WO2020253391A1 - 一种基于数据分析的预检信息交互方法及相关设备 - Google Patents
一种基于数据分析的预检信息交互方法及相关设备 Download PDFInfo
- Publication number
- WO2020253391A1 WO2020253391A1 PCT/CN2020/087597 CN2020087597W WO2020253391A1 WO 2020253391 A1 WO2020253391 A1 WO 2020253391A1 CN 2020087597 W CN2020087597 W CN 2020087597W WO 2020253391 A1 WO2020253391 A1 WO 2020253391A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- preflight
- data
- check
- inspection
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- This application relates to the technical field of massive data analysis, and in particular to a data analysis-based preflight information interaction method and related equipment.
- Pre-screening refers to the process of quickly classifying patients to determine the priority of treatment departments or further treatment, and providing medical guidance when the patient has doubts about the way and process of medical treatment.
- most patients urgently need to solve the pre-inspection problems and the data obtained The information is asymmetric, and complete and effective information feedback cannot be obtained quickly.
- this application proposes a pre-inspection information interaction method and related equipment based on data analysis to solve the problem that patient pre-inspection information cannot be supported by effective data and cannot obtain complete and effective information feedback. .
- this application provides a data analysis-based preflight information interaction method, the method includes:
- the preflight information to be processed includes voice input information, text input information, or preset item selection information;
- the second aspect of the present application provides a data analysis-based preflight information interaction device.
- the data analysis-based preflight information interaction device has an implementation corresponding to the data analysis-based preflight information interaction method provided in the above first aspect.
- the function can be realized by hardware, or by hardware executing corresponding software.
- the hardware or software includes one or more modules corresponding to the above functions, and the modules may be software and/or hardware.
- the memory stores computer-readable instructions.
- the computer-readable instructions are executed by one or more of the processors, one or A plurality of the processors execute the steps of the methods described in the foregoing aspects.
- the present invention uses big data collection, including historical data collection of pre-check question information and corresponding pre-check question answer information, and uses probabilistic analysis to summarize important pre-check information, creating Pre-check information database containing important pre-check information, filter high-frequency entries in the database, based on this set some fixed options containing high-frequency entries, patients can directly get information feedback through these preset options, and another By receiving voice description information and text input information, database information matching is performed. When the matching is successful, the corresponding data information is displayed. When the matching is unsuccessful, a guiding instruction is generated to guide the patient inputting the pre-check information to the manual for consultation.
- the present application of the present invention improves the efficiency of data processing of the pre-inspection information by receiving, identifying and matching the pre-inspection information of the patient, and outputting the feedback content corresponding to the pre-inspection information, and also makes the pre-inspection information proposed by the patient get more and more comprehensive Data support.
- Figure 1 is an overall flowchart of a data analysis-based preflight information interaction method in an embodiment of the application
- FIG. 2 is a schematic diagram of a process of obtaining pre-flight information to be processed from an interactive platform in a data analysis-based preflight information interaction method in an embodiment of the present application;
- FIG. 3 is a schematic diagram of a process of establishing a pre-check information database in a data analysis-based pre-check information interaction method in an embodiment of the present application
- FIG. 4 is a schematic diagram of the process of identifying and matching the content of the acquired pre-inspection information to be processed in the pre-inspection information interaction method based on data analysis of this application;
- Figure 5 is a schematic structural diagram of a data analysis-based preflight information interaction device in an embodiment of the present application.
- the present invention provides a pre-check information interaction method and related equipment based on data analysis, which can be used in a medical pre-check system and can solve the problem of incomplete manual pre-check information data, inaccurate analysis mechanism, and patient pre-check information in existing mechanisms. Problems that do not get fast and efficient feedback.
- Fig. 1 is an overall flow chart of a pre-check information interaction method based on data analysis of this application. As shown in Fig. 1, a pre-check information interaction method based on data analysis includes the following steps:
- preflight information to be processed from the interactive platform, where the preflight information to be processed includes voice input information, text input information, or preset item selection information.
- the way to obtain the pre-check information is to provide different input interfaces through the patient's selection on the interactive platform to obtain the patient's pre-check information.
- the patient’s pre-inspection information includes the pre-inspection information input by the patient’s voice, the pre-inspection information input in the patient’s text, and the pre-inspection information selected by the patient through the interactive platform preset interface; the patient can enter himself through different choices on the interactive platform If you want to solve the problem, for example, when there is pre-inspection information that you want to consult in the preset interface, you can directly click the interface to select and confirm, or you can verbally ask: "Which department is the headache?", or you can type in "Which area the pharmacy is in” and many more.
