CN113643143A - Task splitting method, device and equipment based on artificial intelligence and storage medium - Google Patents
Task splitting method, device and equipment based on artificial intelligence and storage medium Download PDFInfo
- Publication number
- CN113643143A CN113643143A CN202111016223.3A CN202111016223A CN113643143A CN 113643143 A CN113643143 A CN 113643143A CN 202111016223 A CN202111016223 A CN 202111016223A CN 113643143 A CN113643143 A CN 113643143A
- Authority
- CN
- China
- Prior art keywords
- task
- case
- list
- characteristic data
- splitting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 26
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 50
- 239000013598 vector Substances 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 37
- 238000012550 audit Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000011835 investigation Methods 0.000 description 3
- 101150083764 KCNK9 gene Proteins 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
Abstract
The application relates to the technical field of artificial intelligence, and discloses a task splitting method, a device, equipment and a storage medium based on artificial intelligence, wherein the method comprises the following steps: case characteristic data includes: case information characteristic data and entrusted information characteristic data; generating a task according to the entrusted information characteristic data by adopting a task extraction rule to obtain a first task list; inputting case information characteristic data into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector; determining the tasks according to the task classification prediction vectors to obtain a second task list; and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result. The method and the device realize accurate splitting of the task of the case, provide support for determining the entrustment price according to the task subsequently, and provide support for determining the task underwriting end according to the task. This application can be applicable to technical field such as digital medical treatment, wisdom government affairs, science and technology finance.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a storage medium for task splitting based on artificial intelligence.
Background
In the process of checking the claim of the insurance company, the case needs to be entrusted to crowdsourcing companies, and the crowdsourcing companies assist the insurance company in checking the claim by surveying, gathering evidence, deducing and concluding the case. When a traditional case is entrusted, the whole case is entrusted to the same crowdsourcing company, the defect that each case adopts fixed entrusting price exists, and the technical problem that the entrusting price cannot be adjusted due to the fact that the number and types of specific tasks needing to be executed by different cases are different, and the number of tasks of the cases is small or the types of the tasks are different is caused.
Disclosure of Invention
The main purpose of the application is to provide a task splitting method, a device, equipment and a storage medium based on artificial intelligence, and the method, the device, the equipment and the storage medium aim to solve the technical problems that when a case in the prior art is entrusted, the whole case is entrusted to the same crowdsourcing company, the defect that each case adopts fixed entrusting price exists, and the entrusting price cannot be adjusted due to the fact that the number and types of specific tasks to be executed by different cases are different, and the number of the tasks of the case is small or the types of the specific tasks cannot be adjusted at the same time.
In order to achieve the above object, the present application provides a task splitting method based on artificial intelligence, including:
acquiring case characteristic data, wherein the case characteristic data comprises: case information characteristic data and entrusted information characteristic data;
acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list;
inputting the case information characteristic data into a preset task classification prediction model for task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training;
determining the tasks according to the task classification prediction vectors to obtain a second task list;
and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
Further, the step of obtaining case characteristic data includes:
obtaining the data of the entrusted case, wherein the data of the entrusted case comprises the following components: case basic information and entrusted information text;
generating label characteristics according to the case basic information to obtain case information characteristic data;
and respectively generating a task description statement and a task characteristic according to the entrusting information text to obtain entrusting information characteristic data.
Further, the step of generating the label characteristics according to the case basic information to obtain the case information characteristic data includes:
acquiring a label generation script;
executing the label generation script, and performing label prediction on the structured data in the case basic information to obtain a label prediction result;
and generating a vector according to the label prediction result to obtain the case information characteristic data.
Further, the step of generating a task description statement and generating a task feature according to the delegation information text to obtain the delegation information feature data includes:
obtaining a sentence segmentation regular expression;
adopting the sentence segmentation regular expression to split the task description sentences of the entrusted information text to obtain a task description sentence set;
acquiring a task feature extraction model, wherein the task feature extraction model is a model obtained according to the training of a Bert model;
and extracting the characteristics of each task description statement in the task description statement set by adopting the task characteristic extraction model to obtain the entrusted information characteristic data.
Further, the step of performing task merging processing according to the first task list and the second task list to obtain a target task splitting result includes:
combining the tasks in the first task list and the second task list to obtain a task list to be deduplicated;
task duplicate removal processing is carried out on the task list to be subjected to duplicate removal, and a task list to be checked is obtained;
sending the task list to be audited to a task splitting and auditing end;
acquiring a task auditing result which is sent by the task splitting and auditing end and corresponds to the task list to be audited;
when the auditing result of the task auditing result is passed, taking the task list to be audited as the target task splitting result;
and when the audit result of the task audit result is passed, correcting the task list to be audited according to the task correction data of the task audit result to obtain the target task splitting result.
