CN110767318A - Medical data anomaly detection method and device, computer equipment and storage medium - Google Patents
Medical data anomaly detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110767318A CN110767318A CN201910964492.9A CN201910964492A CN110767318A CN 110767318 A CN110767318 A CN 110767318A CN 201910964492 A CN201910964492 A CN 201910964492A CN 110767318 A CN110767318 A CN 110767318A
- Authority
- CN
- China
- Prior art keywords
- case
- detected
- target
- data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 239000003814 drug Substances 0.000 claims abstract description 123
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 229940079593 drug Drugs 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 21
- 230000005856 abnormality Effects 0.000 claims description 17
- 201000010099 disease Diseases 0.000 claims description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 17
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 229940124350 antibacterial drug Drugs 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000007943 implant Substances 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 241000894006 Bacteria Species 0.000 description 1
- 206010067671 Disease complication Diseases 0.000 description 1
- 206010059866 Drug resistance Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 239000003242 anti bacterial agent Substances 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 229940088710 antibiotic agent Drugs 0.000 description 1
- 230000003385 bacteriostatic effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 150000002460 imidazoles Chemical class 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 150000004957 nitroimidazoles Chemical class 0.000 description 1
- 150000007660 quinolones Chemical class 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 229940124530 sulfonamide Drugs 0.000 description 1
- 150000003456 sulfonamides Chemical class 0.000 description 1
- 239000003826 tablet Substances 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to machine learning and provides a medical data anomaly detection method, a medical data anomaly detection device, a computer device and a storage medium. The method comprises the following steps: receiving a medical data abnormity detection instruction, and searching corresponding data of each case to be detected according to the identification of each case to be detected; distributing each case data to be detected to each target server according to each case identification to be detected; acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data; and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal. By adopting the method, the operation pressure of the server can be reduced.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for detecting medical data abnormalities, a computer device, and a storage medium.
Background
Currently, the abnormality detection of medical data is usually performed according to a fixed rule, and a large amount of medical data is generated due to a large change of the medical data in an actual scene. The server checks massive medical data by using a fixed rule, the operating pressure of the server is high, and the server is crashed in severe cases.
Disclosure of Invention
In view of the above, it is necessary to provide a medical data abnormality detection method, apparatus, computer device, and storage medium capable of reducing the operating pressure of a server in response to the above technical problems.
A method of medical data anomaly detection, the method comprising:
receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier;
distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data;
and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal.
In one embodiment, before receiving a medical data anomaly detection instruction, where the medical data anomaly detection instruction carries at least one to-be-detected case identifier, and searching for corresponding to-be-detected case data according to each to-be-detected case identifier, the method further includes:
acquiring historical case data, and dividing the historical case data according to disease codes to obtain each case group corresponding to the historical case data;
deleting historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group;
and performing binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
In one embodiment, deleting historical case data in which the historical usage value of the drug exceeds the target value in each case group to obtain each target case group comprises:
calculating quantiles of historical use values of the drugs in each case group, and calculating a first target value and a second target value corresponding to each case group according to the quantiles;
and obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
In one embodiment, the step of distributing each piece of case data to be detected to each target server according to each piece of case identification to be detected, where the target server is configured to match each piece of distributed case data to be detected using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected includes:
and starting a parallel thread, inputting each case data to be detected into a case type identification tree by using the parallel thread for parallel identification, and obtaining each case type corresponding to each case data to be detected.
In one embodiment, allocating each piece of case data to be detected to each target server according to each case identifier to be detected includes:
and calculating the hash value of each to-be-detected case identifier, and distributing each to-be-detected case data to each target server according to the hash value.
A medical data anomaly detection apparatus, said apparatus comprising:
the data searching module is used for receiving a medical data abnormity detection instruction, the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier;
the data matching module is used for distributing each piece of case data to be detected to each target server according to each case identification to be detected, and the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
the abnormality detection module is used for acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use value according to the case category, and comparing the medicine normal use value with a medicine actual use value in the corresponding to-be-detected case data;
and the abnormity prompting module is used for sending abnormity prompt of the target case data to be detected to the target terminal when the actual medicine use value in the target case data to be detected exceeds the normal medicine use value of the case category corresponding to the target case data to be detected.
