Address data comprehensive processing method and system based on patient information

Abstract

The invention discloses an address data comprehensive processing method based on patient information, and the method comprises the steps: S1, obtaining a case through a diagnosis information output circuit, extracting tumor patient data according to the dimensions of the case, and carrying out the data cleaning; s2, extracting permanent residence information of the tumor patient according to priorities, stopping judgment if any priority can reach a province, supplementing the permanent residence information according to the current content, and continuing subsequent judgment if the province information cannot be extracted; s3, checking the permanent residence of the tumor patient based on the permanent residence information of the tumor patient; s4, performing permanent residence re-calculation based on the verification of the permanent residence of the tumor patient: when the information of the tumor patient is updated, re-calculating the permanent residence of the tumor patient according to the updated information by the permanent residence information; and S5, displaying the address data of the tumor patient through a diagnosis information record display device. The invention further discloses a corresponding system, electronic equipment and a computer readable storage medium.

Description

Technical Field

[0001] The present invention relates to the field of information intelligentization technology for medical information records, and in particular to a method and system for comprehensive processing of address data based on patient information. Background Art

[0002] Diagnosis Related Groups (DRGs) are an important tool for measuring the quality and efficiency of medical services and for medical insurance payment. DRG is essentially a case combination classification scheme, that is, a system that divides patients into several diagnostic groups for management based on factors such as age, disease diagnosis, comorbidities, complications, treatment methods, severity and outcome of symptoms, and resource consumption.

[0003] In addition, the correct filling of the main diagnosis on the front page of the medical record means that the physician and the coder follow the regulations, the physician accurately selects and fills in the main diagnosis on the front page of the inpatient medical record in a standardized manner, and the coder accurately codes according to the disease classification code uniformly issued by the state. The correct rate of the doctor's main diagnosis filling = the number of discharged patient medical records with the main diagnosis filled in correctly on the front page of the medical record / the total number of discharged patient medical records in the same period; the correct rate of the coder's main diagnosis coding = the number of discharged patient medical records with the main diagnosis coded correctly on the front page of the medical record / the total number of discharged patient medical records in the same period. The medical record reflects the rich diagnostic information of the patient. With the construction of the regional medical data platform, it is urgent to establish a complete patient diagnosis and treatment file.

[0004] However, in the process of establishing patient diagnosis and treatment records and conducting scientific research, the existing technology does not have a specific digital information extraction system to carry out automated information extraction. This results in the inability to efficiently and accurately integrate and manage tumor patient data, especially the address data in patient information, and the inability to improve the accuracy of judging the type of tumor and the degree of correlation with address information. It is also impossible to use new data analysis technology and pattern recognition algorithms to extract and analyze case features, which hinders the research progress of clinical epidemiological prediction science and social health research. Therefore, based on this demand, a comprehensive processing method and system for address data based on patient information is developed to facilitate the establishment of accurate patient diagnosis and treatment or health records, and to track the diagnosis and treatment process and conduct clinical research. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for comprehensive processing of address data based on patient information, so as to facilitate the subsequent accurate diagnosis and treatment process of tumors.

[0006] In one aspect, the present invention provides a method for comprehensive processing of address data based on patient information, comprising:

[0007] S1, obtain cases through the diagnostic information output circuit, extract tumor patient data according to case dimensions and perform data cleaning;

[0008] S2, extract the permanent residence information of the tumor patient according to the priority. If any priority can obtain the province, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the province information cannot be extracted, the subsequent judgment is continued;

[0009] S3, verifying the permanent residence of the tumor patient based on the permanent residence information of the tumor patient;

[0010] S4, recalculating the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates information, recalculating the permanent residence of the tumor patient according to the updated information;

[0011] S5, displaying the address data of the tumor patient through the diagnosis information recording and displaying device.

[0012] Preferably, the tumor patient data of S1 includes:

[0013] There are five types of data: structured address information of the main index of cancer patients, unstructured address information of the main index of cancer patients, postal code, telephone number and ID number.

[0014] Preferably, the data cleaning includes:

[0015] For the structured address information of the primary index of tumor patients, it includes: extracting structured provincial, municipal and county contents according to the structured processing logic. If the previous level content is missing, the county level is inferred to the city level, and the city level is inferred to the provincial level according to the address dictionary. The final record includes at least provincial level content;

[0016] For the unstructured address information of the main index of tumor patients, including: detailed and complete relevant address information, then extract the corresponding provincial, municipal and county content according to the unstructured processing logic, and the final record includes at least provincial content;

[0017] For the postal code, the following steps are performed: first, spaces and non-numeric characters are removed on both sides; then, the corresponding province, city, and county content are extracted after accurate matching through the postal code location dictionary; the final record includes at least provincial-level content;

