WO2020077840A1 - 一种医疗数据的处理方法、装置 - Google Patents

一种医疗数据的处理方法、装置 Download PDF

Info

Publication number
WO2020077840A1
WO2020077840A1 PCT/CN2018/123557 CN2018123557W WO2020077840A1 WO 2020077840 A1 WO2020077840 A1 WO 2020077840A1 CN 2018123557 W CN2018123557 W CN 2018123557W WO 2020077840 A1 WO2020077840 A1 WO 2020077840A1
Authority
WO
WIPO (PCT)
Prior art keywords
medical data
labeling
user
task
virtual resources
Prior art date
Application number
PCT/CN2018/123557
Other languages
English (en)
French (fr)
Inventor
普璇
郑映锋
Original Assignee
平安科技（深圳）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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020077840A1 publication Critical patent/WO2020077840A1/zh

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
    • 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

  • the present application relates to the technical field of data processing, and in particular, to a medical data processing method and device.
  • Medical data is the data generated by doctors during the diagnosis and treatment of patients, including basic patient data, electronic medical records, diagnosis and treatment data, medical image data, medical management data, economic data, medical equipment and instrument data, etc.
  • the continuous dataization has not only expanded the information capacity of the hospital database, but also played a positive role in the management, control and medical research of diseases and patients, and is of great value.
  • the embodiments of the present application provide a medical data processing method and device, to solve the problem that the prior art cannot obtain a large amount of labeled medical data with high accuracy.
  • an embodiment of the present application provides a medical data processing method, the method includes: acquiring uploaded medical data to be marked; obtaining a marking result of the medical data, wherein the marking result is determined by the first The user marks the medical data to be marked according to the labeling rule; judges whether the accuracy of the labeling result reaches a preset standard; if the accuracy of the labeling result reaches the preset standard, the medical The data and the annotation result are stored in association, and the number of virtual resources in the account associated with the first user is increased.
  • an embodiment of the present application provides a medical data processing apparatus.
  • the apparatus includes: a first acquiring unit for acquiring uploaded medical data to be marked; a second acquiring unit for acquiring the medical The result of data labeling, wherein the labeling result is obtained by the first user labeling the medical data to be labeled according to a labeling rule; a first judgment unit is used to judge whether the accuracy of the labeling result reaches a preset standard
  • a storage unit for associating the medical data and the labeling result if the accuracy of the labeling result reaches the preset standard, and increasing the virtual resources in the account associated with the first user quantity.
  • the embodiments of the present application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the medical data processing method described above is implemented.
  • an embodiment of the present application provides a computer non-volatile readable storage medium, the computer non-volatile readable storage medium includes a stored program, wherein the computer is not easily controlled when the program is running
  • the device where the lossless readable storage medium is located performs the above medical data processing method.
  • the annotator marks it to determine whether the accuracy of the labeling result reaches the preset standard. If the accuracy of the labeling result reaches the preset standard, the medical data and the label
  • the results are associated with storage, and the number of virtual resources in the account associated with the tagger is increased to encourage the tagger ’s tagging behavior, stimulate the tagger ’s enthusiasm for tagging medical data, make full use of the professional ’s human resources, and ensure the tagging results Accuracy, thereby obtaining a large amount of valuable labeled medical data, and solving the technical problem in the prior art that a sufficient amount of accurate labeled medical data cannot be obtained.
  • FIG. 1 is a flowchart of a medical data processing method according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a medical data processing device according to an embodiment of the present application.
  • FIG. 1 is a flowchart of a medical data processing method according to an embodiment of the present application. As shown in FIG. 1, the method includes the following steps:
  • Medical data is the data generated by doctors during the diagnosis and treatment of patients, including basic patient data, electronic medical records, diagnosis and treatment data, medical image data, medical management, economic data, medical equipment and instrument data, etc.
  • the main source of information includes basic patient data, electronic medical records, diagnosis and treatment data, medical image data, medical management, economic data, medical equipment and instrument data, etc.
  • labeling medical data may refer to: labeling the diseased tissue and the degree of the disease according to the CT image.
  • the first user is also called annotator.
  • the annotator has professional knowledge in the medical field, and the labeling rule may be: a method of labeling according to the type of medical data to be labeled, for example, the aspect to be labeled, the detail level of the label, etc. Marking rules can be formulated according to actual needs.
  • the medical data to be marked is medical data that has been desensitized.
  • Data desensitization refers to the deformation of certain sensitive information through desensitization rules to achieve reliable protection of sensitive private data. By desensitizing medical data in advance, the privacy of patients is effectively protected.
  • the labeler labels the medical data, it is necessary to judge whether the accuracy of the labeling result reaches the preset standard. If the accuracy of the labeling result does not reach the preset standard, the labeling result is discarded, and the medical data needs to be labeled again until the labeling result reaches the preset standard. Re-labeling the medical data can be done by the same labeler or by different labelers.
  • the medical data and the labeling result are stored in association.
  • Virtual resources can refer to electronic money or other media that enable value exchange.
  • the virtual resource may refer to Bitcoin.
  • the annotator marks it to determine whether the accuracy of the labeling result reaches the preset standard. If the accuracy of the labeling result reaches the preset standard, the medical data and the label
  • the results are associated with storage, and the number of virtual resources in the account associated with the tagger is increased to encourage the tagger ’s tagging behavior, stimulate the tagger ’s enthusiasm for tagging medical data, make full use of the professional ’s human resources, and ensure the tagging results Accuracy, thereby obtaining a large amount of valuable labeled medical data, and solving the technical problem in the prior art that a sufficient amount of accurate labeled medical data cannot be obtained.
  • the number of virtual resources in the account associated with the data uploader who uploaded the medical data to be marked is increased to encourage everyone to upload medical data.
  • the uploader can set the attributes of the medical data to be shared or private. For medical data whose attributes are private, it is only visible to specific users, not visible to annotators, and annotators cannot annotate them. For medical data whose attributes are shared, it is visible to the annotator, and the annotator can annotate it.
  • determining whether the accuracy of the labeling result meets a preset standard specifically includes: obtaining the labeling result and judgment result of the labeled medical data; determining whether the labeling result and judgment result of the labeled medical data If the marked results of the marked medical data are consistent with the judgment results, determine that the accuracy of the marked results reaches the preset standard; if the marked results of the marked medical data and the judgment results are inconsistent, determine that the accuracy of the marked results does not Set standards.
  • the evaluation of medical data can be done by specific personnel with expertise in the medical field. By comparing the annotation results of the medical data with the judgment results, the data with inaccurate annotation results can be screened out, and the inaccurate annotation results can be discarded to ensure the accuracy of the annotation results.
  • the method further includes: reducing the labeling professional level of the labeler.
  • increasing the number of virtual resources in the account associated with the first user includes: increasing the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data . That is, there are at least three optional ways.
  • Method 1 increase the number of virtual resources in the account associated with the tagger according to the tagging professional level of the tagger;
  • method 2 increase the tagger according to the importance level of the medical data marked by the tagger
  • the method before increasing the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or medical data importance level, the method further includes: The labeling volume and labeling accuracy determine the first user's labeling professional level.
  • the labeling professional level of the labeler can be determined according to the labeling amount and accuracy of the labeling medical data of the labeler. If a tagger has a large amount of tags and a high tagging accuracy, it can be determined that the tagger has a high level of tagging expertise. If a tagger has a small amount of tags and the tagging accuracy is low, it can be determined that the tagger has a low tagging level.
  • the method before or after obtaining the uploaded medical data to be marked, the method further includes: determining whether a medical data labeling task initiated by the task initiator is detected; after detecting the medical data labeling task, calculating the medical data labeling task The number of corresponding virtual resources; the number of virtual resources corresponding to the medical data labeling task is sent to the terminal corresponding to the task initiator; the number of virtual resources corresponding to the medical data labeling task is deducted from the account associated with the task initiator.
  • calculating the number of virtual resources corresponding to the medical data labeling task includes: calculating the number of virtual resources corresponding to the medical data labeling task according to at least one of the following parameters: medical data labeling task urgency parameters, medical data labeling task designation The amount of labeling and the difficulty parameter of the medical data to be labeled specified by the medical data labeling task.
  • increase the number of virtual resources in the account associated with the first user including: receiving the purchase request of the labeled medical data use right issued by the buyer; deducting the virtual resource from the account associated with the buyer; according to the first preset
  • the rules increase the number of virtual resources in the provider of medical data and the first user account.
  • the virtual resource is deducted from the user's account, and the provider of the medical data and the labeler of the medical data are added according to the first preset rule
  • the first preset rule specifies the ratio of the number of virtual resources added to the account of the provider of medical data and the number of virtual resources added to the account of the provider of medical data.
  • the first preset rule stipulates that the amount added to the medical data provider's account
  • the ratio of the number of virtual resources to the number of virtual resources added to the medical data annotator's account is 1: 4, then increase the lung medical data provider's account by 20 bitcoins to convert the lung medical data Added 80 bitcoins to the account of the tagger. If the provider or annotator of lung medical data is more than one user, add virtual resources to the accounts of each provider and each annotator of lung medical data according to the second preset rule.
  • the importance level of medical data is determined by the value of medical data and has nothing to do with the amount of labeling and the accuracy of labeling.
  • the virtual resources are deducted from the account associated with the initiator of the labeling task and the initiator of the data use request, the number of virtual resources in the account associated with the labeler of medical data is increased, and the virtual resources added to the account associated with the labeler
  • the number of resources is related to the labeler ’s labeling workload, labeling quality, and labeling difficulty. Excellent labelers are encouraged to label medical data and make full use of human resources, so that a large number of accurate medical data labeling results can be obtained. It has laid a good foundation for the further application of medical big data.
  • An embodiment of the present application further provides a medical data processing device, which is used to execute the above medical data processing method.
  • the device includes: a first acquisition unit 10, a second acquisition unit 20, a first judgment unit 30, and a storage unit 40.
  • the first obtaining unit 10 is used to obtain the uploaded medical data to be marked.
  • the second obtaining unit 20 is used to obtain the labeling result of the medical data, where the labeling result is obtained by the first user labeling the medical data to be labeled according to the labeling rule.
  • the first judgment unit 30 is used to judge whether the accuracy of the labeling result reaches a preset standard.
  • the storage unit 40 is configured to, if the accuracy of the labeling result reaches a preset standard, store the medical data and the labeling result in association, and increase the number of virtual resources in the account associated with the first user.
  • Medical data is the data generated by doctors during the diagnosis and treatment of patients, including basic patient data, electronic medical records, diagnosis and treatment data, medical image data, medical management, economic data, medical equipment and instrument data, etc.
  • the main source of information includes basic patient data, electronic medical records, diagnosis and treatment data, medical image data, medical management, economic data, medical equipment and instrument data, etc.
  • labeling medical data may refer to: labeling the diseased tissue and the degree of the disease according to the CT image.
  • the first user is also called annotator.
  • the annotator has professional knowledge in the medical field, and the labeling rule may be: a method of labeling according to the type of medical data to be labeled, for example, the aspect to be labeled, the detail level of the label, etc. Marking rules can be formulated according to actual needs.
  • the medical data to be marked is medical data that has been desensitized.
  • Data desensitization refers to the deformation of certain sensitive information through desensitization rules to achieve reliable protection of sensitive private data. By desensitizing medical data in advance, the privacy of patients is effectively protected.
  • the labeler labels the medical data, it is necessary to judge whether the accuracy of the labeling result reaches the preset standard. If the accuracy of the labeling result does not reach the preset standard, the labeling result is discarded, and the medical data needs to be labeled again until the labeling result reaches the preset standard. Re-labeling the medical data can be done by the same labeler or by different labelers.
  • the medical data and the labeling result are stored in association.
  • Virtual resources can refer to electronic money or other media that enable value exchange.
  • the virtual resource may refer to Bitcoin.
  • the annotator marks it to determine whether the accuracy of the labeling result reaches the preset standard. If the accuracy of the labeling result reaches the preset standard, the medical data and the label
  • the results are associated with storage, and the number of virtual resources in the account associated with the tagger is increased to encourage the tagger ’s tagging behavior, stimulate the tagger ’s enthusiasm for tagging medical data, make full use of the professional ’s human resources, and ensure the tagging results Accuracy, thereby obtaining a large amount of valuable labeled medical data, and solving the technical problem in the prior art that a sufficient amount of accurate labeled medical data cannot be obtained.
  • the number of virtual resources in the account associated with the data uploader who uploaded the medical data to be marked is increased to encourage everyone to upload medical data.
  • the uploader can set the attributes of the medical data to be shared or private. For medical data whose attributes are private, it is only visible to specific users, not visible to annotators, and annotators cannot annotate them. For medical data whose attributes are shared, it is visible to the annotator, and the annotator can annotate it.
  • determining whether the accuracy of the labeling result meets a preset standard specifically includes: obtaining the labeling result and judgment result of the labeled medical data; determining whether the labeling result and judgment result of the labeled medical data If the marked results of the marked medical data are consistent with the judgment results, determine that the accuracy of the marked results reaches the preset standard; if the marked results of the marked medical data and the judgment results are inconsistent, determine that the accuracy of the marked results does not Set standards.
  • the evaluation of medical data can be done by specific personnel with expertise in the medical field. By comparing the annotation results of the medical data with the judgment results, the data with inaccurate annotation results can be screened out, and the inaccurate annotation results can be discarded to ensure the accuracy of the annotation results.
  • the method further includes: reducing the labeling professional level of the labeler.
  • the storage unit 40 includes: a first addition subunit.
  • the first adding subunit is used to increase the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data. That is, there are at least three optional ways.
  • Method 1 increase the number of virtual resources in the account associated with the tagger according to the tagging professional level of the tagger;
  • method 2 increase the tagger according to the importance level of the medical data marked by the tagger
  • the device further includes: a determination unit.
  • the determining unit is used to increase the number of virtual resources in the account associated with the first user before the first increasing subunit increases the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data
  • the labeling amount and labeling accuracy of the data determine the labeling professional level of the first user.
  • the labeling professional level of the labeler can be determined according to the labeling amount and accuracy of the labeling medical data of the labeler. If a tagger has a large amount of tags and a high tagging accuracy, it can be determined that the tagger has a high level of tagging expertise. If a tagger has a small amount of tags and the tagging accuracy is low, it can be determined that the tagger has a low tagging level.
  • the device further includes: a second judgment unit, a calculation unit, a sending unit, and a deduction unit.
  • the second determining unit is configured to determine whether the medical data labeling task initiated by the task initiator is detected before or after the first acquiring unit 10 acquires the uploaded medical data to be labeled.
  • the calculation unit is configured to calculate the number of virtual resources corresponding to the medical data labeling task after detecting the medical data labeling task.
  • the sending unit is used to send the number of virtual resources corresponding to the medical data labeling task to the terminal corresponding to the task initiator.
  • the deduction unit is used to deduct the number of virtual resources corresponding to the medical data labeling task from the account associated with the task initiator.
  • the calculation unit includes: a calculation subunit.
  • the calculation subunit is used to calculate the number of virtual resources corresponding to the medical data labeling task according to at least one of the following parameters: the urgency parameter of the medical data labeling task, the amount of labeling specified by the medical data labeling task, and the to-be-labeled specified by the medical data labeling task The difficulty parameter of the medical data labeling.
  • the storage unit 40 includes: a receiving subunit, a subtraction subunit, and a second adding subunit.
  • the receiving subunit is used to receive the purchase request of the labeled medical data use right issued by the buyer.
  • the deduction subunit is used to deduct virtual resources from the account associated with the purchaser.
  • the second adding subunit is used to increase the number of virtual resources in the medical data provider and the first user account according to the first preset rule.
  • the virtual resource is deducted from the user's account, and the provider of the medical data and the labeler of the medical data are added according to the first preset rule
  • the first preset rule specifies the ratio of the number of virtual resources added to the account of the provider of medical data and the number of virtual resources added to the account of the provider of medical data.
  • the first preset rule stipulates that the amount added to the medical data provider's account
  • the ratio of the number of virtual resources to the number of virtual resources added to the medical data annotator's account is 1: 4, then increase the lung medical data provider's account by 20 bitcoins to convert the lung medical data Added 80 bitcoins to the account of the tagger. If the provider or annotator of lung medical data is more than one user, add virtual resources to the accounts of each provider and each annotator of lung medical data according to the second preset rule.
  • the virtual resources are deducted from the account associated with the initiator of the labeling task and the initiator of the data use request, the number of virtual resources in the account associated with the labeler of medical data is increased, and the virtual resources added to the account associated with the labeler
  • the number of resources is related to the labeler ’s labeling workload, labeling quality, and labeling difficulty. Excellent labelers are encouraged to label medical data and make full use of human resources, so that a large number of accurate medical data labeling results can be obtained. It has laid a good foundation for the further application of medical big data.
  • An embodiment of the present application also provides a computer device including a memory and a processor.
  • the memory is used to store information including program instructions.
  • the processor is used to control the execution of the program instructions.
  • the program instructions are implemented when the processor is loaded and executed The following steps: Obtain the uploaded medical data to be annotated; Obtain the annotated result of the medical data, where the annotated result is obtained by the first user to annotate the medical data to be annotated according to the labeling rules; determine whether the accuracy of the annotated result reaches the preset Standard; if the accuracy of the labeling result reaches the preset standard, the medical data and the labeling result are stored in association, and the number of virtual resources in the account associated with the first user is increased.
  • the following steps are further implemented: increasing the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data.
  • the following steps are further implemented: before increasing the number of virtual resources in the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data ,
  • the first user's labeling professional level is determined according to the labeling amount and labeling accuracy of the medical data that the first user has labeled.
  • the following steps are also implemented: before or after obtaining the uploaded medical data to be marked, it is determined whether the medical data labeling task initiated by the task initiator is detected; After the data labeling task, calculate the number of virtual resources corresponding to the medical data labeling task; send the number of virtual resources corresponding to the medical data labeling task to the terminal corresponding to the task initiator; deduct the medical data labeling task from the account associated with the task initiator The number of corresponding virtual resources.
  • the number of virtual resources corresponding to the medical data labeling task is calculated according to at least one of the following parameters: the urgency parameter of the medical data labeling task, and the medical data labeling task specification The amount of labeling and the difficulty parameter of the medical data to be labeled specified by the medical data labeling task.
  • the following steps are also implemented: receiving the purchase request of the labeled medical data use right issued by the buyer; deducting the virtual resource from the account associated with the buyer; adding according to the first preset rule The provider of medical data and the number of virtual resources in the first user account.
  • Embodiments of the present application also provide a computer non-volatile readable storage medium.
  • the computer non-volatile readable storage medium includes a stored program, where the computer non-volatile readable storage medium is controlled while the program is running.
  • the device performs the following steps: obtaining the uploaded medical data to be labeled; obtaining the labeling results of the medical data, where the labeling results are obtained by the first user to label the medical data to be labeled according to the labeling rules; whether the accuracy of the labeling results is reached Preset standards; if the accuracy of the annotation results reaches the preset standards, the medical data and the annotation results are stored in association, and the number of virtual resources in the account associated with the first user is increased.
  • the device where the computer non-volatile readable storage medium is located also performs the following steps: increasing the account associated with the first user according to the first user's marked professional level and / or the importance level of medical data The number of virtual resources.
  • controlling the device where the computer non-volatile readable storage medium is located while the program is running also performs the following steps: adding the account associated with the first user according to the first user ’s marked professional level and / or the importance level of medical data Before the number of virtual resources in the first user, the first user ’s labeling professional level is determined according to the labeling amount and labeling accuracy of the medical data that the first user has labeled.
  • the device where the computer non-volatile readable storage medium is located also performs the following steps: before or after acquiring the uploaded medical data to be marked, it is determined whether the medical data initiated by the task initiator is detected Labeling task; after detecting medical data labeling task, calculate the number of virtual resources corresponding to medical data labeling task; send the number of virtual resources corresponding to medical data labeling task to the terminal corresponding to the task initiator; from the task initiator ’s associated The number of virtual resources corresponding to the medical data labeling task is deducted from the account.
  • the device where the computer non-volatile readable storage medium is located also performs the following steps: calculating the number of virtual resources corresponding to the medical data labeling task according to at least one of the following parameters: the urgency of the medical data labeling task Parameters, the amount of labeling specified by the medical data labeling task, and the labeling difficulty parameter of the medical data to be labeled specified by the medical data labeling task.
  • the device where the computer non-volatile readable storage medium is located also performs the following steps: receiving the purchase request of the labeled medical data use right issued by the purchaser; deducting the virtual resource from the account associated with the purchaser; Increase the number of virtual resources in the medical data provider and the first user account according to the first preset rule.
  • terminals involved in the embodiments of the present application may include, but are not limited to, personal computers (Personal Computer, PC), personal digital assistants (Personal Digital Assistant, PDA), wireless handheld devices, tablet computers (Tablet Computer), Mobile phones, MP3 players, MP4 players, etc.
  • PC Personal Computer
  • PDA Personal Digital Assistant
  • Tablett Computer Tablet Computer
  • Mobile phones MP3 players, MP4 players, etc.
  • the disclosed system, device, and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined Or it can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium.
  • the above software function unit is stored in a storage medium, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform the methods described in the embodiments of the present application Partial steps.
  • the foregoing storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

一种医疗数据的处理方法、装置，该方法包括：获取已上传的待标注的医疗数据（S102）；获取医疗数据的标注结果（S104），其中，标注结果由第一用户按照标注规则对待标注的医疗数据进行标注得到；判断标注结果的准确性是否达到预设标准（S106）；如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加第一用户关联的账户中的虚拟资源的数量（S108）。因此，该方法能够解决现有技术无法得到大量已标注的准确度高的医疗数据的问题。

Description

一种医疗数据的处理方法、装置
本申请要求于2018年10月15日提交中国专利局、申请号为201811196996.2、发明名称为“一种医疗数据的处理方法、装置、服务器及存储介质”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】
本申请涉及数据处理技术领域，尤其涉及一种医疗数据的处理方法、装置。
【背景技术】
医疗数据是医生对患者诊疗和治疗过程中产生的数据，包括患者基本数据、电子病历、诊疗数据、医学影像数据、医学管理数据、经济数据、医疗设备和仪器数据等，以患者为中心，是医疗信息的主要来源。而不断数据化的信息，在使医院数据库信息容量不断膨胀的同时，也对疾病及病人的管理、控制和医疗研究起到了积极的作用，价值不菲。
目前拥有规范标注的医疗数据缺乏，导致基于医疗大数据的算法研究受到限制。医疗数据的标注需要专业人士，相较其他标注领域，这类人群的数量本来就是极少的。现有的医疗数据的标注工作很多是医院或学术机构小范围内自行完成的。现在的做法，并没有充分利用到大部分的人力资源，标注质量也无法保证，存在无法得到足量准确的已标注的医疗数据的技术问题。
【申请内容】
有鉴于此，本申请实施例提供了一种医疗数据的处理方法、装置，用以解决现有技术无法得到大量已标注的准确度高的医疗数据的问题。
一方面，本申请实施例提供了一种医疗数据的处理方法，所述方法包括：获取已上传的待标注的医疗数据；获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；判断所述标注结果的准确性是否达到预设标准；如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
一方面，本申请实施例提供了一种医疗数据的处理装置，所述装置包括：第一获取单元，用于获取已上传的待标注的医疗数据；第二获取单元，用于获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；第一判断单元，用于判断所述标注结果的准确性是否达到预设标准；存储单元，用于如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
一方面，本申请实施例提供一种计算机设备，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机程序，处理器执行计算机程序时实现如上述医疗数据的处理方法。
一方面，本申请实施例提供一种计算机非易失性可读存储介质，所述计算机非易失性可读存储介质包括存储的程序，其中，在所述程序运行时控制所述计算机非易失性可读存储介质所在设备执行上述医疗数据的处理方法。
在本方案中，当待标注的医疗数据上传之后，标注员对其进行标注，判断标注结果的准确性是否达到预设标准，如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加标注员关联的账户中的虚拟资源的数量，以鼓励标注员的标注行为，激发标注员标注医疗数据的积极性，充分利用了专业人员的人力资源，并且保证了标注结果的准确性，从而得到大量有价值的已标注的医疗数据，解决了现有技术中无法得到足量准确的已标注的医疗数据的技 术问题。
【附图说明】
为了更清楚地说明本申请实施例的技术方案，下面将对实施例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申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其它的附图。
图1是根据本申请实施例的一种医疗数据的处理方法的流程图；
图2是根据本申请实施例的一种医疗数据的处理装置的示意图。
【具体实施方式】
为了更好的理解本申请的技术方案，下面结合附图对本申请实施例进行详细描述。
应当明确，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例，都属于本申请保护的范围。
在本申请实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
应当理解，本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
图1是根据本申请实施例的一种医疗数据的处理方法的流程图，如图1所示，该方法包括如下步骤：
S102，获取已上传的待标注的医疗数据。
S104，获取医疗数据的标注结果，其中，标注结果由第一用户按照标注规则对待标注的医疗数据进行标注得到。
S106，判断标注结果的准确性是否达到预设标准。
S108，如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加第一用户关联的账户中的虚拟资源的数量。
医疗数据是医生对患者诊疗和治疗过程中产生的数据，包括患者基本数据、电子病历、诊疗数据、医学影像数据、医学管理、经济数据、医疗设备和仪器数据等，以患者为中心，是医疗信息的主要来源。
在本方案中，标注医疗数据可以是指：根据CT图像标注病变组织及病变程度。
在本方案中，第一用户又称为标注员。
标注员具有医疗领域的专业知识，标注规则可以是：根据待标注的医疗数据的类型进行标注的方式，例如，需要进行标注的方面、标注的详细程度等。标注规则可以根据实际需求制定。
作为一种可选的实施方式，待标注的医疗数据为已经脱敏的医疗数据。
数据脱敏是指对某些敏感信息通过脱敏规则进行数据的变形，实现敏感隐私数据的可靠保护。通过提前将医疗数据进行脱敏处理，有效保护了患者的隐私。
为了保证标注的准确性，在标注员对医疗数据进行标注之后，需要判断标注结果的准确性是否达到预设标准。如果标注结果的准确性没有达到预设标准，则该标注结果弃用，并且，需要重新对该医疗数据进行标注，直至标注结果达到预设标准。重新对该医疗数据进行标注可以由同一位标注员完成，也可以由不同的标注员完成。
在标注结果的准确性达到预设标准的情况下，将医疗数据和标注结果进行关联存储。
虚拟资源可以是指电子货币或其他能够实现价值交换的媒介。
作为一种可选的实施方式，虚拟资源可以是指比特币。
在本方案中，当待标注的医疗数据上传之后，标注员对其进行标注，判断标注结果的准确性是否达到预设标准，如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加标注员关联的账户中的虚拟资源的数量，以鼓励标注员的标注行为，激发标注员标注医疗数据的积极性，充分利用了专业人员的人力资源，并且保证了标注结果的准确性，从而得到大量有价值的已标注的医疗数据，解决了现有技术中无法得到足量准确的已标注的医疗数据的技术问题。
作为一种可选的实施方式，在获取已上传的待标注的医疗数据之后，增加上传待标注的医疗数据的数据上传者关联的账户中的虚拟资源的数量，以鼓励大家上传医疗数据。上传者在上传待标注的医疗数据时，可以将医疗数据的属性设置为共有或私有。对于属性为私有的医疗数据，仅对特定用户可见，对标注员不可见，标注员也无法对其进行标注。对于属性为共有的医疗数据，对标注员可见，标注员可以对其进行标注。
作为一种可选的实施例，判断标注结果的准确性是否达到预设标准，具体包括：获取已标注的医疗数据的标注结果和评判结果；判断已标注的医疗数据的标注结果和评判结果是否一致； 如果已标注的医疗数据的标注结果和评判结果一致，确定标注结果的准确性达到预设标准；如果已标注的医疗数据的标注结果和评判结果不一致，确定标注结果的准确性没有达到预设标准。
医疗数据的评判可以由具有医学领域专业知识的特定人员来完成。通过将医疗数据的标注结果和评判结果进行对比，能够将标注结果不准确的数据筛选出来，将不准确的标注结果进行弃用，以保证标注结果的准确性。
可选地，如果标注结果的准确性没有达到预设标准，方法还包括：降低标注员的标注专业等级。
可选地，增加第一用户关联的账户中的虚拟资源的数量，包括：按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量。即，至少有三种可选的方式，方式一：按照标注员的标注专业等级增加标注员关联的账户中的虚拟资源的数量；方式二：按照标注员标注的医疗数据的重要性等级增加标注员关联的账户中的虚拟资源的数量；方式三：综合考虑标注员的标注专业等级和医疗数据的重要性等级这二者，增加标注员关联的账户中的虚拟资源的数量。
可选地，在按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量之前，方法还包括：根据第一用户已经标注医疗数据的标注量和标注准确度来确定第一用户的标注专业等级。
确定标注员的标注专业等级的方法可以有多种，例如，根据标注员的标注医疗数据的标注量和标注准确度来确定标注员的标注专业等级。如果一个标注员的标注量较大，并且标注准确度较高，则可以确定该标注员的标注专业等级较高。如果一个标注员的标注量较小，并且标注准确度较低，则可以确定该标注员的标注等级较低。
可选地，在获取已上传的待标注的医疗数据之前或之后，方法还包括：判断是否检测到任务发起者发起的医疗数据标注任务；在检测到医疗数据标注任务之后，计算医疗数据标注任务对应的虚拟资源的数量；将医疗数据标注任务对应的虚拟资源的数量发送至任务发起者对应的终端；从任务发起者关联的账户中扣除医疗数据标注任务对应的虚拟资源的数量。
可选地，计算医疗数据标注任务对应的虚拟资源的数量，包括：根据以下至少一种参数计算医疗数据标注任务对应的虚拟资源的数量：医疗数据标注任务的紧急程度参数、医疗数据标注任务指定的标注量、医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
可选地，增加第一用户关联的账户中的虚拟资源的数量，包括：接收购买者发出的已标注医疗数据使用权购买请求；从购买者关联的账户中扣除虚拟资源；根据第一预设规则增加医疗数据的提供者和第一用户账户中的虚拟资源的数量。
可选地，当有用户想要购买已标注的医疗数据的使用权时，则从该用户的账户中扣除虚拟资源，并根据第一预设规则增加医疗数据的提供者和医疗数据的标注者的账户中的虚拟资源，该第一预设规则规定了向医疗数据的提供者的账户中增加的虚拟资源的数量和向医疗数据的标注者的账户中增加的虚拟资源的数量的比例。例如，用户甲想购买已标注的肺部医疗数据的使用权，则从用户甲的账户中扣除了100个比特币，假设第一预设规则规定了向医疗数据的提供者的账户中增加的虚拟资源的数量和向医疗数据的标注者的账户中增加的虚拟资源的数量的比例是1:4，则将肺部医疗数据的提供者的账户中增加20个比特币，将肺部医疗数据的标注者的账户中增加80个比特币。如果肺部医疗数据的提供者或者标注者不只是一个用户，则按照第二预设规则向肺部医疗数据的每个提供者、每个标注者的账户中增加虚拟资源。
一般来说，标注量和标注准确度不能确定医疗数据的重要性等级，医疗数据的重要性等级是由医疗数据的价值来确定的，与标注量和标注准确度无关。
综上，从标注任务的发起者和数据使用请求的发起者关联的账户中扣除虚拟资源，增加医疗数据的标注者关联的账户中的虚拟资源的数量，并且标注者关联的账户中增加的虚拟资源的数量与标注者的标注工作量、标注质量、标注难易程度相关，鼓励优秀的标注者对医疗数据进行标注，充分利用了人力资源，从而能够得到大量的准确的医疗数据的标注结果，为医疗大数据的进一步应用奠定了很好的基础。
本申请实施例还提供了一种医疗数据的处理装置，该装置用于执行上述医疗数据的处理方法。如图2所示，该装置包括：第一获取单元10、第二获取单元20、第一判断单元30、存储单元40。
第一获取单元10，用于获取已上传的待标注的医疗数据。
第二获取单元20，用于获取医疗数据的标注结果，其中，标注结果由第一用户按照标注规则对待标注的医疗数据进行标注得到。
第一判断单元30，用于判断标注结果的准确性是否达到预设标准。
存储单元40，用于如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加第一用户关联的账户中的虚拟资源的数量。
医疗数据是医生对患者诊疗和治疗过程中产生的数据，包括患者基本数据、电子病历、诊疗数据、医学影像数据、医学管理、经济数据、医疗设备和仪器数据等，以患者为中心，是医疗信息的主要来源。
在本方案中，标注医疗数据可以是指：根据CT图像标注病变组织及病变程度。
在本方案中，第一用户又称为标注员。
标注员具有医疗领域的专业知识，标注规则可以是：根据待标注的医疗数据的类型进行标注的方式，例如，需要进行标注的方面、标注的详细程度等。标注规则可以根据实际需求制定。
作为一种可选的实施方式，待标注的医疗数据为已经脱敏的医疗数据。
数据脱敏是指对某些敏感信息通过脱敏规则进行数据的变形，实现敏感隐私数据的可靠保护。通过提前将医疗数据进行脱敏处理，有效保护了患者的隐私。
为了保证标注的准确性，在标注员对医疗数据进行标注之后，需要判断标注结果的准确性是否达到预设标准。如果标注结果的准确性没有达到预设标准，则该标注结果弃用，并且，需要重新对该医疗数据进行标注，直至标注结果达到预设标准。重新对该医疗数据进行标注可以由同一位标注员完成，也可以由不同的标注员完成。
在标注结果的准确性达到预设标准的情况下，将医疗数据和标注结果进行关联存储。
虚拟资源可以是指电子货币或其他能够实现价值交换的媒介。
作为一种可选的实施方式，虚拟资源可以是指比特币。
在本方案中，当待标注的医疗数据上传之后，标注员对其进行标注，判断标注结果的准确性是否达到预设标准，如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加标注员关联的账户中的虚拟资源的数量，以鼓励标注员的标注行为，激发标注员标注医疗数据的积极性，充分利用了专业人员的人力资源，并且保证了标注结果的准确性，从而得到大量有价值的已标注的医疗数据，解决了现有技术中无法得到足量准确的已标注的医疗数据的技术问题。
作为一种可选的实施方式，在获取已上传的待标注的医疗数据之后，增加上传待标注的医疗数据的数据上传者关联的账户中的虚拟资源的数量，以鼓励大家上传医疗数据。上传者在上传待标注的医疗数据时，可以将医疗数据的属性设置为共有或私有。对于属性为私有的医疗数据，仅对特定用户可见，对标注员不可见，标注员也无法对其进行标注。对于属性为共有的医疗数据，对标注员可见，标注员可以对其进行标注。
作为一种可选的实施例，判断标注结果的准确性是否达到预设标准，具体包括：获取已标注的医疗数据的标注结果和评判结果；判断已标注的医疗数据的标注结果和评判结果是否一致；如果已标注的医疗数据的标注结果和评判结果一致，确定标注结果的准确性达到预设标准；如果已标注的医疗数据的标注结果和评判结果不一致，确定标注结果的准确性没有达到预设标准。
医疗数据的评判可以由具有医学领域专业知识的特定人员来完成。通过将医疗数据的标注结果和评判结果进行对比，能够将标注结果不准确的数据筛选出来，将不准确的标注结果进行弃用，以保证标注结果的准确性。
可选地，如果标注结果的准确性没有达到预设标准，方法还包括：降低标注员的标注专业等级。
可选地，存储单元40包括：第一增加子单元。第一增加子单元，用于按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量。即，至少有三种可选的方式，方式一：按照标注员的标注专业等级增加标注员关联的账户中的虚拟资源的数量；方式二：按照标注员标注的医疗数据的重要性等级增加标注员关联的账户中的虚拟资源的数量；方式三：综合考虑标注员的标注专业等级和医疗数据的重要性等级这二者，增加标注员关联的账户中的虚拟资源的数量。
可选地，装置还包括：确定单元。确定单元，用于在第一增加子单元按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量之前，根据第一用户已经标注医疗数据的标注量和标注准确度来确定第一用户的标注专业等级。
确定标注员的标注专业等级的方法可以有多种，例如，根据标注员的标注医疗数据的标注量和标注准确度来确定标注员的标注专业等级。如果一个标注员的标注量较大，并且标注准确度较高，则可以确定该标注员的标注专业等级较高。如果一个标注员的标注量较小，并且标注准确度较低，则可以确定该标注员的标注等级较低。
可选地，装置还包括：第二判断单元、计算单元、发送单元、扣除单元。第二判断单元，用于在第一获取单元10获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务。计算单元，用于在检测到医疗数据标注任务之后，计算医疗数据标注任务对应的虚拟资源的数量。发送单元，用于将医疗数据标注任务对应的虚拟资源的数量发送至任务发起者对应的终端。扣除单元，用于从任务发起者关联的账户中扣除医疗数据标注任务对应的虚拟资源的数量。
可选地，计算单元包括：计算子单元。计算子单元，用于根据以下至少一种参数计算医疗数据标注任务对应的虚拟资源的数量：医疗数据标注任务的紧急程度参数、医疗数据标注任务指定的标注量、医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
可选地，存储单元40包括：接收子单元、扣除子单元、第二增加子单元。接收子单元，用于接收购买者发出的已标注医疗数据使用权购买请求。扣除子单元，用于从购买者关联的账户中扣除虚拟资源。第二增加子单元，用于根据第一预设规则增加医疗数据的提供者和第一用户账户中的虚拟资源的数量。
可选地，当有用户想要购买已标注的医疗数据的使用权时，则从该用户的账户中扣除虚拟资源，并根据第一预设规则增加医疗数据的提供者和医疗数据的标注者的账户中的虚拟资源， 该第一预设规则规定了向医疗数据的提供者的账户中增加的虚拟资源的数量和向医疗数据的标注者的账户中增加的虚拟资源的数量的比例。例如，用户甲想购买已标注的肺部医疗数据的使用权，则从用户甲的账户中扣除了100个比特币，假设第一预设规则规定了向医疗数据的提供者的账户中增加的虚拟资源的数量和向医疗数据的标注者的账户中增加的虚拟资源的数量的比例是1:4，则将肺部医疗数据的提供者的账户中增加20个比特币，将肺部医疗数据的标注者的账户中增加80个比特币。如果肺部医疗数据的提供者或者标注者不只是一个用户，则按照第二预设规则向肺部医疗数据的每个提供者、每个标注者的账户中增加虚拟资源。
综上，从标注任务的发起者和数据使用请求的发起者关联的账户中扣除虚拟资源，增加医疗数据的标注者关联的账户中的虚拟资源的数量，并且标注者关联的账户中增加的虚拟资源的数量与标注者的标注工作量、标注质量、标注难易程度相关，鼓励优秀的标注者对医疗数据进行标注，充分利用了人力资源，从而能够得到大量的准确的医疗数据的标注结果，为医疗大数据的进一步应用奠定了很好的基础。
本申请实施例还提供了一种计算机设备，该计算机设备包括存储器和处理器，存储器用于存储包括程序指令的信息，处理器用于控制程序指令的执行，程序指令被处理器加载并执行时实现以下步骤：获取已上传的待标注的医疗数据；获取医疗数据的标注结果，其中，标注结果由第一用户按照标注规则对待标注的医疗数据进行标注得到；判断标注结果的准确性是否达到预设标准；如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加第一用户关联的账户中的虚拟资源的数量。
可选地，程序指令被处理器加载并执行时还实现以下步骤：按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量。
可选地，程序指令被处理器加载并执行时还实现以下步骤：在按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量之前，根据第一用户已经标注医疗数据的标注量和标注准确度来确定第一用户的标注专业等级。
可选地，程序指令被处理器加载并执行时还实现以下步骤：在获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务；在检测到医疗数据标注任务之后，计算医疗数据标注任务对应的虚拟资源的数量；将医疗数据标注任务对应的虚拟资源的数量发送至任务发起者对应的终端；从任务发起者关联的账户中扣除医疗数据标注任务对应的虚拟资源的数量。
可选地，程序指令被处理器加载并执行时还实现以下步骤：根据以下至少一种参数计算医疗数据标注任务对应的虚拟资源的数量：医疗数据标注任务的紧急程度参数、医疗数据标注任 务指定的标注量、医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
可选地，程序指令被处理器加载并执行时还实现以下步骤：接收购买者发出的已标注医疗数据使用权购买请求；从购买者关联的账户中扣除虚拟资源；根据第一预设规则增加医疗数据的提供者和第一用户账户中的虚拟资源的数量。
本申请实施例还提供了一种计算机非易失性可读存储介质，计算机非易失性可读存储介质包括存储的程序，其中，在程序运行时控制计算机非易失性可读存储介质所在设备执行以下步骤：获取已上传的待标注的医疗数据；获取医疗数据的标注结果，其中，标注结果由第一用户按照标注规则对待标注的医疗数据进行标注得到；判断标注结果的准确性是否达到预设标准；如果标注结果的准确性达到预设标准，则将医疗数据和标注结果进行关联存储，并增加第一用户关联的账户中的虚拟资源的数量。
可选地，在程序运行时控制计算机非易失性可读存储介质所在设备还执行以下步骤：按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量。
可选地，在程序运行时控制计算机非易失性可读存储介质所在设备还执行以下步骤：在按照第一用户的标注专业等级和/或医疗数据的重要性等级增加第一用户关联的账户中的虚拟资源的数量之前，根据第一用户已经标注医疗数据的标注量和标注准确度来确定第一用户的标注专业等级。
可选地，在程序运行时控制计算机非易失性可读存储介质所在设备还执行以下步骤：在获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务；在检测到医疗数据标注任务之后，计算医疗数据标注任务对应的虚拟资源的数量；将医疗数据标注任务对应的虚拟资源的数量发送至任务发起者对应的终端；从任务发起者关联的账户中扣除医疗数据标注任务对应的虚拟资源的数量。
可选地，在程序运行时控制计算机非易失性可读存储介质所在设备还执行以下步骤：根据以下至少一种参数计算医疗数据标注任务对应的虚拟资源的数量：医疗数据标注任务的紧急程度参数、医疗数据标注任务指定的标注量、医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
可选地，在程序运行时控制计算机非易失性可读存储介质所在设备还执行以下步骤：接收购买者发出的已标注医疗数据使用权购买请求；从购买者关联的账户中扣除虚拟资源；根据第一预设规则增加医疗数据的提供者和第一用户账户中的虚拟资源的数量。
需要说明的是，本申请实施例中所涉及的终端可以包括但不限于个人计算机(Personal  Computer，PC)、个人数字助理(Personal Digital Assistant，PDA)、无线手持设备、平板电脑(Tablet Computer)、手机、MP3播放器、MP4播放器等。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机装置(可以是个人计算机，服务器，或者网络装置等)或处理器(Processor)执行本申请各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。

Claims (20)

  1. 一种医疗数据的处理方法，其特征在于，所述方法包括：
    获取已上传的待标注的医疗数据；
    获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；
    判断所述标注结果的准确性是否达到预设标准；
    如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
  2. 根据权利要求1所述的方法，其特征在于，所述增加所述第一用户关联的账户中的虚拟资源的数量，包括：
    按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量。
  3. 根据权利要求2所述的方法，其特征在于，在所述按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量之前，所述方法还包括：
    根据所述第一用户已经标注医疗数据的标注量和标注准确度来确定所述第一用户的标注专业等级。
  4. 根据权利要求1所述的方法，其特征在于，在所述获取已上传的待标注的医疗数据之前或之后，所述方法还包括：
    判断是否检测到任务发起者发起的医疗数据标注任务；
    在检测到所述医疗数据标注任务之后，计算所述医疗数据标注任务对应的虚拟资源的数量；
    将所述医疗数据标注任务对应的虚拟资源的数量发送至所述任务发起者对应的终端；
    从所述任务发起者关联的账户中扣除所述医疗数据标注任务对应的虚拟资 源的数量。
  5. 根据权利要求4所述的方法，其特征在于，所述计算所述医疗数据标注任务对应的虚拟资源的数量，包括：
    根据以下至少一种参数计算所述医疗数据标注任务对应的虚拟资源的数量：所述医疗数据标注任务的紧急程度参数、所述医疗数据标注任务指定的标注量、所述医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
  6. 根据权利要求1所述的方法，其特征在于，所述增加所述第一用户关联的账户中的虚拟资源的数量，包括：
    接收购买者发出的已标注医疗数据使用权购买请求；
    从所述购买者关联的账户中扣除虚拟资源；
    根据第一预设规则增加所述医疗数据的提供者和所述第一用户账户中的虚拟资源的数量。
  7. 根据权利要求1至6中任意一项所述的方法，其特征在于，所述虚拟资源是比特币。
  8. 一种医疗数据的处理装置，其特征在于，所述装置包括：
    第一获取单元，用于获取已上传的待标注的医疗数据；
    第二获取单元，用于获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；
    第一判断单元，用于判断所述标注结果的准确性是否达到预设标准；
    存储单元，用于如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
  9. 根据权利要求8所述的装置，其特征在于，所述存储单元包括：
    第一增加子单元，用于按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量。
  10. 根据权利要求9所述的装置，其特征在于，所述装置还包括：
    确定单元，用于在所述第一增加子单元按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量之前，根据所述第一用户已经标注医疗数据的标注量和标注准确度来确定所述第一用户的标注专业等级。
  11. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    第二判断单元，用于在所述第一获取单元获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务；
    计算单元，用于在检测到所述医疗数据标注任务之后，计算所述医疗数据标注任务对应的虚拟资源的数量；
    发送单元，用于将所述医疗数据标注任务对应的虚拟资源的数量发送至所述任务发起者对应的终端；
    扣除单元，用于从所述任务发起者关联的账户中扣除所述医疗数据标注任务对应的虚拟资源的数量。
  12. 根据权利要求11所述的装置，其特征在于，所述计算单元包括：
    计算子单元，用于根据以下至少一种参数计算所述医疗数据标注任务对应的虚拟资源的数量：所述医疗数据标注任务的紧急程度参数、所述医疗数据标注任务指定的标注量、所述医疗数据标注任务指定的待标注的医疗数据的标注难度参数。
  13. 一种计算机设备，包括存储器和处理器，所述存储器用于存储包括程序指令的信息，所述处理器用于控制所述程序指令的执行，其特征在于，所述程序指令被所述处理器加载并执行时实现以下步骤：
    获取已上传的待标注的医疗数据；
    获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；
    判断所述标注结果的准确性是否达到预设标准；
    如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
  14. 根据权利要求13所述的计算机设备，其特征在于，所述程序指令被所述处理器加载并执行时还实现以下步骤：
    按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量。
  15. 根据权利要求14所述的计算机设备，其特征在于，所述程序指令被所述处理器加载并执行时还实现以下步骤：
    在所述按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量之前，根据所述第一用户已经标注医疗数据的标注量和标注准确度来确定所述第一用户的标注专业等级。
  16. 根据权利要求13所述的计算机设备，其特征在于，所述程序指令被所述处理器加载并执行时还实现以下步骤：
    在所述获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务；
    在检测到所述医疗数据标注任务之后，计算所述医疗数据标注任务对应的虚拟资源的数量；
    将所述医疗数据标注任务对应的虚拟资源的数量发送至所述任务发起者对应的终端；
    从所述任务发起者关联的账户中扣除所述医疗数据标注任务对应的虚拟资源的数量。
  17. 一种计算机非易失性可读存储介质，其特征在于，所述计算机非易失性可读存储介质包括存储的程序，其中，在所述程序运行时控制所述计算机非易失性可读存储介质所在设备执行以下步骤：
    获取已上传的待标注的医疗数据；
    获取所述医疗数据的标注结果，其中，所述标注结果由第一用户按照标注规则对所述待标注的医疗数据进行标注得到；
    判断所述标注结果的准确性是否达到预设标准；
    如果所述标注结果的准确性达到所述预设标准，则将所述医疗数据和所述标注结果进行关联存储，并增加所述第一用户关联的账户中的虚拟资源的数量。
  18. 根据权利要求17所述的计算机非易失性可读存储介质，其特征在于，在所述程序运行时控制所述计算机非易失性可读存储介质所在设备还执行以下步骤：
    按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量。
  19. 根据权利要求18所述的计算机非易失性可读存储介质，其特征在于，在所述程序运行时控制所述计算机非易失性可读存储介质所在设备还执行以下步骤：
    在所述按照所述第一用户的标注专业等级和/或所述医疗数据的重要性等级增加所述第一用户关联的账户中的虚拟资源的数量之前，根据所述第一用户已经标注医疗数据的标注量和标注准确度来确定所述第一用户的标注专业等级。
  20. 根据权利要求17所述的计算机非易失性可读存储介质，其特征在于，在所述程序运行时控制所述计算机非易失性可读存储介质所在设备还执行以下步骤：
    在所述获取已上传的待标注的医疗数据之前或之后，判断是否检测到任务发起者发起的医疗数据标注任务；
    在检测到所述医疗数据标注任务之后，计算所述医疗数据标注任务对应的虚拟资源的数量；
    将所述医疗数据标注任务对应的虚拟资源的数量发送至所述任务发起者对 应的终端；
    从所述任务发起者关联的账户中扣除所述医疗数据标注任务对应的虚拟资源的数量。
PCT/CN2018/123557 2018-10-15 2018-12-25 一种医疗数据的处理方法、装置 WO2020077840A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811196996.2A CN109065177A (zh) 2018-10-15 2018-10-15 一种医疗数据的处理方法、装置、服务器及存储介质
CN201811196996.2 2018-10-15

Publications (1)

Publication Number Publication Date
WO2020077840A1 true WO2020077840A1 (zh) 2020-04-23

Family

ID=64764783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/123557 WO2020077840A1 (zh) 2018-10-15 2018-12-25 一种医疗数据的处理方法、装置

Country Status (2)

Country Link
CN (1) CN109065177A (zh)
WO (1) WO2020077840A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109065177A (zh) * 2018-10-15 2018-12-21 平安科技（深圳）有限公司 一种医疗数据的处理方法、装置、服务器及存储介质
CN109784381A (zh) * 2018-12-27 2019-05-21 广州华多网络科技有限公司 标注信息处理方法、装置及电子设备
CN112420202A (zh) * 2019-08-23 2021-02-26 阿里巴巴集团控股有限公司 数据的处理方法、装置及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103345576A (zh) * 2013-06-25 2013-10-09 上海交通大学 基于四模态医学影像的病例库诊断系统
CN106295092A (zh) * 2015-05-13 2017-01-04 仁智(苏州)医学研究有限公司 临床医疗的多维度数据分析方法和系统
CN106489149A (zh) * 2016-06-29 2017-03-08 深圳狗尾草智能科技有限公司 一种基于数据挖掘和众包的数据标注方法及系统
CN107273698A (zh) * 2017-07-06 2017-10-20 武靖 人工智能训练标准库的处理与检测方法、系统
CN109065177A (zh) * 2018-10-15 2018-12-21 平安科技（深圳）有限公司 一种医疗数据的处理方法、装置、服务器及存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107194608B (zh) * 2017-06-13 2021-09-17 复旦大学 一种面向残疾人社区的众包标注任务分配方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103345576A (zh) * 2013-06-25 2013-10-09 上海交通大学 基于四模态医学影像的病例库诊断系统
CN106295092A (zh) * 2015-05-13 2017-01-04 仁智(苏州)医学研究有限公司 临床医疗的多维度数据分析方法和系统
CN106489149A (zh) * 2016-06-29 2017-03-08 深圳狗尾草智能科技有限公司 一种基于数据挖掘和众包的数据标注方法及系统
CN107273698A (zh) * 2017-07-06 2017-10-20 武靖 人工智能训练标准库的处理与检测方法、系统
CN109065177A (zh) * 2018-10-15 2018-12-21 平安科技（深圳）有限公司 一种医疗数据的处理方法、装置、服务器及存储介质

Also Published As

Publication number Publication date
CN109065177A (zh) 2018-12-21

Similar Documents

Publication Publication Date Title
CN108028077B (zh) 用于整合临床护理的信息学平台
WO2020077840A1 (zh) 一种医疗数据的处理方法、装置
KR20210107150A (ko) 생리학적 데이터의 제시
US20220125360A1 (en) Method and computer program for determining psychological state through drawing process of counseling recipient
WO2021139477A1 (zh) 智能就医方法、装置、计算机设备及存储介质
CN112233774A (zh) 一种个性化的医学影像管理系统
US20130173439A1 (en) System and Method for Remote Veterinary Image Analysis and Consultation
WO2023185805A1 (zh) 图像处理方法及装置
Wang et al. Technology standards in imaging: a practical overview
US12118272B2 (en) Systems and methods to accept speech input and edit a note upon receipt of an indication to edit
Partridge et al. Implementing a breast cancer registry and treatment plan/summary program in clinical practice: A pilot program
CN109785941B (zh) 一种医生的推荐方法和装置
US20190244696A1 (en) Medical record management system with annotated patient images for rapid retrieval
CN106202907A (zh) 基于云计算的移动查房系统
Aldridge et al. Teaching dermatology using 3-dimensional virtual reality
US20210304845A1 (en) Method and system for processing genetic data
Ash et al. Advancing measurement of the sources and consequences of burnout in a comprehensive cancer center: a structural equation modeling analysis
CN114004802A (zh) 基于模糊综合评价法的数据标注方法、装置及存储介质
CN112712890A (zh) 一种基于手持终端的医疗护理信息交互系统
TWM427917U (en) Portable electrocardiography recording device
US20150073831A1 (en) Evaluating population indicated for medical therapies
JP2016173773A (ja) ワークフローシステム、ワークフローシステムの処理方法、およびプログラム
CN113987016B (zh) 临床递交数据对比方法、装置、计算机设备和存储介质
Holmgren The Health Information Technology Special Issue: Tackling New Challenges to Digital Transformation.
JP7407536B2 (ja) 医療情報管理装置及び医療情報管理システム

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: 18937199

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: 18937199

Country of ref document: EP

Kind code of ref document: A1