaining module 401 is used to obtain question data.
  • the problem decomposition module 402 is used to decompose the problem data.
  • the topic word judgment module 501 is used to judge whether the decomposed question data contains topic words.
  • the type determination module 502 is configured to determine that the question data is a term search when the topic word judgment module 501 determines that the decomposed question data does not contain a topic word.
  • the task judging module 403 is configured to, when the topic word judging module 501 determines that the decomposed question data contains topic words, further judge whether the decomposed question data contains a question task.
  • the first processing module 404 is configured to directly retrieve and return basic data corresponding to the problem data in the knowledge base when the task judgment module 403 determines that the problem data does not include the problem task, or in the case of When the type determination module 502 determines that the question data is a term search, it directly searches for the basic data corresponding to the question data in the term of the knowledge base and returns it.
  • the second processing module 405 is configured to correspond to the basic data corresponding to the problem task in the knowledge base according to the content of the problem task when the task judgment module 403 determines that the problem data includes a problem task Task processing, get the task processing result and return.
  • the first processing module 404 can be specifically used to: From the decomposed question data Determine the subject word; query the attribute and relationship corresponding to the question data within the subject range corresponding to the subject word.
  • the attributes and relationships corresponding to the question data can be queried within the subject range corresponding to the subject words. In this way, compared to querying the attributes and relationships corresponding to the question data in the entire knowledge base data center The relationship greatly reduces the scope of the query, and improves the query speed and query accuracy.
  • FIG. 6 is a schematic structural diagram of a second processing module disclosed in an embodiment of the present invention.
  • the second processing module 60 may include:
  • the topic word determination module 601 is configured to determine topic words from the decomposed question data when the judgment result of the task judgment module 405 is yes;
  • the task processing module 602 is configured to query the basic data corresponding to the question data within the subject range corresponding to the topic words determined by the topic word determination module 601, and determine the task to be performed by identifying the content of the question task Processing; the task processing for determining the basic data.
  • the topic words can be determined first, and then the corresponding task processing can be performed within the scope of the basic data corresponding to the question data within the scope of the topic corresponding to the topic words. The accuracy of the returned results.
  • the data processing device includes a processor and a memory, the above-mentioned problem acquisition module, problem decomposition module, task judgment module, topic word determination module, task processing module, first processing module, second processing module, topic word judgment module, task processing
  • the module and the type determination module are all stored in the memory as a program unit, and the above-mentioned program unit stored in the memory is executed by the processor to realize the corresponding function.
  • the processor contains the kernel, and the kernel calls the corresponding program unit from the memory.
  • One or more kernels can be set, and answer search, processing and return can be realized by adjusting kernel parameters.
  • the embodiment of the present invention provides a storage medium on which a program is stored, and the data processing method is implemented when the program is executed by a processor.
  • the embodiment of the present invention provides a processor, the processor is used to run a program, wherein the data processing method is executed when the program is running.
  • FIG. 7 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention.
  • the electronic device 70 includes at least one processor 701, and at least one memory 702 and a bus 703 connected to the processor 701;
  • the processor and the memory communicate with each other through the bus; the processor is used to call the program instructions in the memory to execute the above-mentioned data processing method.
  • the equipment in this article can be a server, PC, PAD, mobile phone, etc.
  • This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps:
  • problem data does not include a problem task, directly retrieve the basic data corresponding to the problem data in the knowledge base and return;
  • the problem data includes a problem task
  • corresponding task processing is performed on the basic data corresponding to the problem task in the knowledge base according to the content of the problem task, and the task processing result is obtained and returned.
  • the method before determining whether the problem data includes a problem task, the method further includes:
  • the subject words are not included, determine that the question data is a term search, and stop performing the step of judging whether the question data contains a question task; if it contains subject words, determine whether the step of judging whether the question data contains a question task needs to be performed .
  • the direct search of the basic data corresponding to the question data in the knowledge base and return may include: directly in the term of the knowledge base Retrieve and return the basic data corresponding to the question data.
  • the method further includes: determining topic words from the decomposed question data; querying and searching within the topic range corresponding to the topic words The attributes and relationships corresponding to the question data.
  • the decomposed question data contains subject words
  • perform corresponding task processing on the basic data corresponding to the question task in the knowledge base including: The subject words are determined from the decomposed question data; the basic data corresponding to the question data is queried within the subject range corresponding to the subject words, and the task processing that needs to be performed is determined by identifying the content of the question task; The basic data performs the determined task processing.
  • the task processing includes at least one of the following: combination, reasoning, and calculation.
  • the calculation is completed according to the preset calculation formula, wherein the preset formula is based on historical knowledge Accumulation and expert summary methods collect calculation formulas entered into the knowledge base.
  • the device includes one or more processors (CPUs), memory, and buses.
  • the device may also include input/output interfaces, network interfaces, and so on.
  • the memory may include non-permanent memory in computer-readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one Memory chip.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • the memory is an example of a computer-readable medium.
  • Computer-readable media includes permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • this application can be provided as a method, a system, or a computer program product. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • Human Resources & Organizations (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Animal Husbandry (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Agronomy & Crop Science (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种数据处理方法、装置、存储介质及电子设备,包括:获取问题数据(101);对所述问题数据进行分解(102);基于分解后的结果,判断所述问题数据是否包含问题任务(103);若问题数据不包含问题任务,直接在知识库中检索与所述问题数据对应的基础数据并返回(104);若问题数据包含问题任务,根据问题任务的内容,对知识库中与问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回(105)。所述数据处理方法、装置、存储介质及电子设备,不仅能够根据问题数据自动搜索对应的答案,还能在问题数据中包括问题任务时,自动对搜索到的基础数据进行对应的任务处理,从而能够更好地服务于用户,节省用户手动处理任务的时间,极大的提升了用户的使用体验。

