WO2018201668A1 - 文本检索方法、电子装置、计算机可读存储介质及系统 - Google Patents
文本检索方法、电子装置、计算机可读存储介质及系统 Download PDFInfo
- Publication number
- WO2018201668A1 WO2018201668A1 PCT/CN2017/105005 CN2017105005W WO2018201668A1 WO 2018201668 A1 WO2018201668 A1 WO 2018201668A1 CN 2017105005 W CN2017105005 W CN 2017105005W WO 2018201668 A1 WO2018201668 A1 WO 2018201668A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- search term
- data
- consultation
- content
- inquiry
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/93—Document management systems
Definitions
- the present invention relates to the field of Internet technologies, and in particular, to a text retrieval method, an electronic device, a computer readable storage medium, and a system.
- the Internet online consultation is usually carried out as follows: the patient describes his or her condition at one end of the inquiry platform, and the doctor at the other end of the inquiry platform makes a diagnosis based on the symptoms described by the user. And provide advice to the patient.
- This kind of consultation method still relies on the actual doctors. It only moves face to face in the ward to the Internet platform, but it does not fundamentally solve the substantive problem of medical resources shortage.
- the object of the present invention is to provide a text retrieval method, an electronic device, a computer readable storage medium and a system, aiming at achieving the full automation of the online online consultation process.
- the present invention provides a text retrieval method, and the text retrieval method includes:
- the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term;
- the consultation data corresponding to the inquiry content is output.
- the present invention also provides a text retrieval system, the text retrieval system comprising:
- a word processing module configured to perform text pre-processing on the content of the inquiry input by the user, and obtain a pre-processed search term for performing information retrieval on the inquiry content
- a data retrieval module configured to perform a document matching on the search term according to the obtained search term, obtain a corresponding consultation data, and sort the consultation data according to the degree of association with the search term.
- the data output module is configured to output the consultation data corresponding to the inquiry content according to the sorting result.
- the present invention also provides an electronic device including a memory, a processor, and a text retrieval system stored on the memory and operable on the processor, the processor executing the text retrieval system , can achieve the following steps:
- the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term;
- the consultation data corresponding to the inquiry content is output.
- the present invention also provides a computer readable storage medium storing a text retrieval system, the text retrieval system being executable by at least one processor to implement the following steps:
- the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term;
- the consultation data corresponding to the inquiry content is output.
- the beneficial effects of the present invention are: by performing text preprocessing on the content of the inquiry input by the user, obtaining a pre-processed search term for information retrieval of the inquiry content; and querying the index according to the obtained search term
- the database performs document matching on the search term, obtains corresponding consultation data, sorts the consultation data according to the degree of association with the search term, and outputs the consultation data corresponding to the inquiry content according to the sorting result. It has achieved the goal of fully automating the online online consultation process, saving valuable medical resources and improving the efficiency of consultation and utilization of medical resources.
- FIG. 1 is a schematic flow chart of an embodiment of a text retrieval method according to the present invention.
- FIG. 2 is a schematic flow chart of an embodiment of step S10 in the embodiment shown in FIG. 1;
- FIG. 3 is a schematic flowchart of an embodiment of “sorting the consultation data according to the degree of association with the search term” in step S20 of the embodiment of FIG. 1;
- FIG. 4 is a schematic flow chart of another embodiment of a text retrieval method according to the present invention.
- FIG. 5 is a schematic flowchart diagram of still another embodiment of a text retrieval method according to the present invention.
- FIG. 6 is a schematic diagram of an operating environment of a text retrieval system 100 according to a preferred embodiment of the present invention.
- FIG. 7 is a schematic diagram of functional modules of an embodiment of a text retrieval system 100 according to the present invention.
- FIG. 8 is a functional block of an embodiment of the data retrieval module 110 of the embodiment of FIG. schematic diagram
- FIG. 9 is a schematic diagram of functional modules of another implementation manner of the text retrieval system 100 of the present invention.
- FIG. 10 is a schematic diagram of functional modules of still another embodiment of the text retrieval system 100 of the present invention.
- FIG. 1 is a schematic flowchart diagram of an implementation manner of a text retrieval method according to the present invention.
- the text retrieval method may be implemented as the following steps S10-S30:
- Step S10 Perform text pre-processing on the content of the inquiry input by the user, and obtain a pre-processed search term for performing information retrieval on the content of the consultation;
- the system receives the inquiry content input by the user based on the input control corresponding to the online inquiry platform, and performs text pre-processing on the content of the inquiry input by the user, for example, performing Chinese cutting on the content of the inquiry input by the user.
- Step S20 according to the obtained search term, the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term;
- the system queries the corresponding index database according to the search term obtained after pre-processing the content of the consultation.
- the index database is pre-established; for example, for a specific retrieval platform for disease consultation, when the system pre-establishes an index database, the open-ended medical consultation data on the Internet and the system itself accumulate Based on the consultation data, the index database is built. And the index database is continuously updated and supplemented based on social development and current hotspots. For example, the index database is continuously expanded for seasonal epidemics and new types of lesions; in addition, the system will continue to be based on the specific usage of the index platform by the user. Adjust the storage contents of the index database.