[0018] For telephone numbers, the process includes: first removing spaces on both sides, then performing a mobile phone number standardization check, taking the first six digits of the mobile phone number that has passed the standardization check and accurately matching the mobile phone number's location dictionary, and then extracting the corresponding provincial and municipal content, while the county content is empty;

[0019] For the ID card number, it includes: first remove the spaces on the left and right sides, then verify the legitimacy of the ID card number, take the first six digits of the ID card number that passes the legitimacy check, and extract the province, city, and county content after matching with the address dictionary; if it cannot match with the address dictionary, intercept the first two digits to extract the corresponding province information;

[0020] For the place of medical treatment, it includes: extracting the location of the institution based on the reported location of the institution. If the medical institution belongs to the Xinjiang Production and Construction Corps, the extracted place of medical treatment is the Xinjiang Uygur Autonomous Region, and only the province is recorded, and the city and county are empty.

[0021] Preferably, the priority level includes: 0 to 30 levels, which are:

[0022] 0 priority: whether the province, city and county of the current structured address can obtain the provincial value;

[0023] 1st priority: whether the current address is complete and whether the provincial value can be obtained;

[0024] 2. Priority: whether the current address details can be obtained to obtain the provincial value;

[0025] 3. Priority: whether the current address postal code can obtain the provincial value;

[0026] 4. Priority: whether the current address and phone number can be obtained;

[0027] 5 Priority: Whether the province, city and county of the first structured contact can obtain the provincial value;

[0028] 6 Priority: whether the first contact is complete and can obtain the provincial value;

[0029] 7 Priority: whether the first contact details can get the provincial value;

[0030] 8 Priority: Whether the province, city and county of the second structured contact can obtain the provincial value;

[0031] 9 Priority: whether the second contact is complete and can obtain the provincial value;

[0032] 10 Priority: whether the second contact details can obtain the provincial value;

[0033] 11 Priority: Whether the province, city and county of the third structured contact can obtain the provincial value;

[0034] 12 Priority: whether the third contact is complete and can obtain the provincial value;

[0035] 13 Priority: whether the third contact details can obtain the provincial value;

[0036] 14 Priority: Whether the province, city and county of the fourth structured contact can obtain the provincial value;

[0037] 15 Priority: Whether the fourth contact is complete and can obtain the provincial value;

[0038] 16 Priority: Whether the fourth contact details can obtain the provincial value;

[0039] 17 Priority: Whether the first contact phone number can obtain the provincial value;

[0040] 18 Priority: Whether the second contact phone number can obtain the provincial value;

[0041] 19 Priority: Whether the third contact phone number can obtain the provincial value;

[0042] 20 Priority: Whether the fourth contact phone number can obtain the provincial value;

[0043] 21 Priority: Whether the province, city and county of the structured household registration address can obtain the provincial value;

[0044] 22 Priority: whether the provincial value can be obtained if the household address is complete;

[0045] 23 Priority: Whether the household address details can be retrieved to provincial values;

[0046] 24 Priority: Whether the postal code of the registered residence can obtain the provincial value;

[0047] 25 priority: whether the provincial value can be obtained from the ID card number;

[0048] 26 Priority: Whether the province, city and county of the structured birthplace can obtain the provincial value;

[0049] 27 Priority: Whether the birthplace is complete and the provincial value can be obtained;

[0050] 28 Priority: Whether the birthplace details can be retrieved to provincial values;

[0051] 29 Priority: Whether the province, city, and county of the structured native place can obtain the provincial value;

[0052] 30 Priority: Whether the provincial value can be obtained if the place of origin is complete.

[0053] Preferably, the basic strategy for verifying the permanent residence of the tumor patient in S3 is: for the primary index whose permanent residence falls on the address node, the permanent residence derived from all the fields carrying address information of the primary index is used for auxiliary verification; if there is no field carrying address information that can confirm the permanent residence or the evidence is insufficient, the permanent residence is abnormal, and the primary index with the abnormal permanent residence is manually reviewed.

[0054] Preferably, S3 includes:

[0055] S31, screening out the main index of tumor patients that meet the verification range;

[0056] S32, determining whether the detailed address and complete address information of the main index of all tumor patients are standard addresses;

[0057] S33, performing address information item quantity distribution statistics on the non-standard address cancer patient main index, including: for each cancer patient main index, obtaining the address quantity distribution under all nodes of the main index according to the priority node of the permanent residence;

[0058] S34, determining whether manual review is required based on the distribution of all carried address information items and the comparison result with the permanent residence;

[0059] S35, manually review and confirm the patient’s permanent residence;

[0060] S36, the manual review result is updated to the permanent residence of the cancer patient's primary index.