Description

数据处理方法、装置、存储介质及电子设备
本申请要求于2019年09月30日提交中国专利局、申请号为201910945241.6、发明名称为“数据处理方法、装置、存储介质及电子设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本发明涉及数据处理技术,更具体的说,是涉及一种数据处理方法、装置、存储介质及电子设备。
背景技术
油气领域是工业领域中一个重要的子领域,如何对已发现油田进行更加高效和高质量的开采,是本领域技术人员始终致力于的目标之一。
在油田开采过程中,生产持续时间长,涉及的地理条件、生产设备复杂,因此会产生大量发地质资料和生产数据;这些数据对后续油田生产具有重要的指导意义。因此,如何更好的利用已积累的油气领域知识服务于后续的油田生产工作,对于油气领域具有重要意义。
发明内容
有鉴于此,本发明提供如下技术方案:
一种数据处理方法,包括:
获取问题数据;
对所述问题数据进行分解;
基于分解后的结果,判断所述问题数据是否包含问题任务;
若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处 理结果并返回。
可选的,在判断所述问题数据是否包含问题任务之前,所述方法进一步包括:
判断分解后的问题数据中是否包含主题词;
若不包含主题词,确定所述问题数据为词条检索,并停止执行判断所述问题数据是否包含问题任务的步骤;
若包含主题词,确定需要执行判断所述问题数据是否包含问题任务的步骤。
可选的,在所述问题数据为词条检索的情况下,则所述直接在所述知识库中检索与所述问题数据对应的基础数据并返回,包括:
直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
可选的,在所述问题数据包含主题词、而不包含问题任务的情况下,所述方法进一步包括:
从所述分解后的问题数据中确定出主题词;
在所述主题词对应的主题范围内查询与所述问题数据对应的属性和关系。
可选的,在判断分解后的问题数据中是否包含主题词的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,包括:
从所述分解后的问题数据中确定出主题词;
在所述主题词对应的主题范围内查询与所述问题数据对应的基础数据,并通过识别所述问题任务的内容来确定需要执行的任务处理;
对所述基础数据进行确定的所述任务处理。
可选的,所述任务处理包括以下至少之一:组合、推理、计算。
可选的,在对所述知识库中与所述问题任务对应的基础数据进行的任务处理为计算的情况下,根据所述预设的计算公式完成计算,其中,所述预设公式为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
一种数据处理装置,包括:
问题获取模块,用于获取问题数据;
问题分解模块,用于对所述问题数据进行分解;
任务判断模块,用于基于分解后的结果,判断所述问题数据是否包含问题任务;
第一处理模块,用于在所述问题数据不包含问题任务的情况下,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
第二处理模块,用于在所述问题数据包含问题任务的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
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上述任一种所述的数据处理方法。
一种电子设备,包括:
处理器;以及
存储器,用于存储所述处理器的可执行指令;
其中,所述可执行指令包括:
获取问题数据;
对所述问题数据进行分解;
基于分解后的结果,判断所述问题数据是否包含问题任务;
若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
经由上述的技术方案可知,与现有技术相比,本发明实施例公开了一种数据处理方法、装置、存储介质及电子设备,包括:获取问题数据;对所述问题数据进行分解;基于分解后的结果,判断所述问题数据是否包含问题任务;若所述问题数据不包含问题任务,直接在所述知识库中检索与 所述问题数据对应的基础数据并返回;若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。所述数据处理方法、装置、存储介质及电子设备,不仅能够根据问题数据自动搜索对应的答案,还能在问题数据中包括问题任务时,自动对搜索到的基础数据进行对应的任务处理,从而能够更好地服务于用户,节省用户手动处理任务的时间,极大的提升了用户的使用体验。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据提供的附图获得其他的附图。