In one embodiment, the apparatus further comprises:
the historical data dividing module is used for acquiring historical case data, dividing the historical case data according to the disease codes and obtaining each case group corresponding to the historical case data;
the data deleting module is used for deleting the historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group;
and the identification tree obtaining module is used for carrying out binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
In one embodiment, the data deleting module includes:
the target numerical value calculating unit is used for calculating the quantile of the historical use numerical values of the medicines in each case group and calculating a first target numerical value and a second target numerical value corresponding to each case group according to the quantile;
and the numerical value area judging unit is used for obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier;
distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data;
and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier;
distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data;
and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal.
According to the medical data anomaly detection method, the medical data anomaly detection device, the computer equipment and the storage medium, the case identification to be detected corresponding to the case identification to be detected is allocated to the target server for identification by obtaining each case identification to be detected, the case category returned by the target server is obtained, and the anomaly detection result of the case data to be detected is obtained by comparing the normal use value of the medicine corresponding to the case category with the actual use value of the medicine. The target server identifies the case types, so that the operating pressure of the server is reduced, and the downtime of the server is avoided. And the case type identification tree is used in the target server to identify the case type of the case data to be detected, so that the accuracy of obtaining the normal use numerical value of the medicine can be improved, and the accuracy of the abnormal detection result of the case data to be detected can be improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary method for anomaly detection of medical data;
FIG. 2 is a schematic flow chart diagram illustrating a method for anomaly detection of medical data in one embodiment;
FIG. 3 is a schematic flow diagram illustrating training of a case class recognition tree in one embodiment;
FIG. 4 is a schematic flow chart illustrating obtaining a target group of cases in one embodiment;
FIG. 5 is a block diagram showing the construction of a medical data abnormality detecting apparatus according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The medical data abnormality detection method provided by the application can be applied to the application environment shown in fig. 1. The terminal 102 and the server 104 communicate with each other through a network, and the server 104 and each target server communicate with each other through a network. The server 104 receives a medical data anomaly detection instruction sent by the terminal 102, the medical data anomaly detection instruction carries at least one to-be-detected case identifier, and corresponding to each to-be-detected case data is searched according to each to-be-detected case identifier; the server 104 distributes each piece of case data to be detected to each target server according to each piece of case identification to be detected, and the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected; the server 104 acquires the case types corresponding to the case data to be detected returned by the target servers, searches corresponding medicine normal use values according to the case types, and compares the medicine normal use values with the actual use values of the medicines in the corresponding case data to be detected; when the actual use value of the medicine in the case data to be detected exceeds the normal use value of the medicine, the server 104 sends an abnormal prompt of the case data to be detected to the terminal 104. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a medical data anomaly detection method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s202, receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identification, and searching corresponding to each to-be-detected case data according to each to-be-detected case identification.
The case identifier to be detected is used for uniquely identifying the case to be detected, and may be a character string, a name, a numerical value, or the like. The case data to be detected refers to information recorded when the patient visits the clinic. The case data to be detected comprises: disease type, operation level, operation cumulative time, implant condition in body, whether there is infection evidence, accompanying disease complication, age, ventilator use time, length of stay, and drug (antibacterial drug) use, etc
Specifically, the server receives the medical data anomaly detection instruction, analyzes the medical data anomaly detection instruction to obtain at least one to-be-detected case identifier, and searches corresponding to-be-detected case data according to the obtained to-be-detected case identifier, namely, each to-be-detected case identifier corresponds to the to-be-detected case data.
And S204, distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected.
The target server is used for matching each piece of distributed case data to be detected by using a case type identification tree to obtain a case type corresponding to each piece of distributed case data to be detected, and then returning the obtained case type to the server. The distributed case data to be detected refers to the case data to be detected distributed to the target server. The case category refers to the category to which the disease the patient is visiting belongs.
Specifically, the server distributes each case data to be detected to each target server according to each case identifier to be detected, may randomly distribute each case data to be detected to each target server, may distribute each case data to be detected according to the responsibility of each target server, and the like. The target server receives the case data to be detected distributed by the server, matches the distributed case data to be detected in the case category identification tree to obtain the case category corresponding to the distributed case data to be detected, and then returns the case category corresponding to the distributed case data to be detected to the server.
In one embodiment, a master-slave architecture can be used for building a server and a target server to obtain a master server and each slave server, and the master server distributes each piece of case data to be detected to each slave server according to each piece of case identification to be detected.