[0061] Preferably, the S31 includes:

[0062] (1) The calculation result of the primary index permanent residence of the tumor patient is based on a priority level of 1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 21, 22, 23, 26, 27, 28, 29 or 30; and

[0063] (2) The calculation result of the permanent residence of the primary index of the tumor patient is derived from the current address of any case with a priority of 0 and the case under the primary index is completed after the data cleaning;

[0064] The S32 includes:

[0065] (1) The detailed address and complete address information of the primary index start from the leftmost, if there is a province name, and contain the province or autonomous region keyword - standard address;

[0066] (2) The detailed address and complete address information of the primary index start from the leftmost, if there is a city name, and contain the city keyword - standard address;

[0067] (3) The detailed address and complete address information of the primary index start from the leftmost, if there is a county name, and contain the county or district keyword - standard address;

[0068] (4) The detailed address and complete address information of the primary index start from the leftmost side, if there is a province name, city name - standard address;

[0069] (5) The detailed address and complete address information of the main index start from the leftmost side, if there is a city name, county name - standard address;

[0070] (6) The detailed address and complete address information of the primary index start from the leftmost side, if there is a province name, county name - standard address;

[0071] The S34 includes:

[0072] (1) The number of times the permanent residence appears in all address information items in the primary index of cancer patients is 0: manual review;

[0073] (2) The number of times the permanent residence appears in all address information items carried in the main index of cancer patients is less than one-half: manual review;

[0074] (3) The number of times the permanent residence appears in all address information items in the main index of cancer patients is greater than or equal to one-half: non-manual review.

[0075] A second aspect of the present invention is to provide an address data comprehensive processing system based on patient information, comprising:

[0076] A data extraction and cleaning module (101), used to obtain cases through a diagnostic information output circuit, extract tumor patient data according to case dimensions, and perform data cleaning;

[0077] An information extraction and supplementation module (102) is used to extract the permanent residence information of the tumor patient according to the priority. If any priority can be obtained, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the permanent residence information cannot be extracted, the subsequent judgment is continued;

[0078] An address verification module (103), used to verify the permanent residence of the tumor patient based on the permanent residence information of the tumor patient;

[0079] A recalculation module (104) is used to recalculate the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates the information, the permanent residence information recalculates the permanent residence of the tumor patient according to the updated information;

[0080] An information display module (105) is used to display the address data of the tumor patient through the diagnostic information recording and display device.

[0081] A third aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is configured to read the instructions and execute the method described in the first aspect.

[0082] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, and the plurality of instructions can be read by a processor to execute the method described in the first aspect.

[0083] The method, system, electronic device, and computer-readable storage medium provided by the present invention have the following beneficial technical effects:

[0084] (1) Integration and management of cancer patient data including address data

[0085] By integrating multiple data sources, including basic information of cancer patients, admission records, discharge records, test results, treatment plans, etc., we can achieve comprehensive integration and management of cancer patients' hospitalization data, greatly improving the efficiency and accuracy of data management, and helping to analyze the relationship between patients' geographical information and cancer incidence.

[0086] (2) Improving the accuracy of determining the time of new tumor onset

[0087] By integrating multiple diagnostic judgments and data analysis algorithms, we can improve the ability to judge key time points in the tumor development process and increase the accuracy of judging the time of new tumor onset. This helps to integrate professional knowledge from different fields to improve the understanding and judgment of tumor onset time.

[0088] (3) Research data analysis and pattern recognition

[0089] Using advanced data analysis technology and pattern recognition algorithms, we extract and analyze tumor development patterns from a large number of hospitalized cases, including the characteristics of single and multiple primary tumors. This analysis helps to gain a deeper understanding of the biological characteristics and pathological mechanisms of tumors.

[0090] (4) Promotion of basic science and big data analysis

[0091] It will help promote progress in basic scientific research, such as the mechanism of tumor development and the differences between different types, and in the field of tumor epidemiology and geographical distribution. These research results are of great significance for future epidemiological predictions and health policy formulation.

[0092] (5) Research on epidemiology and social health impact

[0093] The data on permanent residence extracted from hospitalized cases are used to conduct research and analysis on cancer epidemiology. These data can reveal the differences in cancer incidence and related factors between different geographical regions, and help formulate public health policies and resource allocation strategies.

[0094] (6) Improve scientific research efficiency

[0095] It involves developing personalized data query and analysis tools, allowing researchers to customize queries on cancer patient data based on specific research needs. This tool helps improve data mining efficiency and the depth of data-driven research. Researchers can quickly retrieve and call the required case data, support a variety of data analysis tools, greatly shorten the time for data processing and analysis, improve scientific research efficiency, and improve the effective use of research resources, thereby promoting the progress of cancer research. In addition, the data visualization function provided by the system helps researchers understand data trends and results more intuitively.