- the method further includes: before acquiring the pre-flight information to be processed from the interactive platform, establishing a pre-flight information database for performing the preflight information content Recognition.
- the recognition includes the classification of the pre-inspection information content of different patients, the processing and analysis of the text content and logical relationship of the classified pre-inspection information, and then the keyword extraction of the pre-inspection information after the recognition, such as The keyword of "Which department has a fever" is: "Fever, department”.
- the extracted keywords are matched with the pre-check information database, and the corresponding data to be output instructions or guidance instructions are generated according to the matching results.
- corresponding expression information is generated according to different output instructions, and the expression information is fed back to the interactive platform in different expression forms, and the patient obtains corresponding data information or guidance information through the feedback content of the interactive platform.
- FIG. 2 is a schematic diagram of the process of obtaining pre-flight information to be processed from the interactive platform in a data analysis-based preflight information interaction method of this application.
- the step S1 and the slave The interactive platform acquires the preflight information to be processed, and the preflight information to be processed includes voice input information, text input information, or preset item selection information, including the following steps:
- S201 Receive a preflight information input form selected on the interactive platform, where the input form includes voice input, text input, and preset item selection;
- the interactive platform can be installed in a self-service terminal, the self-service terminal can be installed in the hospital's outpatient hall and each floor, the interactive platform can use the HIS system, and set the patient pre-check information in the system
- Different input forms are convenient for patients to make input choices. Different input forms for receiving pre-check information are determined by receiving patients’ choices. Patients can choose the input form that suits them. For example, the elderly with weak eyesight can choose the voice input form. Patients with inconvenience in vocalization can choose the form of text input, and patients with weak writing ability can choose preset items to choose the form of input.
- the corresponding input interface is provided to the patient according to the patient's choice.
- the voice input interface is provided, and the patient is voiced to state the pre-check information that needs consultation.
- the patient selects the text input interface it provides The text input interface displays the text input box and prompts the patient to enter text information in the text input box.
- the preset item selection interface is provided, and the major categories of the preset item selection interface are displayed, prompting the patient to do Further selection and determination.
- S203 Acquire voice input information, text input information, or preset item selection information through the information input interface, so as to obtain preflight information content.
- this step by recognizing the voice information described by the patient, sorting out the text in the text input box, and determining the pre-check information in the preset item selection interface, the pre-check information that the patient wants to consult is received.
- the interactive platform provides different input methods for the patient to enter their own pre-inspection information, thereby obtaining the patient’s pre-inspection information, and provides a variety of information data receiving methods, which is convenient for people of all ages and different education levels. It also saves patient consultation time.
- the voice input information, text input information, or preset item selection information obtained through the information input interface to obtain preflight information content includes the following steps:
- the input form is text input
- the input of preflight information is received through the text input interface, and the content of the preflight information is acquired and the information is saved.
- the patient's voice input is received through the pickup module and translated into text through the voice recognition engine, and the text information generated by the recognition is fed back through the voice input interface.
- the patient confirms that the information is correct obtain the patient Save the information after pre-checking the information content.
- the patient when the patient chooses voice input, he can dictate the pre-check information he wants to consult.
- the dictated content is received through the pickup module in the interactive platform.
- the received pre-check information is translated into text through the voice recognition engine.
- the text content is fed back to the voice input interface, and the patient confirms whether it is the pre-inspection information he wants to consult through the text information fed back by the interface, and the confirmed text information is the patient's pre-inspection information obtained by the system.
- the selected item is determined through the preset item selection interface, and the preflight information content of the selected item is obtained.
- the interactive platform displays the preset selection interface.
- the preset selection interface is arranged and displayed according to the common problem categories.
- the patient selects the major category option and enters the specific second level
- the preset item selection interface obtains the patient's pre-inspection information content by receiving the specific second-level preset item finally determined and selected by the patient.
- the corresponding processing mode is used to receive the patient's pre-inspection information, thereby realizing multiple ways of receiving the patient's pre-inspection information data.
- step S1 before obtaining the pre-check information to be processed from the interactive platform, a pre-check information database is established to identify the content of the obtained pre-check information.
- S301 Collect historical data of relevant pre-inspection information, including pre-inspection question information data and corresponding answer information data, and after forming a corresponding relationship between the two, a total sample of pre-inspection information is aggregated and generated.
