CN112800272A - Method and device for identifying insurance claim settlement fraud behavior - Google Patents
Method and device for identifying insurance claim settlement fraud behavior Download PDFInfo
- Publication number
- CN112800272A CN112800272A CN202110061012.5A CN202110061012A CN112800272A CN 112800272 A CN112800272 A CN 112800272A CN 202110061012 A CN202110061012 A CN 202110061012A CN 112800272 A CN112800272 A CN 112800272A
- Authority
- CN
- China
- Prior art keywords
- insurance
- voice data
- settlement
- fraud
- user
- 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 82
- 230000008569 process Effects 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 33
- 230000006399 behavior Effects 0.000 claims abstract description 29
- 230000008451 emotion Effects 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 13
- 230000002996 emotional effect Effects 0.000 claims description 10
- 238000013139 quantization Methods 0.000 claims description 7
- 230000033764 rhythmic process Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 8
- 230000006854 communication Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Abstract
The application discloses a method and a device for identifying insurance claim settlement fraud. Wherein, the method comprises the following steps: acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data in the process of carrying out insurance claim settlement by the insurance claim settlement user; processing the voice data to obtain characteristic information of the voice data; and judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information. The method and the device solve the technical problem that the existing method for identifying the insurance claim settlement fraud has low identification accuracy.
Description
Technical Field
The application relates to the field of insurance case fraud, in particular to a method and a device for identifying insurance claim settlement fraud.
Background
The insurance claim fraud is implemented in the ordinary insurance company claim process according to the face of the normal insurance claim claimant. Although the cheater appears in the face of a normal insurance claimant, the psychological state of 'unexpected' insurance caused by errors, negligence, violation and the like of the cheater in the normal insurance claim case is greatly different from that of the normal insurance claim case, the insurance cheating case actor is intentionally under the subjective condition, namely, an insurance accident is intentionally caused, the cheater obviously knows that the own action causes the damage result of the loss of an insured party (whether property or human body), and actively and directly implements the damage action and the loss generation of the pursuit accident so as to obtain insurance compensation.
The existing insurance anti-fraud system is generally carried out by adopting a rule engine/system, and high-risk time periods, high-risk road sections, high-risk vehicle types, high-risk customers and the like are collected to be used as risk factors. High risk periods such as 8 o 'clock late to 6 o' clock early the next day, high risk road segments such as the sub-county road segments found in historical fraud claims, high risk vehicle models such as some second-hand luxury vehicles, and high risk customers such as those people who have done fraud in insurance co-industrial claims. In the insurance claim settlement cases, no matter the insurance claim settlement cases are in a case reporting link, a survey link and a settlement and claim settlement link, the risk case prompt can be triggered as long as the fields of the risk factors appear. However, the adoption of the insurance anti-fraud system for identifying the insurance claim fraud has the problem of low identification accuracy.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a method and a device for identifying an insurance claim fraud, which at least solve the technical problem that the existing method for identifying the insurance claim fraud has low identification accuracy.
According to an aspect of an embodiment of the present application, there is provided a method for identifying insurance claim fraud, including: acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data in the process of carrying out insurance claim settlement by the insurance claim settlement user; processing the voice data to obtain the characteristic information of the voice data, wherein the characteristic information at least comprises: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance of the voice data; and judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
Optionally, processing the voice data to obtain feature information of the voice data includes: analyzing at least one of the following non-word characteristics of the voice data to obtain emotional characteristic parameters of the insurance claim settlement user: the volume, tone, speed, pause times, rhythm and silent time of the insurance claim settlement user during speaking.
Optionally, judging whether an insurance claim settlement user has fraud behavior in the insurance claim settlement process according to the feature information includes: carrying out quantization processing on the emotion characteristic parameters to obtain the emotion characteristic parameters after quantization processing; and comprehensively judging whether the insurance claim settlement user has fraud behaviors according to the emotional characteristic parameters after the quantitative processing.
Optionally, processing the voice data to obtain feature information of the voice data, further includes: identifying voice data to obtain semantic text data corresponding to the voice data; carrying out word splitting processing on semantic text data to obtain semantic features and word order features; analyzing the following language units of the semantic text data to obtain the structural meaning of the language units: phrases, sentences, and sentence groups.