Further, after the step of obtaining the task audit result corresponding to the task list to be audited, which is sent by the task splitting audit end, the method further includes:
when the auditing result of the task auditing result is passed, case generation is carried out according to the entrusted case data corresponding to the case characteristic data and the target task splitting result to obtain a difficult case;
updating the problem case to a problem case library;
and updating and training the preset task classification prediction model according to the difficult case library.
Further, after the step of performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, the method further includes:
acquiring task allocation configuration data;
according to the task allocation configuration data, performing task matching on the target task splitting result to obtain a hit task identifier set and a miss task identifier set;
distributing each task in the hit task identification set to a task underwriting end according to the task distribution configuration data;
and acquiring a task underwriting end tag library, and distributing each task in the missed task identification set to the task underwriting end according to the case tag of the case characteristic data and the task underwriting end tag library.
This application has still provided a task split device based on artificial intelligence, the device includes:
the data acquisition module is used for acquiring case characteristic data, and the case characteristic data comprises: case information characteristic data and entrusted information characteristic data;
the first task list determining module is used for acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list;
the task classification prediction vector determination module is used for inputting the case information characteristic data into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training;
the second task list determining module is used for determining tasks according to the task classification prediction vectors to obtain a second task list;
and the target task splitting result determining module is used for performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
The present application further proposes a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any of the above methods when executing the computer program.
The present application also proposes a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any of the above.
According to the method, the task extraction rule is adopted, task generation is carried out according to entrusted information characteristic data to obtain a first task list, then case information characteristic data are input into a preset task classification prediction model to carry out task classification prediction to obtain task classification prediction vectors, wherein the preset task classification prediction model is a model obtained based on XGboost model training; and finally, performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, realizing accurate splitting of the task of the case, providing support for subsequently determining a delegation price according to the task, being beneficial to reducing case delegation cost, providing support for determining a task support end according to the task, and being beneficial to improving case execution efficiency and quality.
Drawings
FIG. 1 is a schematic flowchart of a task splitting method based on artificial intelligence according to an embodiment of the present application;
FIG. 2 is a schematic block diagram illustrating a structure of an artificial intelligence based task splitting apparatus according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a task splitting method based on artificial intelligence, where the method includes:
s1: acquiring case characteristic data, wherein the case characteristic data comprises: case information characteristic data and entrusted information characteristic data;
s2: acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list;
s3: inputting the case information characteristic data into a preset task classification prediction model for task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training;
s4: determining the tasks according to the task classification prediction vectors to obtain a second task list;
s5: and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
In the embodiment, by adopting the task extraction rule, task generation is performed according to the entrusted information characteristic data to obtain a first task list, and then the case information characteristic data is input into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; and finally, performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, realizing accurate splitting of the task of the case, providing support for subsequently determining a delegation price according to the task, being beneficial to reducing case delegation cost, providing support for determining a task support end according to the task, and being beneficial to improving case execution efficiency and quality.
For S1, case characteristic data input by the user may be obtained, case characteristic data may be obtained from a database, and case characteristic data may be obtained from a third-party application system.
The case corresponding to the case information characteristic data may be an insurance claim case, or may be another case, for example, a case in the technical fields of digital medical treatment, intelligent government affairs, scientific and technical finance, and the like, which is not limited herein.
The case information feature data is feature data extracted according to case basic information. Case basic information includes but is not limited to: name, gender, age, product identification, and text data corresponding to the picture. The product identification may be data that uniquely identifies a product from a product name, product ID, and the like. It can be understood that the product identifier may also be modified into a service identifier, and the service may also be split by using the method steps of the present application. The service identification may be a service name, a service ID, etc. that uniquely identifies a service.
The text data corresponding to the picture is extracted from the picture by using an OCR (Optical Character Recognition) technique. It can be understood that, when the present application is applied to the underwriting business of the insurance industry, the pictures in the text data corresponding to the pictures include, but are not limited to: the first page of the medical record, the small sum of hospitalization, the small sum of discharge, the medical record, the inspection report and the bill of charge.
The entrusted information feature data is feature data extracted from the entrusted information text. And the entrusting information text is used for describing the text of the tasks and matters needing to be processed.
For S2, the task extraction rule may be obtained from the database, or may be written in a program for implementing the present application.
And generating a task from the entrusted information characteristic data by adopting the task extraction rule, putting the generated task in a list, and taking the obtained list as the first task list.
It can be understood that, when the application is applied to the underwriting business of the insurance industry, the task extraction rules include: rules for judging case types, rules for judging severity degrees and task list sets. The rule for judging the case type is used for judging diseases or accidents. And the rule for judging the severity is used for judging the severity of the case. The task list set comprises: case type, product identification, severity, and task list.
For example, case type is disease, product identification is health risk, severity is depth case, task list includes the following tasks: the medical institution investigation, the case retrieval in the emergency hospital, the visit to the emergency personnel, the peer investigation and the investigation medical insurance are specified, and the examples are not limited specifically.
