CN110728582A - Information processing method, device, storage medium and processor - Google Patents
Information processing method, device, storage medium and processor Download PDFInfo
- Publication number
- CN110728582A CN110728582A CN201910839114.8A CN201910839114A CN110728582A CN 110728582 A CN110728582 A CN 110728582A CN 201910839114 A CN201910839114 A CN 201910839114A CN 110728582 A CN110728582 A CN 110728582A
- Authority
- CN
- China
- Prior art keywords
- case
- information
- vehicle
- identification model
- model
- 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.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000013507 mapping Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 48
- 238000012360 testing method Methods 0.000 claims description 20
- 230000002452 interceptive effect Effects 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 15
- 238000013473 artificial intelligence Methods 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses an information processing method, an information processing device, a storage medium and a processor. Wherein, the method comprises the following steps: acquiring case information of a vehicle insurance case; analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level; and in the case that the importance level is greater than the target threshold value, pushing target information associated with the case information. The invention solves the technical problem of low efficiency of processing the case information of the automobile insurance case in the prior art.
Description
Technical Field
The present invention relates to the field of information processing, and in particular, to a method, an apparatus, a storage medium, and a processor for information processing.
Background
At present, when a car insurance case is processed, the information of the car insurance case is reported manually by depending on employees of an insurance company, the condition of damaged parts is determined by disassembling a vehicle, the accessories, working hours and auxiliary material prices required by vehicle repair are accumulated, and then whether the damaged parts are large cases is determined, and the cases are required to be presented by manually filling the large cases into reports, logging in an settlement system, mails, OA and the like.
The method has high requirements on the quality of related personnel, the site loss prejudgment of the road traffic accident is carried out, the requirements on professional levels such as knowledge storage, experience accumulation and the like of practitioners are high, and low-order operators cannot perform the method; the presentation time cannot be guaranteed, on one hand, hidden and damaged cases exist, enterprises need to maintain and disassemble lost vehicles, the treatment time is long, and on the other hand, operation personnel or major cases cannot be presented in time due to unknown, negligence, attention and the like; the operation data is influenced, major cases cannot be screened in time, and further pending data cannot be reflected in time, so that the authenticity of the operation data is influenced, and the front-end insurance policy making is influenced; cost control is influenced, major cases cannot be screened in time, intervention control cannot be conducted in a preposed mode, fixed certificates cannot be conducted in a preposed mode, fraud and leakage are easy to generate, and high claims are paid; the labor is intensive, and the operations of case identification, report form filling, report sending and the like all need to be deployed by manpower, so that the problem of low efficiency of processing the case information of the vehicle insurance cases is caused.
Aiming at the problem of low efficiency of processing the case information of the car insurance case in the prior art, no effective solution is provided at present.
Disclosure of Invention
The embodiment of the invention provides an information processing method, an information processing device, a storage medium and a processor, and at least solves the technical problem that in the prior art, the efficiency of processing the case information of a car insurance case is low.
According to an aspect of an embodiment of the present invention, there is provided a method of information processing. The method can comprise the following steps: acquiring case information of a vehicle insurance case; analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level; and in the case that the importance level is greater than the target threshold value, pushing target information associated with the case information.
Optionally, the obtaining of the case information of the car insurance case includes: an image of a vehicle associated with a vehicle insurance case is acquired.
Optionally, the obtaining of the case information of the car insurance case includes: text information associated with the car insurance case is obtained.
Optionally, analyzing the case information based on the information recognition model, and obtaining the importance level of the case information includes: identifying the image of the vehicle based on an image identification model to obtain loss data of the vehicle, wherein the information identification model comprises the image identification model, the image identification model is used for establishing a mapping relation between the image of different vehicles and the loss data, and the case information comprises the image of the vehicle; identifying text information associated with the vehicle insurance case based on a text identification model to obtain the type of the vehicle insurance case, wherein the information identification model comprises the text identification model, the text identification model is used for establishing a mapping relation between the text information associated with different vehicle insurance cases and the type of the vehicle insurance case, and the case information comprises the text information associated with the vehicle insurance case; analyzing the loss data of the vehicle and the types of the vehicle insurance cases based on case identification models to obtain the important levels of case information, wherein the information identification models comprise case identification models which are used for establishing the mapping relation between the loss data of different vehicles, the types of the vehicle insurance cases and the important levels of the case information.
Optionally, identifying the image of the vehicle based on the image identification model, and obtaining the loss data of the vehicle includes: extracting features of an image of the vehicle through a convolutional neural network in the image recognition model; and classifying the characteristics of the image of the vehicle through a full connection layer in the image recognition model to obtain the loss data of the vehicle.
Optionally, identifying the text information associated with the vehicle insurance case based on the text identification model, and obtaining the type of the vehicle insurance case includes: extracting key words from the text information associated with the vehicle insurance case; and analyzing the keywords through a hidden layer of the text recognition model to obtain the type of the car insurance case.
Optionally, analyzing the loss data of the vehicle and the type of the vehicle insurance case based on the case identification model, and obtaining the importance level of the case information includes: based on the case identification model, the loss data of the vehicle and the types of the vehicle insurance cases are processed through a deep learning algorithm to obtain the important level of the case information.