[0096] (7) Improve data security

[0097] Multiple encryption technologies and strict authority management mechanisms are used to ensure the security and privacy of patient data, prevent unauthorized access and data leakage, and comply with relevant laws and regulations.

[0098] (8) Identification of survival status of cancer patients

[0099] By analyzing the patient's hospitalization records and follow-up information, the key factors that affect the patient's survival status can be identified. These models can help researchers understand the possible influencing factors of survival outcomes, thereby promoting the progress of medical research. Including long-term survival status monitoring and evaluation methods, by continuously collecting and analyzing patients' hospitalization data, and evaluating patients' treatment and survival outcomes, to provide a scientific basis for disease management strategies.

[0100] (9) Promotion of scientific research methods

[0101] It will help promote the development of customized query methods for tumor data, including improvements in data privacy protection and query efficiency, and provide technical support for future big data-driven medical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Figure 1 It is a flow chart of a method for comprehensive processing of address data based on patient information according to a preferred embodiment of the present invention;

[0103] Figure 2 It is a principle flow chart of a method for comprehensive processing of address data based on patient information according to a preferred embodiment of the present invention;

[0104] Figure 3 It is a flowchart of S3 in the method for comprehensive processing of address data based on patient information according to a preferred embodiment of the present invention;

[0105] Figure 4 It is a principle architecture diagram of an address data comprehensive processing system based on patient information according to a preferred embodiment of the present invention;

[0106] Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0107] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0108] Embodiment 1

[0109] like Figure 1-2 As shown, this embodiment provides a method for comprehensive processing of address data based on patient information, including:

[0110] S1, obtain cases through the diagnostic information output circuit, extract tumor patient data according to case dimensions and perform data cleaning;

[0111] As a preferred embodiment, the tumor patient data of S1 includes:

[0112] There are five types of data: structured address information of the main index of cancer patients, unstructured address information of the main index of cancer patients, postal code, telephone number and ID number.

[0113] As a preferred implementation, the data cleaning includes:

[0114] For the structured address information of the primary index of tumor patients, it includes: extracting structured provincial, municipal and county contents according to the structured processing logic. If the previous level content is missing, the county level is inferred to the city level, and the city level is inferred to the provincial level according to the address dictionary. The final record includes at least the provincial level content (this is because the city level content and the county level content may be empty);

[0115] For the unstructured address information of the primary index of tumor patients, including: detailed and complete relevant address information, then extract the corresponding provincial, municipal and county content according to the unstructured processing logic, and the final record includes at least provincial content (this is because the municipal and county content may be empty);

[0116] For the postal code, the following steps are performed: first, spaces and non-numeric characters are removed on both sides; then, the corresponding province, city, and county contents are extracted after accurate matching through the postal code location dictionary; the final record includes at least the provincial content (this is because the city and county contents may be empty);

[0117] For telephone numbers, the process includes: first removing spaces on both sides, then performing a mobile phone number standardization check, taking the first six digits of the mobile phone number that has passed the standardization check and accurately matching the mobile phone number's location dictionary, and then extracting the corresponding provincial and municipal content, while the county content is empty;

[0118] For the ID card number, the process includes: first removing the spaces on both sides, then verifying the legitimacy of the ID card number, taking the first six digits of the ID card number that passes the legitimacy verification, and extracting the province, city, and county content after matching with the address dictionary (in this embodiment: address dictionary tag df_tag); if it cannot match with the address dictionary, intercepting the first two digits to extract the corresponding province information;

[0119] For the place of medical treatment, it includes: extracting the location of the institution based on the reported location of the institution. If the medical institution belongs to the Xinjiang Production and Construction Corps, the extracted place of medical treatment is the Xinjiang Uygur Autonomous Region, and only the province is recorded, and the city and county are empty.

[0120] S2, extract the permanent residence information of the tumor patient according to the priority. If any priority can obtain the province, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the province information cannot be extracted, the subsequent judgment is continued;

[0121] As a preferred implementation, the priorities include: 0 to 30 levels, which are:

[0122] 0 priority: whether the province, city and county of the current structured address can obtain the provincial value;

[0123] 1st priority: whether the current address is complete and whether the provincial value can be obtained;

[0124] 2. Priority: whether the current address details can be obtained to obtain the provincial value;

[0125] 3. Priority: whether the current address postal code can obtain the provincial value;

[0126] 4. Priority: whether the current address and phone number can be obtained;

[0127] 5 Priority: Whether the province, city and county of the first structured contact can obtain the provincial value;

[0128] 6 Priority: whether the first contact is complete and can obtain the provincial value;

[0129] 7 Priority: whether the first contact details can get the provincial value;

