CN118037458A - Service request processing method, device, computer equipment and storage medium - Google Patents
Service request processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN118037458A CN118037458A CN202410022741.3A CN202410022741A CN118037458A CN 118037458 A CN118037458 A CN 118037458A CN 202410022741 A CN202410022741 A CN 202410022741A CN 118037458 A CN118037458 A CN 118037458A
- Authority
- CN
- China
- Prior art keywords
- standard
- account
- data
- marked
- service request
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000003672 processing method Methods 0.000 title abstract description 7
- 230000036541 health Effects 0.000 claims abstract description 91
- 238000012545 processing Methods 0.000 claims abstract description 60
- 238000003058 natural language processing Methods 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000011156 evaluation Methods 0.000 claims abstract description 28
- 238000004590 computer program Methods 0.000 claims abstract description 26
- 238000012502 risk assessment Methods 0.000 claims abstract description 15
- 238000011158 quantitative evaluation Methods 0.000 claims abstract description 13
- 238000012550 audit Methods 0.000 claims abstract description 12
- 230000006399 behavior Effects 0.000 claims description 80
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 6
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000012911 target assessment Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a service request processing method, a service request processing device, a computer device, a storage medium and a computer program product. The method comprises the following steps: responding to a service request of the marked account, and acquiring a description text of the marked account; inputting the description text of the marked account into a pre-trained natural language processing model, and outputting standard health data and standard behavior data of the marked account; evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determining the risk evaluation grade of the marked account; and under the condition that the risk assessment level of the marked account is low risk, determining that the service request of the marked account passes the audit, and performing service transaction based on the service request. By adopting the method, the efficiency and the accuracy for determining whether the marked account can handle the service can be improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for processing a service request.
Background
To control the underwriting risk, the underwriting enterprise typically determines whether the customer is a high risk customer based on historical application records of the customer, such as whether the customer is experiencing an offending activity.
Currently, when a high-risk client needs to transact a service such as re-application or renewal, the high-risk client is usually required to conduct risk review, and whether the high-risk client can transact the service is determined according to the result of the review. However, as more and more people purchase insurance products, the amount of data that needs to be processed to perform risk review on high risk customers is greater, and therefore, the efficiency and accuracy of determining whether the high risk customers can transact business is lower.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for processing a service request that can improve the efficiency and accuracy of determining whether a signed account can handle a service.
In a first aspect, the present application provides a method for processing a service request, including:
responding to a service request of a marked account, and acquiring a description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account;
Inputting the descriptive text of the marked account into a pre-trained natural language processing model, and outputting standard health data and standard behavior data of the marked account; the pre-trained natural language processing model is obtained by training a machine learning model based on a marked sample description text;
Evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determining a risk evaluation level of the marked account;
Under the condition that the risk assessment level of the marked account is low risk, determining that the service request of the marked account passes the audit, and performing service transaction based on the service request; wherein the service request is used for generating a policy or updating the policy.
In one embodiment, the pre-trained natural language processing model is deployed in a parallel processing framework; the step of inputting the descriptive text of the marked account into a pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account comprises the following steps:
Calling a preset data processing code, dividing the description text of the marked account into a plurality of data blocks, and distributing the data blocks to each computing node of a parallel processing framework, so that each computing node carries out parallel processing on the plurality of data blocks based on the pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account.
In one embodiment, the method further comprises:
uploading descriptive text of the plurality of tagged accounts to a distributed file system;
standard health data and standard behavioral data for a plurality of branded accounts are stored to a production database.
In one embodiment, the evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule to obtain the risk evaluation level of the marked account includes:
determining a target evaluation rule according to the standard health data and the standard behavior data;
and determining that the risk assessment level of the marked account is low risk under the condition that the standard health data and the standard behavior data meet the target assessment rule.
In one embodiment, the pre-trained natural language processing model is obtained by:
Acquiring a sample set, wherein the sample set comprises abnormal health information with labels and abnormal behavior information;
Inputting the sample set into an initial natural language processing model, and outputting a prediction result;
and iteratively adjusting network parameters in the initial natural language processing model based on the difference between the prediction result and the sample set to obtain a pre-trained natural language processing model.