Optionally, after pushing the target information associated with the case information, the method further includes: acquiring sample data of a case identification model corresponding to the target information; and training the case recognition model through the sample data to obtain a target case recognition model, wherein the target case recognition model is used for establishing a mapping relation among loss data of different vehicles, types of vehicle insurance cases and important levels of case information.
Optionally, training the case recognition model through the sample data to obtain the target case recognition model includes: preprocessing sample data to obtain a training set and a test set of a case identification model; and training the case recognition model through a training set and a testing set to obtain a target case recognition model.
According to another aspect of the embodiments of the present invention, there is provided another information processing method. The method can comprise the following steps: inputting and displaying case information of the car insurance case on the interactive interface; and displaying the important level of the case information on the interactive interface, wherein the important level of the case information is obtained by analyzing the case information based on an information identification model, the information identification model is used for establishing a mapping relation between different case information and the important level, and target information associated with the case information is pushed under the condition that the important level is greater than a target threshold value.
According to another aspect of the embodiment of the invention, an information processing device is also provided. The apparatus may include: the acquisition unit is used for acquiring case information of the automobile insurance case; the analysis unit is used for analyzing the case information based on the information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level; and the pushing unit is used for pushing the target information associated with the case information under the condition that the importance level is greater than the target threshold value.
According to another aspect of the embodiments of the present invention, there is provided another information processing apparatus. The apparatus may include: the first display unit is used for inputting and displaying case information of the car insurance case on the interactive interface; and the second display unit is used for displaying the importance level of the case information on the interactive interface, wherein the importance level of the case information is obtained by analyzing the case information based on an information identification model, the information identification model is used for establishing a mapping relation between different case information and the importance level, and target information associated with the case information is pushed under the condition that the importance level is greater than a target threshold value.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium. The storage medium includes a stored program, wherein the apparatus on which the storage medium is located is controlled to execute the method of information processing of the embodiment of the present invention when the program runs.
According to another aspect of the embodiments of the present invention, there is also provided a processor. The processor is used for running a program, wherein the program executes the information processing method of the embodiment of the invention.
In the embodiment of the invention, the case information of the automobile insurance case is obtained; analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level; and in the case that the importance level is greater than the target threshold value, pushing target information associated with the case information. That is to say, the invention pushes the relevant target information of the car insurance case based on the pre-trained information recognition model, avoids the dependence on manual report of case information and the determination of whether the case is a big case, further solves the technical problem of low efficiency of processing the case information of the car insurance case in the prior art, and achieves the technical effect of improving the efficiency of processing the case information of the car insurance case.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow diagram of a method of information processing according to an embodiment of the present invention;
FIG. 2 is a flow diagram of another method of information processing according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a system for intelligently presenting major cases in a car insurance according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an AI picture recognition model according to an embodiment of the invention;
FIG. 5 is a schematic diagram of an NLP model according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an intelligent pattern recognition model according to an embodiment of the invention;
FIG. 7 is a schematic diagram of an information processing apparatus according to an embodiment of the present invention; and
fig. 8 is a schematic diagram of another information processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
The embodiment of the invention provides an information processing method.
Fig. 1 is a flow chart of a method of information processing according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step S102, obtaining the case information of the automobile insurance case.
In the technical solution provided by step S102 of the present invention, when a car insurance case occurs, case information of the car insurance case is obtained, where the case information is information related to the car insurance case, and may be information when an insurance company completes a survey, such as survey information, report information, policy information, loss photo, and the like.
And step S104, analyzing the case information based on the information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level.
In the technical solution provided by step S104 of the present invention, after the case information of the car insurance case is acquired, the case information may be input into the information recognition model, and the case information is analyzed by the information recognition model to obtain the importance level of the case information, where the importance level may be used to indicate whether the car insurance case is a major case.
The information identification model of the embodiment is also an intelligent large case presentation model, different case information can be input into the information identification model, the corresponding important level can be output from the information identification model, and the mapping relation between different case information and the corresponding important level can be established by training the information identification model, so that after the case information of the car insurance case is obtained, the case information can be input into the information identification model, optionally, the case information is input into the information identification model through the model data input interface, and the case information is analyzed through the information identification model, so that the important level of the case information is obtained, and the purpose of intelligently identifying whether the car insurance case is a large case or not is achieved without manual intervention.
And step S106, pushing target information associated with the case information when the importance level is greater than the target threshold value.
In the technical solution provided in step S106 of the present invention, after analyzing the case information based on the information identification model to obtain the importance level of the case information, determining whether the importance level of the case information is greater than a target threshold, where the target threshold may be a critical value for determining whether the case information is a significant case, and the critical value may be configured, that is, the standard for determining the significant case may be configured, and if the importance level of the case information is determined to be greater than the critical value, pushing target information associated with the case information, where the target information may be a message, and the content and the style design of the target information may be configurable. Optionally, the embodiment returns the target information associated with the case information to the insurance company through the model message feedback interface, and may automatically trigger the large case report for the push message of the major case.