In an embodiment, the server may directly use the deployed case category identification tree to identify each case identifier to be detected, so as to obtain a case category corresponding to each case data to be detected.
S206, acquiring the case types corresponding to the case data to be detected returned by the target servers, searching corresponding medicine normal use values according to the case types, and comparing the medicine normal use values with the actual use values of the medicines in the corresponding case data to be detected.
The normal usage value of the drug refers to a normal usage value of the antibacterial drug, and may be a DDD (defined daily dose) value. The antibacterial drugs generally refer to drugs with bactericidal or bacteriostatic activity, including various chemically synthesized drugs such as antibiotics, sulfonamides, imidazoles, nitroimidazoles, quinolones and the like, and when the antibacterial drugs are used over the normal use value of the drugs, the immunity of patients is possibly reduced, adverse reactions occur, the bacteria generate drug resistance and the like. The actual drug use value refers to the use value of the antibacterial drug in the corresponding case data to be detected.
Specifically, the server obtains case categories corresponding to each to-be-detected case data returned by each target server, searches corresponding medicine normal use numerical values according to the case categories, and each case category has a corresponding medicine normal use numerical value which can be a specific numerical value or a numerical value interval and is configured in the server in advance. And the server compares the normal use value of the medicine of the case type corresponding to each to-be-detected case data with the actual use value of the medicine in each to-be-detected case data.
And S208, when the actual use value of the medicine in the target to-be-detected case data exceeds the normal use value of the medicine in the case category corresponding to the target to-be-detected case data, sending an abnormal prompt of the target to-be-detected case data to the target terminal.
The target terminal is a preset terminal for prompting data abnormality, and may be a terminal for sending a data abnormality detection instruction and receiving a data abnormality detection result, or a terminal for receiving only a data abnormality detection result. The target case data to be detected refers to the case data to be detected, wherein the actual use value of the medicine exceeds the normal use value of the medicine.
Specifically, when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, an abnormal prompt of the target case data to be detected is sent to the target terminal. And when the actual use value of the medicine in the target case data to be detected does not exceed the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending a normal prompt of the target case to be detected to the target terminal.
In the medical data abnormality detection method, the target server is used for identifying the case types, so that the operating pressure of the server is reduced, and the downtime of the server is avoided. And the case type identification tree is used in the target server to identify the case type of the case data to be detected, so that the accuracy of obtaining the normal use numerical value of the medicine can be improved, and the accuracy of the abnormal detection result of the case data to be detected can be improved.
In an embodiment, as shown in fig. 3, before step S202, that is, before receiving a medical data anomaly detection instruction, the medical data anomaly detection instruction carrying at least one to-be-detected case identifier, and before searching for corresponding each to-be-detected case data according to each to-be-detected case identifier, the method further includes the steps of:
s302, historical case data are obtained and divided according to disease codes to obtain each case group corresponding to the historical case data.
The disease code refers to International Classification of Diseases (ICD) standard code, and is a code that classifies basic classes according to disease characteristics and rules and represents the classes. The case groups are obtained by dividing case data encoded by the same disease.
Specifically, the server acquires each historical case data, divides each historical case data according to the disease code of each historical case data, and obtains each case group corresponding to each historical case data, namely each historical case data has a corresponding case group.
S304, deleting the historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group.
The target value is obtained according to the drug historical use value of each historical case data of the case group, and is used for searching case data with abnormal drug use value in the historical case data. The target case group is obtained from historical case data with normal drug use values.
Specifically, the server deletes the historical case data of which the historical usage value exceeds the target value in each case group to obtain each target case group, that is, compares the historical usage value of the historical case data in each case group with the target value, and deletes the historical case data exceeding the target value from the case group to obtain the deleted target case group.
S306, performing binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
Wherein the dividing completion condition is that the variation coefficient of the medicine history use numerical value of the history case data in the binary dividing result is smaller than a set threshold value. The partition condition refers to a judgment condition in binary partition, and may be a disease type, a (whether or not) operation level, an operation accumulation time, an implant condition in a body, whether or not there is evidence of infection, accompanying disease or complication, an age, whether or not a ventilator is used, or the like.