- the importance value of each sample information can be calculated by probability statistics, and then the importance value of each sample information is compared with the initial prediction.
- the set importance threshold is compared, each sample set whose importance value exceeds the preset importance threshold is summarized and saved, and a preflight information database is generated based on all the saved sample information.
- filter all the high-frequency entries of the information samples of the pre-check information database such as "department”, "appointment”, etc.
- extract the information samples containing high-frequency entries and summarize them according to different information types.
- the sample set of is classified into several large problem categories, and each information sample containing high-frequency entries corresponds to one of the categories.
- Set all pre-inspection information categories and information samples containing high-frequency entries as fixed preset items. All pre-inspection information categories are used as the first-level display items of the preset item selection interface, corresponding to the pre-inspection information categories
- Information samples containing high-frequency terms are used as secondary display items in the preset item selection interface.
- the pre-flight information database is extracted through the collection, screening and classification of a large amount of pre-flight information historical data in the early stage, and some common preset items are set for filtering high-frequency entries, which not only makes the preflight information database
- the data is more complete and accurate, and the consultation speed of some common pre-check information is shortened through the display of preset items.
- the probability statistics method is used to analyze the importance of the pre-check information in the total sample of the pre-check information, and the importance of the analysis is combined with the preset importance threshold to summarize For preflight information samples that exceed the importance threshold, building a preflight information database based on these samples includes the following steps:
- P is the standard value for quantifying the importance of each pre-inspection information, that is, the importance index value of each pre-inspection information.
- the pre-inspection information A is "Which department does fever belong to?”
- Pre-inspection information with the same or similar inspection information A may include: “Which department is in fever”, “Which department is in fever”, “Which department is in high fever”, etc.
- the number of occurrences of all the above-mentioned pre-inspection information is counted, and the value obtained is The determined m value, its proportional count to the n value of the total number of samples of the pre-inspection information is the P-value of the pre-inspection information "Which department has fever?"
- the importance analysis is specifically a comparison between the importance index value of a certain pre-check information and a preset importance threshold, when the importance index value of the pre-check information is greater than the importance At the threshold value, the pre-check information is an important pre-check problem and can be determined as sample information. For example, if the pre-set importance threshold is 0.1, when the importance index value of the question "Which department is the fever?" P>0.1, the question "Which department is the fever?" is important pre-check information, which can be determined as Important pre-check information sample.
- the obtained important pre-inspection information samples can be sorted according to different sorting methods, and the sorted pre-inspection information samples are aggregated to establish a pre-inspection information database.
- the importance of each pre-inspection information sample is calculated through a probability formula, and the pre-inspection information sample set whose importance exceeds the threshold is aggregated into a pre-inspection information database, and the importance of the pre-inspection information samples is screened , To ensure that every sample data in the pre-check information database is the pre-check information data that patients often consult.
- FIG. 4 is a schematic diagram of the process of identifying and matching the content of the obtained pre-flight information to be processed in the preflight information interaction method based on data analysis of this application, as shown in Figure 4,
- step S2 the content of the acquired preflight information to be processed is identified, the keywords are extracted, and the preflight information database is traversed according to the extracted keywords to perform correlation matching.
- the matching is successful, the corresponding Information data and generate data to be output instructions.
- generating a guidance instruction includes the following steps:
- classifying and identifying the content of the acquired patient pre-check information includes classifying the pre-check information content of different patients, and processing and analyzing the text content and logical relationship of the pre-check information after the classification For example, if the pre-inspection information is “fever, very hot, where to find the doctor?” After identification, it can be classified as consultation question information related to “department”, and then after the second analysis based on the symptom description, it can be transformed into Pre-check information with a more logical relationship such as "Which department should you have a fever” or "Which department doctor should you have a fever”, and then extract the keywords of the identified patient pre-check information. The keywords can be "fever” and so on.
- Words and sentences related to disease symptoms can also be words and sentences related to the procedure of medical treatment such as "registered”.
- the matching keywords can be the same or similar words, such as the keyword “fever”, the same “fever” or similar " Words such as “febrile”, “high fever”, and “high fever” may all match it.
- the search result is marked by the matching degree of the keyword. For example, when the search result of the keyword "fever" shows 9 items, it means that there are 9 items of preflight information in the preflight information database that match the keywords. Mark the 9 pieces of information to confirm that the match is successful; if the keyword search result shows 0, it means that there is no pre-check information that matches the keyword in the pre-check information database, which means that the keyword cannot be hit, and the patient is marked The preflight information of is not matched successfully.