The above-described method of this embodiment is further described below.
As an alternative implementation, in step S102, acquiring case information of the car insurance case includes: an image of a vehicle associated with a vehicle insurance case is acquired.
In this embodiment, the vehicle involved in the vehicle insurance case may be a loss vehicle, the case information of the vehicle insurance case may be image information of the vehicle, and thus the information to acquire the vehicle insurance case may be to acquire an image of the vehicle associated with the vehicle insurance case, which may be a loss photograph of the vehicle.
As an alternative implementation, in step S102, acquiring case information of the car insurance case includes: text information associated with the car insurance case is obtained.
In this embodiment, the case information of the vehicle insurance case may also be text information associated with the vehicle insurance case, where the text information may be used to describe the vehicle insurance case, and may be information obtained when the insurance company completes the survey, such as survey information, report information, policy information, and the like.
As an alternative implementation, in step S104, analyzing the case information based on the information recognition model to obtain the importance level of the case information includes: identifying the image of the vehicle based on an image identification model to obtain loss data of the vehicle, wherein the information identification model comprises the image identification model, the image identification model is used for establishing a mapping relation between the image of different vehicles and the loss data, and the case information comprises the image of the vehicle; identifying text information associated with the vehicle insurance case based on a text identification model to obtain the type of the vehicle insurance case, wherein the information identification model comprises the text identification model, the text identification model is used for establishing a mapping relation between the text information associated with different vehicle insurance cases and the type of the vehicle insurance case, and the case information comprises the text information associated with the vehicle insurance case; analyzing the loss data of the vehicle and the types of the vehicle insurance cases based on case identification models to obtain the important levels of case information, wherein the information identification models comprise case identification models which are used for establishing the mapping relation between the loss data of different vehicles, the types of the vehicle insurance cases and the important levels of the case information.
In this embodiment, the information recognition model may include an image recognition model, the image recognition model may be a picture recognition model, Artificial Intelligence (AI) may be applied to establish a mapping relationship between images of different vehicles and corresponding loss data, the embodiment may use an image of a vehicle as an input of the image recognition model, automatically recognize the image of the vehicle based on the image recognition model to obtain loss data of the vehicle, and output the loss data of the vehicle through an output layer of the image recognition model, where the loss data may be loss parts, the number of loss of accessories, and the degree of loss of the vehicle, so that no human intervention is required.
The information identification model of the embodiment may further include a text identification model, the text identification model may be a Neuro-Linguistic Programming (NLP) model, the model may use an NLP technique to establish a mapping relationship between text information associated with different car insurance cases and types of the car insurance cases, the text information associated with the car insurance cases may be used as an input of the text identification model, the text information associated with the car insurance cases is identified based on the text identification model to obtain the types of the car insurance cases, and the types of the car insurance cases may be output through an output layer of the text identification model, and the types may be types of cases such as a water flooded car type, a train type, and the like.
The information identification model of the embodiment may further include a case identification model, which may be an intelligent large case identification model, and may be used to establish a mapping relationship between loss data of different vehicles, types of the car insurance cases, and importance levels of case information, and to predict case loss, for example, to predict loss in a road traffic accident site. According to the embodiment, the loss data of the vehicle and the type of the vehicle insurance case can be used as the input of the case identification model, the loss data of the vehicle and the type of the vehicle insurance case are analyzed based on the case identification model to obtain the important level of the case information, and the important level of the case information is output through the output layer of the case identification model.
As an optional implementation, identifying the image of the vehicle based on the image identification model to obtain the loss data of the vehicle includes: extracting features of an image of the vehicle through a convolutional neural network in the image recognition model; and classifying the characteristics of the image of the vehicle through a full connection layer in the image recognition model to obtain the loss data of the vehicle.
In this embodiment, when the image of the vehicle is recognized to obtain the loss data of the vehicle, the features of the image of the vehicle may be extracted through a Convolutional Neural Network (CNN) algorithm in the image recognition model by a multi-layer convolution operation or a pooling operation to obtain the features of the image with high quality, and the features of the image may be input to all connection layers of the image recognition model to be classified, so as to obtain the loss data of the loss part, the loss degree, the number of accessories, and the like of the vehicle.
As an optional implementation manner, identifying the text information associated with the vehicle insurance case based on the text identification model to obtain the type of the vehicle insurance case includes: extracting key words from the text information associated with the vehicle insurance case; and analyzing the keywords through a hidden layer of the text recognition model to obtain the type of the car insurance case.
In this embodiment, when the text information associated with the car insurance case is identified based on the text identification Model to obtain the type of the car insurance case, a keyword may be extracted from the text information transmitted by the insurance company, where the keyword may be a core keyword of the text information, and the keyword is analyzed through a Hidden layer of the text identification Model, for example, the keyword of the text information is sequentially analyzed through a Hidden Markov Model (HMM), a Conditional Random Field (CRF), and a Bi-directional cyclic neural network (Bi-LSTM) to obtain case types such as a fire car type, a water flooded car type, and the like of the car insurance case.