In one embodiment, the inputting the sample set into the initial natural language processing model, outputting the prediction result includes:
Analyzing the sample set based on a conditional random field model to obtain initial health data and initial behavior data;
And carrying out standardized processing on the initial health data and the initial behavior data based on a similarity matching algorithm to obtain standard health data and standard behavior data.
In a second aspect, the present application further provides a service request processing device, including:
The text acquisition module is used for responding to the service request of the marked account and acquiring the description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account;
The text processing module is used for inputting the descriptive text of the marked account into a pre-trained natural language processing model and outputting standard health data and standard behavior data of the marked account; the pre-trained natural language processing model is obtained by training a machine learning model based on a marked sample description text;
the first determining module is used for evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule and determining the risk evaluation grade of the marked account;
The second determining module is used for determining that the service request of the marked account passes the audit and conducting service transaction based on the service request under the condition that the risk assessment level of the marked account is low risk; wherein the service request is used for generating a policy or updating the policy.
In a third aspect, the application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the methods described above when the processor executes the computer program.
In a fourth aspect, the application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the preceding claims.
In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any of the preceding claims.
According to the processing method, the processing device, the computer equipment, the storage medium and the computer program product for the service request, the description text of the marked account is analyzed based on the pre-trained natural language processing model, and the standardized analysis result is subjected to quantitative evaluation, so that real-time risk evaluation of different marked accounts is realized, and the efficiency and the accuracy of whether the marked accounts can handle the service are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
FIG. 1 is an application environment diagram of a method of processing a service request in one embodiment;
FIG. 2 is a flow diagram of a method of processing a service request in one embodiment;
FIG. 3 is a flow chart illustrating a method for processing a service request according to another embodiment;
FIG. 4 is a flow diagram of obtaining a pre-trained natural language processing model in one embodiment;
FIG. 5 is a flowchart illustrating a process for determining a risk assessment level of a tagging account according to a predetermined quantitative assessment rule in one embodiment;
FIG. 6 is a block diagram of an apparatus for processing a service request in one embodiment;
Fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The service request processing method provided by the embodiment of the application can be applied to an application environment shown in figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The user may send a service request to the server 104 through the terminal 102. Server 104 may store descriptive text for a plurality of accounts. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In an exemplary embodiment, as shown in fig. 2, a method for processing a service request is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps 202 to 208. Wherein:
Step 202, responding to a service request of a marked account, and acquiring a description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account.
The marked account may be an account in which the applicant has an abnormal health condition or an account in which abnormal operation behavior exists. The descriptive text of the account may include historical policy of the account, applicant base information, etc. The health description text may be text related to a health condition in the description text of the account. For example, the health description text may include medical records, lifestyle habits, and the like. The behavior descriptive text may be text related to the operational behavior in descriptive text of the account. For example, the behavioral description text may include payment records, breach records, and the like.
Illustratively, the server 104 may obtain a service request sent by the terminal 102, and determine a corresponding account according to the obtained service request; under the condition that the account corresponding to the service request is marked with a risk identifier, determining that the account is a marked account, and acquiring a description text of the account; and performing business transaction based on the business request when the account corresponding to the business request is a non-marked account.
Step 204, the description text of the marked account is input into a pre-trained natural language processing model, and standard health data and standard behavior data of the marked account are output; the pre-trained natural language processing model is obtained by training a machine learning model based on the marked sample description text.
The standard health data may be standard text related to health conditions, among others. The standard behavior data may be standard text related to the operation behavior. For example, the standard health data/standard behavioral data of the branded account may include one or more of a plurality of candidate standard texts.
For example, the server 104 may input descriptive text for a plurality of tagged accounts into a pre-trained natural language processing model in response to service requests for the plurality of tagged accounts, outputting standard health data and standard behavioral data for each tagged account.