图1为本发明实施例公开的一种数据处理方法的流程图;
图2为本发明实施例公开的另一种数据处理方法的流程图;
图3为本发明实施例公开的又一种数据处理方法的流程图;
图4为本发明实施例公开的一种数据处理装置的结构示意图;
图5为本发明实施例公开的另一种数据处理装置的结构示意图;
图6为本发明实施例公开的第二处理模块的结构示意图;
图7为本发明实施例公开的电子设备结构示意图。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
图1为本发明实施例公开的一种数据处理方法的流程图,参见图1所 示,数据处理方法可以包括:
步骤101:获取问题数据。
本实施例所述数据处理方法的执行主体可以是智能问答工具或系统的处理器,在实际应用场景中,用户首先通过输入装置,如键盘、语音采集装置等输入问题数据,系统获取所述问题数据,后续可以对所述问题数据进行相应的处理和查询检索工作。
其中,所述智能问答工作或系统的正常工作需要基于预先建立好的知识库实现。所述知识库可以是特定领域的知识库,如油气领域知识库,该油气领域知识库中可以对行业知识、行业数据、物理模型、行业规律等知识进行整合存储。
步骤102:对所述问题数据进行分解。
对所述问题数据进行语句分解是为了更加准确的进行任务识别,例如问题数据为“史南油田的发现井是哪个?”,则对其进行语句分解,分解结果包括“史南油田”、“的”、“发现井”、“是哪个”。
步骤103:基于分解后的结果,判断所述问题数据是否包含问题任务。
本实施例中,所述问题数据的类别可以包括任务问题和非任务问题,通过问题数据中是否包含问题任务来确定问题数据的类别。包含问题任务的为任务问题,所述任务问题是指回答所述问题数据不仅需要在知识库中查找数据,还需要对查找到的数据进行进一步处理,完成任务要求。其中的处理可以但不限制为包括计算、组合等处理。不包含问题任务的为非任务问题,所述非任务问题即答案不需要进行额外的处理,直接根据问题数据在所述知识库中进行相应查找检索,将查找到的数据直接作为答案返回即可。
步骤104:若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回。
例如,所述问题数据是“大庆油田位于哪个平原?”,这个知识点早就收录在油气领域知识库中,因此,直接在知识库中搜索就可以得到答案,即所述基础数据。
步骤105:若所述问题数据包含问题任务,根据所述问题任务的内容, 对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
其中,所述任务处理可以但不限制为合、推理、计算中的任意一种或几种的组合。在对所述知识库中与所述问题任务对应的基础数据进行的任务处理为计算的情况下,根据所述预设的计算公式完成计算,其中,所述预设公式为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
例如,所述问题数据为“东京油气田的采油井数量是多少?”,实际上,这个问题是一个统计类的问题。油气田包含油气藏,油气田节点的存储信息中是没有采油井数量这个属性的。因此要回答这个问题,需要查询到油气田下包含的油气藏,根据每个油气藏中采油井的数量进行统计,最后得到油气田包含的采油井的总数量。所以整个过程涉及查询、组合、计算。
这样,在建立的比较完备的油气领域知识库的基础上,通过对问题语句进行意图识别、知识检索、任务执行、答案组合的流程,对问题返回基于知识库中基础知识的知识及答案。答案中可以包含知识库中的基础知识,也可以是对多种基础知识的组合和计算得到的答案。
本实施例中,所述数据处理方法不仅能够根据问题数据自动搜索对应的答案,还能在问题数据中包括问题任务时,自动对搜索到的基础数据进行对应的任务处理,从而能够更好地服务于用户,节省用户手动处理任务的时间,极大的提升了用户的使用体验。
图2为本发明实施例公开的另一种数据处理方法的流程图,参见图2所示,数据处理方法可以包括:
步骤201:获取问题数据。
步骤202:对所述问题数据进行分解。步骤203:判断分解后的问题数据中是否包含主题词,若不包含,进入步骤204;若包含,进入步骤205。
主题词可以按照油气领域的业务需求,分为油气田、油气藏、盆地、地质勘探等等类别。例如上述“史南油田的发现井是哪个?”中,“史南油田”即为主题词,其归类在油气田分类下。