For another example, the case type is accident, the product identification is accident risk, the severity is deep case, and the task list includes the following tasks: visiting the accident person or family, reviewing medical institution medical records, visiting and visiting functional departments or doctors of the medical institution, investigating designated hospitals (hospitalization and outpatient service), visiting and visiting residential areas, investigating and co-operating (including insurance and mutual assistance), and investigating social security, which are not limited in detail herein.
Judging the case type according to the entrusted information characteristic data by adopting a rule of judging the case type of the task extraction rule to obtain a target case type; judging the severity of the case according to the entrusted information characteristic data by adopting a severity judgment rule of the task extraction rule to obtain a target severity; and taking the product identifier, the target case type and the target severity of the case characteristic data as associated data, searching the associated data in a task list set of the task extraction rule, and taking a task list corresponding to the associated data (namely the associated data consisting of the case type, the product identifier and the severity) searched in the task list set as the first task list.
For S3, each vector element in the task classification prediction vector corresponds to a task label, and the number of vector elements of the task classification prediction vector is the same as the number of task labels.
Wherein a plurality of first training samples are obtained, the first training samples comprising: and training a first initial model by adopting a plurality of first training samples and taking the trained first initial model as the preset task classification prediction model, wherein the first initial model adopts an XGboost model.
The method steps for training the first initial model by using a plurality of first training samples are not described herein again.
The XGboost model, namely, the Extreme Gradient Boosting, is a tool of a large-scale parallel booted tree, is one of the fastest and best open source booted tree toolkits at present, is more than 10 times faster than a common toolkit, is a completely enhanced version in a GB method, is also an algorithm based on residual optimization, and is expected to establish K regression trees so that a predicted value of a tree group is close to a true value (accuracy) as much as possible and has generalization capability as much as possible.
For S4, the task label corresponding to each vector element with 1 in the task classification prediction vector is used as a target task label, the tasks corresponding to the target task labels are placed in a list, and the obtained list is used as the second task list.
For example, the total number of Task tags is 15, the Task classification prediction vector is [011111000000000], and the Task tags corresponding to Task2, Task3, Task4, Task5, and Task6 are selected, so that the second Task list includes: task2, Task3, Task4, Task5, and Task6, which are not specifically limited by way of example.
For step S5, putting all tasks of the first task list and the second task list in the same list, to obtain a task list to be deduplicated; and then, task deduplication processing is carried out on the task list to be deduplicated, and the task list to be deduplicated after the task deduplication processing is used as the target task splitting result.
The target task splitting result comprises the following steps: one or more task identifications. The task identification may be a task name, a task ID, etc. that uniquely identifies a task.
That is, the case corresponding to each case feature data may be split into one or more tasks.
In an embodiment, the acquiring case characteristic data includes:
s11: obtaining the data of the entrusted case, wherein the data of the entrusted case comprises the following components: case basic information and entrusted information text;
s12: generating label characteristics according to the case basic information to obtain case information characteristic data;
s13: and respectively generating a task description statement and a task characteristic according to the entrusting information text to obtain entrusting information characteristic data.
In this embodiment, the case information feature data is obtained by performing tag feature generation according to the case basic information, and the delegation information feature data is obtained by performing task description statement generation and task feature generation respectively according to the delegation information text, so that support is provided for subsequent task splitting based on feature data.
For S11, the data of the requested case input by the user may be obtained, the data of the requested case may be obtained from a database, or the data of the requested case may be obtained from a third-party application system.
And S12, performing label feature generation on the structured data in the case information text, and obtaining the case information feature data according to the generated label features.
The structured data in the case information text includes but is not limited to: name, gender, age, product identification.
The case information characteristic data is a characteristic vector, and each vector element in the case information characteristic data corresponds to a label.
For example, the case information feature data is [ 23 ], where a vector element value of 2 corresponds to a label of gender, a vector element value of 2 means gender is female, a vector element value of 3 corresponds to an age, and a vector element value of 3 means an age greater than or equal to 4 years, which is not limited by the example.
For S13, the request information text is split into task description statements, then task features are generated from each split task description statement, and all generated task features are used as the request information feature data.
A task description statement is a statement that describes a task. For example, the task description statement is a query for a specific medical institution, and is not specifically limited by the examples herein. For another example, the task description statement is a interviewer accident person, and is not limited in detail here.
In an embodiment, the generating of the label feature according to the case basic information to obtain the case information feature data includes:
s121: acquiring a label generation script;
s122: executing the label generation script, and performing label prediction on the structured data in the case basic information to obtain a label prediction result;
s123: and generating a vector according to the label prediction result to obtain the case information characteristic data.
According to the embodiment, the label prediction of the structured data in the case basic information is carried out by executing the label generation script, and then the case information characteristic data is generated according to the label prediction result, so that support is provided for the follow-up task splitting based on the characteristic data.
For S121, the tag generation script may be obtained from a database, or may be obtained from a third-party application system.
The tag generation script is a script for converting structured data into a tag value. The label generation script can be developed by using Lua (small script language, compiled by standard C, and compiled and run on almost all operating systems and platforms) script language.