As an alternative embodiment, analyzing the loss data of the vehicle and the type of the vehicle insurance case based on the case identification model, and obtaining the importance level of the case information includes: based on the case identification model, the loss data of the vehicle and the types of the vehicle insurance cases are processed through a deep learning algorithm to obtain the important level of the case information.
In this embodiment, when analyzing the loss data of the vehicle and the types of the car insurance cases to obtain the important levels of the case information, the case identification model may use a plurality of algorithms of deep learning to calculate the input loss data of the vehicle and the types of the car insurance cases, and output the case loss prejudgment result, thereby obtaining the important levels of the case information.
The information identification model of the embodiment can compare the loss pre-judgment result, automatically judge whether the car insurance case is a big case or not, and return the judgment result to the insurance company through the model message feedback interface, so that the message can be pushed for the big case, and the big case presentation is automatically triggered.
As an optional implementation manner, after pushing the target information associated with the case information in step S106, the method further includes: acquiring sample data of a case identification model corresponding to the target information; and training the case recognition model through the sample data to obtain a target case recognition model, wherein the target case recognition model is used for establishing a mapping relation among loss data of different vehicles, types of vehicle insurance cases and important levels of case information.
The case identification model of the embodiment has a yield design, the production data written back to the target information can be determined as sample data of the case identification model, the sample data can be continuously input into the case identification model through the model message feedback interface, and the case identification model is optimized, for example, parameters of the case identification model are optimized, so that the target case identification model is obtained, and the case identification model can also be used for establishing mapping relations among loss data of different vehicles, types of vehicle insurance cases and important levels of case information.
The initial accuracy of the case identification model in the embodiment is equal to or more than 70%, and the accuracy can be continuously improved along with continuous training of model yield to obtain the target case identification model, so that the accuracy of the model is continuously improved.
As an optional implementation manner, training the case recognition model through sample data to obtain a target case recognition model includes: preprocessing sample data to obtain a training set and a test set of a case identification model; and training the case recognition model through a training set and a testing set to obtain a target case recognition model.
In this embodiment, when the case identification model is optimally trained through sample data, the input sample data may be preprocessed, for example, the data set marking, the data set cleaning, the data set amplifying, the data set splitting, and the like are performed, so as to obtain a training set and a testing set, then the case identification model is trained through the training set and the testing set, and manual training, for example, feature selection, model training through the training set, model testing through the testing set, then model evaluation, and then automatic training, for example, feature selection, model training through the training set, model testing through the testing set, and then model evaluation may be performed, wherein the configured algorithm may be an algorithm parameter configuration file, a second generation artificial intelligence learning system (TensorFlow), a deep learning library (MXNet), and the like, and the model evaluation result in the automatic training can be subjected to an improvement algorithm with low availability and iterative processing. After model training, when the model comes online, a model call interface (API) may be formed, which may include a GPI cluster, a High Performance Computing (HPC) cluster.
It should be noted that the algorithm, parameters, and the like of the model training of this embodiment are all designed to be configurable.
The embodiment of the invention also provides another information processing method from the user interaction angle.
Fig. 2 is a flow chart of another method of information processing according to an embodiment of the present invention. As shown in fig. 2, the method may include the steps of:
and S202, inputting and displaying case information of the car insurance case on the interactive interface.
In the technical solution provided by step S202 of the present invention, when a car insurance case occurs, case information of the car insurance case is input, and the case information of the car insurance case is displayed on the interactive interface, where the case information is information related to the car insurance case, and may be information when an insurance company completes a survey, such as survey information, report information, policy information, loss photograph, and the like.
And S204, displaying the important level of the case information on the interactive interface, wherein the important level of the case information is obtained by analyzing the case information based on the information recognition model.
In the technical solution provided by step S204 of the present invention, after the case information of the car insurance case is input and displayed on the interactive interface, the important level of the case information is displayed on the interactive interface, wherein the important level of the case information is obtained by analyzing the case information based on an information identification model, the information identification model is used for establishing a mapping relationship between different case information and important levels, and the target information associated with the case information is pushed when the important level is greater than a target threshold.
The information identification model of the embodiment is also an intelligent large case presentation model, different case information can be input into the information identification model, the corresponding important level can be output from the information identification model, and the mapping relation between different case information and the corresponding important level can be established by training the information identification model, so that after the case information of the car insurance case is obtained, the case information can be input into the information identification model, optionally, the case information is input into the information identification model through the model data input interface, and the case information is analyzed through the information identification model, so that the important level of the case information is obtained, and the important level of the case information is displayed on the interactive interface, so that the purpose of intelligently identifying whether the car insurance case is a large case or not is achieved without manual intervention.
Optionally, in this embodiment, after analyzing the case information based on the information recognition model to obtain the importance level of the case information, it is determined whether the importance level of the case information is greater than a target threshold, where the target threshold may be a critical value used to determine whether the case information is a significant case, and the critical value may be configured, and if the importance level of the case information is determined to be greater than the critical value, target information associated with the case information is pushed, and the target information may be a message, and both content and style design of the message are configurable. Optionally, the embodiment may return target information associated with case information to the insurance company through the model message feedback interface, and may automatically trigger large case report for a significant case push message.