And step 206, evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determining the risk evaluation grade of the marked account.
Illustratively, the server 104 may obtain the risk type corresponding to the service request; and under the condition that the standard health data and the standard behavior data meet the quantitative evaluation rules corresponding to the dangerous types, determining the risk evaluation level of the marked account as low risk.
Step 208, determining that the service request of the marked account passes the audit and performing service transaction based on the service request under the condition that the risk assessment level of the marked account is low risk; wherein the service request is used to generate a policy or update a policy.
According to the method for processing the service request, the description text of the marked account is analyzed based on the pre-trained natural language processing model, and quantitative evaluation is performed through the standardized analysis result, so that real-time risk evaluation of different marked accounts is realized, and the efficiency and accuracy of whether the marked accounts can handle the service are improved.
In an exemplary embodiment, as shown in fig. 3, a method for processing a service request is provided, including the following steps 302 to 308. Wherein:
Step 302, responding to a service request of a marked account, and acquiring a description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account.
Step 304, the description text of the marked account is input into a pre-trained natural language processing model, and standard health data and standard behavior data of the marked account are output; the pre-trained natural language processing model is obtained by training a machine learning model based on the marked sample description text.
Referring to fig. 4, fig. 4 is a flow chart illustrating a method for obtaining a pre-trained natural language processing model according to an embodiment, where the method for obtaining the pre-trained natural language processing model may include:
Step A1, a sample set is obtained, wherein the sample set comprises abnormal health information with labels and abnormal behavior information.
For example, the server 104 may randomly sample the descriptive text of the plurality of marked accounts, and label the abnormal health information and the abnormal behavior information in the descriptive text through the machine learning platform to obtain a sample set.
And step A2, inputting the sample set into an initial natural language processing model, and outputting a prediction result.
For example, the server 104 may perform preprocessing such as cleaning, word segmentation, fuzzy dictionary matching, etc. on the sample set, and input the preprocessed sample set to the initial natural language model to obtain the prediction result.
And step A3, iteratively adjusting network parameters in the initial natural language processing model based on the difference between the prediction result and the sample set to obtain a pre-trained natural language processing model.
In the embodiment, the natural language model is trained through a large number of marked description texts, so that the natural language model can learn the language rules and modes of the description texts better, and the accuracy of analyzing the description texts by the natural language model is improved through iterative tuning of the natural language model.
Alternatively, the initial natural language model may be a conditional random field (CRF, conditional random field) model, and the step A2 may include:
And step A21, analyzing the sample set based on the conditional random field model to obtain initial health data and initial behavior data.
Illustratively, the CRF model may parse the sample set, determine a labeling sequence, and determine corresponding initial health data and initial behavior data according to the labeling sequence.
And step A22, carrying out standardized processing on the initial health data and the initial behavior data based on a similarity matching algorithm to obtain standard health data and standard behavior data.
The standard health data may include standard texts such as standard disease names, standard behavior codes, and the like. The standard behavior data may include standard text of standard behavior types, standard behavior descriptions, and the like.
Therefore, abnormal health information and abnormal behavior information in the descriptive text of the risk account can be analyzed through the pre-trained natural language processing model, corresponding standard texts are obtained, quantitative risk assessment is carried out through the standard texts, and accuracy of determining the risk assessment level can be improved.
In an exemplary embodiment, the pre-trained natural language processing model may be deployed in a parallel processing framework, and the step 304 may include:
Step 3041, calling a preset data processing code, dividing the description text of the marked account into a plurality of data blocks, and distributing the data blocks to each computing node of the parallel processing framework, so that each computing node carries out parallel processing on the plurality of data blocks based on a pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account.
For example, the server 104 may divide the obtained descriptive text into data blocks with preset sizes, distribute the data blocks to the computing nodes of the parallel processing framework, and combine and sort the computing results of the parallel processing. The preset data processing code can be realized through a programming language Python. The parallel processing framework may be a distributed computing framework MapReduce.
