我正在尝试对批量专利数据进行一些数据分析(数据通常在这里找到，但目前已关闭-https://ped.uspto.gov/peds/)。
以下是JSON文件中的第一个条目：
{
"PatentBulkData":[
{
"patentCaseMetadata":{
"applicationNumberText":{
"value":"15733015",
"electronicText":"15733015"
},
"filingDate":"2020-01-01",
"applicationTypeCategory":"Utility",
"partyBag":{
"applicantBagOrInventorBagOrOwnerBag":[
{
"applicant":[
{
"contactOrPublicationContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"personStructuredName":{
"firstName":"Birol",
"middleName":"",
"lastName":"Cimen"
}
}
]
},
"cityName":"Hengelo",
"geographicRegionName":{
"value":"",
"geographicRegionCategory":"STATE"
},
"countryCode":"NL"
}
]
}
]
},
{
"partyIdentifierOrContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"personStructuredName":{
"lastName":"Oppedahl Patent Law Firm LLC (Mink)"
}
}
]
},
"postalAddressBag":{
"postalAddress":[
{
"postalStructuredAddress":{
"addressLineText":[
{
"value":"P O Box 351240"
}
],
"cityName":"Westminster",
"geographicRegionName":[
{
"value":"CO"
}
],
"countryCode":"US",
"postalCode":"80035"
}
}
]
}
},
{
"value":"133517"
}
]
}
]
},
"groupArtUnitNumber":{
"value":"3771",
"electronicText":"3771"
},
"applicationConfirmationNumber":"7897",
"applicantFileReference":"FP01.P035 SST02US",
"priorityClaimBag":{
"priorityClaim":[
{
"ipOfficeName":"NETHERLANDS",
"applicationNumber":{
"applicationNumberText":"2019179"
},
"filingDate":"2017-07-05",
"sequenceNumber":"1"
}
]
},
"patentClassificationBag":{
"cpcClassificationBagOrIPCClassificationOrECLAClassificationBag":[
{
"ipOfficeCode":"US",
"mainNationalClassification":{
"nationalClass":"606",
"nationalSubclass":"133000"
}
}
]
},
"businessEntityStatusCategory":"SMALL",
"firstInventorToFileIndicator":"true",
"inventionTitle":{
"content":[
"Hair removal device for removing body hair on a body surface"
]
},
"applicationStatusCategory":"Application Dispatched from Preexam, Not Yet Docketed",
"applicationStatusDate":"2020-05-08",
"officialFileLocationCategory":"ELECTRONIC",
"patentPublicationIdentification":{
"publicationNumber":"US20200170371A1",
"publicationDate":"2020-06-04"
},
"relatedDocumentData":{
"parentDocumentDataOrChildDocumentData":[
{
"descriptionText":"This application is National Stage Entry of",
"applicationNumberText":"PCT/NL2018/050434",
"filingDate":"2018-07-04",
"parentDocumentStatusCode":"Published",
"patentNumber":""
}
]
}
},
"prosecutionHistoryDataBag":{
"prosecutionHistoryData":[
{
"eventDate":"2020-06-05",
"eventCode":"PG-ISSUE",
"eventDescriptionText":"PG-Pub Issue Notification"
},
{
"eventDate":"2020-05-11",
"eventCode":"M903",
"eventDescriptionText":"Notice of DO/EO Acceptance Mailed"
},
{
"eventDate":"2020-05-11",
"eventCode":"FLRCPT.U",
"eventDescriptionText":"Filing Receipt - Updated"
},
{
"eventDate":"2020-05-11",
"eventCode":"MPEN",
"eventDescriptionText":"Mail Pre-Exam Notice"
},
{
"eventDate":"2020-02-26",
"eventCode":"EML_NTR",
"eventDescriptionText":"Email Notification"
},
{
"eventDate":"2020-02-26",
"eventCode":"EML_NTR",
"eventDescriptionText":"Email Notification"
},
{
"eventDate":"2020-02-26",
"eventCode":"CCRDY",
"eventDescriptionText":"Application ready for PDX access by participating foreign offices"
},
{
"eventDate":"2020-01-05",
"eventCode":"371COMP",
"eventDescriptionText":"371 Completion Date"
},
{
"eventDate":"2020-02-25",
"eventCode":"PGPC",
"eventDescriptionText":"Sent to Classification Contractor"
},
{
"eventDate":"2020-02-25",
"eventCode":"FTFS",