In the embodiment, case information of the car insurance case is acquired; analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level; and in the case that the importance level is greater than the target threshold value, pushing target information associated with the case information. That is to say, the invention pushes the relevant target information of the car insurance case based on the pre-trained information recognition model, avoids the dependence on manual report of case information and the determination of whether the case is a big case, further solves the technical problem of low efficiency of processing the case information of the car insurance case in the prior art, and achieves the technical effect of improving the efficiency of processing the case information of the car insurance case.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Example 2
The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.
At present, for example, insurance companies with the insurance premium scale of over 400 hundred million in China are taken as examples, the number of vehicle insurance cases marked as major cases accounts for 11 percent, and the amount accounts for 72 percent. The number of cases reported in the requirement of the large case management and control timeliness is only 23%, 77% of major cases are not managed and controlled or cannot be managed and controlled in time, and therefore the operation data, the cost and the customer service of an insurance company are seriously affected.
The current insurance market has no related technical means, usually depends on manual reporting of employees of insurance companies, and has the defects of intensive labor, incapability of guaranteeing time efficiency, high requirements on quality of personnel and the like.
The embodiment provides a solution for realizing intelligent presentation of major cases in car insurance based on an AI technology, and when a car insurance case occurs, the AI picture recognition technology is used for judging the loss part and the loss degree, the NLP technology is used for judging the type of a flooded car and the type of a burning car, the intelligent major case recognition model is used for prejudging the loss and identifying whether the major case exists, and the major case presentation is automatically triggered in real time aiming at the major case.
Fig. 3 is a schematic diagram of a system for intelligently reporting major cases in a car insurance according to an embodiment of the invention. As shown in fig. 3, when the insurance company completes the survey, the data of survey information, report information, policy information, loss photograph, etc. can be transmitted to the intelligent case report model through the model data input interface.
The intelligent case presentation model of the embodiment includes an AI picture recognition model for picture information recognition. Based on the AI picture recognition model, the lost part, the accessory loss quantity and the loss degree of the output vehicle are intelligently recognized, so that manual intervention is not needed.
Fig. 4 is a schematic diagram of an AI picture recognition model according to an embodiment of the present invention. As shown in fig. 4, the AI image recognition model according to this embodiment uses a convolutional neural network algorithm to extract features from input case data (X1, X2 … … Xn) of a vehicle through a multi-layer (for example, more than four layers) convolution operation and pooling operation, to obtain a high-quality feature image, inputs the high-quality feature image into a full-link layer to perform classification processing, and further outputs data such as a loss part and a loss degree.
The intelligent case presentation model of the embodiment further comprises an NLP model for text information recognition. Based on the NLP model, case types such as a flooded car type, a burnt car type and the like can be intelligently identified.
Fig. 5 is a schematic diagram of an NLP model according to an embodiment of the present invention. As shown in fig. 5, the text information transmitted by the insurance company is analyzed by using the natural language processing technology, the core keywords of the text information are extracted, the core keywords are identified by using hidden layers (HMM, CRF, BI-LSM), and data required by subsequent case identification models such as a burning car and a flooding car during operation are output through an output unit.
The intelligent case submitting model of the embodiment also comprises a case identification model which is used for calculating input data by using various algorithms of deep learning, outputting case loss prejudgment results and completing intelligent case submitting treatment in a matching way. The embodiment can be based on an intelligent large case recognition model, loss positions, loss quantity of accessories and loss degree of a vehicle output by combining an AI picture recognition model, case types output by an NLP model and other data transmitted by an insurance company can intelligently predict case loss degree, the judgment result is transmitted back to the insurance company through a model message feedback interface, and a message is pushed for a large case, wherein the large case standard is configurable, if the large case is the large case, the large case can be intelligently submitted and a subsequent claim settlement flow is carried out, optionally, if the large case is not submitted, the subsequent claim settlement flow can be directly entered, wherein the submission content and the submission style are configurable.
The intelligent case presentation model of the embodiment has a data receiving design, and the written-back production data is continuously input into the case identification model through the model message feedback interface to optimize the model.
Fig. 6 is a schematic diagram of an intelligent pattern recognition model according to an embodiment of the invention. As shown in fig. 6, when the case recognition model is optimally trained through sample data, the input sample data may be preprocessed, for example, the data set marking, the data set cleaning, the data set amplifying, the data set splitting, etc. are performed, so as to obtain a training set and a testing set, then, the case recognition model is trained through the training set and the testing set, and manual training can be firstly carried out, for example, feature selection is carried out, model training is carried out through the training set, model testing is carried out through the testing set, then model evaluation is performed, followed by automatic training, e.g., feature selection, model training through the training set, model testing through the test set, then model evaluation, wherein, the configured algorithm can be an algorithm parameter configuration file, TensorFlow, MXNet and the like, and the model evaluation result in the automatic training can be subjected to an improvement algorithm with low availability and iterative processing. After model training, when the model comes online, a model call interface (API) may be formed, which may include a GPI cluster, a high performance computing HPC cluster.