In the embodiment, the pre-trained natural language processing model is deployed in the parallel processing framework, and the description text is divided into the data blocks which can be processed by the parallel processing framework, so that batch analysis of the description text can be realized, and the analysis efficiency of the description text is improved.
Optionally, the method for processing the service request may further include:
step 301, uploading descriptive text of a plurality of tagged accounts to a distributed file system.
For example, descriptive text for a plurality of tagged accounts may be batch migrated to distributed file system HDFS (Hadoop Distributed System) via data transfer tool Sqoop (SQL-to-Hadoop). In one possible implementation, server 104 may batch upload the generated/updated descriptive text to the distributed file system in response to the generation/update of the descriptive text of the account.
Step 305, storing standard health data and standard behavior data of the plurality of marked accounts into a production database.
For example, standard health data and standard behavior data stored in the Hive data table may be synchronized back to the production database by the offline synchronization tool DataX.
Therefore, by uploading a large amount of description texts to the distributed file system in advance, the description texts of the marked account can be obtained rapidly when the service request of the marked account is received, and finally the efficiency of determining whether the marked account can handle the service is improved; by synchronizing the standard health data and the standard behavior data back to the production database in batches, the risk evaluation grades of a plurality of marked accounts can be synchronously evaluated, and the efficiency of determining whether the marked accounts can handle the service is further improved.
And 306, evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determining the risk evaluation grade of the marked account.
In an exemplary embodiment, the step 306 may include:
step 3061, determining the target evaluation rule according to the standard health data and the standard behavior data.
Step 3062, determining that the risk assessment level of the tagging account is low risk if the standard health data and the standard behavior data satisfy the target assessment rule.
Referring to fig. 5, fig. 5 is a flowchart illustrating a process of determining a risk assessment level of a marked account according to a preset quantitative assessment rule in an embodiment. Among them, the dangerous seed types may include: accident risk, life risk, etc. In one possible implementation, the descriptive text of the tagged account is entered into a pre-trained natural language processing model, which may output data of risk type, cure level, cure time, etc. It should be noted that, fig. 5 is schematically illustrated by taking the example that the target evaluation rule is determined by the standard health data, the target evaluation rule may be determined by the standard behavior data, or may be determined by both the standard health data and the standard behavior data.
In the embodiment, by adopting the evaluation rule matched with the data to be evaluated for evaluation, the targeted processing of the data to be evaluated can be realized, and the efficiency and the accuracy of determining the risk evaluation grade of the marked account are improved.
Step 308, determining that the service request of the marked account passes the audit and conducting service transaction based on the service request under the condition that the risk assessment level of the marked account is low risk; wherein the service request is used to generate a policy or update a policy.
In one possible implementation, the business request may be used to generate an online policy, and the server 104 may generate the online policy for the risk account in response to the marked account passing the audit. In another possible implementation, the business request may be for a underwriting, and the server 104 may determine that the risk account underwriting passes and generate a policy in response to the marked account passing the audit. In yet another possible implementation, the business request may be for renewal or policy preservation and the server 104 may determine that the risk account is underwritten and update the policy in response to the marked account passing the audit.
In this embodiment, since it can be quickly and accurately determined whether the service request of the marked account passes the audit, the efficiency and accuracy of generating/updating the policy can be improved.
In summary, in the method for processing the service request, the description text of the marked account is analyzed based on the pre-trained natural language processing model, and the standardized analysis result is quantitatively evaluated, so that real-time risk evaluation of different marked accounts is realized, the efficiency and accuracy of whether the marked accounts can handle the service are improved, and the efficiency and accuracy of generating/updating the policy are improved. .
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a service request processing device for realizing the above related service request processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the processing device for one or more service requests provided below may refer to the limitation of the processing method for service requests hereinabove, and will not be described herein.
In an exemplary embodiment, as shown in fig. 6, there is provided a service request processing apparatus 400, including: a text acquisition module 401, a text processing module 402, a first determination module 403, and a second determination module 404, wherein:
a text obtaining module 401, configured to obtain a description text of the marked account in response to a service request of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account.
The text processing module 402 is configured to input a descriptive text of the marked account into the pre-trained natural language processing model, and output standard health data and standard behavior data of the marked account; the pre-trained natural language processing model is obtained by training a machine learning model based on the marked sample description text.
The first determining module 403 is configured to evaluate the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determine a risk evaluation level of the marked account.
A second determining module 404, configured to determine that the service request of the marked account passes the audit and perform service transaction based on the service request if the risk assessment level of the marked account is low risk; wherein the service request is used to generate a policy or update a policy.
In one embodiment, the pre-trained natural language processing model is deployed in a parallel processing framework; the text processing module 402 includes:
And the parallel processing sub-module is used for calling a preset data processing code, dividing the description text of the marked account into a plurality of data blocks, and distributing the data blocks to each computing node of the parallel processing framework, so that each computing node carries out parallel processing on the plurality of data blocks based on a pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account.
In one embodiment, the processing apparatus 400 for service request includes:
and the text uploading module is used for uploading the descriptive texts of the plurality of marked accounts to the distributed file system.
And the standard data storage module is used for storing the standard health data and the standard behavior data of the plurality of marked accounts into the production database.
In one embodiment, the first determining module 403 includes:
And the evaluation rule determination submodule is used for determining a target evaluation rule according to the standard health data and the standard behavior data.
And the evaluation grade determining sub-module is used for determining that the risk evaluation grade of the marked account is low risk under the condition that the standard health data and the standard behavior data meet the target evaluation rule.
In one embodiment, the method for obtaining the pre-trained natural language processing model includes:
Acquiring a sample set, wherein the sample set comprises abnormal health information with labels and abnormal behavior information;
Inputting the sample set into an initial natural language processing model, and outputting a prediction result;
and iteratively adjusting network parameters in the initial natural language processing model based on the difference between the prediction result and the sample set to obtain a pre-trained natural language processing model.
In one embodiment, the inputting the sample set into the initial natural language processing model and outputting the prediction result includes:
Analyzing the sample set based on the conditional random field model to obtain initial health data and initial behavior data;
And carrying out standardized processing on the initial health data and the initial behavior data based on a similarity matching algorithm to obtain standard health data and standard behavior data.
The modules in the service request processing device may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one exemplary embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store descriptive text for the account. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of processing a service request.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor performing the steps of the method embodiments described above when the computer program is executed.
In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method embodiments described above.
In an exemplary embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, user health information, user behavior information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method for processing a service request, the method comprising:
responding to a service request of a marked account, and acquiring a description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account;
Inputting the descriptive text of the marked account into a pre-trained natural language processing model, and outputting standard health data and standard behavior data of the marked account; the pre-trained natural language processing model is obtained by training a machine learning model based on a marked sample description text;
Evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule, and determining a risk evaluation level of the marked account;
Under the condition that the risk assessment level of the marked account is low risk, determining that the service request of the marked account passes the audit, and performing service transaction based on the service request; wherein the service request is used for generating a policy or updating the policy.
2. The method of claim 1, wherein the pre-trained natural language processing model is deployed in a parallel processing framework; the step of inputting the descriptive text of the marked account into a pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account comprises the following steps:
Calling a preset data processing code, dividing the description text of the marked account into a plurality of data blocks, and distributing the data blocks to each computing node of a parallel processing framework, so that each computing node carries out parallel processing on the plurality of data blocks based on the pre-trained natural language processing model to obtain standard health data and standard behavior data of the marked account.
3. The method according to claim 1, wherein the method further comprises:
uploading descriptive text of the plurality of tagged accounts to a distributed file system;
standard health data and standard behavioral data for a plurality of branded accounts are stored to a production database.
4. The method of claim 1, wherein the evaluating the standard health data and the standard behavioral data according to a preset quantitative evaluation rule to obtain a risk evaluation level of the marked account comprises:
determining a target evaluation rule according to the standard health data and the standard behavior data;
and determining that the risk assessment level of the marked account is low risk under the condition that the standard health data and the standard behavior data meet the target assessment rule.