- the specific query method includes, but is not limited to, directly selecting the query data corresponding to the search term in the index database, or including the search term and the synonyms corresponding to the search term in the index database.
- the consultation data is selected; or, the inquiry data including the search term and the related words corresponding to the search term in the index database are selected.
- the synonym corresponding to the search term can be understood as: a word similar to the meaning of the search term, for example, the arm and the arm can be understood as the mutual synonyms, and the thigh and the leg can be understood as the mutual synonyms.
- the related words corresponding to the search term can be understood as: words associated with the meaning of the search term, for example, the finger and the toe can be understood as interrelated words.
- the interview data is sorted according to the degree of association with the search term; for example, according to the degree of association with the search term, the obtained consultation data is sorted from first to last.
- the degree of association between the questionnaire data and the search term obtained by the system is mainly determined by the number of search terms included in the consultation data, and the number of search words included in the consultation data is more The degree of association will be higher.
- the system may determine a specific manner for determining the degree of association between the consultation data and the search term according to different application scenarios, and the embodiment of the present invention does not specifically determine the degree of association between the consultation data and the search term. limited.
- Step S30 outputting the consultation data corresponding to the inquiry content according to the sorting result.
- the system outputs the consultation data corresponding to the inquiry content input by the user according to the ranking result of the consultation data.
- the specific presentation manner of the system outputting the consultation data includes, but is not limited to, directly displaying the consultation data on the user operation interface; or sending the inquiry data to the associated client, for example, sending the message through a short message. It can be saved to the mobile phone number or sent to WeChat, etc.
- the system directly displays the inquiry data on the user operation interface
- the system in a preferred embodiment, in order to facilitate the user to quickly find the desired result, the system only sets the preset number in front.
- the consultation data is displayed. For example, according to the size of the user interface, only the first five consultation data, or the first eight consultation data, are displayed.
- the specific output manner of the system outputting the diagnosis data is not specifically limited in the embodiment of the present invention.
- the text retrieval method in this embodiment performs text pre-processing on the content of the inquiry input by the user, and obtains a pre-processed search term for information retrieval of the inquiry content; a search term, the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term; according to the sort result, outputs the consultation Contents corresponding to the consultation data; with the full benefits of the online online consultation process, saving valuable medical resources, improving the efficiency of consultation and utilization of medical resources.
- step S10 in the embodiment of FIG. 1 can be implemented as step S11 as described below.
- Step S11 performing a Chinese word for the content of the inquiry input by the user
- Step S12 According to a preset extraction rule, extract a corresponding central word from the content of the consultation after the word is cut;
- the system receives the content of the inquiry input by the user, and performs Chinese word-cutting on the content of the inquiry input by the user.
- the system extracts the corresponding central word from the inquiry content after the word is cut, it can be extracted according to the disease name, drug name, diagnosis, body part, medical terminology; for example, the user input the inquiry content is “kicking the ball and kicking the foot” ", the system extracts the following central words " ⁇ " and "foot” from the content of the consultation after the word is cut.
- the Chinese word segmentation can also be understood as a Chinese word segmentation, which refers to dividing a Chinese character sequence into a single word.
- Chinese word segmentation is the basis of text mining. For a piece of Chinese input, successful Chinese word segmentation can achieve the effect of automatically recognizing the meaning of the sentence. This The method is also called the mechanical word segmentation method. It is based on a certain strategy to match the Chinese character string to be analyzed with the term in a "sufficiently large" machine dictionary. If a string is found in the dictionary, the matching is successful ( A word is recognized; and in the specific application of the text retrieval method of the present invention, the index database has all the functions of the above-mentioned "machine dictionary".
- Step S13 performing association expansion on the extracted central word to obtain a related word associated with the central word
- Step S14 using the central word and the related word as the search term corresponding to the inquiry content.
- the system expands the relevance of the extracted central words, the medical words are searched for the necessary central words, and the related words associated with the central words are obtained to achieve the purpose of expanding the search content.
- the system expands the association by using the disease name, the drug name, the diagnosis, and the body part as "necessary central words". For example, extend “arm” to “arm”; extend “acetaminophen” to “Merlin”, “Tynoline”, and so on.
- the central word and the related words associated with the central word are used as search terms corresponding to the content of the consultation, and the search data is searched to expand the search range and avoid data omission.
- the present embodiment searches by expanding the central word, improves the accuracy of the retrieval, and avoids the problem that the retrieval data is incomplete due to data omission.
- step S20 of the embodiment of the text retrieval method of FIG. 1 of the present invention in the step S20 of the embodiment of the text retrieval method of FIG. 1 of the present invention, the ranking of the consultation data according to the degree of association with the search term can be implemented as steps S21-S24 as described below:
- Step S21 Obtain the number of the search terms included in the consultation data
- Step S22 referring to the inquiry content input by the user, querying and obtaining the weight value corresponding to the search term from the index database;
- Step S23 calculating a score value corresponding to the consultation data according to the number of the search words in the consultation data and the weight value of the search term;
- Step S24 Sorting the consultation data from front to back according to the size of the score value corresponding to the consultation data.
- the system obtains the number of the search terms included in the consultation data based on each of the obtained consultation data, and queries the index database to include the information included in the consultation data based on the content of the inquiry input by the user.