It should be noted that the model training algorithm, parameters, and the like of this embodiment are all designed to be configurable.
The initial accuracy of the intelligent large case presentation model of the embodiment is ensured to be more than or equal to 70%, and the accuracy can be continuously improved along with the continuous training of model collection.
The embodiment pushes the relevant information of the car insurance case based on the pre-trained intelligent large case presentation model, avoids manual report of case information and determines whether the case is a large case, and by the method, the major cases of the insurance company can be presented in time by 70% in a ratio, the case operation manpower is optimized by 40%, the personnel quality requirement is reduced, the pending data system is more timely and accurately embodied, the number of cases is 70% in a ratio, the major cases can be timely mastered, the front intervention is realized, the cost is controllable, the technical problem that the efficiency of processing the case information of the car insurance case in the prior art is low is solved, and the technical effect of improving the efficiency of processing the case information of the car insurance case is achieved.
Example 3
The embodiment of the invention also provides an information processing device. It should be noted that the information processing apparatus of this embodiment can be used to execute the information processing method shown in fig. 1 according to the embodiment of the present invention.
Fig. 7 is a schematic diagram of an information processing apparatus according to an embodiment of the present invention. As shown in fig. 7, the information processing apparatus 70 may include: an acquisition unit 71, an analysis unit 72 and a push unit 73.
The acquiring unit 71 is used for acquiring case information of the vehicle insurance case.
The analysis unit 72 is configured to analyze the case information based on an information identification model to obtain an importance level of the case information, where the information identification model is used to establish a mapping relationship between different case information and importance levels.
A pushing unit 73 for pushing the target information associated with the case information in case that the importance level is greater than the target threshold.
Alternatively, the acquisition unit 71 includes: a first acquisition module to acquire an image of a vehicle associated with a vehicle insurance case.
Alternatively, the acquisition unit 71 includes: and the second acquisition module is used for acquiring the text information associated with the car insurance case.
Optionally, the analyzing unit 72 comprises: the system comprises a first identification module, a second identification module and a management module, wherein the first identification module is used for identifying an image of a vehicle based on an image identification model to obtain loss data of the vehicle, the information identification model comprises the image identification model, the image identification model is used for establishing a mapping relation between images of different vehicles and the loss data, and case information comprises the image of the vehicle; the second identification module is used for identifying the text information associated with the vehicle insurance case based on the text identification model to obtain the type of the vehicle insurance case, wherein the information identification model comprises the text identification model, the text identification model is used for establishing the mapping relation between the text information associated with different vehicle insurance cases and the type of the vehicle insurance case, and the case information comprises the text information associated with the vehicle insurance case; and the analysis module is used for analyzing the loss data of the vehicle and the types of the vehicle insurance cases based on the case identification model to obtain the important levels of the case information, wherein the information identification model comprises a case identification model, and the case identification model is used for establishing the mapping relation among the loss data of different vehicles, the types of the vehicle insurance cases and the important levels of the case information.
Optionally, the first identification module comprises: the first extraction submodule is used for extracting the characteristics of the image of the vehicle through a convolutional neural network in the image recognition model; and the classification module is used for classifying the characteristics of the image of the vehicle through a full connection layer in the image recognition model to obtain the loss data of the vehicle.
Optionally, the second identification module comprises: the second extraction submodule is used for extracting key words from the text information associated with the automobile insurance case; and the analysis submodule is used for analyzing the key words through the hidden layer of the text recognition model to obtain the type of the car insurance case.
Optionally, the analysis module comprises: and the processing submodule is used for processing the loss data of the vehicle and the types of the vehicle insurance cases through a deep learning algorithm based on the case identification model to obtain the important level of the case information.
Optionally, the apparatus further comprises: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring sample data of a case identification model corresponding to target information after the target information associated with the case information is pushed; and the training unit is used for training the case recognition model through the sample data to obtain a target case recognition model, wherein the target case recognition model is used for establishing a mapping relation among loss data of different vehicles, types of the car insurance cases and important levels of case information.
Optionally, the training unit comprises: the processing module is used for preprocessing the sample data to obtain a training set and a test set of the case identification model; and the training module is used for training the case recognition model through the training set and the testing set to obtain a target case recognition model.
The embodiment of the invention also provides a schematic diagram of another information processing device. It should be noted that the information processing apparatus of this embodiment can be used to execute the information processing method shown in fig. 2 according to the embodiment of the present invention.
Fig. 8 is a schematic diagram of another information processing apparatus according to an embodiment of the present invention. As shown in fig. 8, the information processing apparatus 80 may include: a first display unit 81 and a second display unit 82.
And the first display unit 81 is used for inputting and displaying case information of the car insurance case on the interactive interface.
And the second display unit 82 is configured to display the importance levels of the case information on the interactive interface, where the importance levels of the case information are obtained by analyzing the case information based on an information identification model, the information identification model is used to establish mapping relationships between different case information and importance levels, and target information associated with the case information is pushed when the importance levels are greater than a target threshold.