步骤204:确定所述问题数据为词条检索,直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
若所述问题数据若不包含主题词,确定所述问题数据为词条检索。其中所述词条可以是领域内一些术语定义,例如问题数据为“什么是射孔?”,这个问题数据中没有油气主体,所以属于词条检索,其中“射孔”就是词条。通过在知识库中的检索,可以得到“射孔”的解释为:固井后将射孔枪下到油气井中指定层段,将套管、水泥环和地层射穿,使油气从储层流入井筒的作业。
步骤205:基于分解后的结果,判断所述问题数据是否包含问题任务,若包含,进入步骤206,若不包含,进入步骤207。
在确定问题数据包含主题词后,进一步判断所述问题数据是否包含问题任务。
步骤206:根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
在确定所述问题数据包含主题词和问题任务时,除了在知识库中进行相应查询检索操作外,还需要对查询到的数据进行进一步的任务处理。
步骤207:直接在所述知识库中检索与所述问题数据对应的基础数据并返回。
在确定所述问题数据包含主题词但不包含问题任务时,在知识库中进行相应查询检索即可,具体主题问答可以是对基础实体、属性、关系等数据的查询。还以“史南油田的发现井是哪个?”为例,在这个问题中,涉及的基础实体(主题词)是史南油田,发现井可能是该实体的某个属性或者某个关系,所以通过对该实体的属性和关系进行查询。
本实施例中,对问题数据分解后,首先判断其是否包含主题词,再进一步根据是否包含主题词而确定执行判断问题数据是否包含问题任务的必要性,通过本实施例相关内容的介绍,能够使领域人员更好的了解本申请公开实施例的具体实现。
基于上述实施例公开的内容,在其他的实现中,在所述问题数据包含 主题词、而不包含问题任务的情况下,数据处理方法进一步可以包括:从所述分解后的问题数据中确定出主题词;在所述主题词对应的主题范围内查询与所述问题数据对应的属性和关系。
由于问题数据中包含主题词,因此,可以在主题词对应的主题范围内查询与所述问题数据对应的属性和关系,这样,相对于在整个知识库数据中心查询所述问题数据对应的属性和关系,大大缩小了查询范围,提升了查询速度和查询精度。
在上述本发明公开的实施例的基础上,图3为本发明实施例公开的又一种数据处理方法的流程图,参见图3所示,数据处理方法可以包括:
步骤301:获取问题数据。
步骤302:对所述问题数据进行分解。
步骤303:判断分解后的问题数据中是否包含主题词,若不包含,进入步骤304;若包含,进入步骤305。
步骤304:确定所述问题数据为词条检索,直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
步骤305:基于分解后的结果,判断所述问题数据是否包含问题任务,若包含,进入步骤306,若不包含,进入步骤308。
步骤306:,从所述分解后的问题数据中确定出主题词。
步骤307:在所述主题词对应的主题范围内查询与所述问题数据对应的基础数据,并通过识别所述问题任务的内容来确定需要执行的任务处理;对所述基础数据进行确定的所述任务处理。
步骤308:直接在所述知识库中检索与所述问题数据对应的基础数据并返回。
上述实施例介绍了一个完整的数据处理方法的实现,所述数据处理方法在建立的比较完备的油气领域知识库的基础上,通过对问题语句进行意图识别、知识检索、任务执行、答案组合的流程,对问题返回基于知识库中基础知识的知识及答案。实现中不仅能够根据问题数据自动搜索对应的答案,还能在问题数据中包括问题任务时,自动对搜索到的基础数据进行 对应的任务处理,从而能够更好地服务于用户,节省用户手动处理任务的时间,极大的提升了用户的使用体验。
上述各实施例中,所述根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回,可以包括:依据预设的计算公式对知识库中与所述问题任务对应的基础数据进行计算处理,将计算后的结果返回。
其中,所述预设的计算公式可以为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
在其他的实现中,问题任务可以包括对基础关系的组合、推理,以及对基础属性值的计算。具体计算根据问题中的不同任务,会涉及不同的公式,例如有些是带有实际生产中的物理意义的公式,有些是求和、求平均等。
对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本发明,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本发明所必须的。