- the corresponding information data is extracted based on the matched pre-inspection information sample, and generated based on the data Instructions to be output;
- the system automatically calls the guidance instructions to generate the instructions to be output, the guidance instructions may include secondary input instructions , Change the input form instructions or direct them to the manual consultation desk for consultation instructions.
- pre-inspection information feedback instructions are obtained.
- step S3, outputting the generated data to-be-output instruction or the guidance instruction to the interactive platform includes the following steps:
- the data information content is sorted according to the generated corresponding data pending output instructions, and the corresponding data presentation information is generated. For example, when the pre-inspection information with the keyword "fever" is matched successfully, the generated data to be output instructions are sorted by content, and the expression information: "please go to the respiratory department to register" can be generated.
- the corresponding guidance instruction expression information is generated according to the guidance instruction.
- the corresponding expression information is generated according to the generated guidance instruction, for example, when the guidance instruction is a secondary input instruction, the expression information It can be: “please re-enter the question you want to consult”.
- the expression information can be: “you can try to change the input method to enter the question you want to consult”.
- the stated information can be "the system cannot find relevant information, if you need help, please go to the manual consultation desk” to guide the patient to the manual service desk Consult again.
- the expression information is output to the interactive platform in different expression forms, and the expression form may adopt an output method including voice broadcast or text display on the interface of the interactive platform.
- the expression information includes data expression information or guiding expression information, and the patient can receive the expression information by selecting different expression forms.
- the interactive platform will verbally play the presentation information to the patient through the player of the system.
- the interactive platform will display the presentation information in text In the text output box of the platform interface, feedback to the patient.
- the expression information is fed back to the patient through different expression forms, which facilitates the patient to receive the feedback information more conveniently and quickly.
- the guidance information is fed back to the patient when the matching is not successful, ensuring that the patient's pre-check information is final Feedback and resolve.
- a pre-inspection information interaction device based on data analysis includes the following modules:
- the information receiving module is configured to obtain preflight information to be processed from the interactive platform, where the preflight information to be processed includes voice input information, text input information, or preset item selection information;
- the information recognition and matching module is configured to recognize the content of the acquired pre-flight information to be processed, extract keywords therein, traverse the preflight information database according to the extracted keywords, and perform correlation matching.
- the matching is successful , Extract the corresponding information data and generate data to be output instructions, when the matching is unsuccessful, generate guidance instructions;
- the instruction output module is configured to output the generated data to-be-output instruction or the guide instruction to the interactive platform.
- a computer device including a memory and a processor, and computer-readable instructions are stored in the memory.
- the one or more processors execute The computer-readable instructions implement the steps of the data analysis-based preflight information interaction method described in the foregoing embodiments.
- the steps include: S1, obtaining pre-flight information to be processed from the interactive platform, where the pre-flight information to be processed includes voice input information, text input information, or preset item selection information; S2, the obtained pending preflight information
- the content of the preflight information is identified, the keywords are extracted, and the preflight information database is traversed according to the extracted keywords to perform correlation matching.
- the matching is successful, the corresponding information data is extracted and the data to be output instructions are generated.
- the matching is not successful When the time, a guide instruction is generated; S3, the generated data to be output instruction or the guide instruction is output to the interactive platform.
- a storage medium storing computer-readable instructions.
- the one or more processors execute the operations described in the foregoing embodiments. Steps of the pre-inspection information interaction method based on data analysis.
- the storage medium may be a non-volatile storage medium or a volatile storage medium.