- the weight value of each search term is multiplied by the weight amount corresponding to each search term, and the search score of the search term in the query data is obtained, and the same question data is included in the query data.
- the search scores corresponding to all the search terms are added respectively, and the total score corresponding to the consultation data is obtained, and the consultation data is sorted according to the total score corresponding to each consultation data. For the convenience of data processing, according to the total score, the order data is sorted from front to back, and the sorted consultation data is obtained, so that the system outputs the sorted consultation data.
- the embodiment of the present invention improves the intelligence of sorting by sorting the consultation data according to the number and weight of the search words.
- the file retrieval method of the present invention may be further after step S30 of the embodiment of FIG. Perform the following steps:
- Step S40 Monitor an operation event performed by the user based on the output of the inquiry data, and acquire and record the diagnosis data corresponding to the operation event.
- the operation event performed by the user for the consultation data is monitored, for example, a viewing operation event performed by the user for the consultation data, and a limited number based on the display.
- the number of consultation data is performed by the page turning operation or the sliding progress bar operation.
- the system acquires and records the diagnostic data corresponding to the above operation event by monitoring the operation event performed by the user for the consultation data.
- the diagnostic data described in the embodiments of the present invention can be understood as the medical examination data output by the system viewed by the user.
- the text retrieval method of the present invention is the embodiment described in FIG. After step S40, the following steps can also be performed:
- Step S50 Mark the diagnostic data, and dynamically evaluate, according to the index database, a weight value of the search term included in the diagnostic data in the index database.
- the system marks the diagnostic data and feeds it back to the index database; in order to improve the accuracy of the text retrieval, the index database on which the system queries the user-entered inquiry content is continuously If the update is changed, the system obtains the search term contained in the diagnostic data viewed by the user by monitoring the operation event performed by the user for the above-mentioned consultation data, and dynamically evaluates the weight value corresponding to the search term, and updates the index database for subsequent follow-up.
- a search query for the search term provides a basis.
- the embodiment of the present invention improves the retrieval efficiency by monitoring the operation event performed by the user and dynamically updating the weight value of the search term in the index database based on the operation event performed by the user.
- FIG. 6 is a schematic diagram of an operating environment of a text retrieval system 100 according to a preferred embodiment of the present invention.
- the text retrieval system 100 is installed and operated in the electronic device 1.
- the electronic device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server.
- the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13.
- Figure 6 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
- the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk or memory of the electronic device 1.
- the memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc.
- the memory 11 may also include an internal storage unit of the electronic device 1 as well as External storage device.
- the memory 11 is used to store application software and various types of data installed in the electronic device 1, such as program codes of the text retrieval system 100.
- the memory 11 can also be used to temporarily store data that has been output or is about to be output.
- the processor 12 in some embodiments, may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as executing a text retrieval system 100 and so on.
- CPU Central Processing Unit
- microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as executing a text retrieval system 100 and so on.
- the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like in some embodiments.
- the display 13 is for displaying information processed in the electronic device 1 and a user interface for displaying visualization, such as an inquiry content input interface or the like.
- the components 11-13 of the electronic device 1 communicate with one another via a system bus.
- FIG. 7 is a schematic diagram of functional modules of an embodiment of the text retrieval system 100 of the present invention.
- the text retrieval system 100 can be partitioned into one or more modules, one or more modules being stored in the memory 11 and being processed by one or more processors (the processor 12 in this embodiment). Executed to complete the present invention.
- the text retrieval system 100 can be divided into: a word processing module 110, a data retrieval module 120, and a data output module 130.
- module refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable than the program for describing the execution process of the text retrieval system 100 in the electronic device 1, wherein:
- the word processing module 110 is configured to perform text pre-processing on the content of the inquiry input by the user, and obtain a pre-processed search term for performing information retrieval on the inquiry content;
- the data retrieval module 120 is configured to perform a document matching on the search term according to the obtained search term, obtain a corresponding consultation data, and perform the consultation data according to the degree of association with the search term. Sort
- the data output module 130 is configured to output the consultation data corresponding to the inquiry content according to the sorting result.
- the data retrieval module 120 is further configured to:
- the consultation data is sorted from front to back according to the size of the score value corresponding to the consultation data.
- the word processing module 110 of the text retrieval system 100 includes:
- the word-cutting unit 111 is configured to perform a Chinese word-cutting on the content of the inquiry input by the user;
- the extracting unit 112 is configured to extract a corresponding central word from the content of the consultation after the word is cut according to the preset extraction rule;
- the expansion unit 113 is configured to perform association expansion on the extracted central word to obtain a related word associated with the central word; and use the central word and the related word as the search term corresponding to the inquiry content.
- the text retrieval system 100 of the present invention further includes:
- the operation monitoring module 140 is configured to monitor an operation event performed by the user based on the output of the inquiry data, and acquire and record the diagnosis data corresponding to the operation event.
- the text retrieval system 100 of the present invention further includes:
- the dynamic evaluation module 150 is configured to mark the diagnostic data, and dynamically evaluate, according to the index database, a weight value of the search term included in the diagnostic data in the index database.