Specifically, historical case data in each target case group is acquired, all the historical case data are divided into two branches, the variation coefficient of the medicine historical use value corresponding to each division result is calculated, and when the variation coefficient is smaller than a set threshold (generally between 0.7 and 1), the division results are the historical case data of the same class. And when the coefficient of variation is not less than the set threshold, dividing the division results again according to the division conditions until the coefficient of variation of the medicine history use numerical value corresponding to each division result is less than the set threshold, and achieving the division finishing conditions to obtain the case category identification tree. At this time, a case category corresponding to each division result in case category identification and a drug normal use numerical value corresponding to the case category are set. And then deploying the set case category identification tree into each target server.
In the embodiment, the historical case data is screened, binary division is performed according to the screening result to obtain the case type identification tree, and the case type identification tree is deployed to each target server, so that the case type identification tree is convenient to use directly in the follow-up process, and the efficiency of obtaining the case type corresponding to the case data to be detected is improved.
In one embodiment, as shown in fig. 4, the step S304 of deleting historical case data with a drug historical usage value exceeding a target value in each case group to obtain each target case group includes the steps of:
s402, calculating quantiles of the historical use values of the drugs in each case group, and calculating a first target value and a second target value corresponding to each case group according to the quantiles.
Wherein, the quantile refers to 25% quantile and 75% quantile of the medicine historical use value corresponding to each historical case data in the case group. The first target value is the normal upper limit value of the historical usage value of the drug in the case group, and the second target value is the normal lower limit value of the historical usage value of the drug in the case group.
Specifically, the server calculates a 25% quantile and a 75% quantile of the historical use values of the drugs in each case group, and then calculates a first target value and a second target value corresponding to each case group according to the 25% quantile and the 75% quantile of each case group. Where the normal upper limit value Q may be used3+K(Q3-Q1) K ∈ (0,0.5) and a normal upper limit value ═ Q3-K(Q3-Q1) And calculating the K epsilon (0,0.5) to obtain a first target value and a second target value. Q3Is 75% quantile, Q1Is 25% quantile and K is the adjustment coefficient.
S404, obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
The target numerical value region is a normal region of the medicine history use numerical values obtained according to the upper normal limit value and the lower normal limit value of the medicine history use.
Specifically, the server obtains a target value area according to the second target value and the second target value, and when the historical usage value of the drug in each case group is not in the target value area, it indicates that the historical case data of the historical usage value is abnormal historical case data, and deletes the historical case data of which the historical usage value is not in the target value area to obtain each target case group. The historical case data of which the historical use value of the medicine in the case group exceeds the normal upper limit value and the normal lower limit value corresponding to the case group is eliminated from the case group, and the target case group is obtained. And removing abnormal historical case data in all case groups to obtain each target case group.
In the above embodiment, the first target value and the second target value in the historical case data are obtained through calculation to obtain the target value area, the historical use value of the drug in the historical case data is judged according to the target value area to obtain the abnormal condition of the historical case data, the abnormal historical case data is removed to obtain each target case group, the historical case data are all normal historical case data, and the training of the case type identification tree is facilitated.
In one embodiment, step S204, allocating each to-be-detected case data to each target server according to each to-be-detected case identifier, where the target server is configured to match each allocated to-be-detected case data using a case category identification tree to obtain a case category corresponding to each allocated to-be-detected case data, and includes the steps of:
and starting a parallel thread, inputting each case data to be detected into a case type identification tree by using the parallel thread for parallel identification, and obtaining each case type corresponding to each case data to be detected.
Specifically, the server starts a parallel thread, and the parallel thread is used for inputting each case data to be detected into a case category identification tree to be identified in parallel to obtain each case category corresponding to each case data to be detected. The method and the system improve the utilization efficiency of server resources by parallelly identifying the case categories corresponding to the case data to be detected.
In one embodiment, the step S204 of distributing each to-be-detected case data to each target server according to each to-be-detected case identifier includes the steps of:
calculating the hash value of each to-be-detected case identification, and distributing each to-be-detected case data to each target server according to the hash value
Specifically, the server calculates the hash value of each to-be-detected case identifier, and distributes each to-be-detected case data to each target server according to the hash value
In the embodiment, the hash value of the identification of the case to be detected is calculated, and the case data to be detected is distributed according to the hash value, so that the case data to be detected can be distributed to the target server in a balanced manner, and the processing efficiency is improved.