- the steps include: S1, obtaining pre-flight information to be processed from the interactive platform, where the pre-flight information to be processed includes voice input information, text input information, or preset item selection information; S2, the obtained pending preflight information The content of the preflight information is identified, the keywords are extracted, and the preflight information database is traversed according to the extracted keywords to perform correlation matching. When the matching is successful, the corresponding information data is extracted and the data to be output instructions are generated. The matching is not successful When, generate a guidance instruction; S3, output the generated data to-be-output instruction or the guidance instruction to the interactive platform.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
Claims (20)
- 一种基于数据分析的预检信息交互方法,其中,包括:从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息;对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令;将生成的所述数据待输出指令或者所述引导指令,输出于交互平台。
- 如权利要求1所述的一种基于数据分析的预检信息交互方法,其中,所述从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息,包括:接收交互平台上选择的预检信息输入形式,所述输入形式包括语音输入、文字输入、预设项选择;根据所述选择的预检信息输入形式,向病人提供对应的信息输入界面,所述信息输入界面包括与所述语音输入形式对应的语音输入界面、与所述文字输入形式对应的文字输入界面或者与所述预设项选择输入形式对应的预设项选择界面;通过所述信息输入界面获取语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容。
- 如权利要求2所述的一种基于数据分析的预检信息交互方法,其中,所述通过所述信息输入界面获取的语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容,包括:当输入形式为文字输入时,通过文字输入界面接收预检信息的输入,获取预检信息内容后保存信息;当输入形式为语音输入时,通过拾音模块接收语音输入,并通过语音识别引擎转译为文字后,通过语音输入界面反馈识别生成的文字信息,并在该文字信息被确认为正确后,获取预检信息内容后保存信息;当输入形式为预设项选择时,通过预设项选择界面确定选择项目,获取被选择项目的预检信息内容。
- 如权利要求1所述的一种基于数据分析的预检信息交互方法,其中,在所述的从交互平台获取待处理的预检信息之前,建立预检信息数据库,用于对获取的预检信息内容进行识别,包括:采集相关预检信息的历史数据,包括预检问题信息数据和相对应的答案信息数据,两者之间形成对应关系后,汇总生成预检信息总样本;运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析, 根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库;筛选所述预检信息数据库中的高频词条,将包含所述高频词条的相关预检信息设置为固定的预设项,作为预设项选择界面的显示项目。
- 如权利要求4所述的一种基于数据分析的预检信息交互方法,其中,所述运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析,根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库,包括:根据概率学公式:P(A)=m/n计算所述预检信息总样本中的预检信息的重要度,其中,P(A)值为某一预检信息A的重要度量化体现,m指与预检信息A相同或相似的预检信息出现的次数,n指预检信息总样本数;进行所述重要度分析,包括P(A)值与设定的重要度阈值进行对比,当某一预检信息样本A的P(A)值大于所述重要度阈值时,标记此预检信息A为重要的预检信息样本;将标记的重要的预检信息样本汇总后建立预检信息数据库。
- 如权利要求1所述的一种基于数据分析的预检信息交互方法,其中,对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令,包括:对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词,遍历预检信息数据库,搜寻与所述提取的关键词相同或相近似的可能语句进行信息相关度匹配;搜寻结果命中关键词时,标记所述搜寻结果与所述的获取的待处理预检信息匹配成功,搜寻结果为零时,标记所述的获取的待处理预检信息匹配不成功;根据所述搜寻结果与所述的获取的待处理预检信息匹配成功的标记,提取所述搜寻结果相对应的预检信息数据,并据此生成数据待输出的指令,根据所述获取的待处理预检信息匹配不成功的标记,生成引导指令。
- 如权利要求1所述的一种基于数据分析的预检信息交互方法,其中,将生成的所述数据待输出指令或者所述引导指令,输出于交互平台,包括:当所述的获取的待处理预检信息匹配成功时,根据所述数据待输出的指令,生成相应的数据表述信息;当所述的获取的待处理预检信息匹配不成功时,根据所述引导指令,生成相应的引导指令表述信息;将所述表述信息用不同表述形式输出于所述交互平台,所述表述形式可采用包括语音播报或交互平台界面文字显示的输出方式。