- the text retrieval system of the embodiment of the present invention performs text pre-processing on the content of the inquiry input by the user, and obtains a pre-processed search term for information retrieval of the inquiry content;
- the search term, the query index database performs document matching on the search term, obtains corresponding consultation data, and sorts the consultation data according to the degree of association with the search term; according to the sort result, outputs the question
- the consultation data corresponding to the diagnosis content the beneficial effect of fully automated online online consultation process, saving valuable medical resources, improving the efficiency of consultation and the utilization of medical resources.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种文本检索方法及系统,包括:对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词(S10);根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序(S20);按照排序结果,输出所述问诊内容对应的问诊数据(S30)。该方法和系统能够达到互联网在线问诊过程全自动化的目的,节约了医疗资源,提高了问诊效率和医疗资源的利用率。
Description
本申请申明享有2017年5月5日递交的申请号为201710313524.X、名称为“文本检索方法及系统”的中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
本发明涉及互联网技术领域,尤其涉及一种文本检索方法、电子装置、计算机可读存储介质及系统。
近年来,随着互联网技术的高速发展和逐渐普及,互联网也越来越多的参与到人们的工作和生活中来。目前,基于医疗资源紧张、看病贵、看病难等问题的存在,越来越多的用户开始在网上进行健康保健咨询,或者查阅病情等;例如,进行轻微的或者普通的伤病自诊断,比如感冒、扭伤脚等。而互联网在线问诊平台是互联网在医疗领域的新应用,因其高效和便捷,得到了越来越多用户的青睐。
但现有的互联网在线问诊平台中,通常采用如下方式进行互联网在线问诊:患者在问诊平台的一端描述自己的病情症状,由问诊平台另一端的医生根据用户描述的症状做出诊断,并且提供建议给患者。这种问诊方式依然依赖实际中的医生,仅仅是将在病房中的面对面,迁移至了互联网平台上,但并未从根本上对医疗资源紧张这一实质问题进行彻底解决。
发明内容
本发明的目的在于提供一种文本检索方法、电子装置、计算机可读存储介质及系统,旨在达到互联网在线问诊过程的全自动化的目的。
为实现上述目的,本发明提供一种文本检索方法,所述文本检索方法包括:
对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
按照排序结果,输出所述问诊内容对应的问诊数据。
为实现上述目的,本发明还提供一种文本检索系统,所述文本检索系统包括:
文字处理模块,用于对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
数据检索模块,用于根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
数据输出模块,用于按照排序结果,输出所述问诊内容对应的问诊数据。
此外,本发明还提供一种电子装置,该电子装置包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的文本检索系统,所述处理器执行所述文本检索系统,可实现如下步骤:
对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
按照排序结果,输出所述问诊内容对应的问诊数据。
进一步地,本发明还提供一种计算机可读存储介质,所述计算机可读存储介质存储有文本检索系统,所述文本检索系统可被至少一个处理器执行,以实现以下步骤:
对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
按照排序结果,输出所述问诊内容对应的问诊数据。
本发明的有益效果是:通过对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据;达到了互联网在线问诊过程全自动化的目的,节约了宝贵的医疗资源,提高了问诊效率和医疗资源利用率。
图1为本发明文本检索方法的一种实施方式的流程示意图;
图2为图1所述实施例中步骤S10的一种实施方式的流程示意图;
图3为图1所述实施例的步骤S20中“将所述问诊数据按照与所述检索词的关联程度进行排序”的一种实施方式的流程示意图;
图4为本发明文本检索方法的另一种实施方式的流程示意图;
图5为本发明文本检索方法的又一种实施方式的流程示意图;
图6为本发明文本检索系统100较佳实施例的运行环境示意图;
图7为本发明文本检索系统100的一种实施方式的功能模块示意图;
图8为图7所述实施例的数据检索模块110的一种实施方式的功能模块
示意图;
图9为本发明文本检索系统100中的另一种实施方式的功能模块示意图;
图10为本发明文本检索系统100中的又一种实施方式的功能模块示意图。
以下结合附图对本发明的原理和特征进行描述,所举实例只用于解释本发明,并非用于限定本发明的范围。
本发明提供了一种文本检索方法,旨在达到互联网在线问诊过程的全自动化的目的。如图1所示,图1为本发明文本检索方法的一种实施方式的流程示意图,所述文本检索方法可以实施为如下步骤S10-S30:
步骤S10、对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
本发明实施例中,系统接收到用户基于在线问诊平台对应的输入控件输入的问诊内容,对用户输入的上述问诊内容进行文字预处理,例如,对用户输入的问诊内容进行中文切词,或者直接提取出用户输入的问诊内容中的关键词,或者,仅仅只是进行单纯的文字处理(比如,修正错别字等);对用户输入的上述问诊数据进行预处理后,得到对应的检索词,以便后续系统利用得到的检索词对用户输入的上述问诊内容进行信息检索。
步骤S20、根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