In one embodiment, the corresponding data of each case to be detected can be distributed to each target server in a polling manner according to the identification of the case to be detected.
In one embodiment, the model-taking calculation may be performed on the to-be-detected case identifier, and the data of each to-be-detected case is distributed to each target server according to the result of the model-taking calculation.
In one embodiment, the to-be-detected case data corresponding to each to-be-detected case identifier is sent to a message queue according to the to-be-detected case identifier, and when the target server can perform task processing, the target server acquires the to-be-detected case data from the message queue.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a medical data anomaly detection apparatus 500, comprising: a data lookup module 502, a data matching module 504, an anomaly detection module 506, and an anomaly prompt module 508, wherein:
the data searching module 502 is configured to receive a medical data anomaly detection instruction, where the medical data anomaly detection instruction carries at least one to-be-detected case identifier, and search, according to each to-be-detected case identifier, for corresponding each to-be-detected case data;
the data matching module 504 is configured to allocate each to-be-detected case data to each target server according to each to-be-detected case identifier, where the target servers are configured to match each allocated to-be-detected case data using a case category identification tree to obtain a case category corresponding to each allocated to-be-detected case data;
the anomaly detection module 506 is configured to acquire a case category corresponding to each to-be-detected case data returned by each target server, search a corresponding drug normal usage value according to the case category, and compare the drug normal usage value with a drug actual usage value in the corresponding to-be-detected case data;
the abnormality prompting module 508 is configured to send an abnormality prompt of the target case data to be detected to a target terminal when the actual usage value of the drug in the target case data to be detected exceeds the normal usage value of the drug in the case category corresponding to the target case data to be detected.
In one embodiment, the medical data anomaly detection apparatus 500 further includes:
the historical data dividing module is used for acquiring historical case data, dividing the historical case data according to the disease codes and obtaining each case group corresponding to the historical case data;
the data deleting module is used for deleting the historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group;
and the identification tree obtaining module is used for carrying out binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
In one embodiment, a data deletion module includes:
the target numerical value calculating unit is used for calculating the quantile of the historical use numerical values of the medicines in each case group and calculating a first target numerical value and a second target numerical value corresponding to each case group according to the quantile;
and the numerical value area judging unit is used for obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
In an embodiment, the data matching module 504 is further configured to start a parallel thread, and input each case data to be detected into the case category identification tree by using the parallel thread for parallel identification, so as to obtain each case category corresponding to each case data to be detected.
In an embodiment, the data matching module 504 is further configured to calculate a hash value of each identifier of the case to be detected, and distribute each data of the case to be detected to each target server according to the hash value
For specific limitations of the medical data abnormality detection apparatus, reference may be made to the above limitations of the medical data abnormality detection method, which are not described herein again. All or part of the modules in the medical data abnormality detection device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing case data to be detected. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a medical data anomaly detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier; distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected; acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data; and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical case data, and dividing the historical case data according to disease codes to obtain each case group corresponding to the historical case data; deleting historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group; and performing binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
In one embodiment, the processor, when executing the computer program, further performs the steps of: calculating quantiles of historical use values of the drugs in each case group, and calculating a first target value and a second target value corresponding to each case group according to the quantiles; and obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and starting a parallel thread, inputting each case data to be detected into a case type identification tree by using the parallel thread for parallel identification, and obtaining each case type corresponding to each case data to be detected.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and calculating the hash value of each to-be-detected case identifier, and distributing each to-be-detected case data to each target server according to the hash value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identifier, and searching corresponding to each to-be-detected case data according to each to-be-detected case identifier; distributing each piece of case data to be detected to each target server according to each case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected; acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data; and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to the target terminal.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical case data, and dividing the historical case data according to disease codes to obtain each case group corresponding to the historical case data; deleting historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group; and performing binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
In one embodiment, the computer program when executed by the processor further performs the steps of: calculating quantiles of historical use values of the drugs in each case group, and calculating a first target value and a second target value corresponding to each case group according to the quantiles; and obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
In one embodiment, the computer program when executed by the processor further performs the steps of: and starting a parallel thread, inputting each case data to be detected into a case type identification tree by using the parallel thread for parallel identification, and obtaining each case type corresponding to each case data to be detected.
