CN112632995A - User service request processing method and device, server and storage medium - Google Patents
User service request processing method and device, server and storage medium Download PDFInfo
- Publication number
- CN112632995A CN112632995A CN202011402770.0A CN202011402770A CN112632995A CN 112632995 A CN112632995 A CN 112632995A CN 202011402770 A CN202011402770 A CN 202011402770A CN 112632995 A CN112632995 A CN 112632995A
- Authority
- CN
- China
- Prior art keywords
- user
- time
- information
- illness
- disease
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The method can acquire application information of a target service which is applied by a user and health state information of the user, wherein the application information of the target service which is applied comprises first time, and a disease name and corresponding disease time are extracted from the health state information of the user. And comparing the illness time with the first time, if the illness time is earlier than the first time, adding a first label in the application information of the applied target service, and if the illness time is later than the first time, adding a second label in the request information of the applied target service. By the method, the auditing efficiency can be improved, and the problem of misjudgment after long-time work through manual auditing is avoided.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing a user service request, a server, and a storage medium.
Background
With the rapid development of the insurance guarantee industry, how to accurately identify whether the real illness time of the applicant is before or after application of insurance is the key to whether the applicant can have insurance qualification and obtain claim. The traditional solution can only manually check and judge, and specifically, in the claim stage, auditors manually find the matching relationship between the disease and the illness time from the electronic medical record of the applicant, and judge whether the applicant is qualified for claim. However, the manual review method is inefficient, and the misjudgment rate is high in some cases after long-time work along with the subjective activity of the reviewers.
Disclosure of Invention
The embodiment of the invention provides a user service request processing method and device, a server and a storage medium, wherein the user service request processing method can be used for acquiring health state information of a user, converting the health state information in a picture format into health state text information in a text format through character recognition, and further extracting and obtaining a disease name and corresponding illness time in the health state text information through natural language processing. Comparing the disease time of the user with the first time in the application information of the target service which has been applied by the user, if the disease time of the user is determined to be earlier than the first time, adding a first label in the application information of the target service which has been applied by the user, otherwise, if the disease time of the user is determined to be later than the first time, adding a second label in the application information of the target service which has been applied by the user. Further, the staff member who applies for the qualification management system or performs manual review on the tag (the first tag or the second tag) in the application information of the target service that the user has applied for can be used as a reference to determine whether the user qualifies for applying for the target service. By the method, the auditing efficiency can be improved, and the problem of misjudgment after long-time work through manual auditing is avoided.
In a first aspect, an embodiment of the present invention provides a method for processing a user service request, where the method includes:
acquiring application information of a target service which has been applied by a user and health state information of the user, wherein the application information of the target service which has been applied comprises first time;
extracting a disease name and corresponding disease time from the health state information of the user;
and comparing the illness time with the first time, if the illness time is earlier than the first time, adding a first label in the application information of the applied target service, and if the illness time is later than the first time, adding a second label in the request information of the applied target service.
Further, the health status information of the user includes a physical examination report of the user and/or an electronic medical record of the user.
Further, the acquiring the health status information of the user comprises:
acquiring the health state information submitted by the user; and/or
And acquiring the health state information of the user in a corresponding information management system according to the user information of the user.
Further, the acquiring the health status information of the user in the corresponding information management system according to the user information of the user includes:
if the age of the user is determined to be larger than the set age, acquiring health state information of the user in a corresponding information management system according to the user information of the user; or
And if the detection time of the health state information submitted by the user is determined to be after the first time, acquiring the health state information of the user in a corresponding information management system according to the user information of the user.
Further, the extracting of the disease name and the corresponding disease duration from the health status information of the user includes:
performing character recognition on the health state information based on a character recognition technology to obtain health state text information;
identifying a disease name and a corresponding illness time in the health status text information based on an entity identification model;
and matching the disease name with a set disease database, acquiring the matched disease name and determining the illness time corresponding to the matched disease name.
Further, the identifying a disease name in the health status textual information based on an entity identification model comprises:
labeling the health state text information according to a BIEO labeling mode;
and extracting the disease name in the health state text information labeled by the BIEO based on a BilSTM + CRF model.
Further, the identifying the disease time corresponding to the disease name in the health status text information based on the entity identification model includes:
and determining the disease time corresponding to the disease name in the health status text information based on a rule engine.
Further, after the determining the illness time corresponding to the illness name in the health status text information based on the rule engine, the method further includes:
and if the illness time is relative time, converting the relative time into absolute time, and taking the absolute time obtained by conversion as the illness time.
Further, the method further comprises:
if the first label is determined to be carried in the application information of the applied target service, judging that the user does not have claim settlement qualification;
and if the second label is determined to be carried in the application information of the applied target service, judging that the user has claim settlement qualification.
Further, before extracting the disease name and the corresponding disease duration from the health status information of the user, the method further includes:
and constructing an entity recognition model initial model, training the entity recognition model initial model by using a training text, and obtaining the entity recognition model.
Further, the constructing an entity recognition initial model, training the entity recognition initial model by using a training text, and obtaining the entity recognition model includes:
marking the training text by adopting a BIEO marking mode;
performing off-line training on the training text labeled by the BIEO on the basis of a Bert pre-training model and a BilSTM + CRF model, and obtaining a trained entity recognition initial model; and
and testing the trained entity recognition initial model, and taking the trained entity recognition initial model with the accuracy rate higher than the set accuracy rate as the entity recognition model according to the test result.
In a second aspect, an embodiment of the present invention further provides a device for processing a user service request, including:
a processor and a memory, the memory being configured to store at least one instruction, which is loaded and executed by the processor to implement the user service request processing method provided by the first aspect.
In a third aspect, an embodiment of the present invention further provides a server, including:
the second aspect provides a user service request processing apparatus.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the user service request processing method provided in the first aspect.
According to the technical scheme, after the health state information of the user is obtained, the health state information in the picture format is converted into the health state text information in the text format through character recognition, and the disease name and the corresponding disease duration in the health state text information are further extracted through natural language processing. Comparing the disease time of the user with the first time in the application information of the target service which has been applied by the user, if the disease time of the user is determined to be earlier than the first time, adding a first label in the application information of the target service which has been applied by the user, otherwise, if the disease time of the user is determined to be later than the first time, adding a second label in the application information of the target service which has been applied by the user. Further, the staff member who applies for the qualification management system or performs manual review on the tag (the first tag or the second tag) in the application information of the target service that the user has applied for can be used as a reference to determine whether the user qualifies for applying for the target service.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a user service request processing method according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of a BIEO labeling method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of an offline training model according to an embodiment of the present invention;
FIG. 4 is a BiLSTM + CRF architecture diagram provided by an embodiment of the present invention;
fig. 5 is a schematic diagram of a user service request processing system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a user service request processing method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step 101: acquiring application information of a user who has applied for a target service and health state information of the user.
The application information of the target service applied by the user can be obtained from the database, and the first time of the target service is further obtained from the application information of the target service applied. The target service may be an insurance or mutual aid claim service, and the first time may be a time to invest or join in mutual aid. For example, the target service is a health insurance, the user completes the insurance application operation of the health insurance at the time A, and the user proposes a claim based on the health insurance at the time B, wherein the time B is later than the time A. According to the operation step of step 101, the insurance application information of the user about the health insurance can be obtained in the database, and the insurance application time can be determined according to the insurance application information.
The method for acquiring the health state information of the user comprises the following steps:
the first acquisition mode: and acquiring the personal health state information submitted by the user. Specifically, when the user requests the requested target service, a copy of the health status information of the user is provided according to the corresponding requirement, that is, the health status information of the user provided in the service requesting stage can be acquired.
The second acquisition mode is as follows: and acquiring the health state information of the user in the corresponding information management system. Specifically, the user information of the corresponding user may be determined according to the application information of the applied target service, and the health status information of the user may be acquired in the corresponding information management system according to the user information.
In an implementation manner, in order to reduce the working strength of the target service platform, the first obtaining manner may be set as a default obtaining manner, and if an abnormal condition occurs in the health state information obtaining operation stage of the user based on the first obtaining manner, the health state information of the user may be obtained through the second obtaining manner. Wherein the abnormal condition includes:
in the first case:
and determining that the age of the user is greater than the set age in the stage that the user requests the requested target service.
In this case, the target service platform may determine that the user is an elderly person, and may not be skilled in the network platform to acquire the health status information of the user, and the target service platform may be acquired instead. Specifically, when the target service platform requests the requested target service, and the platform determines that the age of the user is greater than the set age, the target service platform may send a prompt message to the user, and the user may click an option in the prompt message to select whether the platform is required to obtain the health status information. If the user authorization platform is obtained instead, the target service platform can obtain the health state information of the user in the corresponding time period in the corresponding information management system based on the identity information of the user and the corresponding file of the applied target service.
In the second case:
the detection time of the health status information submitted by the user is after the first time.
In this case, the target service platform may determine that the temporal coverage of the health status information provided by the user is low. For example, the target service is a health insurance, the user completes the insurance application operation of the health insurance at the time A, the user proposes a claim based on the health insurance at the time B, and the user provides the health status information of the user after proposing the claim. However, the detection time of the target service platform detecting the health status information provided by the user is all later than the A time. In order to ensure the time coverage of the health state information of the user, the target service platform can acquire the health state information of the user in a corresponding time period in a corresponding information management system based on the identity information of the user and a corresponding file of the applied target service.
In one implementation, the health status information may include an electronic medical record and/or a physical examination report. The electronic medical record can be an electronic medical record of a user in one or more hospitals, and the physical examination report can be a physical examination report of the user in a hospital or a physical examination center. If the target service platform needs to acquire the electronic medical record of the user, the electronic medical record of the user can be acquired in the electronic medical record management system based on the identity information of the user and the corresponding file which applies for the target service.
In an implementation manner, the health status information of the user may be obtained by simultaneously adopting the first obtaining manner and the second obtaining manner.
The electronic medical records can comprise electronic medical records which are uploaded to an electronic medical record management system by all hospitals where the user visits at one time, and the electronic medical records can specifically comprise electronic medical records for outpatient service and electronic medical records for hospitalization.
Step 102: and extracting the disease name and the corresponding disease time from the health state information of the user.
The electronic medical record acquired in step 101 may be in a picture format or a PDF format, and after the electronic medical record is acquired, the electronic medical record in the picture format or the PDF format may be identified as a text form based on a character recognition technology (e.g., Optical Character Recognition (OCR)), and the texts identified by the OCR are recombined into a section of medical record text. If the acquired electronic medical records of the user comprise the electronic medical records for hospitalization, the medical record texts corresponding to the electronic medical records for hospitalization can be classified, and specifically, the medical records for hospitalization and the medical records for discharge can be respectively processed.
Case (considering user privacy and convenience of example and writing, here simplifying electronic medical records and their format):
name: king certain;
the admission time is as follows: 2020-3-15
The current medical history: the patient was admitted to the hospital in a heart attack burst 2 weeks before.
History of the past: none.
And (4) obtaining a result after extraction: { history of present disease: [ {2020-3-1: Heart disease } ]
According to the character information identified in the electronic medical record, the admission time of Wangzhizi of the patient is 2020-3-15, the extracted disease name is heart disease, and the illness time is 2 weeks before the admission time. Based on a rule engine in the entity recognition model, the relative time can be converted into absolute time, namely, the affected time of the patient Wangzao is 2020-3-1, and the entity recognition model outputs a recognition result: patient wangzhi { current medical history: [ {2020-3-1: heart disease } ] }.
Step 103: comparing the illness time of the disease extracted in the step 102 with the first time of the target service acquired in the step 101, if the illness time is earlier than the first time, adding a first label to the user target service application information, and if the illness time is later than the first time, adding a second label to the user target service request information.
If the first time of the target service of the user (the Wangzao) is 2020-3-20, the time of the Wangzao suffering from the disease (the heart disease) can be determined to be earlier than the first time (such as the insurance time of health insurance). Further, a first tag may be added to the information of the target service application of wang, and the information of the target service application of wang to which the first tag is added is stored in a database of the target service platform, and a subsequent user application qualification management system or a worker who performs manual review may review the information of the target service application to which the tag is added in the database, and the tag (the first tag or the second tag) in the information of the user target service application may be used as a reference to determine whether the user qualifies for applying for the target service. Specifically, the tag in the information of the wangzao target service application is a first tag, and the result of the audit on the wangzao target service application is as follows: prior disease (heart disease) and no claim qualification.
In this embodiment, the steps 102-103 are executed by the entity identification model provided in the present application, and the entity identification model may be further constructed before the step 102 is executed, and the construction process of the entity identification model is as follows:
1. sequence labeling is carried out on the identified medical record texts, and labeling can be carried out in a BIEO labeling mode.
BIEO in the BIEO notation is the first letter of the four words Begin, Intermediate, End, Other. The BIEO labeling means is to label that each word belongs to the beginning, middle or end of a named entity, or belongs to another.
Fig. 2 is a schematic labeling diagram of a BIEO labeling manner provided in an embodiment of the present invention, and as shown in fig. 2, in the BIEO format labeling performed on medical record text data, specifically, B-leave: the starting character of a DISEASE, I-DISEASE: middle character of a certain DISEASE, E-away: ending character of a certain disease, O: non-disease character, S.disease is a single word.
As shown in fig. 2, after the DISEASE name "gastric mucosal lesion" in the electronic medical record is divided into five characters, i.e., "stomach", "mucosa", "membrane", "DISEASE" and "lesion", the named entity label information of "stomach" is "B-DISEASE", "mucosa", "membrane" and "DISEASE" is "I-DISEASE", and the named entity label information of "lesion" is "E-DISEASE" according to the contextual characteristics of the word segmentation.
2. Entity recognition model offline training based on BilSTM + CRF
Fig. 3 is a schematic flow chart of an offline training model according to an embodiment of the present invention, and as shown in fig. 3, the offline training of the entity recognition model based on BiLSTM + CRF includes the following steps:
and 2.1, carrying out exploratory analysis on the medical record text data.
The exploratory analysis mainly analyzes the distribution of the text length, and the text length with proper size is selected to cut the text when the entity recognition is carried out, so that the accuracy of the model is improved. In general, the text length in the medical record is about 1000, so it is best to keep the text length at 1000 to do the stage. Since the longest sequence length supported by Bert is 512. So 512 sequence lengths are used as text truncation lengths in this embodiment.
2.2, loading a Bert pre-training model.
The disease entity recognition part of the scheme is also loaded with a Bert Chinese pre-training model. And loading a Bert pre-training model, and mapping based on the Bert pre-training model to obtain a word vector of each character in the training text. And the recognition task of the medical disease named entity can be further completed by following Bilstm and CRF after Bert.
2.3 entity recognition model training
Fig. 4 is a BiLSTM + CRF architecture diagram provided in an embodiment of the present invention, and as shown in fig. 4, a model is trained on a GPU, an optimal number of training rounds is determined to be 20 rounds according to a data set and a present service, and a Bert converts a training text into a vector format after being input each time. The data of the model training is N M, N is BATCH _ SIZE SIZE, and M is vector latitude SIZE. The word vector after being mapped by the Bert is input into a bidirectional LSTM neural network for learning, and the learned vector is further transmitted into a Conditional Random Fields (CRF) structure for learning. Conditional probability needs to be calculated for the CRF processing sequence labeling problem, and the final class probability is calculated by adopting a maximum likelihood method through a dimension bit algorithm.
2.4 model parameter adjustment and optimization verification
And testing the trained entity recognition initial model, and taking the trained entity recognition initial model with the accuracy rate higher than the set accuracy rate as the entity recognition model according to the test result.
Fig. 5 is a schematic diagram of a user service request processing system according to an embodiment of the present invention, and as shown in fig. 5, the user service request processing system may specifically include a business application layer, a model service layer, and a data storage layer.
The data storage layer stores data, and files can be stored in a MySQL, txt or picture mode.
The model service layer can provide OCR picture to text service, medical history text classification service, text entity recognition service and time-disease retrieval matching service.
The business application layer can extract corresponding disease-illness time information from the time-illness information provided by the model service layer, and mark corresponding labels on the target service application information of the user based on the comparison result of the illness time of the disease and the first time of the target service of the user, so that corresponding application qualification verification operation can be carried out in subsequent verification operation by referring to the labels in the target service application information of the user.
An embodiment of the present invention further provides a user service request processing apparatus, which includes a processor and a memory, where the memory is used to store at least one instruction, and the instruction is loaded and executed by the processor to implement the user service request processing method in the embodiment shown in fig. 1.
The embodiment of the invention also provides a server, and the server can comprise the user service request processing device.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the user service request processing method in the embodiment shown in fig. 1.
It should be noted that the terminal according to the embodiment of the present invention may include, but is not limited to, a Personal Computer (PC), a Personal Digital Assistant (PDA), a wireless handheld device, a Tablet Computer (Tablet Computer), a mobile phone, an MP3 player, an MP4 player, and the like.
It should be understood that the application may be an application program (native app) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, which is not limited in this embodiment of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing a user service request, the method comprising:
acquiring application information of a target service which has been applied by a user and health state information of the user, wherein the application information of the target service which has been applied comprises first time;
extracting a disease name and corresponding disease time from the health state information of the user;
and comparing the illness time with the first time, if the illness time is earlier than the first time, adding a first label in the application information of the applied target service, and if the illness time is later than the first time, adding a second label in the request information of the applied target service.
2. The method of claim 1, wherein the health status information of the user comprises a physical examination report of the user and/or an electronic medical record of the user.
3. The method of claim 1, wherein obtaining the health status information of the user comprises:
acquiring the health state information submitted by the user; and/or
And acquiring the health state information of the user in a corresponding information management system according to the user information of the user.
4. The method according to claim 3, wherein the obtaining the health status information of the user at the corresponding information management system according to the user information of the user comprises:
if the age of the user is determined to be larger than the set age, acquiring health state information of the user in a corresponding information management system according to the user information of the user; or
And if the detection time of the health state information submitted by the user is determined to be after the first time of the applied target service, acquiring the health state information of the user in a corresponding information management system according to the user information of the user.
5. The method of claim 1, wherein extracting the disease name and the corresponding disease time from the health status information of the user comprises:
performing character recognition on the health state information based on a character recognition technology to obtain health state text information;
identifying a disease name and a corresponding illness time in the health status text information based on an entity identification model;
and matching the disease name with a set disease database, acquiring the matched disease name and determining the illness time corresponding to the matched disease name.
6. The method of claim 5, wherein the identifying the illness time corresponding to the illness name in the health status text information based on the entity recognition model comprises:
and determining the disease time corresponding to the disease name in the health status text information based on a rule engine.
7. The method of claim 6, wherein the determining the illness time corresponding to the illness name in the health status text information based on the rules engine further comprises:
and if the illness time is relative time, converting the relative time into absolute time, and taking the absolute time obtained by conversion as the illness time.
8. A user service request processing apparatus, the apparatus comprising:
a processor and a memory for storing at least one instruction which is loaded and executed by the processor to implement the user service request processing method of any of claims 1-7.
9. A server, characterized in that the server comprises the user service request processing means of claim 8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for user service request handling according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402770.0A CN112632995A (en) | 2020-12-02 | 2020-12-02 | User service request processing method and device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402770.0A CN112632995A (en) | 2020-12-02 | 2020-12-02 | User service request processing method and device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112632995A true CN112632995A (en) | 2021-04-09 |
Family
ID=75308095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011402770.0A Pending CN112632995A (en) | 2020-12-02 | 2020-12-02 | User service request processing method and device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632995A (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631235A (en) * | 2016-03-10 | 2016-06-01 | 深圳市前海安测信息技术有限公司 | Medical big data based medical insurance actuarial system and medical big data based medical insurance actuarial method |
| CN106295151A (en) * | 2016-08-03 | 2017-01-04 | 合肥奇也信息科技有限公司 | A kind of medical care insurance is settled a claim system online |
| CN107798613A (en) * | 2016-12-28 | 2018-03-13 | 平安科技（深圳）有限公司 | Core pays for the generation method and device of foundation |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN109785159A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of life insurance core duty data processing method, server and computer-readable medium |
| CN110070449A (en) * | 2019-03-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Project kind matching process, device, computer equipment and storage medium |
| CN110119991A (en) * | 2019-04-12 | 2019-08-13 | 深圳壹账通智能科技有限公司 | Checking method, device and storage medium are compensated in medical treatment based on machine learning |
| CN110428339A (en) * | 2019-08-02 | 2019-11-08 | 泰康保险集团股份有限公司 | Claims Resolution identification method, device, electronic equipment and computer-readable medium |
| CN110674392A (en) * | 2019-08-15 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Project recommendation method and device based on historical health record |
| CN110852105A (en) * | 2019-11-06 | 2020-02-28 | 天津开心生活科技有限公司 | Time data normalization method, device, medium and electronic equipment |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN111009329A (en) * | 2019-12-03 | 2020-04-14 | 中国医学科学院北京协和医院 | Rare disease study group management method, storage medium, and computer program product |
| CN111063406A (en) * | 2019-11-21 | 2020-04-24 | 泰康保险集团股份有限公司 | Claims reference information generation method and device |
| CN111274806A (en) * | 2020-01-20 | 2020-06-12 | 医惠科技有限公司 | Method and device for recognizing word segmentation and part of speech and method and device for analyzing electronic medical record |
| CN111784525A (en) * | 2020-07-10 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method, device and system for processing insurance claim settlement request based on multi-party security calculation |
| CN111861768A (en) * | 2020-07-31 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Business processing method and device based on artificial intelligence, computer equipment and medium |
| CN111933239A (en) * | 2020-09-17 | 2020-11-13 | 泰康保险集团股份有限公司 | Data processing method, device, system and storage medium |
-
2020
- 2020-12-02 CN CN202011402770.0A patent/CN112632995A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631235A (en) * | 2016-03-10 | 2016-06-01 | 深圳市前海安测信息技术有限公司 | Medical big data based medical insurance actuarial system and medical big data based medical insurance actuarial method |
| CN106295151A (en) * | 2016-08-03 | 2017-01-04 | 合肥奇也信息科技有限公司 | A kind of medical care insurance is settled a claim system online |
| CN107798613A (en) * | 2016-12-28 | 2018-03-13 | 平安科技（深圳）有限公司 | Core pays for the generation method and device of foundation |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN109785159A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of life insurance core duty data processing method, server and computer-readable medium |
| CN110070449A (en) * | 2019-03-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Project kind matching process, device, computer equipment and storage medium |
| CN110119991A (en) * | 2019-04-12 | 2019-08-13 | 深圳壹账通智能科技有限公司 | Checking method, device and storage medium are compensated in medical treatment based on machine learning |
| CN110428339A (en) * | 2019-08-02 | 2019-11-08 | 泰康保险集团股份有限公司 | Claims Resolution identification method, device, electronic equipment and computer-readable medium |
| CN110674392A (en) * | 2019-08-15 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Project recommendation method and device based on historical health record |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN110852105A (en) * | 2019-11-06 | 2020-02-28 | 天津开心生活科技有限公司 | Time data normalization method, device, medium and electronic equipment |
| CN111063406A (en) * | 2019-11-21 | 2020-04-24 | 泰康保险集团股份有限公司 | Claims reference information generation method and device |
| CN111009329A (en) * | 2019-12-03 | 2020-04-14 | 中国医学科学院北京协和医院 | Rare disease study group management method, storage medium, and computer program product |
| CN111274806A (en) * | 2020-01-20 | 2020-06-12 | 医惠科技有限公司 | Method and device for recognizing word segmentation and part of speech and method and device for analyzing electronic medical record |
| CN111784525A (en) * | 2020-07-10 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method, device and system for processing insurance claim settlement request based on multi-party security calculation |
| CN111861768A (en) * | 2020-07-31 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Business processing method and device based on artificial intelligence, computer equipment and medium |
| CN111933239A (en) * | 2020-09-17 | 2020-11-13 | 泰康保险集团股份有限公司 | Data processing method, device, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522557B (en) | Training method and device of text relation extraction model and readable storage medium | |
| CN112328742B (en) | Training method and device based on artificial intelligence, computer equipment and storage medium | |
| CN111198948B (en) | Text classification correction method, apparatus, device and computer readable storage medium | |
| CN111028934B (en) | Diagnostic quality inspection method, diagnostic quality inspection device, electronic equipment and storage medium | |
| CN107680661B (en) | System and method for estimating medical resource demand | |
| CN111611775B (en) | Entity identification model generation method, entity identification device and equipment | |
| CN111859919A (en) | Text error correction model training method and device, electronic equipment and storage medium | |
| CN112287069B (en) | Information retrieval method and device based on voice semantics and computer equipment | |
| CN111429204A (en) | Hotel recommendation method, system, electronic equipment and storage medium | |
| CN113420122A (en) | Method, device and equipment for analyzing text and storage medium | |
| CN112307337B (en) | Associated recommendation method and device based on tag knowledge graph and computer equipment | |
| US20210303725A1 (en) | Partially customized machine learning models for data de-identification | |
| CN112465231B (en) | Method, apparatus and readable storage medium for predicting regional population health status | |
| CN112906361A (en) | Text data labeling method and device, electronic equipment and storage medium | |
| CN112860842A (en) | Medical record labeling method and device and storage medium | |
| CN115935914A (en) | Admission record missing text supplementing method | |
| CN112949320B (en) | Sequence labeling method, device, equipment and medium based on conditional random field | |
| CN116721778A (en) | Medical term standardization method, system, equipment and medium | |
| CN112632995A (en) | User service request processing method and device, server and storage medium | |
| CN113901817A (en) | Document classification method and device, computer equipment and storage medium | |
| CN114238597A (en) | Information extraction method, device, equipment and storage medium | |
| CN113780318A (en) | Method, apparatus, server and medium for generating prompt information | |
| CN112668327A (en) | Information extraction method and device, computer equipment and storage medium | |
| CN113535888A (en) | Emotion analysis device and method, computing equipment and readable storage medium | |
| US11983489B1 (en) | Extractive summary generation by abstractive trained model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210409 |
|
| RJ01 | Rejection of invention patent application after publication |