系统根据对问诊内容预处理后得到的检索词,查询对应的索引数据库。本发明实施例中,所述的索引数据库是预先建立的;例如,针对疾病问诊这一具体的检索平台,系统预先建立索引数据库时,将互联网上开源的医学问诊数据以及系统自身积累的问诊数据作为依据,来组建该索引数据库。且该索引数据库基于社会发展以及时事热点进行不断更新和补充,例如,针对季节性流行病和新型病变,不断扩充该索引数据库;另外,系统也将会根据用户针对索引平台的具体使用情况,不断调整该索引数据库的存储内容。
系统利用检索词查询索引数据库时,其具体的查询方式包括但不限于:直接将索引数据库中包含检索词对应的问诊数据挑选出来,或者,将索引数据库中包含检索词以及检索词对应的近义词的问诊数据挑选出来;或者,将索引数据库中包含检索词以及检索词对应的关联词的问诊数据挑选出来。其中,检索词对应的近义词可以理解为:与检索词词义相近的词语,例如,胳膊和手臂可以理解为二者互为近义词,大腿和腿部可以理解为二者互为近义词。检索词对应的关联词可以理解为:与检索词词义相关联的词语,例如,手指头和脚趾头可以理解为相互关联的词语。
系统得到检索词对应的问诊数据后,根据与检索词的关联程度对问诊数据进行排序;比如,按照与检索词关联程度的高低,由先至后的对得到的问诊数据进行排序。本发明实施例中,系统得到的问诊数据与检索词的关联程度主要由问诊数据中所包含的检索词的个数来决定,问诊数据中包含的检索词的个数越多,其关联程度将越高。在具体的应用场景中,系统可以根据不同的应用场景来确定问诊数据与检索词的关联程度的具体判断方式,本发明实施例对问诊数据与检索词的关联程度的具体确定方式不作具体限定。
步骤S30、按照排序结果,输出所述问诊内容对应的问诊数据。
系统根据对问诊数据的排序结果,输出用户输入的问诊内容所对应的问诊数据。本发明实施例中,系统输出问诊数据的具体呈现方式包括但不限于:直接将问诊数据显示在用户操作界面上;或者,将问诊数据发送至关联的客户端,例如通过短消息发送至手机号码上或者发送至微信等,便于用户保存等。另外,针对系统直接将问诊数据显示在用户操作界面上这一输出方式,在一优选的实施例中,为了便于用户快捷地找出想要的结果,系统仅将排在前面的预设数量问诊数据显示出来,比如,根据用户操作界面的大小,仅显示前五条问诊数据,或者前八条问诊数据等。本发明实施例对系统输出问诊数据的具体输出方式不进行具体限定。
与现有技术相比,本实施例文本检索方法通过对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据;具有互联网在线问诊过程全自动化的有益效果,节约了宝贵的医疗资源,提高了问诊效率和医疗资源利用率。
在一优选的实施例中,如图2所示,在上述图1的所述实施例的基础上,本发明文本检索方法图1所述实施例中的步骤S10可以实施为如下描述的步骤S11-S14:
步骤S11、对用户输入的问诊内容进行中文切词;
步骤S12、按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;
本发明实施例中,系统接收用户输入的问诊内容,对用户输入的问诊内容进行中文切词。系统从切词后的问诊内容中提取对应的中心词时,可以按照疾病名、药品名、诊断、身体部位、医学名词进行提取;例如,用户输入的问诊内容为“踢球崴了脚”,则系统从切词后的问诊内容中,提取出如下中心词“崴”“脚”。
本发明实施例中,中文切词也可以理解为中文分词,指的是将一个汉字序列切分成一个一个单独的词。中文分词是文本挖掘的基础,对于输入的一段中文,成功的进行中文分词,可以达到电脑自动识别语句含义的效果。这
种方法又叫做机械分词方法,它是按照一定的策略将待分析的汉字串与一个“充分大的”机器词典中的词条进行配,若在词典中找到某个字符串,则匹配成功(识别出一个词);而在本发明文本检索方法这一具体的应用中,索引数据库便具备上述“机器词典”的全部功能。
步骤S13、对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;
步骤S14、将所述中心词和关联词作为所述问诊内容对应的检索词。
系统对提取出的中心词进行关联性扩展时,对必要的中心词查询医学关联词,得到与中心词相关联的关联词,达到扩展搜索内容的目的。本发明实施例中,系统将疾病名、药品名、诊断、身体部位作为“必要的中心词”,进行关联性扩展。例如,将“胳膊”扩展到“手臂”;将“对乙酰氨基酚”扩展到“美林”、“泰诺林”等。扩展后,将中心词和与中心词相关联的关联词一起作为问诊内容对应的检索词,进行问诊数据的检索,扩大检索范围,避免数据遗漏。
与现有技术相比,本实施例通过扩展中心词进行检索,提高了检索的准确率,避免因数据遗漏造成的检索数据不齐全的问题。
在一优选的实施例中,如图3所示,在上述图1和图2的所述实施例的基础上,本发明文本检索方法图1所述实施例的步骤S20中,“将所述问诊数据按照与所述检索词的关联程度进行排序”可以实施为如下描述的步骤S21-S24:
步骤S21、获取所述问诊数据中包含的所述检索词的数量;
步骤S22、参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;
步骤S23、根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;
步骤S24、按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
本发明实施例中,系统基于得到的每一条问诊数据,获取该问诊数据所包含的检索词的数量,基于用户输入的问诊内容,从索引数据库中查询该问诊数据中所包含的每一个检索词的权重值,将每一个检索词对应的数据量乘以该检索词对应的权重值,得到该检索词在该条问诊数据中的检索分值,将同一条问诊数据中包含的所有检索词对应的检索分值分别相加,得到该条问诊数据对应的总分值,按照每一条问诊数据对应的总分值,对问诊数据进行排序。为了数据处理的便捷性,按照总分值的由大到小,对问诊数据按照由前到后进行排序,得到排序后的问诊数据,以便系统输出排序后的问诊数据。
与现有技术相比,本发明实施例通过按照检索词的数量和权重对问诊数据进行排序,提高了排序的智能性。
在一优选的实施例中,如图4所示,在上述图1、图2和图3所述实施例的基础上,本发明文件检索方法在图1所述实施例的步骤S30之后还可以执行如下步骤:
步骤S40、监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
本发明实施例中,系统输出问诊内容对应的问诊数据后,监测用户针对该问诊数据所执行的操作事件,例如,用户针对上述问诊数据执行的查看操作事件、基于显示的有限条数的问诊数据执行的翻页操作或者下滑进度条操作等。通过监测用户针对问诊数据所执行的操作事件,系统获取并记录上述操作事件对应的诊断数据。本发明实施例所描述的诊断数据可以理解为:用户查看的系统所输出的问诊数据。
进一步地,在一优选的实施例中,如图5所示,在上述图1、图2、图3和图4所述实施例的基础上,本发明文本检索方法在图4所述实施例的步骤S40之后还可以执行如下步骤:
步骤S50、标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