[0130] 8 Priority: Whether the province, city and county of the second structured contact can obtain the provincial value;

[0131] 9 Priority: whether the second contact is complete and can obtain the provincial value;

[0132] 10 Priority: whether the second contact details can obtain the provincial value;

[0133] 11 Priority: Whether the province, city and county of the third structured contact can obtain the provincial value;

[0134] 12 Priority: whether the third contact is complete and can obtain the provincial value;

[0135] 13 Priority: whether the third contact details can obtain the provincial value;

[0136] 14 Priority: Whether the province, city and county of the fourth structured contact can obtain the provincial value;

[0137] 15 Priority: Whether the fourth contact is complete and can obtain the provincial value;

[0138] 16 Priority: Whether the fourth contact details can obtain the provincial value;

[0139] 17 Priority: Whether the first contact phone number can obtain the provincial value;

[0140] 18 Priority: Whether the second contact phone number can obtain the provincial value;

[0141] 19 Priority: Whether the third contact phone number can obtain the provincial value;

[0142] 20 Priority: Whether the fourth contact phone number can obtain the provincial value;

[0143] 21 Priority: Whether the province, city and county of the structured household registration address can obtain the provincial value;

[0144] 22 Priority: whether the provincial value can be obtained if the household address is complete;

[0145] 23 Priority: Whether the household address details can be retrieved to provincial values;

[0146] 24 Priority: Whether the postal code of the registered residence can obtain the provincial value;

[0147] 25 priority: whether the provincial value can be obtained from the ID card number;

[0148] 26 Priority: Whether the province, city and county of the structured birthplace can obtain the provincial value;

[0149] 27 Priority: Whether the birthplace is complete and the provincial value can be obtained;

[0150] 28 Priority: Whether the birthplace details can be retrieved to provincial values;

[0151] 29 Priority: Whether the province, city, and county of the structured native place can obtain the provincial value;

[0152] 30 Priority: Whether the provincial value can be obtained if the place of origin is complete.

[0153] In this embodiment, matching is performed according to the following priorities. If any priority can obtain the province, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the province information cannot be extracted, the subsequent judgment is continued. The matching priority order is as follows:

[0154] My current address

[0155] 0. Structured current address province, city, county

[0156] 1. Complete current address

[0157] 2. Current address details

[0158] 3. Current address postal code

[0159] 4. Current address and phone number

[0160] Contact Address

[0161] ●Contact 1 address

[0162] 5. Structured contact person 1 province, city and county

[0163] 6. Contact 1 Complete

[0164] 7. Contact 1 details

[0165] ●Contact 2 address

[0166] 8. Structured contact person 2 provinces, cities and counties

[0167] 9. Contact 2 Complete

[0168] 10. Contact 2 details

[0169] ●Contact person 3 address

[0170] 11. Structured contacts 3 provinces, cities and counties

[0171] 12. Contact 3 Complete

[0172] 13. Contact 3 details

[0173] Contact 4 Address

[0174] 14. Structured contacts 4 provinces, cities and counties

[0175] 15. Contact 4 Complete

[0176] 16. Contact 4 details

[0177] ●Contact phone number

[0178] 17. Contact 1 Phone Number

[0179] 18. Contact 2 phone number

[0180] 19. Contact 3 phone number

[0181] 20. Contact 4 Phone Number

[0182] Personal account address

[0183] 21. Structured household registration address province, city and county

[0184] 22. Complete household address

[0185] 23. Household address details

[0186] 24. Postal code of registered residence

[0187] 25. Personal ID number

[0188] My birthplace

[0189] 26. Structured birthplace province, city, county

[0190] 27. Birthplace complete

[0191] 28. Birthplace details

[0192] My place of origin

[0193] 29. Structured place of origin, province, city, county

[0194] 30. Complete place of origin;

[0195] S3, verifying the permanent residence of the tumor patient based on the permanent residence information of the tumor patient;

[0196] As a preferred implementation, the basic strategy for verifying the permanent residence of the tumor patient in S3 is: for the primary index whose permanent residence falls on the address node, the permanent residence derived from all the fields carrying address information of the primary index is used for auxiliary verification; if there is no field carrying address information that can confirm the permanent residence (no evidence) or there is little evidence (insufficient evidence), then the permanent residence is abnormal, and the primary index with the abnormal permanent residence is manually reviewed.

[0197] like Figure 3 As shown, as a preferred implementation, S3 includes:

[0198] S31, screening out the main index of tumor patients that meet the verification range;

[0199] In this embodiment, the S31 includes:

[0200] (1) The calculation result of the primary index permanent residence of the tumor patient is based on a priority level of 1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 21, 22, 23, 26, 27, 28, 29 or 30; and

[0201] (2) The calculation result of the permanent residence of the main index of the tumor patient is derived from the current address of any case with a priority of 0 under the main index after the data cleaning is completed.