Optionally, judging whether an insurance claim settlement user has fraud behavior in the insurance claim settlement process according to the feature information includes: judging whether the voice data is the voice data after being processed intentionally according to the semantic features and the word sequence features; and if so, determining that the insurance claim settlement user possibly has fraud in the insurance claim settlement process.
Optionally, judging whether an insurance claim settlement user has fraud behavior in the insurance claim settlement process according to the feature information includes: judging whether the voice data is the voice data after being processed intentionally or not according to the structural meaning of the language unit and the emotional characteristic parameters of the insurance claim settlement user; and if so, determining that the insurance claim settlement user possibly has fraud in the insurance claim settlement process.
Optionally, the determining whether the voice data is the voice data after being processed intentionally according to the structural meaning of the language unit includes: judging that adjectives or adverbs with biased structures exist in the language units; and if the adjective or adverb with the bias structure exists in the language unit, determining the voice data as the voice data which is processed deliberately.
Optionally, the method further includes: if the insurance claim settlement user is judged to have fraud behavior in the insurance claim settlement process, generating a target question based on the voice data by using a question-answer generating system; acquiring response voice data of an insurance claim settlement user to a target problem; processing the response voice data to obtain the characteristic information of the response voice data; and judging whether the insurance claim settlement user possibly having the fraudulent conduct has the fraudulent conduct or not according to the characteristic information of the response voice data.
According to another aspect of the embodiments of the present application, there is also provided an apparatus for identifying insurance claim fraud, including: the acquiring module is used for acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data of the insurance claim settlement user in an insurance claim settlement process; the processing module is used for processing the voice data to obtain the characteristic information of the voice data, and the characteristic information at least comprises: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance of the voice data; and the judging module is used for judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
According to yet another aspect of the embodiments of the present application, there is further provided a computer-readable storage medium, where the storage medium includes a stored program, and where the program is executed to control a device where the storage medium is located to perform the above method for identifying insurance claim fraud.
According to yet another aspect of the embodiments of the present application, there is also provided a processor for executing a program stored in a memory, wherein the program executes the above method for identifying insurance claim fraud.
In the embodiment of the application, the voice data of the insurance claim settlement user is obtained, wherein the voice data is the voice data of the insurance claim settlement user in the insurance claim settlement process; processing the voice data to obtain the characteristic information of the voice data, wherein the characteristic information at least comprises: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance of the voice data; the method for judging whether the insurance claim user has fraud behaviors in the insurance claim process according to the characteristic information judges and identifies fraud risks by performing analysis on the content, expression mode and language behaviors of the claim language, thereby realizing the technical effect of improving the accuracy rate of identifying the insurance claim fraud behaviors and further solving the technical problem of low identification accuracy rate of the conventional method for identifying the insurance claim fraud behaviors.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of a method of identifying insurance claim fraud according to an embodiment of the present application;
fig. 2 is a block diagram of an apparatus for identifying insurance claim fraud according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application 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 application 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.
In accordance with an embodiment of the present application, there is provided an embodiment of a method of identifying insurance claim fraud, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flow chart of a method for identifying insurance claim fraud according to an embodiment of the present application, as shown in fig. 1, the method including the steps of:
step S102, voice data of the insurance claim settlement user is obtained, wherein the voice data is voice data in the insurance claim settlement process of the insurance claim settlement user.
The insurance client in the claim process mainly informs the insurance reason and states the loss condition in a language mode to carry out the claim. The language in the claim scene has functions of not only expression and understanding, but also has functional meaning and behavior action from the psychological point of view, and the language provides implementation possibility for judging and identifying fraud risk by analyzing the content, expression mode and language behavior of the claim language.
Step S104, processing the voice data to obtain the characteristic information of the voice data, wherein the characteristic information at least comprises: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance of the voice data.
And step S106, judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
Through the steps, the fraud risk is judged and identified through the analysis on the content, the expression mode and the language behavior of the claim language, so that the technical effect of improving the accuracy rate of identifying the insurance claim fraud behavior is realized.
According to an alternative embodiment of the present application, step S104 may be implemented by: analyzing at least one of the following non-word characteristics of the voice data to obtain emotional characteristic parameters of the insurance claim settlement user: the volume, tone, speed, pause times, rhythm and silent time of the insurance claim settlement user during speaking.
According to an alternative embodiment of the present application, in the step S106, whether fraud is present in the insurance claim settlement process by the insurance claim settlement user can be determined by the following method: carrying out quantization processing on the emotion characteristic parameters to obtain the emotion characteristic parameters after quantization processing; and comprehensively judging whether the insurance claim settlement user has fraud behaviors according to the emotional characteristic parameters after the quantitative processing.