本发明实施例中,系统基于监测并获取的诊断数据,将上述诊断数据进行标记后反馈至索引数据库;为了提高文本检索的准确性,系统查询用户输入的问诊内容所基于的索引数据库是不断更新变化的,系统通过监测用户针对上述问诊数据所执行的操作事件,获取用户查看的诊断数据中所包含的检索词,并动态评估该检索词对应的权重值,更新索引数据库,为后续相同检索词的再次检索查询,提供依据。
与现有技术相比,本发明实施例通过监测用户执行的操作事件并基于用户执行的操作事件动态更新索引数据库中的检索词的权重值,提高了检索效率。
请参阅图6,图6为本发明文本检索系统100较佳实施例的运行环境示意图。
基于图1至图5所述实例文本检索方法所公开的内容,在本实施例中,文本检索系统100安装并运行于电子装置1中。电子装置1可以是桌上型计算机、笔记本、掌上电脑及服务器等计算设备。该电子装置1可包括,但不仅限于,存储器11、处理器12及显示器13。图6仅示出了具有组件11-13的电子装置1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
存储器11在一些实施例中可以是电子装置1的内部存储单元,例如该电子装置1的硬盘或内存。存储器11在另一些实施例中也可以是电子装置1的外部存储设备,例如电子装置1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,存储器11还可以既包括电子装置1的内部存储单元也包括
外部存储设备。存储器11用于存储安装于电子装置1的应用软件及各类数据,例如文本检索系统100的程序代码等。存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU),微处理器或其他数据处理芯片,用于运行存储器11中存储的程序代码或处理数据,例如执行文本检索系统100等。
显示器13在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。显示器13用于显示在电子装置1中处理的信息以及用于显示可视化的用户界面,例如问诊内容输入界面等。电子装置1的部件11-13通过系统总线相互通信。
请参阅图7,图7为本发明文本检索系统100的一种实施方式的功能模块示意图。在本实施例中,文本检索系统100可以被分割成一个或多个模块,一个或者多个模块被存储于存储器11中,并由一个或多个处理器(本实施例为处理器12)所执行,以完成本发明。例如,在图7中,文本检索系统100可以被分割成:文字处理模块110、数据检索模块120及数据输出模块130。本发明所称的模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述文本检索系统100在电子装置1中的执行过程,其中:
文字处理模块110,用于对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;
数据检索模块120,用于根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;
数据输出模块130,用于按照排序结果,输出所述问诊内容对应的问诊数据。
在本发明一优选的实施例中,如图7所示,本发明文本检索系统中,所述数据检索模块120还用于:
获取所述问诊数据中包含的所述检索词的数量;
参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;
根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;
按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
在本发明一优选的实施例中,如图8所示,图7所述实施例中,所述文本检索系统100的所述文字处理模块110包括:
切词单元111,用于对用户输入的问诊内容进行中文切词;
提取单元112,用于按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;
扩展单元113,用于对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;将所述中心词和关联词作为所述问诊内容对应的检索词。
在本发明一优选的实施例中,如图9所示,本发明文本检索系统100还包括:
操作监测模块140,用于监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
在本发明一优选的实施例中,如图10所示,本发明文本检索系统100还包括:
动态评估模块150,用于标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
与现有技术相比,本发明实施例文本检索系统通过对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据;具有互联网在线问诊过程全自动化的有益效果,节约了宝贵的医疗资源,提高了问诊效率和医疗资源利用率。
以上所述仅为本发明的较佳实施例,并不用以限制本发明,凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。
Claims (20)
- 一种文本检索方法,其特征在于,所述文本检索方法包括:对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据。
- 如权利要求1所述的文本检索方法,其特征在于,所述对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词的步骤,包括:对用户输入的问诊内容进行中文切词;按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;将所述中心词和关联词作为所述问诊内容对应的检索词。
- 如权利要求1所述的文本检索方法,其特征在于,所述将所述问诊数据按照与所述检索词的关联程度进行排序,包括:获取所述问诊数据中包含的所述检索词的数量;参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
- 如权利要求1所述的文本检索方法,其特征在于,所述文本检索方法还包括:监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
- 如权利要求4所述的文本检索方法,其特征在于,所述文本检索方法还包括:标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
- 一种电子装置,其特征在于,该电子装置包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的文本检索系统,所述处理器执行所述文本检索系统,可实现如下步骤:对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据。
- 如权利要求6所述的电子装置,其特征在于,所述对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词的步骤,包括:对用户输入的问诊内容进行中文切词;按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;将所述中心词和关联词作为所述问诊内容对应的检索词。