[0202] S32, determining whether the detailed address and complete address information of the main index of all tumor patients are standard addresses.

[0203] In this embodiment, the S32 includes:

[0204] (1) The detailed address and complete address information of the primary index start from the leftmost, if there is a province name, and contain the province or autonomous region keyword - standard address;

[0205] (2) The detailed address and complete address information of the primary index start from the leftmost, if there is a city name, and contain the city keyword - standard address;

[0206] (3) The detailed address and complete address information of the primary index start from the leftmost, if there is a county name, and contain the county or district keyword - standard address;

[0207] (4) The detailed address and complete address information of the main index start from the leftmost, if there is a province name, city name - standard address;

[0208] (5) The detailed address and complete address information of the main index start from the leftmost side, if there is a city name, county name - standard address;

[0209] (6) The detailed address and complete address information of the main index start from the leftmost, if there is a province name, county name - standard address.

[0210] S33, performing address information item quantity distribution statistics on the non-standard address cancer patient main index, including: for each cancer patient main index, according to the priority node of the permanent residence, obtaining the address quantity distribution under all nodes of the main index.

[0211] S34, determining whether manual review is required based on the distribution of all carried address information items and the comparison results with the permanent residence.

[0212] In this embodiment, the S34 includes:

[0213] (1) The number of times the permanent residence appears in all address information items in the primary index of cancer patients is 0: manual review;

[0214] For example: G loba lXXXXXXXXXXX, platform permanent residence: Shandong Province, the number of addresses is Beijing: 2 times, Fujian Province: 5 times, Jiangsu Province: 4 times. If Shandong Province does not appear in all other address information items, then the extraction of the patient's permanent residence is inaccurate and needs to be manually reviewed.

[0215] (2) The number of times the permanent residence appears in all address information items carried in the main index of cancer patients is less than one-half (rounded off): manual review;

[0216] (3) The number of times the permanent residence appears in all address information items in the main index of cancer patients is greater than or equal to one-half: non-manual review.

[0217] S35, manually review and confirm the patient’s permanent residence;

[0218] S36, the manual review result is updated to the permanent residence of the cancer patient's primary index.

[0219] S4, recalculating the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates information, recalculating the permanent residence of the tumor patient according to the updated information;

[0220] S5, displaying the address data of the tumor patient through the diagnosis information recording and displaying device.

[0221] As a preferred embodiment, the diagnostic information output circuit reads the enable signal, timing signal, reset signal, and clock signal in the control device to monitor whether a problem occurs; determines the operating status and fault status of the control device when it is started based on the information of each electrical signal; generates maintenance diagnostic information based on the judgment result, and outputs the diagnostic information to the outside as an electrical signal via the power interface of the first universal interface through the first control switch; the diagnostic information output circuit sets the power interface to the power pull-up state through the second control switch S2, thereby setting it to the signal input state, and detecting the response signal from the external diagnostic circuit; the diagnostic information output circuit reads the data pin of the first universal interface, monitors whether a normal external device other than the diagnostic information recording and display device is connected to the first universal interface, and controls the update of the patient medical record information data and the output of the modification information according to the monitoring result.

[0222] As a preferred embodiment, the diagnostic information recording and display device has a diagnostic information recording and display circuit and a second universal interface, and the diagnostic information recording and display device is connected to a control device via a cable such as a USB cable for use; the diagnostic information recording and display device is provided with a data pin connected to the second universal interface, and by detecting the data pin, the diagnostic information output circuit of the control device can determine the working status of the external device and the diagnostic information recording and display device.

[0223] As a preferred embodiment, a personal computer or a numerical control device with a display is connected to the diagnostic information recording and display circuit; the diagnostic information recording and display circuit monitors the power interface of the second universal interface, analyzes the electrical signal input through the power interface, and obtains the diagnostic information of the control device generated by the control device; the acquired diagnostic information is output to the personal computer or the numerical control device, and displayed on the display via the personal computer or the numerical control device, thereby notifying the user who extracted the patient diagnostic package information; the diagnostic information recording and display circuit generates a response signal to the diagnostic information according to the third control switch, and outputs it to the diagnostic information output circuit via the power interface of the second universal interface.

[0224] Embodiment 2

[0225] like Figure 4As shown, this embodiment provides a comprehensive address data processing system based on patient information, including:

[0226] The data extraction and cleaning module 101 is used to obtain cases through the diagnostic information output circuit, extract tumor patient data according to the case dimension, and perform data cleaning;

[0227] The information extraction and supplementation module 102 is used to extract the permanent residence information of the tumor patient according to the priority. If any priority can be obtained as a province, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the province information cannot be extracted, the subsequent judgment is continued;

[0228] An address verification module 103 is used to verify the permanent residence of the tumor patient based on the permanent residence information of the tumor patient;

[0229] The recalculation module 104 is used to recalculate the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates the information, the permanent residence information recalculates the permanent residence of the tumor patient according to the updated information;

[0230] The information display module 105 is used to display the address data of the tumor patient through the diagnosis information recording and displaying device.

[0231] The present invention also provides a memory storing a plurality of instructions, wherein the instructions are used to implement the method described in the first embodiment.

[0232] like Figure 5 As shown, the present invention also provides an electronic device, including a processor 301 and a memory 302 connected to the processor 301, wherein the memory 302 stores a plurality of instructions, which can be loaded and executed by the processor so that the processor can execute the method described in Example 1.

[0233] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for comprehensive processing of address data based on patient information, characterized in that: include: S1, obtain cases through the diagnostic information output circuit, extract tumor patient data according to case dimensions and perform data cleaning; S2, extract the permanent residence information of the tumor patient according to the priority. If any priority can obtain the province, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the province information cannot be extracted, the subsequent judgment is continued; S3, verifying the permanent residence of the tumor patient based on the permanent residence information of the tumor patient; S4, recalculating the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates information, recalculating the permanent residence of the tumor patient according to the updated information; S5, displaying the address data of the tumor patient through the diagnosis information recording and displaying device.

2. A method for comprehensive processing of address data based on patient information according to claim 1, characterized in that: The tumor patient data of S1 includes: There are five types of data: structured address information of the main index of cancer patients, unstructured address information of the main index of cancer patients, postal code, telephone number and ID number.

3. A method for comprehensive processing of address data based on patient information according to claim 2, characterized in that: The data cleaning includes: For the structured address information of the primary index of tumor patients, it includes: extracting structured provincial, municipal and county contents according to the structured processing logic. If the previous level content is missing, the county level is inferred to the city level, and the city level is inferred to the provincial level according to the address dictionary. The final record includes at least provincial level content; For the unstructured address information of the main index of tumor patients, including: detailed and complete relevant address information, then extract the corresponding provincial, municipal and county content according to the unstructured processing logic, and the final record includes at least provincial content; For the postal code, the following steps are performed: first, spaces and non-numeric characters are removed on both sides; then, the corresponding province, city, and county content are extracted after accurate matching through the postal code location dictionary; the final record includes at least provincial-level content; For telephone numbers, the process includes: first removing spaces on both sides, then performing a mobile phone number standardization check, taking the first six digits of the mobile phone number that has passed the standardization check and accurately matching the mobile phone number's location dictionary, and then extracting the corresponding provincial and municipal content, while the county content is empty; For the ID card number, it includes: first remove the spaces on the left and right sides, then verify the legitimacy of the ID card number, take the first six digits of the ID card number that passes the legitimacy check, and extract the province, city, and county content after matching with the address dictionary; if it cannot match with the address dictionary, intercept the first two digits to extract the corresponding province information; For the place of medical treatment, it includes: extracting the location of the institution based on the reported location of the institution. If the medical institution belongs to the Xinjiang Production and Construction Corps, the extracted place of medical treatment is the Xinjiang Uygur Autonomous Region, and only the province is recorded, and the city and county are empty.

4. A method for comprehensive processing of address data based on patient information according to claim 3, characterized in that: The priorities include: 0 to 30, which are: 0 priority: whether the province, city and county of the current structured address can obtain the provincial value; 1st priority: whether the current address is complete and whether the provincial value can be obtained; 2. Priority: whether the current address details can be obtained to obtain the provincial value; 3. Priority: whether the current address postal code can obtain the provincial value; 4. Priority: whether the current address and phone number can be obtained; 5 Priority: Whether the province, city and county of the first structured contact can obtain the provincial value; 6 Priority: whether the first contact is complete and can obtain the provincial value; 7 Priority: whether the first contact details can get the provincial value; 8 Priority: Whether the province, city and county of the second structured contact can obtain the provincial value; 9 Priority: whether the second contact is complete and can obtain the provincial value; 10 Priority: whether the second contact details can obtain the provincial value; 11 Priority: Whether the province, city and county of the third structured contact can obtain the provincial value; 12 Priority: whether the third contact is complete and can obtain the provincial value; 13 Priority: whether the third contact details can obtain the provincial value; 14 Priority: Whether the province, city and county of the fourth structured contact can obtain the provincial value; 15 Priority: Whether the fourth contact is complete and can obtain the provincial value; 16 Priority: Whether the fourth contact details can obtain the provincial value; 17 Priority: Whether the first contact phone number can obtain the provincial value; 18 Priority: Whether the second contact phone number can obtain the provincial value; 19 Priority: Whether the third contact phone number can obtain the provincial value; 20 Priority: Whether the fourth contact phone number can obtain the provincial value; 21 Priority: Whether the province, city and county of the structured household registration address can obtain the provincial value; 22 Priority: whether the provincial value can be obtained if the household address is complete; 23 Priority: Whether the household address details can be retrieved to provincial values; 24 Priority: Whether the postal code of the registered residence can obtain the provincial value; 25 priority: whether the provincial value can be obtained from the ID card number; 26 Priority: Whether the province, city and county of the structured birthplace can obtain the provincial value; 27 Priority: Whether the birthplace is complete and the provincial value can be obtained; 28 Priority: Whether the birthplace details can be retrieved to provincial values; 29 Priority: Whether the province, city, and county of the structured native place can obtain the provincial value; 30 Priority: Whether the provincial value can be obtained if the place of origin is complete.

5. A method for comprehensive processing of address data based on patient information according to claim 4, characterized in that: The basic strategy for verifying the permanent residence of the tumor patient in S3 is: for the primary index whose permanent residence falls on the address node, the permanent residence derived from all the fields carrying address information of the primary index is used for auxiliary verification; if there is no field carrying address information that can confirm the permanent residence or the evidence is insufficient, the permanent residence is abnormal, and the primary index with the abnormal permanent residence is manually reviewed.

6. A method for comprehensive processing of address data based on patient information according to claim 5, characterized in that: The S3 includes: S31, screening out the main index of tumor patients that meet the verification range; S32, determining whether the detailed address and complete address information of the main index of all tumor patients are standard addresses; S33, performing address information item quantity distribution statistics on the non-standard address cancer patient main index, including: for each cancer patient main index, obtaining the address quantity distribution under all nodes of the main index according to the priority node of the permanent residence; S34, determining whether manual review is required based on the distribution of all carried address information items and the comparison result with the permanent residence; S35, manually review and confirm the patient’s permanent residence; S36, the manual review result is updated to the permanent residence of the cancer patient's primary index.

7. A method for comprehensive processing of address data based on patient information according to claim 6, characterized in that: The S31 includes: (1) The calculation result of the primary index permanent residence of the tumor patient is based on a priority level of 1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 21, 22, 23, 26, 27, 28, 29 or 30; and (2) The calculation result of the permanent residence of the primary index of the tumor patient is derived from the current address of any case with a priority of 0 and the case under the primary index is completed after the data cleaning; The S32 includes: (1) The detailed address and complete address information of the primary index start from the leftmost, if there is a province name, and contain the province or autonomous region keyword - standard address; (2) The detailed address and complete address information of the primary index start from the leftmost, if there is a city name, and contain the city keyword - standard address; (3) The detailed address and complete address information of the primary index start from the leftmost, if there is a county name, and contain the county or district keyword - standard address; (4) The detailed address and complete address information of the main index start from the leftmost, if there is a province name, city name - standard address; (5) The detailed address and complete address information of the main index start from the leftmost side, if there is a city name, county name - standard address; (6) The detailed address and complete address information of the primary index start from the leftmost side, if there is a province name, county name - standard address; The S34 includes: (1) The number of times the permanent residence appears in all address information items in the primary index of cancer patients is 0: manual review; (2) The number of times the permanent residence appears in all address information items carried in the main index of cancer patients is less than one-half: manual review; (3) The number of times the permanent residence appears in all address information items in the main index of cancer patients is greater than or equal to one-half: non-manual review.

8. A comprehensive address data processing system based on patient information, used to implement the method according to any one of claims 1 to 7, characterized in that: include: A data extraction and cleaning module (101), used to obtain cases through a diagnostic information output circuit, extract tumor patient data according to case dimensions, and perform data cleaning; An information extraction and supplementation module (102) is used to extract the permanent residence information of the tumor patient according to the priority. If any priority can be obtained, the judgment is stopped and the permanent residence information is supplemented according to the current content. If the permanent residence information cannot be extracted, the subsequent judgment is continued; An address verification module (103), used to verify the permanent residence of the tumor patient based on the permanent residence information of the tumor patient; A recalculation module (104) is used to recalculate the permanent residence of the tumor patient based on the permanent residence verification, including: when the tumor patient updates the information, the permanent residence information recalculates the permanent residence of the tumor patient according to the updated information; An information display module (105) is used to display the address data of the tumor patient through the diagnostic information recording and display device.

9. An electronic device, comprising a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is used to read the instructions and execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of instructions, wherein the plurality of instructions can be read by a processor and executed by a method according to any one of claims 1 to 7.

Images