- 一种基于数据分析的预检信息交互装置,其中,包括如下模块:信息接收模块,设置为从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息;信息识别匹配模块,设置为对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令;指令输出模块,设置为将生成的所述数据待输出指令或者所述引导指令,输出于交互平台。
- 一种计算机设备,其中,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述计算机可读指令被一个或多个所述处理器执行时,使得一个或多个所述处理器执行如下步骤:从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息;对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令;将生成的所述数据待输出指令或者所述引导指令,输出于交互平台。
- 如权利要求9所述的计算机设备,其中,所述从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息,包括:接收交互平台上选择的预检信息输入形式,所述输入形式包括语音输入、文字输入、预设项选择;根据所述选择的预检信息输入形式,向病人提供对应的信息输入界面,所述信息输入界面包括与所述语音输入形式对应的语音输入界面、与所述文字输入形式对应的文字输入界面或者与所述预设项选择输入形式对应的预设项选择界面;通过所述信息输入界面获取语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容。
- 如权利要求10所述的计算机设备,其中,所述通过所述信息输入界面获取的语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容,包括:当输入形式为文字输入时,通过文字输入界面接收预检信息的输入,获取预检信息内容后保存信息;当输入形式为语音输入时,通过拾音模块接收语音输入,并通过语音识别引擎转译为文字后,通过语音输入界面反馈识别生成的文字信息,并在该文字信息被确认为正确后,获取预检信息内容后保存信息;当输入形式为预设项选择时,通过预设项选择界面确定选择项目,获取被选择项目的预检信息内容。
- 如权利要求9所述的计算机设备,其中,在所述的从交互平台获取待处理的预检信息之前,建立预检信息数据库,用于对获取的预检信息内容进行识别,包括:采集相关预检信息的历史数据,包括预检问题信息数据和相对应的答案信息数据,两者之间形成对应关系后,汇总生成预检信息总样本;运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析,根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库;筛选所述预检信息数据库中的高频词条,将包含所述高频词条的相关预检信息设置为固定的预设项,作为预设项选择界面的显示项目。
- 如权利要求12所述的计算机设备,其中,所述运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析,根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库,包括:根据概率学公式:P(A)=m/n计算所述预检信息总样本中的预检信息的重要度,其中,P(A)值为某一预检信息A的重要度量化体现,m指与预检信息A相同或相似的预检信息出现的次数,n指预检信息总样本数;进行所述重要度分析,包括P(A)值与设定的重要度阈值进行对比,当某一预检信息样本A的P(A)值大于所述重要度阈值时,标记此预检信息A为重要的预检信息样本;将标记的重要的预检信息样本汇总后建立预检信息数据库。
- 如权利要求9所述的计算机设备,其中,对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令,包括:对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词,遍历预检信息数据库,搜寻与所述提取的关键词相同或相近似的可能语句进行信息相关度匹配;搜寻结果命中关键词时,标记所述搜寻结果与所述的获取的待处理预检信息匹配成功,搜寻结果为零时,标记所述的获取的待处理预检信息匹配不成功;根据所述搜寻结果与所述的获取的待处理预检信息匹配成功的标记,提取所述搜寻结果相对应的预检信息数据,并据此生成数据待输出的指令,根据所述获取的待处理预检信息匹配不成功的标记,生成引导指令。
- 如权利要求9所述的计算机设备,其中,将生成的所述数据待输出指令或者所述引导指令,输出于交互平台,包括:当所述的获取的待处理预检信息匹配成功时,根据所述数据待输出的指令,生成相应的数据表述信息;当所述的获取的待处理预检信息匹配不成功时,根据所述引导指令,生成相应的引导指令表述信息;将所述表述信息用不同表述形式输出于所述交互平台,所述表述形式可采用包括语音播报或交互平台界面文字显示的输出方式。
- 一种存储有计算机可读指令的存储介质,其中,所述计算机可读指令被一个或多个处理器执行时,使得一个或多个所述处理器执行如下步骤:从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息;对所述的获取的待处理预检信息的内容进行识别,提取其中的关键词,根据所述提取的关键词遍历预检信息数据库,进行相关度匹配,匹配成功时,提取相应信息数据并生成数据待输出指令,匹配不成功时,生成引导指令;将生成的所述数据待输出指令或者所述引导指令,输出于交互平台。
- 如权利要求16所述的存储介质,其中,所述从交互平台获取待处理的预检信息,所述待处理预检信息包括语音输入信息、文字输入信息或者预设项选择信息,包括:接收交互平台上选择的预检信息输入形式,所述输入形式包括语音输入、文字输入、预设项选择;根据所述选择的预检信息输入形式,向病人提供对应的信息输入界面,所述信息输入界面包括与所述语音输入形式对应的语音输入界面、与所述文字输入形式对应的文字输入界面或者与所述预设项选择输入形式对应的预设项选择界面;通过所述信息输入界面获取语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容。
- 如权利要求17所述的存储介质,其中,所述通过所述信息输入界面获取的语音输入信息、文字输入信息或者预设项选择信息,从而获取预检信息内容,包括:当输入形式为文字输入时,通过文字输入界面接收预检信息的输入,获取预检信息内容后保存信息;当输入形式为语音输入时,通过拾音模块接收语音输入,并通过语音识别引擎转译为文字后,通过语音输入界面反馈识别生成的文字信息,并在该文字信息被确认为正确后,获取预检信息内容后保存信息;当输入形式为预设项选择时,通过预设项选择界面确定选择项目,获取被选择项目的预检信息内容。