- 如权利要求6所述的电子装置,其特征在于,所述将所述问诊数据按照与所述检索词的关联程度进行排序的步骤,包括:获取所述问诊数据中包含的所述检索词的数量;参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
- 如权利要求6所述的电子装置,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
- 如权利要求9所述的电子装置,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
- 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有文本检索系统,所述文本检索系统可被至少一个处理器执行,以实现以下步骤:对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据。
- 如权利要求11所述的计算机可读存储介质,其特征在于,所述对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词的步骤,包括:对用户输入的问诊内容进行中文切词;按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;将所述中心词和关联词作为所述问诊内容对应的检索词。
- 如权利要求11所述的计算机可读存储介质,其特征在于,所述将所述问诊数据按照与所述检索词的关联程度进行排序,包括:获取所述问诊数据中包含的所述检索词的数量;参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
- 如权利要求11所述的计算机可读存储介质,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
- 如权利要求14所述的计算机可读存储介质,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
- 一种文本检索系统,其特征在于,所述文本检索系统可被至少一个处理器执行,以实现以下步骤:对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词;根据得到的所述检索词,查询索引数据库对所述检索词进行文档匹配,得到对应的问诊数据,将所述问诊数据按照与所述检索词的关联程度进行排序;按照排序结果,输出所述问诊内容对应的问诊数据。
- 如权利要求16所述的文本检索系统,其特征在于,所述对用户输入的问诊内容进行文字预处理,得到预处理后的用于对所述问诊内容进行信息检索的检索词的步骤,包括:对用户输入的问诊内容进行中文切词;按照预设提取规则,从切词后的问诊内容中提取出对应的中心词;对提取出的中心词进行关联性扩展,得到与所述中心词相关联的关联词;将所述中心词和关联词作为所述问诊内容对应的检索词。
- 如权利要求16所述的文本检索系统,其特征在于,所述将所述问诊数据按照与所述检索词的关联程度进行排序,包括:获取所述问诊数据中包含的所述检索词的数量;参照用户输入的所述问诊内容,从所述索引数据库中查询并获取所述检索词对应的权重值;根据所述检索词在所述问诊数据中的数量以及所述检索词的权重值,计算所述问诊数据对应的得分值;按照所述问诊数据对应的得分值的大小,由前至后对所述问诊数据进行排序。
- 如权利要求16所述的文本检索系统,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:监测用户基于输出的所述问诊数据执行的操作事件,获取并记录所述操作事件对应的诊断数据。
- 如权利要求19所述的文本检索系统,其特征在于,所述处理器执行所述文本检索系统,还可实现如下步骤:标记所述诊断数据,基于所述索引数据库,动态评估所述诊断数据中包含的所述检索词在所述索引数据库中的权重值。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710313524.X | 2017-05-05 | ||
| CN201710313524.XA CN107766400A (zh) | 2017-05-05 | 2017-05-05 | 文本检索方法及系统 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2018201668A1 true WO2018201668A1 (zh) | 2018-11-08 |
Family
ID=61265237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2017/105005 Ceased WO2018201668A1 (zh) | 2017-05-05 | 2017-09-30 | 文本检索方法、电子装置、计算机可读存储介质及系统 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107766400A (zh) |
| WO (1) | WO2018201668A1 (zh) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109036506B (zh) * | 2018-07-25 | 2023-04-18 | 平安科技(深圳)有限公司 | 互联网医疗问诊的监管方法、电子装置及可读存储介质 |
| CN111341457B (zh) * | 2020-02-25 | 2024-05-10 | 广州七乐康药业连锁有限公司 | 一种基于大数据检索的医疗诊断信息可视化方法及装置 |
| CN114116736A (zh) * | 2020-09-01 | 2022-03-01 | 上海智臻智能网络科技股份有限公司 | 知识库更新、更新验证和基于知识库的搜索方法及装置 |
| CN111966884B (zh) * | 2020-10-21 | 2021-01-26 | 北京妙医佳健康科技集团有限公司 | 一种信息推送方法和装置 |
| CN113827274B (zh) * | 2021-11-23 | 2022-02-22 | 广东恒腾科技有限公司 | 一种无线彩超设备的自动控制系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030033279A1 (en) * | 2001-05-04 | 2003-02-13 | Gibson Michael A. | Methods and apparatus for high-speed approximate sub-string searches |
| CN101158971A (zh) * | 2007-11-15 | 2008-04-09 | 深圳市迅雷网络技术有限公司 | 一种基于搜索引擎的搜索结果排序方法及装置 |
| CN103136352A (zh) * | 2013-02-27 | 2013-06-05 | 华中师范大学 | 基于双层语义分析的全文检索系统 |
| CN103309886A (zh) * | 2012-03-13 | 2013-09-18 | 阿里巴巴集团控股有限公司 | 一种基于交易平台的结构化信息搜索方法和装置 |