In one embodiment, the computer program when executed by the processor further performs the steps of: and calculating the hash value of each to-be-detected case identifier, and distributing each to-be-detected case data to each target server according to the hash value.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of medical data anomaly detection, the method comprising:
receiving a medical data abnormity detection instruction, wherein the medical data abnormity detection instruction carries at least one to-be-detected case identification, and searching corresponding to each to-be-detected case data according to each to-be-detected case identification;
distributing each piece of case data to be detected to each target server according to each piece of case identification to be detected, wherein the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use numerical value according to the case category, and comparing the medicine normal use numerical value with a medicine actual use numerical value in the corresponding to-be-detected case data;
and when the actual use value of the medicine in the target case data to be detected exceeds the normal use value of the medicine in the case category corresponding to the target case data to be detected, sending an abnormal prompt of the target case data to be detected to a target terminal.
2. The method according to claim 1, wherein before the receiving the medical data anomaly detection instruction, which carries at least one to-be-detected case identifier, and searching for each corresponding to-be-detected case data according to each to-be-detected case identifier, the method further comprises:
acquiring historical case data, and dividing the historical case data according to disease codes to obtain each case group corresponding to the historical case data;
deleting historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group;
and performing binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
3. The method of claim 2, wherein the deleting historical case data for which the historical usage value of the drug in the respective case group exceeds the target value to obtain the respective target case group comprises:
calculating quantiles of historical use values of the medicines in each case group, and calculating a first target value and a second target value corresponding to each case group according to the quantiles;
and obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area when the historical use numerical value of the medicine in each case group is not in the target numerical value area to obtain each target case group.
4. The method according to claim 1, wherein the step of distributing each piece of case data to be detected to each target server according to each piece of case identification to be detected, the target server being configured to match each piece of distributed case data to be detected using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected comprises:
and starting a parallel thread, inputting the case data to be detected into the case type identification tree by using the parallel thread for parallel identification, and obtaining each case type corresponding to the case data to be detected.
5. The method according to claim 1, wherein distributing the respective case data to be detected to respective target servers according to the respective case identifiers to be detected comprises:
and calculating the hash value of each to-be-detected case identifier, and distributing the to-be-detected case data to each target server according to the hash value.
6. A medical data anomaly detection apparatus, the apparatus comprising:
the data searching module is used for receiving a medical data abnormity detection instruction, the medical data abnormity detection instruction carries at least one to-be-detected case identification, and searching corresponding to each to-be-detected case data according to each to-be-detected case identification;
the data matching module is used for distributing each piece of case data to be detected to each target server according to each piece of case identification to be detected, and the target servers are used for matching each piece of distributed case data to be detected by using a case category identification tree to obtain a case category corresponding to each piece of distributed case data to be detected;
the abnormality detection module is used for acquiring a case category corresponding to each to-be-detected case data returned by each target server, searching a corresponding medicine normal use value according to the case category, and comparing the medicine normal use value with a medicine actual use value in the corresponding to-be-detected case data;
and the abnormity prompting module is used for sending abnormity prompt of the target case data to be detected to a target terminal when the actual medicine use value in the target case data to be detected exceeds the normal medicine use value of the case category corresponding to the target case data to be detected.
7. The apparatus of claim 6, further comprising:
the historical data dividing module is used for acquiring historical case data and dividing the historical case data according to disease codes to obtain each case group corresponding to the historical case data;
the data deleting module is used for deleting the historical case data of which the historical use value of the medicine exceeds the target value in each case group to obtain each target case group;
and the identification tree obtaining module is used for carrying out binary division on the target case group according to the division conditions, obtaining a case category identification tree when the division completion conditions are met, and deploying the case category identification tree to each target server.
8. The apparatus of claim 7, wherein the data deletion module comprises:
the target numerical value calculating unit is used for calculating the quantile of the historical use numerical values of the medicines in each case group and calculating a first target numerical value and a second target numerical value corresponding to each case group according to the quantile;
and the numerical value area judging unit is used for obtaining a target numerical value area according to the second target numerical value and the second target numerical value, and deleting the historical case data of which the historical use numerical value is not in the target numerical value area to obtain each target case group when the historical use numerical value of the medicine in each case group is not in the target numerical value area.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910964492.9A CN110767318A (en) | 2019-10-11 | 2019-10-11 | Medical data anomaly detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910964492.9A CN110767318A (en) | 2019-10-11 | 2019-10-11 | Medical data anomaly detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110767318A true CN110767318A (en) | 2020-02-07 |
Family
ID=69331843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910964492.9A Pending CN110767318A (en) | 2019-10-11 | 2019-10-11 | Medical data anomaly detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110767318A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376381A (en) * | 2018-09-10 | 2019-02-22 | 平安科技（深圳）有限公司 | Method for detecting abnormality, device, computer equipment and storage medium are submitted an expense account in medical insurance |
| CN109545387A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | One kind abnormal case recognition methods neural network based and calculating equipment |
| CN109543956A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | The detection method and relevant device of violation medical institutions based on data analysis |
| CN109659035A (en) * | 2018-12-13 | 2019-04-19 | 平安医疗健康管理股份有限公司 | Medical data exception recognition methods, equipment and storage medium based on machine learning |
| CN109767840A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of method for detecting abnormality, abnormal detector and computer readable storage medium |
| CN110021439A (en) * | 2019-03-07 | 2019-07-16 | 平安科技（深圳）有限公司 | Medical data classification method, device and computer equipment based on machine learning |
-
2019
- 2019-10-11 CN CN201910964492.9A patent/CN110767318A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376381A (en) * | 2018-09-10 | 2019-02-22 | 平安科技（深圳）有限公司 | Method for detecting abnormality, device, computer equipment and storage medium are submitted an expense account in medical insurance |
| CN109543956A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | The detection method and relevant device of violation medical institutions based on data analysis |
| CN109545387A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | One kind abnormal case recognition methods neural network based and calculating equipment |
| CN109659035A (en) * | 2018-12-13 | 2019-04-19 | 平安医疗健康管理股份有限公司 | Medical data exception recognition methods, equipment and storage medium based on machine learning |
| CN109767840A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of method for detecting abnormality, abnormal detector and computer readable storage medium |
| CN110021439A (en) * | 2019-03-07 | 2019-07-16 | 平安科技（深圳）有限公司 | Medical data classification method, device and computer equipment based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110750267B (en) | Service information updating method, device, computer equipment and storage medium | |
| CN109871305B (en) | Alarm information processing method and device, computer equipment and storage medium | |
| CN109215771B (en) | Medical mapping relation library establishment method, device, computer equipment and storage medium | |
| CN108845869B (en) | Concurrent request control method, device, computer equipment and storage medium | |
| CN108834086B (en) | Method and device for sending short message, computer equipment and storage medium | |
| CN109614238B (en) | Target object identification method, device and system and readable storage medium | |
| WO2022062353A1 (en) | Medical data processing method and apparatus, and computer device and storage medium | |
| CN108924258B (en) | Background information pushing method and device, computer equipment and storage medium | |
| CN109359809B (en) | Work task allocation method, system, computer device and storage medium | |
| CN108449237B (en) | Network performance monitoring method and device, computer equipment and storage medium | |
| CN111865691B (en) | Alarm file distribution method, device, equipment and medium based on artificial intelligence | |
| CN112016318A (en) | Triage information recommendation method, device, equipment and medium based on interpretation model | |
| CN110931090A (en) | Disease data processing method and device, computer equipment and storage medium | |
| CN109922013B (en) | Service access flow control method, device, server and storage medium | |
| CN108200087B (en) | Web intrusion detection method and device, computer equipment and storage medium | |
| CN109542962B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113515322B (en) | Application program loading method and device, computer equipment and readable storage medium | |
| CN111741112A (en) | File downloading method, device, equipment and storage medium based on artificial intelligence | |
| CN112017745A (en) | Decision information recommendation method, decision information recommendation device, medicine information recommendation method, medicine information recommendation device, equipment and medium | |
| CN108389124B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN109614399B (en) | Bitmap data query method and device, computer equipment and storage medium | |
| CN109901998B (en) | Resource recovery method, device, system, computer equipment and storage medium | |
| CN113609230A (en) | Data synchronization abnormity warning method and device, computer equipment and storage medium | |
| CN110767318A (en) | Medical data anomaly detection method and device, computer equipment and storage medium | |
| CN111898035A (en) | Data processing strategy configuration method and device based on Internet of things and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40023172 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220525 Address after: 518048 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200207 |
|
| RJ01 | Rejection of invention patent application after publication |