- 如权利要求16所述的存储介质,其中,在所述的从交互平台获取待处理的预检信息之前,建立预检信息数据库,用于对获取的预检信息内容进行识别,包括:采集相关预检信息的历史数据,包括预检问题信息数据和相对应的答案信息数据,两者之间形成对应关系后,汇总生成预检信息总样本;运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析,根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库;筛选所述预检信息数据库中的高频词条,将包含所述高频词条的相关预检信息设置为固定的预设项,作为预设项选择界面的显示项目。
- 如权利要求19所述的存储介质,其中,所述运用概率统计方法,对所述预检信息总样本中的预检信息进行重要度分析,根据分析所得的重要度配合预设的重要度阈值,汇总超过重要度阈值的预检信息样本,根据这些样本建立预检信息数据库,包括:根据概率学公式:P(A)=m/n计算所述预检信息总样本中的预检信息的重要度,其中,P(A)值为某一预检信息A的重要度量化体现,m指与预检信息A相同或相似的预检信息出现的次数,n指预检信息总样本数;进行所述重要度分析,包括P(A)值与设定的重要度阈值进行对比,当某一预检信息样本A的P(A)值大于所述重要度阈值时,标记此预检信息A为重要的预检信息样本;将标记的重要的预检信息样本汇总后建立预检信息数据库。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910540617.5 | 2019-06-21 | ||
| CN201910540617.5A CN110415828B (zh) | 2019-06-21 | 2019-06-21 | 一种基于数据分析的预检信息交互方法及相关设备 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020253391A1 true WO2020253391A1 (zh) | 2020-12-24 |
Family
ID=68359486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/087597 Ceased WO2020253391A1 (zh) | 2019-06-21 | 2020-04-28 | 一种基于数据分析的预检信息交互方法及相关设备 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110415828B (zh) |
| WO (1) | WO2020253391A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035994A (zh) * | 2022-06-13 | 2022-09-09 | 中国电信股份有限公司 | 医疗服务引导方法、装置、电子设备及存储介质 |
| CN116893273A (zh) * | 2023-09-11 | 2023-10-17 | 广州伊创科技股份有限公司 | 一种自动检测系统及方法 |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415828B (zh) * | 2019-06-21 | 2023-03-31 | 深圳壹账通智能科技有限公司 | 一种基于数据分析的预检信息交互方法及相关设备 |
| CN112017646A (zh) * | 2020-08-21 | 2020-12-01 | 博泰车联网(南京)有限公司 | 一种语音处理方法、装置及计算机存储介质 |
| CN112364065B (zh) * | 2020-10-27 | 2022-04-15 | 刘锋 | 一种获取大数据中转、反馈的方法及系统 |
| CN112258074B (zh) * | 2020-11-02 | 2021-07-02 | 深圳市力天世纪供应链管理有限公司 | 一种基于大数据分析的电商商品仓储物流智能调度方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060184393A1 (en) * | 2004-12-29 | 2006-08-17 | Ewin Leon H | Online medical data collection |
| CN102103455A (zh) * | 2009-12-18 | 2011-06-22 | 上海智问软件技术有限公司 | 一种基于交互输入的智能提示系统及其实现方法 |
| CN106326640A (zh) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | 一种医疗语音控制系统及其控制方法 |
| CN106650261A (zh) * | 2016-12-22 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | 智能问诊方法、装置和系统 |
| CN110415828A (zh) * | 2019-06-21 | 2019-11-05 | 深圳壹账通智能科技有限公司 | 一种基于数据分析的预检信息交互方法及相关设备 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101645125B (zh) * | 2008-08-05 | 2011-07-20 | 珠海金山软件有限公司 | 过滤以及监控程序的行为的方法 |
| CN105045919B (zh) * | 2015-08-24 | 2019-08-16 | 北京云知声信息技术有限公司 | 一种信息输出方法及装置 |
| CN106202349B (zh) * | 2016-06-29 | 2020-08-21 | 新华三技术有限公司 | 网页分类字典生成方法及装置 |
| CN106383875B (zh) * | 2016-09-09 | 2019-10-15 | 北京百度网讯科技有限公司 | 基于人工智能的人机交互方法和装置 |
| CN107818781B (zh) * | 2017-09-11 | 2021-08-10 | 远光软件股份有限公司 | 智能交互方法、设备及存储介质 |
| CN107885888A (zh) * | 2017-12-11 | 2018-04-06 | 北京百度网讯科技有限公司 | 信息处理方法及装置、终端设备以及计算机可读存储介质 |
| CN109145099B (zh) * | 2018-08-17 | 2021-02-23 | 百度在线网络技术(北京)有限公司 | 基于人工智能的问答方法和装置 |
-
2019
- 2019-06-21 CN CN201910540617.5A patent/CN110415828B/zh not_active Expired - Fee Related
-
2020
- 2020-04-28 WO PCT/CN2020/087597 patent/WO2020253391A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060184393A1 (en) * | 2004-12-29 | 2006-08-17 | Ewin Leon H | Online medical data collection |
| CN102103455A (zh) * | 2009-12-18 | 2011-06-22 | 上海智问软件技术有限公司 | 一种基于交互输入的智能提示系统及其实现方法 |
| CN106326640A (zh) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | 一种医疗语音控制系统及其控制方法 |
| CN106650261A (zh) * | 2016-12-22 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | 智能问诊方法、装置和系统 |
| CN110415828A (zh) * | 2019-06-21 | 2019-11-05 | 深圳壹账通智能科技有限公司 | 一种基于数据分析的预检信息交互方法及相关设备 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035994A (zh) * | 2022-06-13 | 2022-09-09 | 中国电信股份有限公司 | 医疗服务引导方法、装置、电子设备及存储介质 |
| CN116893273A (zh) * | 2023-09-11 | 2023-10-17 | 广州伊创科技股份有限公司 | 一种自动检测系统及方法 |
| CN116893273B (zh) * | 2023-09-11 | 2024-01-05 | 广州伊创科技股份有限公司 | 一种自动检测系统及方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110415828B (zh) | 2023-03-31 |
| CN110415828A (zh) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020253391A1 (zh) | 一种基于数据分析的预检信息交互方法及相关设备 | |
| JP6095621B2 (ja) | 回答候補間の関係を識別および表示する機構、方法、コンピュータ・プログラム、ならびに装置 | |
| CN109686439B (zh) | 遗传病基因检测的数据分析方法、系统及存储介质 | |
| EP3623970A1 (en) | Medical intelligent triage method and device | |
| KR20150142070A (ko) | 문서 분류 시스템, 문서 분류 방법 및 문서 분류 프로그램 | |
| CN113724848A (zh) | 基于人工智能的医疗资源推荐方法、装置、服务器及介质 | |
| WO2020237872A1 (zh) | 语义分析模型准确度的校验方法、装置、存储介质及设备 | |
| KR102126911B1 (ko) | KeyplayerRank를 이용한 소셜 미디어상의 주제별 키플레이어 탐지 방법 | |
| CN106557653A (zh) | 一种移动医疗智能导医系统及其方法 | |
| JP2010515171A (ja) | 概念ベースの検索とランク付けを伴う情報検索のシステム、方法およびソフトウェア | |
| JP6187474B2 (ja) | 医療情報解析プログラム、医療情報解析装置、および医療情報解析方法 | |
| WO2014078612A2 (en) | Multi-dimensional feature merging for open domain question answering | |
| US20110295877A1 (en) | System and method for online handwriting recognition in web queries | |
| EP3028180A1 (en) | Method for systematic mass normalization of titles | |
| US9542474B2 (en) | Forensic system, forensic method, and forensic program | |
| CN117909702A (zh) | 多模态大模型的质量评估方法、系统、设备及存储介质 | |
| CN114841136B (zh) | 一种检查报告编辑方法、装置及设备 | |
| US11640499B2 (en) | Systems, methods and computer program products for mining text documents to identify seminal issues and cases | |
| Liquitay et al. | Search strategies (filters) to identify systematic reviews in MEDLINE and Embase | |
| KR101839572B1 (ko) | 질병 관련 유전자 관계 분석 장치 및 방법 | |
| JP6842397B2 (ja) | 業務支援システムおよび業務支援方法 | |
| CN102890690A (zh) | 目标信息搜索方法和装置 | |
| CN110648754A (zh) | 科室推荐方法、装置及设备 | |
| CN112861510A (zh) | 纪要处理方法、装置、设备和存储介质 | |
| WO2015023031A1 (ko) | 전문분야 검색 지원 방법 및 그 장치 |
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: 20826522 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: 20826522 Country of ref document: EP Kind code of ref document: A1 |
|
| 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 1205A DATED 28/03/2022) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20826522 Country of ref document: EP Kind code of ref document: A1 |