5. The method of claim 1, wherein the pre-trained natural language processing model is obtained by:
Acquiring a sample set, wherein the sample set comprises abnormal health information with labels and abnormal behavior information;
Inputting the sample set into an initial natural language processing model, and outputting a prediction result;
and iteratively adjusting network parameters in the initial natural language processing model based on the difference between the prediction result and the sample set to obtain a pre-trained natural language processing model.
6. The method of claim 5, wherein inputting the set of samples into an initial natural language processing model, outputting a prediction result, comprises:
Analyzing the sample set based on a conditional random field model to obtain initial health data and initial behavior data;
And carrying out standardized processing on the initial health data and the initial behavior data based on a similarity matching algorithm to obtain standard health data and standard behavior data.
7. A service request processing apparatus, the apparatus comprising:
The text acquisition module is used for responding to the service request of the marked account and acquiring the description text of the marked account; the description text comprises a health description text and a behavior description text, wherein the health description text is used for recording the health condition of an account owner, and the behavior description text is used for recording the operation behavior of the account;
The text processing module is used for inputting the descriptive text of the marked account into a pre-trained natural language processing model and outputting standard health data and standard behavior data of the marked account; the pre-trained natural language processing model is obtained by training a machine learning model based on a marked sample description text;
the first determining module is used for evaluating the standard health data and the standard behavior data according to a preset quantitative evaluation rule and determining the risk evaluation grade of the marked account;
The second determining module is used for determining that the service request of the marked account passes the audit and conducting service transaction based on the service request under the condition that the risk assessment level of the marked account is low risk; wherein the service request is used for generating a policy or updating the policy.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022741.3A CN118037458A (en) | 2024-01-08 | 2024-01-08 | Service request processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022741.3A CN118037458A (en) | 2024-01-08 | 2024-01-08 | Service request processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118037458A true CN118037458A (en) | 2024-05-14 |
Family
ID=90988506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410022741.3A Pending CN118037458A (en) | 2024-01-08 | 2024-01-08 | Service request processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118037458A (en) |
-
2024
- 2024-01-08 CN CN202410022741.3A patent/CN118037458A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10127477B2 (en) | Distributed event prediction and machine learning object recognition system | |
| CN112148973B (en) | Data processing method and device for information push | |
| CN116757297A (en) | Method and system for selecting features of machine learning samples | |
| CN112035611B (en) | Target user recommendation method, device, computer equipment and storage medium | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN116882520A (en) | Prediction method and system for predetermined prediction problem | |
| CN110738511A (en) | Intelligent customer service method and device | |
| CN112990281A (en) | Abnormal bid identification model training method, abnormal bid identification method and abnormal bid identification device | |
| CN117649239A (en) | Transaction information identification method and device based on generated language model | |
| US20240193485A1 (en) | System and method of operationalizing automated feature engineering | |
| CN112418978A (en) | Product recommendation method, device, equipment and medium | |
| CN115630221A (en) | Terminal application interface display data processing method and device and computer equipment | |
| CN117522519A (en) | Product recommendation method, device, apparatus, storage medium and program product | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN114693409A (en) | Product matching method, device, computer equipment, storage medium and program product | |
| CN117312657A (en) | Abnormal function positioning method and device for financial application, computer equipment and medium | |
| CN117473081A (en) | Text management method, apparatus, computer device and storage medium | |
| CN112258368A (en) | Method and device for processing government affair items | |
| CN115114073A (en) | Alarm information processing method and device, storage medium and electronic equipment | |
| CN115907954A (en) | Account identification method and device, computer equipment and storage medium | |
| CN118037458A (en) | Service request processing method, device, computer equipment and storage medium | |
| CN111127057A (en) | Multi-dimensional user portrait restoration method | |
| CN111400413B (en) | Method and system for determining category of knowledge points in knowledge base | |
| Brown et al. | Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model | |
| CN117455664A (en) | Method and device for processing resource data, computer equipment and storage medium |
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 |