In the step, the voice of the reporter is identified, typical non-word characteristics of the reporter, such as volume, tone, speech speed, pause, rhythm, silence and the like, are analyzed, and characteristic parameters of emotion of the reporter are generated through quantitative analysis to judge whether fraud is possible, for example, the reporter is quite quiet in speaking, free in response and quite clear in arrangement, which indicates that insurance claim fraud behavior may exist in the reporter.
The following describes a process of quantifying the emotional characteristic parameter in a specific embodiment:
taking the pitch of the insurance claim user when speaking as an example, the pitch of the speaker is divided into 1 to 10 different pitch classes, and the lower the pitch class is, the quieter the speaker is when speaking is indicated.
Similarly, the speaking speed of the speaker can be set to different levels, and the calmness degree of the speaker during speaking can be calculated and measured through the maximum likelihood criterion and the like.
In some optional embodiments of the present application, step S104 may also be implemented by: identifying voice data to obtain semantic text data corresponding to the voice data; carrying out word splitting processing on semantic text data to obtain semantic features and word order features; analyzing the following language units of the semantic text data to obtain the structural meaning of the language units: phrases, sentences, and sentence groups.
According to an alternative embodiment of the present application, step S106 can also be implemented by: judging whether the voice data is the voice data after being processed deliberately or not according to the semantic features and the word sequence features; and if so, determining that the insurance claim settlement user possibly has fraud in the insurance claim settlement process.
According to another alternative embodiment of the present application, step S106 can also be implemented by: judging whether the voice data is the voice data after being processed intentionally or not according to the structural meaning of the language unit and the emotional characteristic parameters of the insurance claim settlement user; and if so, determining that the insurance claim settlement user possibly has fraud in the insurance claim settlement process.
In an alternative embodiment of the present application, the determining whether the voice data is the voice data after being deliberately processed according to the structural meaning of the language unit is performed by: judging that adjectives or adverbs with biased structures exist in the language units; and if the adjective or adverb with the bias structure exists in the language unit, determining the voice data as the voice data which is processed deliberately.
In this step, firstly, the voice data of the person who reports the case is recognized as semantic text data by a voice recognition technology, and then the recognized semantic text data is comprehensively analyzed, which mainly comprises the following two methods:
a) firstly, splitting words and word sequences of a language text of a reporter to obtain semantic features and word sequence features of semantic text data, and then judging whether the language of the reporter is contradictory or not or whether the language of the reporter is processed and organized or not and whether the language of the reporter conforms to the conventional semantic features or not by comprehensively judging the semantic features and the word sequence features.
According to an optional embodiment of the application, the adjectives and adverbs of the biased structure are added to the reports and the claim texts on the basis of multi-directional high-risk nouns and pronouns in the original rule anti-fraud system, so that the dimensionality of identification of risk factors of the fraud cases is increased, and the identification accuracy is improved through the multi-dimensional risk consistency. The structure of bias-positive is called bias-positive phrase. The phrase is composed of a modifier and a central phrase, and the structural components have modification and modified relations. Verbs, nouns, adjectives and phrases in which they preceded the modifying element.
b) By means of feature recognition of phrases, sentences and sentence groups of the language text and the combination of the quantization parameters of typical non-word features mentioned above, the hidden pragmatic meanings of grammatical units such as words and sentences selected and used in the claim text and the structural meanings contained in the arrangement of the linguistic units according to a certain sequence are analyzed, and the claim language operation characteristics of topic events, main roles, grammatical structures and the like in the claim text are judged through an analysis decision model.
In this step, on the basis of lexical analysis, the anti-fraud system of claim based on semantic analysis adds structural meaning recognition of text phrases, sentences, sentence clusters, and the like of claim. It should be pointed out that, because the insurance fraudsters are mostly "actuaries" of the claim language, the elaborately organized claim language expression thereof is full of calculation and calculation, and high-risk nouns and pronouns can be avoided to a great extent; therefore, it is often the uniqueness of the claims anti-fraud system based on semantic analysis that further identifies insurance fraud and its type by grammatical structural meaning.