For S122, executing the tag generation script, and performing tag prediction on the structured data in the case basic information, that is, converting the structured data in the case information text into a tag value.
For example, the tag value for sex is 1 for male, 2 for sex for female, 1 for age less than 1, 2 for age greater than or equal to 1 and less than 4, and 3 for age greater than or equal to 4, which are not specifically limited by the example.
For example, if the gender of the structured data in the case information text is female and the age is 3 years, the tag prediction result is: sex 2 and age 2, and are not specifically limited by way of example herein.
And S123, generating a vector according to the label prediction result by adopting a preset label arrangement sequence, and taking the generated vector as the case information characteristic data.
For example, the label prediction result is: gender 2 and age 3, the preset tag arrangement order is: gender and age, the case information characteristic data is [ 23 ], which is not specifically limited in this example.
In an embodiment, the generating a task description statement and generating a task feature according to the request information text to obtain the request information feature data respectively includes:
s131: obtaining a sentence segmentation regular expression;
s132: adopting the sentence segmentation regular expression to split the task description sentences of the entrusted information text to obtain a task description sentence set;
s133: acquiring a task feature extraction model, wherein the task feature extraction model is a model obtained according to the training of a Bert model;
s134: and extracting the characteristics of each task description statement in the task description statement set by adopting the task characteristic extraction model to obtain the entrusted information characteristic data.
In the embodiment, the sentence segmentation regular expression is adopted to split the task description sentences, and the task feature extraction model is adopted to generate the task features, so that support is provided for the subsequent task splitting based on the feature data.
For S131, the sentence division regular expression may be obtained from a database, or may be obtained from a third-party application system.
The sentence division regular expression is a regular expression obtained according to the divider. Segmenters include, but are not limited to: numbers, commas, pauses, periods.
For S132, the sentence segmentation regular expression is adopted, the entrustment information text is segmented into short sentences, each short sentence obtained by segmentation is used as a task description sentence, and each task description sentence is used as the task description sentence set.
For step S133, the task feature extraction model may be obtained from a database, or may be obtained from a third-party application system.
The task feature extraction model is a model for extracting features of a text.
Obtaining a plurality of second training samples, the second training samples comprising: and describing a sample text and a task feature calibration value by a task, training a second initial model by adopting a plurality of second training samples, and taking the second initial model after training as a task feature extraction model, wherein the second initial model adopts a Bert (bidirectional Encoder retrieval from transformations) model.
The method steps for training the second initial model by using a plurality of second training samples are not described herein again.
For step S134, each task description statement in the task description statement set is input into the task feature extraction model, the task feature extraction model is spliced with respect to feature extraction data output by each task description statement, and the spliced data is used as the entrusted information feature data.
In an embodiment, the performing task merging processing according to the first task list and the second task list to obtain a target task splitting result includes:
s51: combining the tasks in the first task list and the second task list to obtain a task list to be deduplicated;
s52: task duplicate removal processing is carried out on the task list to be subjected to duplicate removal, and a task list to be checked is obtained;
s53: sending the task list to be audited to a task splitting and auditing end;
s54: acquiring a task auditing result which is sent by the task splitting and auditing end and corresponds to the task list to be audited;
s55: when the auditing result of the task auditing result is passed, taking the task list to be audited as the target task splitting result;
s56: and when the audit result of the task audit result is passed, correcting the task list to be audited according to the task correction data of the task audit result to obtain the target task splitting result.
According to the embodiment, the task merging processing and the duplicate removal processing are firstly carried out on the first task list and the second task list, then the first task list and the second task list are sent to the task splitting and auditing end for auditing, and the target task splitting result is determined according to the auditing result of the task splitting and auditing end, so that the accurate splitting of the task of the case is realized, the support is provided for subsequently determining the consignation price according to the task, and the case consignation cost is reduced.
And S51, combining the tasks in the first task list and the second task list, and taking the data obtained after the combination as a task list to be deduplicated.
And S52, performing task duplicate removal processing on the tasks of the task list to be subjected to task duplicate removal processing, and taking the task list to be subjected to task duplicate removal processing as the task list to be audited.
That is, each task identifier in the task list to be audited has uniqueness.
And S53, the task list to be audited is sent to the task splitting auditing end through the communication connection with the task splitting auditing end.
And auditing the task list to be audited by the auditor through the task splitting and auditing end, and generating a task auditing result according to the task list to be audited.
The task auditing result comprises the following steps: and the task correction data is not null when the audit result is passed and the task correction data is not null when the audit result is not passed.
And S54, acquiring a task auditing result corresponding to the task list to be audited, which is sent by the task splitting auditing end, through the communication connection with the task splitting auditing end.
For S55, when the result of the task review passes, it means that the result of the automatic splitting meets the review requirement, and therefore the task list to be reviewed is directly used as the target task splitting result.
For S56, when the audit result of the task audit result is failed, it means that the result of automatic splitting does not meet the audit requirement, so that the task list to be audited is replaced and updated according to the task correction data of the task audit result, and the task list to be audited after replacement and update is used as the target task split result.