| CN103425687A (zh) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | 一种基于关键词的检索方法和系统 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5963940A (en) * | 1995-08-16 | 1999-10-05 | Syracuse University | Natural language information retrieval system and method |
| AU2448101A (en) * | 1999-12-20 | 2001-07-03 | Answerchase, Inc. | Answer retrieval technique |
| CN1389811A (zh) * | 2002-02-06 | 2003-01-08 | 北京造极人工智能技术有限公司 | 搜索引擎的智能化搜索方法 |
| CN100595763C (zh) * | 2008-02-26 | 2010-03-24 | 华中科技大学 | 基于自然语言的全文检索系统 |
| CN102289436B (zh) * | 2010-06-18 | 2013-12-25 | 阿里巴巴集团控股有限公司 | 确定搜索词权重值方法及装置、搜索结果生成方法及装置 |
| CN103530789B (zh) * | 2012-07-03 | 2018-09-07 | 百度在线网络技术(北京)有限公司 | 一种用于确定重点索引词的方法、装置和设备 |
-
2017
- 2017-05-05 CN CN201710313524.XA patent/CN107766400A/zh active Pending
- 2017-09-30 WO PCT/CN2017/105005 patent/WO2018201668A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030033279A1 (en) * | 2001-05-04 | 2003-02-13 | Gibson Michael A. | Methods and apparatus for high-speed approximate sub-string searches |
| CN101158971A (zh) * | 2007-11-15 | 2008-04-09 | 深圳市迅雷网络技术有限公司 | 一种基于搜索引擎的搜索结果排序方法及装置 |
| CN103309886A (zh) * | 2012-03-13 | 2013-09-18 | 阿里巴巴集团控股有限公司 | 一种基于交易平台的结构化信息搜索方法和装置 |
| CN103425687A (zh) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | 一种基于关键词的检索方法和系统 |
| CN103136352A (zh) * | 2013-02-27 | 2013-06-05 | 华中师范大学 | 基于双层语义分析的全文检索系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107766400A (zh) | 2018-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113707300B (zh) | 基于人工智能的搜索意图识别方法、装置、设备及介质 | |
| US11182445B2 (en) | Method, apparatus, server, and storage medium for recalling for search | |
| WO2018201668A1 (zh) | 文本检索方法、电子装置、计算机可读存储介质及系统 | |
| CN100492364C (zh) | 用于多语言信息检索的系统、方法、软件和界面 | |
| CN107609163B (zh) | 医学知识图谱的生成方法、存储介质及服务器 | |
| US9558263B2 (en) | Identifying and displaying relationships between candidate answers | |
| CN118296120A (zh) | 多模态多尺度多路召回的大型语言模型检索增强生成方法 | |
| CN111581337B (zh) | 医疗文本搜索方法、装置、计算机设备及存储介质 | |
| CN111460090A (zh) | 基于向量的文档检索方法、装置、计算机设备及存储介质 | |
| US20140365502A1 (en) | Determining Answers in a Question/Answer System when Answer is Not Contained in Corpus | |
| CN111695336A (zh) | 疾病名称对码方法、装置、计算机设备及存储介质 | |
| US20230376682A1 (en) | Information search system and information search method using index | |
| CN114860887B (zh) | 基于智能联想的疾病内容推送方法、装置、设备及介质 | |
| CN108427702B (zh) | 目标文档获取方法及应用服务器 | |
| WO2023029510A1 (zh) | 基于人工智能的远程问诊方法、装置、设备及介质 | |
| CN114139530A (zh) | 同义词提取方法、装置、电子设备及存储介质 | |
| CN112527954A (zh) | 非结构化数据全文搜索方法、系统及计算机设备 | |
| CN110569419A (zh) | 问答系统优化方法、装置、计算机设备及存储介质 | |
| CN114741492B (zh) | 文本搜索方法、装置、设备及存储介质 | |
| CN102737045A (zh) | 一种相关度计算方法和装置 | |
| CN114003712B (zh) | 基于人工智能的文档搜索方法、装置、设备及存储介质 | |
| CN103970732B (zh) | 新词译文的挖掘方法和装置 | |
| Zhao et al. | Scholar name disambiguation with search-enhanced LLM across language | |
| CN112182405A (zh) | 数据搜索方法、装置、设备及存储介质 | |
| CN113793668B (zh) | 基于人工智能的症状标准化方法、装置、电子设备及介质 |
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: 17908536 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 08.01.2020) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 17908536 Country of ref document: EP Kind code of ref document: A1 |