上述本发明公开的实施例中详细描述了方法,对于本发明的方法可采用多种形式的装置实现,因此本发明还公开了一种装置,下面给出具体的实施例进行详细说明。
图4为本发明实施例公开的一种数据处理装置的结构示意图,参见图4所示,数据处理装置40可以包括:
问题获取模块401,用于获取问题数据。
本实施例所述数据处理装置的执行主体可以是智能问答工具或系统的处理器,在实际应用场景中,用户首先通过输入装置,如键盘、语音采集 装置等输入问题数据,系统获取所述问题数据,后续可以对所述问题数据进行相应的处理和查询检索工作。
其中,所述智能问答工作或系统的正常工作需要基于预先建立好的知识库实现。所述知识库可以是特定领域的知识库,如油气领域知识库,该油气领域知识库中可以对行业知识、行业数据、物理模型、行业规律等知识进行整合存储。
问题分解模块402,用于对所述问题数据进行分解。
对所述问题数据进行语句分解是为了更加准确的进行任务识别。
任务判断模块403,用于基于分解后的结果,判断所述问题数据是否包含问题任务。
本实施例中,所述问题数据的类别可以包括任务问题和非任务问题,通过问题数据中是否包含问题任务来确定问题数据的类别。包含问题任务的为任务问题,所述任务问题是指回答所述问题数据不仅需要在知识库中查找数据,还需要对查找到的数据进行进一步处理,完成任务要求。其中的处理可以但不限制为包括计算、组合等处理。不包含问题任务的为非任务问题,所述非任务问题即答案不需要进行额外的处理,直接根据问题数据在所述知识库中进行相应查找检索,将查找到的数据直接作为答案返回即可。
第一处理模块404,用于在所述问题数据不包含问题任务的情况下,直接在所述知识库中检索与所述问题数据对应的基础数据并返回。
第二处理模块405,用于在所述问题数据包含问题任务的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
其中,所述任务处理可以但不限制为合、推理、计算中的任意一种或几种的组合。在对所述知识库中与所述问题任务对应的基础数据进行的任务处理为计算的情况下,根据所述预设的计算公式完成计算,其中,所述预设公式为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
在建立的比较完备的油气领域知识库的基础上,通过对问题语句进行 意图识别、知识检索、任务执行、答案组合的流程,对问题返回基于知识库中基础知识的知识及答案。答案中可以包含知识库中的基础知识,也可以是对多种基础知识的组合和计算得到的答案。
本实施例中,所述数据处理装置不仅能够根据问题数据自动搜索对应的答案,还能在问题数据中包括问题任务时,自动对搜索到的基础数据进行对应的任务处理,从而能够更好地服务于用户,节省用户手动处理任务的时间,极大的提升了用户的使用体验。
图5为本发明实施例公开的另一种数据处理装置的结构示意图,如图5所示,数据处理装置50可以包括:
问题获取模块401,用于获取问题数据。
问题分解模块402,用于对所述问题数据进行分解。
主题词判断模块501,用于判断分解后的问题数据中是否包含主题词。
类型确定模块502,用于在所述主题词判断模块501确定分解后的问题数据中不包含主题词时,确定所述问题数据为词条检索。
任务判断模块403,用于在所述主题词判断模块501确定分解后的问题数据中包含主题词时,进一步判断所述分解后的问题数据是否包含问题任务。
第一处理模块404,用于在所述任务判断模块403确定问题数据不包含问题任务的情况下,直接在所述知识库中检索与所述问题数据对应的基础数据并返回,或在所述类型确定模块502确定所述问题数据为词条检索时,直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
第二处理模块405,用于在所述任务判断模块403确定问题数据包含问题任务的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
本实施例中,对问题数据分解后,首先判断其是否包含主题词,再进一步根据是否包含主题词而确定执行判断问题数据是否包含问题任务的必要性,通过本实施例相关内容的介绍,能够使领域人员更好的了解本申请 公开实施例的具体实现。
基于上述实施例公开的内容,在其他的实现中,在所述问题数据包含主题词、而不包含问题任务的情况下,第一处理模块404具体可用于:从所述分解后的问题数据中确定出主题词;在所述主题词对应的主题范围内查询与所述问题数据对应的属性和关系。