"eventDescriptionText":"FITF set to YES - revise initial setting"
},
{
"eventDate":"2020-01-02",
"eventCode":"PTA.RFE",
"eventDescriptionText":"Patent Term Adjustment - Ready for Examination"
},
{
"eventDate":"2020-02-26",
"eventCode":"FLRCPT.O",
"eventDescriptionText":"Filing Receipt"
},
{
"eventDate":"2020-02-26",
"eventCode":"M903",
"eventDescriptionText":"Notice of DO/EO Acceptance Mailed"
},
{
"eventDate":"2019-12-31",
"eventCode":"SREXR141",
"eventDescriptionText":"PTO/SB/69-Authorize EPO Access to Search Results"
},
{
"eventDate":"2019-12-31",
"eventCode":"APPERMS",
"eventDescriptionText":"Applicants have given acceptable permission for participating foreign "
},
{
"eventDate":"2020-02-25",
"eventCode":"SMAL",
"eventDescriptionText":"Applicant Has Filed a Verified Statement of Small Entity Status in Compliance with 37 CFR 1.27"
},
{
"eventDate":"2019-12-31",
"eventCode":"L194",
"eventDescriptionText":"Cleared by OIPE CSR"
},
{
"eventDate":"2019-12-31",
"eventCode":"WIDS",
"eventDescriptionText":"Information Disclosure Statement (IDS) Filed"
},
{
"eventDate":"2019-12-31",
"eventCode":"WIDS",
"eventDescriptionText":"Information Disclosure Statement (IDS) Filed"
},
{
"eventDate":"2019-12-31",
"eventCode":"BIG.",
"eventDescriptionText":"ENTITY STATUS SET TO UNDISCOUNTED (INITIAL DEFAULT SETTING OR STATUS CHANGE)"
},
{
"eventDate":"2019-12-31",
"eventCode":"IEXX",
"eventDescriptionText":"Initial Exam Team nn"
}
]
},
"st96Version":"V3_1",
"ipoVersion":"US_V8_0"
},
我将json数据作为字典导入。然而，获取我想要检索的信息的最佳方式是什么。我应该使用json.normalize将其展开并转换为Dataframe吗？
我想特别检索"；起诉历史数据"；。例如，对于其他专利申请，这将提供关于已经发布了多少办公室行动的具体信息。
最后，我想交叉引用专利审查员的这一审查行动数据(当分配给审查员时，可以在"申请人BagOrInventorBagOrOwnerBag"中找到(。
有没有什么好的资源可以解释如何清理json数据，这样我就可以把这些信息分解成单独的列？
感谢您提供的信息！以下是审查员的一个例子：
{
"patentCaseMetadata":{
"applicationNumberText":{
"value":"16732312",
"electronicText":"16732312"
},
"filingDate":"2020-01-01",
"applicationTypeCategory":"Utility",
"partyBag":{
"applicantBagOrInventorBagOrOwnerBag":[
{
"primaryExaminerOrAssistantExaminerOrAuthorizedOfficer":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"personFullName":"ORGAD, EDAN"
}
]
}
}
]
},
{
"applicant":[
{
"contactOrPublicationContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"organizationStandardName":{
"content":[
"Communication Systems LLC"
]
}
}
]
},
"cityName":"Santa Fe",
"geographicRegionName":{
"value":"NM",
"geographicRegionCategory":"STATE"
},
"countryCode":""
}
]
}
]
}
]
},
"groupArtUnitNumber":{
"value":"2414",
"electronicText":"2414"
},
"applicationConfirmationNumber":"8996",
"applicantFileReference":"CS1003US03",
"patentClassificationBag":{
"cpcClassificationBagOrIPCClassificationOrECLAClassificationBag":[
{
"ipOfficeCode":"US",
"mainNationalClassification":{
"nationalClass":"370",
"nationalSubclass":"329000"
}
}
]
},
"businessEntityStatusCategory":"SMALL",
"firstInventorToFileIndicator":"true",
"inventionTitle":{
"content":[
"APPARATUSES, METHODS, AND COMPUTER-READABLE MEDIUM FOR COMMUNICATION IN A WIRELESS LOCAL AREA NETWORK"
]
},
"applicationStatusCategory":"Docketed New Case - Ready for Examination",
"applicationStatusDate":"2020-02-07",
"officialFileLocationCategory":"ELECTRONIC",
"patentPublicationIdentification":{
"publicationNumber":"US20200154403A1",
"publicationDate":"2020-05-14"
}
},
"prosecutionHistoryDataBag":{
"prosecutionHistoryData":[
{
"eventDate":"2020-05-19",
"eventCode":"PG-ISSUE",
"eventDescriptionText":"PG-Pub Issue Notification"
}
]
},
"assignmentDataBag":{
"assignmentData":[
{
"reelNumber":"52436",
"frameNumber":"295",
"documentReceivedDate":"2020-04-20",
"recordedDate":"2020-04-20",
"mailDate":"2020-04-21",
"pageTotalQuantity":3,
"conveyanceText":"ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS).",
"assignorBag":{
"assignor":[
{
"executionDate":"2016-07-14",
"contactOrPublicationContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"value":"ATEFI, ALI"
}
]
}
}
]
}
]
},
"assigneeBag":{
"assignee":[
{
"contactOrPublicationContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"value":"COMMUNICATION SYSTEMS LLC"
}
]
},
"postalAddressBag":{
"postalAddress":[
{
"postalAddressText":[
{
"sequenceNumber":"1",
"value":"530-B HARKLE ROAD"
},
{
"sequenceNumber":"2",
"value":"STE. 100"
},
{
"sequenceNumber":"3",
"value":"SANTA FE NEW MEXICO 87505"
}
]
}
]
}
}
]
}
]
},
"correspondenceAddress":{
"partyIdentifierOrContact":[
{
"name":{
"personNameOrOrganizationNameOrEntityName":[
{
"value":"ALI ATEFI"
}
]
},
"postalAddressBag":{
"postalAddress":[
{
"postalAddressText":[
{
"sequenceNumber":"1",
"value":"530-B HARKLE ROAD"
},
{
"sequenceNumber":"2",
"value":"STE. 100"
},
{
"sequenceNumber":"3",
"value":"SANTA FE, NM 87505"
}
]
}
]
}
}
]
},
"sequenceNumber":"1"
}
],
"assignmentTotalQuantity":1
},
"st96Version":"V3_1",
"ipoVersion":"US_V8_0"
},
我的解析不会通过应用程序BagOrInventorBagOrOwnerBag。以下是我尝试获取Examiner名称的示例解析，它返回一个空的数据帧：
jsonpath_expression = parse('PatentBulkData[*].patentCaseMetadata.partyBag.applicantBagOrInventorBagOrOwnerBag.primaryExaminerOrAssistantExaminerOrAuthorizedOfficer.name.personNameOrOrganizationNameOrEntityName.personFullName[*]')
如果我以applicationBagOrInventorBagOrOwnerBag结束，我会返回一个包含正确信息的数据帧——只包含括号和所有其他JSON表示法。我是不是错过了关键结构？
再次感谢！
为了解析或多或少复杂的JSON文档，您可能需要查看JSONPath"查询语言"；。
jsonpath-rw中有一个很好的Python实现。由于您需要的数据像这样嵌套
{
"PatentBulkData": [
{
"prosecutionHistoryDataBag": {
"prosecutionHistoryData": [
{
"eventDate": "2020-06-05",
"eventCode": "PG-ISSUE",
"eventDescriptionText": "PG-Pub Issue Notification"
},
JSONPath将是
在关键字
PatentBulkData下，获取数组的每个元素，然后是关键字prosecutionHistoryDataBag，然后是密钥prosecutionHistoryData，最后是该关键字下的所有数组元素。
或
PatentBulkData[*].prosecutionHistoryDataBag.prosecutionHistoryData[*]
这就是你在Python 中要做的
import json
from jsonpath_rw import jsonpath, parse
import pandas as pd
# Parse the string containing the whole JSON document
data = json.loads(<YOUR_JSON_STRING>)
jsonpath_expr = parse('PatentBulkData[*].prosecutionHistoryDataBag.prosecutionHistoryData[*]')
# Extract the raw value from each matching element,
# i.e. every element of the JSON array
matches = [match.value for match in jsonpath_expr.find(data)]
# Create dataframe from the list of dictionaries
df = pd.DataFrame.from_records(matches)
结果：
| eventDate | eventCode | eventDescriptionText |
|-------------|:------------|:----------------------------------|
| 2020-06-05 | PG-ISSUE | PG-Pub Issue Notification |
| 2020-05-11 | M903 | Notice of DO/EO Acceptance Mailed |
| 2020-05-11 | FLRCPT.U | Filing Receipt - Updated |
| 2020-05-11 | MPEN | Mail Pre-Exam Notice |
| 2020-02-26 | EML_NTR | Email Notification |
编辑
对于检查者查询，您需要查找嵌套数组。每次到达树中的一个数组时，都需要获得一个([0]、[1]等(或数组中的所有元素([*](：
examiner_expr = parse(
"PatentBulkData[*].patentCaseMetadata.partyBag"
".applicantBagOrInventorBagOrOwnerBag[*]"
".primaryExaminerOrAssistantExaminerOrAuthorizedOfficer[*]"
".name.personNameOrOrganizationNameOrEntityName[*]"
".personFullName"
)
[match.value for match in examiner_expr.find(data)]
# ['ORGAD, EDAN']