In an embodiment, after obtaining the task auditing result corresponding to the task list to be audited, which is sent by the task splitting and auditing end, the method further includes:
s541: when the auditing result of the task auditing result is passed, case generation is carried out according to the entrusted case data corresponding to the case characteristic data and the target task splitting result to obtain a difficult case;
s542: updating the problem case to a problem case library;
s543: and updating and training the preset task classification prediction model according to the difficult case library.
According to the method and the device, the difficult problem case is generated when the audit result of the task audit result is failed, and a data basis is provided for continuous optimization of a preset task classification prediction model.
For S541, when the audit result of the task audit result is failed, it means that the result of automatic splitting does not meet the audit requirement, and the accuracy of the task of automatic splitting is not enough, so that a preset case generation rule is adopted to perform case generation according to the committed case data corresponding to the case feature data and the target task split result, and the generated case is taken as a difficult case.
For S542, the problem case is added to the problem case base, thereby completing the automatic updating of the problem case base.
For S543, generating a third training sample according to each puzzle case in the puzzle case library; and training the preset task classification prediction model by adopting each third training sample, and using the trained preset task classification prediction model for task classification prediction of an actual production environment.
In an embodiment, after performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, the method further includes:
s61: acquiring task allocation configuration data;
s62: according to the task allocation configuration data, performing task matching on the target task splitting result to obtain a hit task identifier set and a miss task identifier set;
s63: distributing each task in the hit task identification set to a task underwriting end according to the task distribution configuration data;
s64: and acquiring a task underwriting end tag library, and distributing each task in the missed task identification set to the task underwriting end according to the case tag of the case characteristic data and the task underwriting end tag library.
According to the embodiment, the task allocation is performed by preferentially adopting the task allocation configuration data, and the task allocation is performed on the task which cannot be performed according to the task allocation configuration data by adopting the task underwriting end tag library, so that the individualized task allocation is met, and the efficiency and the quality of case execution are improved.
For S61, the task allocation configuration data may be obtained from a database, or may be obtained from a third-party application system.
The task allocation configuration data includes: the task insurance system comprises task identifiers and task underwriting end identifiers, wherein each task identifier corresponds to one task underwriting end identifier. The task underwriting end identifier can be data which uniquely identifies one task underwriting end, such as a task underwriting end name, a task underwriting end ID and the like. And the task underwriting end is a software module for crowdsourcing companies to receive tasks and feed back task execution results.
For S62, matching each task identifier in the task allocation configuration data in the target task splitting result, taking each matched task identifier as a hit task identifier, and taking all hit task identifiers as a hit task identifier set.
And deleting each hit task identifier from the target task splitting result, and taking the target task splitting result subjected to deletion processing as a missed task identifier set.
And S63, according to the task underwriting end identification of the task allocation configuration data, allocating the task corresponding to each task identification in the hit task identification set to the task underwriting end.
For example, the task identifier a1 in the hit task identifier set, and the task underwriting end corresponding to the task identifier a1 in the task allocation configuration data is identified as CB1, then the task corresponding to the task identifier a1 in the hit task identifier set is allocated to the task underwriting end corresponding to CB1, which is not limited in this example.
For S64, the task underwriting end tag library may be obtained from a database, or may be obtained from a third-party application system.
The task underwriting end label library comprises: the task underwriting system comprises task underwriting end identifications and task underwriting end label sets, wherein each task underwriting end identification corresponds to one task underwriting end label set. The task underwriting end label set comprises one or more task underwriting end labels. Task underwriting end tags include, but are not limited to: provinces, cities, administrative areas, case types.
Wherein the case characteristic data further comprises: case label. Case tags include, but are not limited to: case province, case city, case administrative region, case type.
And matching a task underwriting end label set from a task underwriting end label library according to the case labels of the case characteristic data, and taking the task underwriting end identification corresponding to the matched task underwriting end label set as a candidate task underwriting end identification.
And acquiring the residual executable data corresponding to each candidate task underwriting end identifier. The remaining executable data includes: the task identification and the residual executable number, wherein the residual executable number is the number of the tasks corresponding to the task identification which can be accepted.
And distributing each task in the missed task identifier set according to the residual executable data corresponding to each candidate task underwriting end identifier. For example, the task identifier in the missed task identifier set is B1, B1 is searched for the task identifiers in the remaining executable data corresponding to each candidate task underwriting end identifier, a maximum value is found from each remaining executable quantity corresponding to each matched task identifier to serve as a target remaining executable quantity, the candidate task underwriting end identifier corresponding to the target remaining executable quantity serves as a target task underwriting end identifier, and the task identifier B1 in the missed task identifier set is allocated to the task underwriting end corresponding to the target task underwriting end identifier.
Referring to fig. 2, the present application further provides an artificial intelligence based task splitting apparatus, the apparatus including:
a data obtaining module 100, configured to obtain case characteristic data, where the case characteristic data includes: case information characteristic data and entrusted information characteristic data;
a first task list determining module 200, configured to obtain a task extraction rule, and generate a task according to the delegation information feature data by using the task extraction rule to obtain a first task list;
the task classification prediction vector determination module 300 is configured to input the case information feature data into a preset task classification prediction model for task classification prediction, so as to obtain a task classification prediction vector, where the preset task classification prediction model is a model obtained based on XGboost model training;
a second task list determining module 400, configured to determine a task according to the task classification prediction vector to obtain a second task list;
and a target task splitting result determining module 500, configured to perform task merging processing according to the first task list and the second task list to obtain a target task splitting result.
In the embodiment, by adopting the task extraction rule, task generation is performed according to the entrusted information characteristic data to obtain a first task list, and then the case information characteristic data is input into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; and finally, performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, realizing accurate splitting of the task of the case, providing support for subsequently determining a delegation price according to the task, being beneficial to reducing case delegation cost, providing support for determining a task support end according to the task, and being beneficial to improving case execution efficiency and quality.
In one embodiment, the data obtaining module 100 includes: a consignment case data acquisition sub-module, a case information characteristic data determination sub-module and a consignment information characteristic data determination sub-module;
the entrusted case data acquisition submodule is used for acquiring entrusted case data, and the entrusted case data comprises: case basic information and entrusted information text;
the case information characteristic data determining submodule is used for generating label characteristics according to the case basic information to obtain the case information characteristic data;
and the entrusting information characteristic data determining submodule is used for respectively generating task description sentences and task characteristics according to the entrusting information text to obtain the entrusting information characteristic data.
In one embodiment, the case information characteristic data determining sub-module includes: the device comprises a script obtaining unit, a label predicting unit and a vector generating unit;
the script obtaining unit is used for obtaining the label generation script;
the label prediction unit is used for executing the label generation script and performing label prediction on the structured data in the case basic information to obtain a label prediction result;
and the vector generation unit is used for generating vectors according to the label prediction result to obtain the case information characteristic data.
In one embodiment, the delegation information feature data determining submodule includes: a task description statement splitting unit and a feature extraction unit;
the task description sentence splitting unit is used for acquiring a sentence segmentation regular expression, and splitting the task description sentences of the entrusted information text by adopting the sentence segmentation regular expression to obtain a task description sentence set;
the feature extraction unit is configured to obtain a task feature extraction model, where the task feature extraction model is a model obtained by training according to a Bert model, and feature extraction is performed on each task description statement in the task description statement set by using the task feature extraction model to obtain the delegation information feature data.
In one embodiment, the target task split result determining module 500 includes: a task list determination submodule to be audited, a task audit submodule and a target task splitting result determination submodule;
the task list to be audited determining submodule is used for performing table combining processing on the tasks in the first task list and the second task list to obtain a task list to be deduplicated, and performing task deduplication processing on the task list to be deduplicated to obtain a task list to be audited;
the task auditing submodule is used for sending the task list to be audited to a task splitting and auditing end and acquiring a task auditing result which is sent by the task splitting and auditing end and corresponds to the task list to be audited;
and the target task splitting result determining submodule is used for taking the task list to be audited as the target task splitting result when the auditing result of the task auditing result is passed, and correcting the task list to be audited according to the task correction data of the task auditing result when the auditing result of the task auditing result is failed to obtain the target task splitting result.
In one embodiment, the above apparatus further comprises: the system comprises a problem case base updating module and a preset task classification prediction model updating module;
the difficult case base updating module is used for generating cases according to the entrusted case data corresponding to the case characteristic data and the target task splitting result when the checking result of the task checking result is passed, obtaining difficult cases and updating the difficult cases to a difficult case base;
and the preset task classification prediction model updating module is used for updating and training the preset task classification prediction model according to the difficult case library.
In one embodiment, the above apparatus further comprises: the system comprises a first task allocation module and a second task allocation module;
the first task allocation module is used for acquiring task allocation configuration data, performing task matching on the target task splitting result according to the task allocation configuration data to obtain a hit task identifier set and a miss task identifier set, and allocating each task in the hit task identifier set to a task underwriting end according to the task allocation configuration data;
and the second task allocation module is used for acquiring a task underwriting end tag library, and allocating each task in the missed task identifier set to the task underwriting end according to the case tag of the case characteristic data and the task underwriting end tag library.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer equipment is used for storing data such as a task splitting method based on artificial intelligence. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an artificial intelligence based task splitting method. The task splitting method based on artificial intelligence comprises the following steps: acquiring case characteristic data, wherein the case characteristic data comprises: case information characteristic data and entrusted information characteristic data; acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list; inputting the case information characteristic data into a preset task classification prediction model for task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; determining the tasks according to the task classification prediction vectors to obtain a second task list; and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
In the embodiment, by adopting the task extraction rule, task generation is performed according to the entrusted information characteristic data to obtain a first task list, and then the case information characteristic data is input into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; and finally, performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, realizing accurate splitting of the task of the case, providing support for subsequently determining a delegation price according to the task, being beneficial to reducing case delegation cost, providing support for determining a task support end according to the task, and being beneficial to improving case execution efficiency and quality.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a task splitting method based on artificial intelligence, and the method includes the following steps: acquiring case characteristic data, wherein the case characteristic data comprises: case information characteristic data and entrusted information characteristic data; acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list; inputting the case information characteristic data into a preset task classification prediction model for task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; determining the tasks according to the task classification prediction vectors to obtain a second task list; and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
In the task splitting method based on artificial intelligence, the task extraction rule is adopted, the task is generated according to the entrusted information characteristic data to obtain a first task list, and then the case information characteristic data is input into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training; and finally, performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, realizing accurate splitting of the task of the case, providing support for subsequently determining a delegation price according to the task, being beneficial to reducing case delegation cost, providing support for determining a task support end according to the task, and being beneficial to improving case execution efficiency and quality.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A task splitting method based on artificial intelligence is characterized by comprising the following steps:
acquiring case characteristic data, wherein the case characteristic data comprises: case information characteristic data and entrusted information characteristic data;
acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list;
inputting the case information characteristic data into a preset task classification prediction model for task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training;
determining the tasks according to the task classification prediction vectors to obtain a second task list;
and performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
2. The artificial intelligence based task splitting method according to claim 1, wherein the obtaining case feature data comprises:
obtaining the data of the entrusted case, wherein the data of the entrusted case comprises the following components: case basic information and entrusted information text;
generating label characteristics according to the case basic information to obtain case information characteristic data;
and respectively generating a task description statement and a task characteristic according to the entrusting information text to obtain entrusting information characteristic data.
3. The artificial intelligence based task splitting method according to claim 2, wherein the tag feature generation is performed according to the case basic information, and obtaining the case information feature data comprises:
acquiring a label generation script;
executing the label generation script, and performing label prediction on the structured data in the case basic information to obtain a label prediction result;
and generating a vector according to the label prediction result to obtain the case information characteristic data.
4. The artificial intelligence based task splitting method according to claim 2, wherein the task description statement generation and the task feature generation are performed according to the delegation information text, and obtaining the delegation information feature data comprises:
obtaining a sentence segmentation regular expression;
adopting the sentence segmentation regular expression to split the task description sentences of the entrusted information text to obtain a task description sentence set;
acquiring a task feature extraction model, wherein the task feature extraction model is a model obtained according to the training of a Bert model;
and extracting the characteristics of each task description statement in the task description statement set by adopting the task characteristic extraction model to obtain the entrusted information characteristic data.
5. The artificial intelligence based task splitting method according to claim 1, wherein the task merging processing according to the first task list and the second task list to obtain a target task splitting result includes:
combining the tasks in the first task list and the second task list to obtain a task list to be deduplicated;
task duplicate removal processing is carried out on the task list to be subjected to duplicate removal, and a task list to be checked is obtained;
sending the task list to be audited to a task splitting and auditing end;
acquiring a task auditing result which is sent by the task splitting and auditing end and corresponds to the task list to be audited;
when the auditing result of the task auditing result is passed, taking the task list to be audited as the target task splitting result;
and when the audit result of the task audit result is passed, correcting the task list to be audited according to the task correction data of the task audit result to obtain the target task splitting result.
6. The method for splitting the task based on the artificial intelligence according to claim 5, wherein after the task auditing result corresponding to the task list to be audited and sent by the task splitting auditing end is obtained, the method further comprises:
when the auditing result of the task auditing result is passed, case generation is carried out according to the entrusted case data corresponding to the case characteristic data and the target task splitting result to obtain a difficult case;
updating the problem case to a problem case library;
and updating and training the preset task classification prediction model according to the difficult case library.
7. The artificial intelligence based task splitting method according to claim 1, wherein after performing task merging processing according to the first task list and the second task list to obtain a target task splitting result, the method further comprises:
acquiring task allocation configuration data;
according to the task allocation configuration data, performing task matching on the target task splitting result to obtain a hit task identifier set and a miss task identifier set;
distributing each task in the hit task identification set to a task underwriting end according to the task distribution configuration data;
and acquiring a task underwriting end tag library, and distributing each task in the missed task identification set to the task underwriting end according to the case tag of the case characteristic data and the task underwriting end tag library.
8. An artificial intelligence based task splitting device, the device comprising:
the data acquisition module is used for acquiring case characteristic data, and the case characteristic data comprises: case information characteristic data and entrusted information characteristic data;
the first task list determining module is used for acquiring a task extraction rule, and generating a task according to the entrusted information characteristic data by adopting the task extraction rule to obtain a first task list;
the task classification prediction vector determination module is used for inputting the case information characteristic data into a preset task classification prediction model to perform task classification prediction to obtain a task classification prediction vector, wherein the preset task classification prediction model is a model obtained based on XGboost model training;
the second task list determining module is used for determining tasks according to the task classification prediction vectors to obtain a second task list;
and the target task splitting result determining module is used for performing task merging processing according to the first task list and the second task list to obtain a target task splitting result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111016223.3A CN113643143A (en) | 2021-08-31 | 2021-08-31 | Task splitting method, device and equipment based on artificial intelligence and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111016223.3A CN113643143A (en) | 2021-08-31 | 2021-08-31 | Task splitting method, device and equipment based on artificial intelligence and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113643143A true CN113643143A (en) | 2021-11-12 |
Family
ID=78424684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111016223.3A Pending CN113643143A (en) | 2021-08-31 | 2021-08-31 | Task splitting method, device and equipment based on artificial intelligence and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643143A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119202A (en) * | 2021-11-29 | 2022-03-01 | 阿尔法时刻科技(深圳)有限公司 | Automatic configuration method and system of credit management platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
| CN112529390A (en) * | 2020-12-02 | 2021-03-19 | 平安医疗健康管理股份有限公司 | Task allocation method and device, computer equipment and storage medium |
| CN112734210A (en) * | 2020-12-31 | 2021-04-30 | 深圳银雁数据科技有限公司 | Intelligent case division method and system |
| CN112767180A (en) * | 2021-01-06 | 2021-05-07 | 大童保险销售服务有限公司 | Method and device for generating insurance case public estimation report and storage medium |
| CN112819538A (en) * | 2021-02-04 | 2021-05-18 | 长沙理工大学 | User task prediction method and device, computer equipment and storage medium |
| CN112925911A (en) * | 2021-02-25 | 2021-06-08 | 平安普惠企业管理有限公司 | Complaint classification method based on multi-modal data and related equipment thereof |
-
2021
- 2021-08-31 CN CN202111016223.3A patent/CN113643143A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
| CN112529390A (en) * | 2020-12-02 | 2021-03-19 | 平安医疗健康管理股份有限公司 | Task allocation method and device, computer equipment and storage medium |
| CN112734210A (en) * | 2020-12-31 | 2021-04-30 | 深圳银雁数据科技有限公司 | Intelligent case division method and system |
| CN112767180A (en) * | 2021-01-06 | 2021-05-07 | 大童保险销售服务有限公司 | Method and device for generating insurance case public estimation report and storage medium |
| CN112819538A (en) * | 2021-02-04 | 2021-05-18 | 长沙理工大学 | User task prediction method and device, computer equipment and storage medium |
| CN112925911A (en) * | 2021-02-25 | 2021-06-08 | 平安普惠企业管理有限公司 | Complaint classification method based on multi-modal data and related equipment thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119202A (en) * | 2021-11-29 | 2022-03-01 | 阿尔法时刻科技(深圳)有限公司 | Automatic configuration method and system of credit management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| CN109190110B (en) | Named entity recognition model training method and system and electronic equipment | |
| US20200042580A1 (en) | Systems and methods for enhancing and refining knowledge representations of large document corpora | |
| CN112711660B (en) | Method for constructing text classification sample and method for training text classification model | |
| CN112685475A (en) | Report query method and device, computer equipment and storage medium | |
| JP7128919B2 (en) | Skill term evaluation method and device, electronic device, computer readable medium | |
| CN113112282A (en) | Method, device, equipment and medium for processing consult problem based on client portrait | |
| WO2019191817A1 (en) | A system and method for generating documents | |
| CN112800248A (en) | Similar case retrieval method, similar case retrieval device, computer equipment and storage medium | |
| CN115759667A (en) | Talent information intelligent matching method, system, equipment and medium | |
| US20130132289A1 (en) | Oil and gas interest tracking system | |
| CN113643143A (en) | Task splitting method, device and equipment based on artificial intelligence and storage medium | |
| CN111191153A (en) | Information technology consultation service display device | |
| CN114003692A (en) | Contract text information processing method and device, computer equipment and storage medium | |
| CN113641796A (en) | Data searching method, system and storage medium | |
| Gößwein et al. | Data identification and process monitoring for reproducible earth observation research | |
| CN116127105B (en) | Data collection method and device for big data platform | |
| CN112559526A (en) | Data table export method and device, computer equipment and storage medium | |
| WO2021009375A1 (en) | A method for extracting information from semi-structured documents, a related system and a processing device | |
| CN114692785B (en) | Behavior classification method, device, equipment and storage medium | |
| US11334719B2 (en) | Systems and methods for predicting mapping between named entities and parameters using a model based on same predefined number of words that occur prior to the named entity via machine learning techniques | |
| CN112364169B (en) | Nlp-based wifi identification method, electronic device and medium | |
| US11599801B2 (en) | Method for solving problem, computing system and program product | |
| US20220229863A1 (en) | Assigning documents to entities of a database | |
| CN114238768A (en) | Information pushing method and device, 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220525 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right |