由于问题数据中包含主题词,因此,可以在主题词对应的主题范围内查询与所述问题数据对应的属性和关系,这样,相对于在整个知识库数据中心查询所述问题数据对应的属性和关系,大大缩小了查询范围,提升了查询速度和查询精度。
图6为本发明实施例公开的第二处理模块的结构示意图,参见图6所示,第二处理模块60可以包括:
主题词确定模块601,用于在所述任务判断模块405的判断结果为是时,从所述分解后的问题数据中确定出主题词;
任务处理模块602,用于在所述主题词确定模块601确定的主题词对应的主题范围内查询与所述问题数据对应的基础数据,并通过识别所述问题任务的内容来确定需要执行的任务处理;对所述基础数据进行确定的所述任务处理。
本实施例中,在问题数据包含主题词和问题任务时,能够先确定主题词,然后在主题词对应的主题范围内查询与所述问题数据对应的基础数据范围内进行相应的任务处理,保障返回结果的准确性。
所述数据处理装置包括处理器和存储器,上述问题获取模块、问题分解模块、任务判断模块、主题词确定模块、任务处理模块、第一处理模块、第二处理模块、主题词判断模块、任务处理模块和类型确定模块等均作为程序单元存储在存储器中,由处理器执行存储在存储器中的上述程序单元来实现相应的功能。
处理器中包含内核,由内核去存储器中调取相应的程序单元。内核可 以设置一个或以上,通过调整内核参数来实现答案搜索、处理及返回。
本发明实施例提供了一种存储介质,其上存储有程序,该程序被处理器执行时实现所述数据处理方法。
本发明实施例提供了一种处理器,所述处理器用于运行程序,其中,所述程序运行时执行所述数据处理方法。
图7为本发明实施例公开的电子设备结构示意图,如图7所示,所述电子设备70包括至少一个处理器701、以及与处理器701连接的至少一个存储器702、总线703;其中,处理器、存储器通过总线完成相互间的通信;处理器用于调用存储器中的程序指令,以执行上述的数据处理方法。本文中的设备可以是服务器、PC、PAD、手机等。
本申请还提供了一种计算机程序产品,当在数据处理设备上执行时,适于执行初始化有如下方法步骤的程序:
获取问题数据;
对所述问题数据进行分解;
基于分解后的结果,判断所述问题数据是否包含问题任务;
若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
其中,在判断所述问题数据是否包含问题任务之前,所述方法进一步包括:
判断分解后的问题数据中是否包含主题词;
若不包含主题词,确定所述问题数据为词条检索,并停止执行判断所述问题数据是否包含问题任务的步骤;若包含主题词,确定需要执行判断所述问题数据是否包含问题任务的步骤。
其中,在所述问题数据为词条检索的情况下,所述直接在所述知识库中检索与所述问题数据对应的基础数据并返回,可以包括:直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
在所述问题数据包含主题词、而不包含问题任务的情况下,所述方法进一步包括:从所述分解后的问题数据中确定出主题词;在所述主题词对应的主题范围内查询与所述问题数据对应的属性和关系。
在判断分解后的问题数据中是否包含主题词的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,包括:从所述分解后的问题数据中确定出主题词;在所述主题词对应的主题范围内查询与所述问题数据对应的基础数据,并通过识别所述问题任务的内容来确定需要执行的任务处理;对所述基础数据进行确定的所述任务处理。
其中,所述任务处理包括以下至少之一:组合、推理、计算。
其中,在对所述知识库中与所述问题任务对应的基础数据进行的任务处理为计算的情况下,根据所述预设的计算公式完成计算,其中,所述预设公式为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
在一个典型的配置中,设备包括一个或多个处理器(CPU)、存储器和总线。设备还可以包括输入/输出接口、网络接口等。
存储器可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM),存储器包括至少一个存储芯片。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以 由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白,本申请的实施例可提供为方法、系统或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已,并不用于限制本申请。对于本领域技术人员来说,本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种数据处理方法,其特征在于,包括:
    获取问题数据;
    对所述问题数据进行分解;
    基于分解后的结果,判断所述问题数据是否包含问题任务;
    若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
    若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
  2. 根据权利要求1所述的数据处理方法,其特征在于,在判断所述问题数据是否包含问题任务之前,所述方法进一步包括:
    判断分解后的问题数据中是否包含主题词;
    若不包含主题词,确定所述问题数据为词条检索,并停止执行判断所述问题数据是否包含问题任务的步骤;
    若包含主题词,确定需要执行判断所述问题数据是否包含问题任务的步骤。
  3. 根据权利要求2所述的数据处理方法,其特征在于,在所述问题数据为词条检索的情况下,则所述直接在所述知识库中检索与所述问题数据对应的基础数据并返回,包括:
    直接在所述知识库的词条中检索与所述问题数据对应的基础数据并返回。
  4. 根据权利要求2所述的数据处理方方法,其特征在于,在所述问题数据包含主题词、而不包含问题任务的情况下,所述方法进一步包括:
    从所述分解后的问题数据中确定出主题词;
    在所述主题词对应的主题范围内查询与所述问题数据对应的属性和关系。
  5. 根据权利要求2所述的数据处理方法,其特征在于,在判断分解后的问题数据中是否包含主题词的情况下,根据所述问题任务的内容,对所 述知识库中与所述问题任务对应的基础数据进行对应的任务处理,包括:
    从所述分解后的问题数据中确定出主题词;
    在所述主题词对应的主题范围内查询与所述问题数据对应的基础数据,并通过识别所述问题任务的内容来确定需要执行的任务处理;
    对所述基础数据进行确定的所述任务处理。
  6. 根据权利要求1所述的数据处理方法,其特征在于,所述任务处理包括以下至少之一:组合、推理、计算。
  7. 根据权利要求6所述的数据处理方法,其特征在于,在对所述知识库中与所述问题任务对应的基础数据进行的任务处理为计算的情况下,根据所述预设的计算公式完成计算,其中,所述预设公式为通过历史知识积累和专家总结方式收集录入到知识库中的计算公式。
  8. 一种数据处理装置,其特征在于,包括:
    问题获取模块,用于获取问题数据;
    问题分解模块,用于对所述问题数据进行分解;
    任务判断模块,用于基于分解后的结果,判断所述问题数据是否包含问题任务;
    第一处理模块,用于在所述问题数据不包含问题任务的情况下,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
    第二处理模块,用于在所述问题数据包含问题任务的情况下,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
  9. 一种计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现权利要求1-7任一项所述的数据处理方法。
  10. 一种电子设备,其特征在于,包括:
    处理器;以及
    存储器,用于存储所述处理器的可执行指令;
    其中,所述可执行指令包括:
    获取问题数据;
    对所述问题数据进行分解;
    基于分解后的结果,判断所述问题数据是否包含问题任务;
    若所述问题数据不包含问题任务,直接在所述知识库中检索与所述问题数据对应的基础数据并返回;
    若所述问题数据包含问题任务,根据所述问题任务的内容,对所述知识库中与所述问题任务对应的基础数据进行对应的任务处理,得到任务处理结果并返回。
PCT/CN2020/103211 2019-09-30 2020-07-21 数据处理方法、装置、存储介质及电子设备 WO2021063087A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910945241.6A CN112579642A (zh) 2019-09-30 2019-09-30 数据处理方法、装置、存储介质及电子设备
CN201910945241.6 2019-09-30

Publications (1)

Publication Number Publication Date
WO2021063087A1 true WO2021063087A1 (zh) 2021-04-08

Family

ID=75117047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/103211 WO2021063087A1 (zh) 2019-09-30 2020-07-21 数据处理方法、装置、存储介质及电子设备

Country Status (2)

Country Link
CN (1) CN112579642A (zh)
WO (1) WO2021063087A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101986293A (zh) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 用于在搜索界面中呈现搜索答案信息的方法及设备
US20150356142A1 (en) * 2014-06-06 2015-12-10 Xerox Corporation Question answering system adapted to style of user requests
CN105787134A (zh) * 2016-04-07 2016-07-20 上海智臻智能网络科技股份有限公司 智能问答方法、装置及系统
CN107918678A (zh) * 2017-12-28 2018-04-17 北京洪泰同创信息技术有限公司 问答信息处理方法、问答信息处理系统及服务器
CN107993724A (zh) * 2017-11-09 2018-05-04 易保互联医疗信息科技(北京)有限公司 一种医学智能问答数据处理的方法及装置
CN108959627A (zh) * 2018-07-23 2018-12-07 北京光年无限科技有限公司 基于智能机器人的问答交互方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101986293A (zh) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 用于在搜索界面中呈现搜索答案信息的方法及设备
US20150356142A1 (en) * 2014-06-06 2015-12-10 Xerox Corporation Question answering system adapted to style of user requests
CN105787134A (zh) * 2016-04-07 2016-07-20 上海智臻智能网络科技股份有限公司 智能问答方法、装置及系统
CN107993724A (zh) * 2017-11-09 2018-05-04 易保互联医疗信息科技(北京)有限公司 一种医学智能问答数据处理的方法及装置
CN107918678A (zh) * 2017-12-28 2018-04-17 北京洪泰同创信息技术有限公司 问答信息处理方法、问答信息处理系统及服务器
CN108959627A (zh) * 2018-07-23 2018-12-07 北京光年无限科技有限公司 基于智能机器人的问答交互方法及系统

Also Published As

Publication number Publication date
CN112579642A (zh) 2021-03-30

Similar Documents

Publication Publication Date Title
CN109284363A (zh) 一种问答方法、装置、电子设备及存储介质
US20210019341A1 (en) Implementing a software action based on machine interpretation of a language input
US10504120B2 (en) Determining a temporary transaction limit
CN105183923B (zh) 新词发现方法及装置
CN108920654A (zh) 一种问答文本语义匹配的方法和装置
US8224805B2 (en) Method for generating context hierarchy and system for generating context hierarchy
CN103678316B (zh) 实体关系分类装置和实体关系分类方法
CN113342976B (zh) 一种自动采集处理数据的方法、装置、存储介质及设备
US20140280242A1 (en) Method and apparatus for acquiring hot topics
US7203685B2 (en) Apparatus and method for estimating cardinality when data skew is present
CN111930848B (zh) 数据分区存储方法、装置及系统
CN102737042B (zh) 建立问句生成模型的方法和装置以及问句生成方法和装置
TW201546633A (zh) 文本資訊的匹配、業務對象的推送方法和裝置
CN105787134B (zh) 智能问答方法、装置及系统
CN106156271A (zh) 基于分布式存储的关联信息索引系统及其建立与使用方法
CN108027814A (zh) 停用词识别方法与装置
WO2016101812A1 (zh) 用于对搜索数据进行处理的方法及设备
TW201737127A (zh) 資料檢索方法和裝置、資料儲存方法和裝置
CN103020074A (zh) 基于本体的对象级搜索技术
CN112907358A (zh) 贷款用户信用评分方法、装置、计算机设备和存储介质
CN112000790A (zh) 一种法律文本精确检索方法、终端系统和可读存储介质
WO2021063087A1 (zh) 数据处理方法、装置、存储介质及电子设备
US11853297B2 (en) Methods and apparatus for retrieving information via an intermediate representation
CN111752922A (zh) 一种建立知识数据库、实现知识查询的方法及装置
CN116610810A (zh) 基于调控云知识图谱血缘关系的智能搜索方法及系统

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: 20872383

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: 20872383

Country of ref document: EP

Kind code of ref document: A1