If the insurance claim settlement user is judged to have fraud behavior in the insurance claim settlement process, generating a target question based on the voice data by using a question-answer generating system; acquiring response voice data of an insurance claim settlement user to a target problem; processing the response voice data to obtain the characteristic information of the response voice data; and judging whether the insurance claim settlement user possibly having the fraudulent conduct has the fraudulent conduct or not according to the characteristic information of the response voice data.
Through the analysis, for insurance claim settlement users with possible fraud behaviors, on the basis of psychological traces and doubtful points, a question-answer generating system is adopted to generate corresponding questions, and then inquiry, information and data supplement and fraud risk identification and solution are communicated to risk clients. According to the actual situation, the audio materials in the communication process can be detected and judged again, and the process is circulated until the fact is clear.
The embodiment of the application provides a claims anti-fraud system based on semantic analysis, and by introducing a Natural Language Processing (NLP) technology which analyzes, understands and processes the computational linguistics and understands and processes Natural Language information into a core through a formal computational model, one of the core research points of the computational linguistics and Natural Language information Processing research is the automatic Understanding (Language Understanding) of the Language and is brought into an insurance claims anti-fraud scene. The following advantages are mainly present with respect to the existing insurance anti-fraud system:
the cross discipline technology of computer science, psychology and linguistics is comprehensively utilized, NLP and the like are introduced into a scene of anti-fraud of claim settlement:
1. in the process of claim settlement, intervening from the stage of voice reporting, and carrying out quantitative analysis on non-word characteristics such as volume, tone, speech speed, pause, rhythm, silence and the like;
2. on the basis of analyzing nouns and pronouns by an original fraud rule system, adjectives and adverbs of a bias structure are added, and characteristics such as interword punctuations, word sequences and the like are considered, so that the dimensionality of identification of risk factors of a fraud case is increased, and the accuracy of identification is improved through the multi-dimensional risk consistency;
3. structural meaning recognition of claim text phrases, sentences, sentence groups and the like is added, parameter characteristics such as tone, speed and the like are introduced, and fraud is comprehensively analyzed and evaluated;
4. comprehensively analyzing and evaluating the results according to methods such as a decision tree and the like, generating a targeted problem through a question-answer generating system, supplementing and perfecting materials through secondary communication and verification, and determining the fact.
Fig. 2 is a block diagram of an apparatus for identifying insurance claim fraud according to an embodiment of the present application, as shown in fig. 2, the apparatus including:
the obtaining module 20 is configured to obtain voice data of an insurance claim settlement user, where the voice data is voice data of the insurance claim settlement user in an insurance claim settlement process;
a processing module 22, configured to process the voice data to obtain feature information of the voice data, where the feature information at least includes: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance of the voice data;
and the judging module 24 is used for judging whether fraud behaviors exist in the insurance claim settlement process by the insurance claim settlement user according to the characteristic information.
It should be noted that, reference may be made to the description related to the embodiment shown in fig. 1 for a preferred implementation of the embodiment shown in fig. 2, and details are not described here again.
The embodiment of the application also provides a computer readable storage medium, which comprises a stored program, wherein when the program runs, the device on which the storage medium is located is controlled to execute the above method for identifying the insurance claim fraud.
The storage medium stores a program for executing the following functions: acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data in the process of carrying out insurance claim settlement by the insurance claim settlement user; processing the voice data to obtain characteristic information of the voice data; and judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
The embodiment of the application also provides a processor which is used for running the program stored in the memory, wherein the program runs and executes the method for identifying the insurance claim fraud.
The processor is used for running a program for executing the following functions: acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data in the process of carrying out insurance claim settlement by the insurance claim settlement user; processing the voice data to obtain characteristic information of the voice data; and judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present application, 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 application 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 application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in 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 application. And the aforementioned storage medium includes: a U-disk, a Read Only Memory (ROM), a random access Memory (RDELYKM), a removable hard disk, a magnetic or optical disk, or other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method of identifying insurance claim fraud, comprising:
acquiring voice data of an insurance claim settlement user, wherein the voice data is voice data in the process of carrying out insurance claim settlement by the insurance claim settlement user;
processing the voice data to obtain feature information of the voice data, wherein the feature information at least comprises: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance forming the voice data;
and judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
2. The method of claim 1, wherein processing the voice data to obtain feature information of the voice data comprises:
analyzing at least one of the following non-word characteristics of the voice data to obtain emotional characteristic parameters of the insurance claim settlement user: the volume, tone, speed, pause times, rhythm and silent time of the insurance claim settlement user during speaking.
3. The method according to claim 2, wherein determining whether fraud is present in the insurance claim settlement process by the insurance claim settlement user according to the characteristic information comprises:
carrying out quantization processing on the emotion characteristic parameters to obtain the emotion characteristic parameters after quantization processing;
and comprehensively judging whether the insurance claim settlement user has fraud behaviors according to the emotional characteristic parameters after the quantitative processing.
4. The method of claim 2, wherein processing the voice data to obtain feature information of the voice data further comprises:
recognizing the voice data to obtain semantic text data corresponding to the voice data;
performing word splitting processing on the semantic text data to obtain the semantic features and the word order features;
analyzing the following language units of the semantic text data to obtain the structural significance of the language units: phrases, sentences, and sentence groups.
5. The method according to claim 4, wherein determining whether fraud is present in the insurance claim settlement process by the insurance claim settlement user according to the characteristic information comprises:
judging whether the voice data is the voice data after being processed deliberately or not according to the semantic features and the word sequence features;
and if so, determining that the insurance claim user may have fraud in the insurance claim settlement process.
6. The method according to claim 4, wherein determining whether fraud is present in the insurance claim settlement process by the insurance claim settlement user according to the characteristic information comprises:
judging whether the voice data is processed intentionally or not according to the structural meaning of the language unit and the emotional characteristic parameters of the insurance claim settlement user;
and if so, determining that the insurance claim user may have fraud in the insurance claim settlement process.
7. The method according to claim 6, wherein determining whether the speech data is intentionally processed speech data according to the structural meaning of the language unit comprises:
judging that adjectives or adverbs with biased structures exist in the language units;
and if the adjectives or adverbs with the bias structures exist in the language units, determining that the voice data are the voice data which are processed deliberately.
8. The method of claim 1, further comprising:
if the insurance claim settlement user is judged to have fraud behavior in the insurance claim settlement process, generating a target question by using a question-answer generating system based on the voice data;
acquiring response voice data of the insurance claim settlement user to the target problem;
processing the response voice data to obtain the characteristic information of the response voice data;
and judging whether the insurance claim user possibly having fraud has fraud or not according to the feature information of the response voice data.
9. An apparatus for identifying insurance claim fraud, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring voice data of an insurance claim settlement user, and the voice data is voice data in the insurance claim settlement process of the insurance claim settlement user;
a processing module, configured to process the voice data to obtain feature information of the voice data, where the feature information at least includes: the emotion characteristic parameters of the insurance claim settlement user, the semantic characteristics of the voice data, the word order characteristics of the voice data and the language unit structure significance forming the voice data;
and the judging module is used for judging whether the insurance claim settlement user has fraud behaviors in the insurance claim settlement process according to the characteristic information.
10. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus on which the storage medium is located to perform the method for identifying insurance claim fraud of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110061012.5A CN112800272A (en) | 2021-01-18 | 2021-01-18 | Method and device for identifying insurance claim settlement fraud behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110061012.5A CN112800272A (en) | 2021-01-18 | 2021-01-18 | Method and device for identifying insurance claim settlement fraud behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112800272A true CN112800272A (en) | 2021-05-14 |
Family
ID=75809993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110061012.5A Pending CN112800272A (en) | 2021-01-18 | 2021-01-18 | Method and device for identifying insurance claim settlement fraud behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800272A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114170030A (en) * | 2021-12-08 | 2022-03-11 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and medium for remote damage assessment of vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110015948A1 (en) * | 2009-07-20 | 2011-01-20 | Jonathan Kaleb Adams | Computer system for analyzing claims files to identify premium fraud |
| US20140058763A1 (en) * | 2012-07-24 | 2014-02-27 | Deloitte Development Llc | Fraud detection methods and systems |
| CN107680602A (en) * | 2017-08-24 | 2018-02-09 | 平安科技（深圳）有限公司 | Voice fraud recognition methods, device, terminal device and storage medium |
| CN109544324A (en) * | 2018-11-27 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Credit is counter to cheat method, system, equipment and computer readable storage medium |
| CN109558592A (en) * | 2018-11-29 | 2019-04-02 | 上海点融信息科技有限责任公司 | The method and apparatus of customer Credit Risk assessment information is obtained based on artificial intelligence |
| CN109599116A (en) * | 2018-10-08 | 2019-04-09 | 中国平安财产保险股份有限公司 | The method, apparatus and computer equipment of supervision settlement of insurance claim based on speech recognition |
| US20190130490A1 (en) * | 2017-10-26 | 2019-05-02 | CSAA Insurance Services, Inc. | Systems and Methods for Detecting a Fraudulent Claim During a Call Related to an Insurance Policy |
| US20190373105A1 (en) * | 2018-05-30 | 2019-12-05 | International Business Machines Corporation | Cognitive telephone fraud detection |
-
2021
- 2021-01-18 CN CN202110061012.5A patent/CN112800272A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110015948A1 (en) * | 2009-07-20 | 2011-01-20 | Jonathan Kaleb Adams | Computer system for analyzing claims files to identify premium fraud |
| US20140058763A1 (en) * | 2012-07-24 | 2014-02-27 | Deloitte Development Llc | Fraud detection methods and systems |
| CN107680602A (en) * | 2017-08-24 | 2018-02-09 | 平安科技（深圳）有限公司 | Voice fraud recognition methods, device, terminal device and storage medium |
| US20190130490A1 (en) * | 2017-10-26 | 2019-05-02 | CSAA Insurance Services, Inc. | Systems and Methods for Detecting a Fraudulent Claim During a Call Related to an Insurance Policy |
| US20190373105A1 (en) * | 2018-05-30 | 2019-12-05 | International Business Machines Corporation | Cognitive telephone fraud detection |
| CN109599116A (en) * | 2018-10-08 | 2019-04-09 | 中国平安财产保险股份有限公司 | The method, apparatus and computer equipment of supervision settlement of insurance claim based on speech recognition |
| CN109544324A (en) * | 2018-11-27 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Credit is counter to cheat method, system, equipment and computer readable storage medium |
| CN109558592A (en) * | 2018-11-29 | 2019-04-02 | 上海点融信息科技有限责任公司 | The method and apparatus of customer Credit Risk assessment information is obtained based on artificial intelligence |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114170030A (en) * | 2021-12-08 | 2022-03-11 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and medium for remote damage assessment of vehicle |
| CN114170030B (en) * | 2021-12-08 | 2023-09-26 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device and medium for remote damage assessment of vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Van Schijndel et al. | Single‐stage prediction models do not explain the magnitude of syntactic disambiguation difficulty | |
| Ahmed et al. | Preech: A system for {Privacy-Preserving} speech transcription | |
| WO2017067153A1 (en) | Credit risk assessment method and device based on text analysis, and storage medium | |
| US6490560B1 (en) | Method and system for non-intrusive speaker verification using behavior models | |
| US7689418B2 (en) | Method and system for non-intrusive speaker verification using behavior models | |
| Qian et al. | Towards privacy-preserving speech data publishing | |
| Sadia et al. | Modality in editorials of Pakistani English newspapers: A corpus based study | |
| Qaffas | Improvement of Chatbots semantics using wit. ai and word sequence kernel: Education Chatbot as a case study | |
| US20240119939A1 (en) | System and method for understanding and explaining spoken interactions using speech acoustic and linguistic markers | |
| KR20180120488A (en) | Classification and prediction method of customer complaints using text mining techniques | |
| An et al. | Automatically Classifying Self-Rated Personality Scores from Speech. | |
| JP2012113542A (en) | Device and method for emotion estimation, program and recording medium for the same | |
| Ehrhardt et al. | Authorship attribution analysis | |
| Wang et al. | Automatic detection of speaker state: Lexical, prosodic, and phonetic approaches to level-of-interest and intoxication classification | |
| Schmitt et al. | Towards adaptive spoken dialog systems | |
| CN112800272A (en) | Method and device for identifying insurance claim settlement fraud behavior | |
| Rodellar‐Biarge et al. | Towards the search of detection in speech‐relevant features for stress | |
| EP1470549B1 (en) | Method and system for non-intrusive speaker verification using behavior models | |
| Rubin | Identifying certainty in texts | |
| Quinn et al. | Identifying questions & requests in conversation | |
| Caines et al. | Grammatical error detection in transcriptions of spoken English | |
| CN109960807A (en) | A kind of intelligent semantic matching process based on context relation | |
| Cocioceanu et al. | Computer-based statistical description of phonetical balance for Romanian utterances | |
| Matsubara et al. | Example-based speech intention understanding and its application to in-car spoken dialogue system | |
| Köse et al. | Mining chat conversations for sex identification |
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 |