The embodiment pushes the relevant target information of the car insurance case based on the pre-trained information recognition model, avoids the dependence on manual report of case information and the determination of whether the case is a big case, further solves the technical problem that the efficiency of processing the case information of the car insurance case is low in the prior art, and achieves the technical effect of improving the efficiency of processing the case information of the car insurance case.
Example 4
According to an embodiment of the present invention, there is also provided a storage medium including a stored program, wherein the program executes the method of information processing described in embodiment 1.
Example 5
According to an embodiment of the present invention, there is also provided a processor configured to execute a program, where the program executes the method for processing information described in embodiment 1.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (14)
1. A method of information processing, comprising:
acquiring case information of a vehicle insurance case;
analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level;
and pushing target information associated with the case information if the importance level is greater than a target threshold.
2. The method of claim 1, wherein obtaining case information for a vehicle insurance case comprises:
an image of a vehicle associated with the vehicle insurance case is acquired.
3. The method of claim 1, wherein obtaining case information for a vehicle insurance case comprises:
and acquiring text information associated with the car insurance case.
4. The method of claim 1, wherein analyzing the case information based on an information recognition model to obtain the importance level of the case information comprises:
identifying an image of a vehicle based on an image identification model to obtain loss data of the vehicle, wherein the information identification model comprises the image identification model, the image identification model is used for establishing a mapping relation between the image of different vehicles and the loss data, and the case information comprises the image of the vehicle;
identifying text information associated with the vehicle insurance case based on a text identification model to obtain the type of the vehicle insurance case, wherein the information identification model comprises the text identification model, the text identification model is used for establishing a mapping relation between text information associated with different vehicle insurance cases and the type of the vehicle insurance case, and the case information comprises the text information associated with the vehicle insurance case;
analyzing the loss data of the vehicle and the type of the vehicle insurance case based on a case identification model to obtain the important level of the case information, wherein the information identification model comprises the case identification model, and the case identification model is used for establishing the mapping relation among the loss data of different vehicles, the type of the vehicle insurance case and the important level of the case information.
5. The method of claim 4, wherein identifying an image of a vehicle based on an image recognition model, and obtaining loss data for the vehicle comprises:
extracting features of an image of the vehicle through a convolutional neural network in the image recognition model;
and classifying the characteristics of the image of the vehicle through a full connection layer in the image recognition model to obtain the loss data of the vehicle.
6. The method of claim 4, wherein identifying the text information associated with the vehicle insurance case based on a text recognition model to obtain the type of the vehicle insurance case comprises:
extracting key words from the text information associated with the car insurance case;
and analyzing the keywords through a hidden layer of the text recognition model to obtain the type of the car insurance case.
7. The method of claim 4, wherein analyzing the loss data of the vehicle and the type of the car insurance case based on a case identification model, and obtaining the importance level of the case information comprises:
and processing the loss data of the vehicle and the types of the vehicle insurance cases through a deep learning algorithm based on a case identification model to obtain the important level of the case information.
8. The method of claim 7, wherein after pushing the target information associated with the case information, the method further comprises:
acquiring sample data of the case identification model corresponding to the target information;
and training the case recognition model through the sample data to obtain a target case recognition model, wherein the target case recognition model is used for establishing a mapping relation among loss data of different vehicles, types of vehicle insurance cases and important levels of case information.
9. The method of claim 8, wherein training the case recognition model with the sample data to obtain a target case recognition model comprises:
preprocessing the sample data to obtain a training set and a test set of the case identification model;
and training the case recognition model through the training set and the testing set to obtain the target case recognition model.
10. A method of information processing, comprising:
inputting and displaying case information of the car insurance case on the interactive interface;
and displaying the importance level of the case information on the interactive interface, wherein the importance level of the case information is obtained by analyzing the case information based on an information identification model, the information identification model is used for establishing a mapping relation between different case information and the importance level, and target information associated with the case information is pushed under the condition that the importance level is greater than a target threshold value.
11. An information processing apparatus, comprising:
the acquisition unit is used for acquiring case information of the automobile insurance case;
the analysis unit is used for analyzing the case information based on an information identification model to obtain the important level of the case information, wherein the information identification model is used for establishing the mapping relation between different case information and the important level;
a pushing unit, configured to push target information associated with the case information if the importance level is greater than a target threshold.
12. An information processing apparatus, comprising:
the first display unit is used for inputting and displaying case information of the car insurance case on the interactive interface;
and the second display unit is used for displaying the importance level of the case information on the interactive interface, wherein the importance level of the case information is obtained by analyzing the case information based on an information identification model, the information identification model is used for establishing a mapping relation between different case information and the importance level, and target information associated with the case information is pushed under the condition that the importance level is greater than a target threshold value.
13. A storage medium, characterized in that the storage medium comprises a stored program, wherein the program, when executed, controls an apparatus in which the storage medium is located to perform the method of any one of claims 1 to 10.
14. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910839114.8A CN110728582B (en) | 2019-09-05 | 2019-09-05 | Information processing method, device, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910839114.8A CN110728582B (en) | 2019-09-05 | 2019-09-05 | Information processing method, device, storage medium and processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110728582A true CN110728582A (en) | 2020-01-24 |
| CN110728582B CN110728582B (en) | 2022-03-08 |
Family
ID=69217867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910839114.8A Active CN110728582B (en) | 2019-09-05 | 2019-09-05 | Information processing method, device, storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728582B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311424A (en) * | 2020-03-06 | 2020-06-19 | 德联易控科技(北京)有限公司 | Data analysis method and device in vehicle accident, storage medium and processor |
| CN111461901A (en) * | 2020-03-31 | 2020-07-28 | 德联易控科技(北京)有限公司 | Method and device for outputting vehicle insurance claim settlement information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600421A (en) * | 2016-11-21 | 2017-04-26 | 中国平安财产保险股份有限公司 | Intelligent car insurance loss assessment method and system based on image recognition |
| CN108257024A (en) * | 2017-04-14 | 2018-07-06 | 平安科技（深圳）有限公司 | A kind of Claims Resolution case treating method and apparatus |
| CN108765176A (en) * | 2018-06-04 | 2018-11-06 | 中国平安人寿保险股份有限公司 | Settlement of insurance claim case processing method, device, computer equipment and storage medium |
| CN108961082A (en) * | 2018-07-06 | 2018-12-07 | 北京精友世纪软件技术有限公司 | A kind of vehicle insurance loss assessment system and method based on AI image recognition |
| CN109544355A (en) * | 2018-10-19 | 2019-03-29 | 中国平安财产保险股份有限公司 | Vehicle insurance case surveys damage identification method, device and terminal device |
| CN109784170A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | Vehicle insurance damage identification method, device, equipment and storage medium based on image recognition |
-
2019
- 2019-09-05 CN CN201910839114.8A patent/CN110728582B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600421A (en) * | 2016-11-21 | 2017-04-26 | 中国平安财产保险股份有限公司 | Intelligent car insurance loss assessment method and system based on image recognition |
| CN108257024A (en) * | 2017-04-14 | 2018-07-06 | 平安科技（深圳）有限公司 | A kind of Claims Resolution case treating method and apparatus |
| CN108765176A (en) * | 2018-06-04 | 2018-11-06 | 中国平安人寿保险股份有限公司 | Settlement of insurance claim case processing method, device, computer equipment and storage medium |
| CN108961082A (en) * | 2018-07-06 | 2018-12-07 | 北京精友世纪软件技术有限公司 | A kind of vehicle insurance loss assessment system and method based on AI image recognition |
| CN109544355A (en) * | 2018-10-19 | 2019-03-29 | 中国平安财产保险股份有限公司 | Vehicle insurance case surveys damage identification method, device and terminal device |
| CN109784170A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | Vehicle insurance damage identification method, device, equipment and storage medium based on image recognition |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311424A (en) * | 2020-03-06 | 2020-06-19 | 德联易控科技(北京)有限公司 | Data analysis method and device in vehicle accident, storage medium and processor |
| CN111311424B (en) * | 2020-03-06 | 2023-08-22 | 德联易控科技(北京)有限公司 | Data analysis method, device, storage medium and processor in vehicle insurance accident |
| CN111461901A (en) * | 2020-03-31 | 2020-07-28 | 德联易控科技(北京)有限公司 | Method and device for outputting vehicle insurance claim settlement information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110728582B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090902B (en) | Non-reference image quality objective evaluation method based on multi-scale generation countermeasure network | |
| CN107657267B (en) | Product potential user mining method and device | |
| CN108885700A (en) | Data set semi-automatic labelling | |
| CN108734184B (en) | Method and device for analyzing sensitive image | |
| CN110009508A (en) | A kind of vehicle insurance compensates method and system automatically | |
| CN106874134B (en) | Work order type processing method, device and system | |
| CN104702492A (en) | Garbage message model training method, garbage message identifying method and device thereof | |
| CN111428599B (en) | Bill identification method, device and equipment | |
| CN106296195A (en) | A kind of Risk Identification Method and device | |
| CN108108744B (en) | Method and system for radiation image auxiliary analysis | |
| CN110728582B (en) | Information processing method, device, storage medium and processor | |
| CN108734296A (en) | Optimize method, apparatus, electronic equipment and the medium of the training data of supervised learning | |
| CN113222149B (en) | Model training method, device, equipment and storage medium | |
| CN111476296A (en) | Sample generation method, classification model training method, identification method and corresponding devices | |
| CN110399559A (en) | Intelligence insurance recommender system and computer storage medium | |
| CN111275338A (en) | Method, device, equipment and storage medium for judging enterprise fraud behaviors | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN110633919A (en) | Method and device for evaluating business entity | |
| CN114722945A (en) | Inventory client intention prediction method and device | |
| CN110751170A (en) | Panel quality detection method, system, terminal device and computer readable medium | |
| CN117172795A (en) | Intelligent technical service fee online consultation system | |
| CN116563028A (en) | AI-based report data verification method, system and storage medium | |
| CN115880077A (en) | Recommendation method and device based on client label, electronic device and storage medium | |
| CN113870020A (en) | Overdue risk control method and device | |
| CN113240513A (en) | Method for determining user credit line and related device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |