Fraud risk alerting method for long-term care insurance disability rating assessment

Abstract

The disclosure provides a fraud risk early warning method for long-term care insurance disability rating assessment, which comprises: determining to-be-analyzed data, wherein the to-be-analyzed data comprises medical record photos of a target object and assessment process audio; performing disability rating rationality assessment according to the medical record photos to obtain a first assessment result; performing reliability assessment according to the assessment process audio to obtain a second assessment result; and performing fraud risk early warning according to the first assessment result and the second assessment result. By implementing the method of the disclosure, the traditional single data audit can be upgraded to joint analysis of objective medical records and subjective assessment process, and cross verification can be performed from two aspects of content rationality and process reliability, thereby greatly improving the comprehensiveness and accuracy of fraud risk identification, and providing a more solid evidence chain foundation for subsequent risk early warning.

Description

Technical Field

[0001] This disclosure relates to the field of computer software technology, specifically to a fraud risk warning method for assessing disability levels in long-term care insurance. Background Technology

[0002] In insurance business, assessment mainly involves assessors visiting the home of the person being assessed (the applicant), conducting interviews and observations based on an assessment scale, completing the scale according to their disability status, calculating the final score, and obtaining the assessment conclusion, i.e., the disability level. To prevent insurance fraud, it is necessary to review the disability level.

[0003] In related technologies, manual review is usually used. However, with a large number of tasks to be reviewed, manual review is very inefficient. It can only conduct a very small number of random checks and cannot cover the entire volume. In addition, manual review is subject to subjective bias, making it difficult to guarantee the reliability of the review results and to provide timely warnings of fraud risks. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the purpose of this disclosure is to propose a fraud risk warning method, device, electronic device and storage medium for long-term care insurance disability level assessment, which can upgrade the traditional single data review to a joint analysis of objective medical records and subjective assessment process, and can cross-verify from the two levels of content rationality and process reliability, thereby significantly improving the comprehensiveness and accuracy of fraud risk identification and providing a more solid evidence chain foundation for subsequent risk warning.

[0006] To achieve the above objectives, the fraud risk warning method for long-term care insurance disability level assessment proposed in the first aspect of this disclosure includes:

[0007] The data to be analyzed is determined, wherein the data to be analyzed includes medical record photos of the target object and audio of the evaluation process; An assessment of the reasonableness of the disability level is conducted based on the aforementioned medical record photos to obtain a first assessment result; A reliability assessment is performed based on the audio of the assessment process to obtain a second assessment result; Based on the first assessment result and the second assessment result, a fraud risk warning is issued.

[0008] To achieve the above objectives, the fraud risk warning device for long-term care insurance disability level assessment proposed in the second aspect of this disclosure includes: The determination module is used to determine the data to be analyzed, wherein the data to be analyzed includes medical record photos of the target object and audio of the evaluation process; The first assessment module is used to assess the rationality of the disability level based on the medical record photos, so as to obtain the first assessment result; The second evaluation module is used to perform a reliability evaluation based on the audio of the evaluation process to obtain a second evaluation result; The early warning module is used to issue fraud risk warnings based on the first assessment result and the second assessment result.

[0009] The electronic device proposed in the third aspect of this disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fraud risk warning method for long-term care insurance disability level assessment as proposed in the first aspect of this disclosure.

[0010] The fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements a fraud risk warning method for long-term care insurance disability level assessment as proposed in the first aspect of this disclosure.

[0011] A fifth aspect of this disclosure provides a computer program product that, when executed by a processor, performs a fraud risk warning method for long-term care insurance disability level assessment as proposed in a first aspect of this disclosure.

[0012] This disclosure provides a fraud risk warning method, device, electronic device, and storage medium for long-term care insurance disability level assessment. The method involves identifying data to be analyzed, including photos of the target individual's medical records and audio recordings of the assessment process. A first assessment result is obtained by evaluating the reasonableness of the disability level based on the medical record photos. A second assessment result is obtained by evaluating the reliability of the assessment process audio. Finally, a fraud risk warning is issued based on both the first and second assessment results. This upgrades the traditional single-data review to a joint analysis of objective medical records and subjective assessment processes, enabling cross-verification from both the reasonableness of the content and the reliability of the process. This significantly improves the comprehensiveness and accuracy of fraud risk identification, providing a more solid evidence chain for subsequent risk warnings.

[0013] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0014] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which: Figure 1This is a flowchart illustrating a fraud risk warning method for assessing disability levels in long-term care insurance, as proposed in one embodiment of this disclosure. Figure 2 This is a flowchart illustrating a fraud risk warning method for assessing disability levels in long-term care insurance, as proposed in another embodiment of this disclosure. Figure 3 This is a flowchart illustrating a general intelligent monitoring method for fraud prevention in long-term care insurance disability level assessment, as proposed in this disclosure. Figure 4 This is a schematic diagram of system interaction in the fraud risk warning process proposed in this disclosure; Figure 5 This is a schematic diagram of the structure of a fraud risk warning device for long-term care insurance disability level assessment proposed in another embodiment of this disclosure; Figure 6 This is a block diagram of an electronic device according to an embodiment of the present application. Detailed Implementation

[0015] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0016] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0017] Figure 1 This is a flowchart illustrating a fraud risk warning method for assessing disability levels in long-term care insurance, as proposed in one embodiment of this disclosure.

[0018] It should be noted that the execution subject of the fraud risk warning method for long-term care insurance disability level assessment in this embodiment is the fraud risk warning device for long-term care insurance disability level assessment. This device can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc. For example, the terminal may be a mobile phone, a PDA, etc.

[0019] like Figure 1As shown, the fraud risk warning method for long-term care insurance disability level assessment includes: S101: Determine the data to be analyzed, which includes medical record photos of the target subject and audio recordings of the evaluation process.

[0020] Among them, the data to be analyzed may refer to insurance business data that needs to be used for fraud risk warning.

[0021] The target group can refer to the policyholder.

[0022] Among them, medical record photos can refer to case photos related to the disability level of the target subject.

[0023] The audio recording of the assessment process can refer to the audio recording of insurance agents assessing the disability level of the policyholder.

[0024] In this embodiment of the disclosure, by determining the data to be parsed, reliable data support can be provided for subsequent fraud risk warning.

[0025] S102: Conduct a rationale assessment of the disability level based on medical record photos to obtain the first assessment result.

[0026] The first assessment result can be used to indicate the degree of match between medical record photos and disability levels.

[0027] For example, in the embodiments of this disclosure, when assessing the rationality of disability level based on medical record photos, the medical record photos may be input into a pre-trained machine learning model to determine a first assessment result. Alternatively, the first assessment result may be obtained by assessing the rationality of disability level based on medical record photos using any other possible method. There are no limitations on this.

[0028] Optionally, in some embodiments, when assessing the reasonableness of disability levels based on medical record photos to obtain a first assessment result, the process may involve optical character recognition (OCR) of the medical record photos to obtain medical record information; determining the disease category of the target object from the medical record information; determining the reference disability level corresponding to the disease category from a preset relationship table; determining the comparison result between the reference disability level and the actual disability level of the target object; and determining the first assessment result based on the comparison result. This transforms disability level assessment from purely manual judgment into a quantifiable data comparison process, enabling rapid verification of the reasonableness of the actual disability level of the target object. This not only significantly improves review efficiency but also effectively screens out abnormal cases that seriously deviate from conventional medical logic, providing an objective and quantifiable preliminary judgment basis for fraud risk warning.

[0029] Medical record information may include, for example, disease diagnosis, medical history, treatment plan, and history of complications.

[0030] The preset relationship table refers to a pre-configured table used to indicate the disability level corresponding to different disease categories. The reference disability level refers to the disability level determined in the preset relationship table that corresponds to the obtained disease category. The actual disability level refers to the current disability level determined for the target object.

[0031] For example, in this embodiment of the present disclosure, when determining the first assessment result based on the comparison results, the first assessment result may be determined to be reliable when the comparison results indicate that the reference disability level is consistent with the actual disability level of the target object; when the comparison results indicate that the reference disability level is inconsistent with the actual disability level of the target object, the degree of unreliability may be determined based on the difference between the reference disability level and the actual disability level of the target object.

[0032] S103: Perform a reliability assessment based on the audio from the assessment process to obtain a second assessment result.

[0033] The second assessment result can be used to describe whether there is false information in the audio of the assessment process.

[0034] Optionally, when performing a reliability assessment based on the audio of the assessment process to obtain a second assessment result, this disclosure may input the audio of the assessment process into a pre-trained machine learning model to obtain the corresponding second assessment result.

[0035] In other words, the reliability assessment can be performed by combining the audio of the evaluation process in this embodiment, thereby providing multi-dimensional reference information for subsequent fraud risk warning.

[0036] S104: Based on the results of the first and second assessments, issue a fraud risk warning.

[0037] For example, in this embodiment of the disclosure, when a fraud risk warning is issued based on the first assessment result and the second assessment result, the fraud risk warning may be triggered when either assessment result indicates that it is unreliable.

[0038] Optionally, in some embodiments, when issuing a fraud risk warning based on the first assessment result and the second assessment result, a first warning value may be determined based on the first assessment result; a second warning value may be determined based on the second assessment result; and a fraud risk warning may be issued based on the first and second warning values. This allows the qualitative conclusions of the two dimensions—the rationality of the disability level and the reliability of the assessment process—to be transformed into superimposed and calculable quantitative scores. This quantitative fusion mechanism can construct a comprehensive risk scoring model, avoiding potential misjudgments from a single dimension, making the final fraud risk warning more scientific, accurate, and interpretable.

[0039] The first warning value and the second warning value can refer to the values ​​obtained by quantifying the first assessment result and the second assessment result, and can be used to indicate the possibility of fraud risk.

[0040] For example, in this embodiment of the present disclosure, when issuing a fraud risk warning based on a first warning value and a second warning value, the sum of the first warning value and the second warning value may be determined, and a risk warning may be triggered when the sum is greater than a preset threshold.

[0041] In this embodiment, the process involves identifying the data to be analyzed, which includes medical record photos of the target individual and audio recordings of the assessment process. A first assessment result is obtained by evaluating the reasonableness of the disability level based on the medical record photos. A second assessment result is obtained by evaluating the reliability of the assessment process audio. Finally, a fraud risk warning is issued based on both the first and second assessment results. This upgrades the traditional single-data review to a joint analysis of objective medical records and subjective assessment processes, enabling cross-verification from both the perspectives of content reasonableness and process reliability. This significantly improves the comprehensiveness and accuracy of fraud risk identification, providing a more solid evidence chain for subsequent risk warnings.

[0042] Figure 2 This is a flowchart illustrating a fraud risk warning method for assessing disability levels in long-term care insurance, as proposed in another embodiment of this disclosure.

[0043] like Figure 2 As shown, the fraud risk warning method for long-term care insurance disability level assessment includes: S201: Identify the data to be analyzed, which includes medical records photos of the target subject and audio recordings of the evaluation process.

[0044] S202: Conduct a rationale assessment of the disability level based on medical record photos to obtain the first assessment result.

[0045] For a detailed description of S201 and S202, please refer to the above embodiments, which will not be repeated here.

[0046] S203: Determine the timbre characteristics of different speakers in the audio of the evaluation process.

[0047] The speaker can refer to anyone whose voice data is present in the audio of the evaluation process, such as an insurance company employee, the policyholder, or a relative of the policyholder.

[0048] In this embodiment of the disclosure, when the timbre characteristics of different speakers in the audio of the evaluation process are determined, a reliable execution basis can be provided for the subsequent extraction of the dialogue content text corresponding to the target speaker.

[0049] S204: Transcribe the audio of the evaluation process into text based on timbre characteristics to obtain the dialogue text corresponding to the target speaker, wherein the target speaker is the target object and / or the target object's family members.

[0050] In other words, in this embodiment of the present disclosure, the audio of the evaluation process can be transcribed into text based on timbre characteristics to extract the dialogue content text corresponding to the target speaker.

[0051] S205: Conduct a reliability assessment based on the dialogue text to obtain a second assessment result.

[0052] Optionally, in some embodiments, when performing a reliability assessment based on the dialogue text to obtain a second assessment result, the content matching result between the dialogue text and the information in the medical record photograph can be determined; based on the content matching result, the second assessment result is determined. This allows for the automatic identification of discrepancies or contradictions between verbal statements at the assessment site and written medical records. This cross-comparison mechanism is a direct means of detecting information falsification or concealment. Once a content mismatch is detected, a high-risk warning can be triggered, effectively preventing fraudulent activities that rely on falsified information to pass the assessment.

[0053] Content matching results can be used to indicate whether there are discrepancies between verbal statements made at the assessment site and written medical records.

[0054] Optionally, in some embodiments, when performing a reliability assessment based on the dialogue text to obtain a second assessment result, it may also involve obtaining the contextual consistency verification result of the dialogue text; and determining the second assessment result based on the contextual consistency verification result. This allows for a deeper understanding of the semantic level, identifying logical inconsistencies, contradictions, or statements that contradict common sense in the dialogue between the target or their family members. This verification method based on semantic coherence can effectively uncover pre-rehearsed or deliberately fabricated fraudulent statements, enhancing the depth of risk assessment from the perspective of verbal logic.

[0055] Among them, the consistency check result can be used to indicate whether the target or their family members have contradicted each other during the conversation.

[0056] In other words, this embodiment of the disclosure can determine the timbre characteristics of different speakers in the audio of the evaluation process; transcribe the audio of the evaluation process into text based on the timbre characteristics to obtain the dialogue content text corresponding to the target speaker, wherein the target speaker is the target object and / or the target object's family member; and perform a reliability assessment based on the dialogue content text to obtain a second evaluation result. Thus, it is possible to accurately isolate and focus on the statements of key stakeholders, effectively eliminating voice interference from evaluators or other irrelevant personnel. This "voice identity recognition + targeted transcription" processing method ensures that the text data used for subsequent semantic analysis is highly pure and relevant, laying a solid foundation for in-depth exploration of potential risks in oral statements.

[0057] S206: Based on the results of the first and second assessments, issue a fraud risk warning.

[0058] For a detailed description of S206, please refer to the above embodiments, which will not be repeated here.

[0059] In this embodiment, the timbre characteristics of different speakers in the evaluation process audio are determined; the evaluation process audio is transcribed into text based on the timbre characteristics to obtain the dialogue text corresponding to the target speaker, where the target speaker is the target object and / or the target object's family member; a reliability assessment is performed based on the dialogue text to obtain a second evaluation result. This allows for precise isolation and focus on the statements of key stakeholders, effectively eliminating interference from the evaluator or other irrelevant personnel. This "voice identity recognition + targeted transcription" processing method ensures that the text data used for subsequent semantic analysis is highly pure and relevant, laying a solid foundation for in-depth exploration of potential risks in oral statements.

[0060] In summary, as described in the above embodiments, Figure 3 As shown, Figure 3 This is a flowchart illustrating a general intelligent monitoring method for fraud prevention in long-term care insurance disability level assessment, as proposed in this disclosure. The specific steps include: Step 01: The operator uploads photos of the medical records and audio recordings of the assessment; Step 02: The program periodically scans unanalyzed image data and automatically analyzes it; Step 03: Using high-precision OCR technology, key information in the medical record is automatically identified and extracted, including disease diagnosis, medical history, treatment plan, and history of complications.

[0061] Step 04: ① Based on the medical records of disabled individuals and historical data on disability levels, a disease and disability level comparison table was obtained. ② The system automatically identifies the correlation between different disease categories and disability levels (mild / moderate / severe, levels 1, 2, and 3) to determine whether the disability assessment rating is reasonable and whether there is a phenomenon of over-assessment for low disability. Step 05: Convert speech to text and obtain the text of the dialogue content of different people based on the voice timbre in the speech. A: Assessor B: The insured person or family member being assessed.

[0062] Step 06: Analyze the responses of the insured person or their family during the inquiry process using a large language model to determine whether there are inconsistencies or discrepancies with the medical record information, and to identify any intentional exaggeration of the degree of disability or even fraud, and issue an early warning accordingly; Step 07: Summarize the results of the intelligent analysis and issue risk warnings within the system.

[0063] like Figure 4 As shown, Figure 4 This is a schematic diagram of system interaction in the fraud risk warning process proposed in this disclosure.

[0064] Figure 5 This is a schematic diagram of the structure of a fraud risk warning device for assessing disability levels in long-term care insurance, as proposed in one embodiment of this disclosure.

[0065] like Figure 5 As shown, the fraud risk warning device 50 for long-term care insurance disability level assessment includes: The determination module 501 is used to determine the data to be analyzed, which includes medical record photos of the target object and audio of the evaluation process; The first assessment module 502 is used to assess the rationality of the disability level based on medical record photos in order to obtain the first assessment result; The second evaluation module 503 is used to perform a reliability evaluation based on the audio of the evaluation process to obtain a second evaluation result; The early warning module 504 is used to issue fraud risk warnings based on the first assessment results and the second assessment results.

[0066] It should be noted that the aforementioned explanation of the fraud risk warning method for assessing the disability level of long-term care insurance also applies to the fraud risk warning device for assessing the disability level of long-term care insurance in this embodiment, and will not be repeated here.

[0067] In this embodiment, the process involves identifying the data to be analyzed, which includes medical record photos of the target individual and audio recordings of the assessment process. A first assessment result is obtained by evaluating the reasonableness of the disability level based on the medical record photos. A second assessment result is obtained by evaluating the reliability of the assessment process audio. Finally, a fraud risk warning is issued based on both the first and second assessment results. This upgrades the traditional single-data review to a joint analysis of objective medical records and subjective assessment processes, enabling cross-verification from both the perspectives of content reasonableness and process reliability. This significantly improves the comprehensiveness and accuracy of fraud risk identification, providing a more solid evidence chain for subsequent risk warnings.

[0068] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0069] Figure 6 This is a block diagram of an electronic device according to an embodiment of the present application.

[0070] like Figure 6 As shown, the electronic device includes: The memory 601, the processor 602, and the computer instructions stored in the memory 601 and executable on the processor 602.

[0071] When the processor 602 executes instructions, it implements the fraud risk warning method for assessing the disability level of long-term care insurance provided in the above embodiments.

[0072] Furthermore, electronic devices also include: Communication interface 603 is used for communication between memory 601 and processor 602.

[0073] The memory 601 is used to store computer instructions that can be run on the processor 602.

[0074] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0075] The processor 602 is used to implement the fraud risk warning method for long-term care insurance disability level assessment in the above embodiments when executing the program.

[0076] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0077] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0078] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0079] This application also proposes a computer program product that, when executed by an instruction processor, implements the fraud risk warning method for long-term care insurance disability level assessment according to the embodiments of this application.

[0080] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0081] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0082] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0083] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0084] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0085] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0086] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0087] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A fraud risk warning method for assessing disability levels in long-term care insurance, characterized in that, include: The data to be analyzed is determined, wherein the data to be analyzed includes medical record photos of the target object and audio of the evaluation process; An assessment of the reasonableness of the disability level is conducted based on the aforementioned medical record photos to obtain a first assessment result; A reliability assessment is performed based on the audio of the assessment process to obtain a second assessment result; Based on the first assessment result and the second assessment result, a fraud risk warning is issued.

2. The method as described in claim 1, characterized in that, The assessment of the reasonableness of the disability level based on the medical record photos, to obtain a first assessment result, includes: Optical character recognition is performed on the medical record photograph to obtain medical record information; Determine the disease category of the target subject from the medical record information; Determine the reference disability level corresponding to the disease category from the preset relationship table; Determine the comparison result between the reference disability level and the actual disability level of the target object; Based on the comparison results, the first evaluation result is determined.

3. The method as described in claim 1, characterized in that, The reliability assessment based on the audio of the assessment process to obtain a second assessment result includes: Determine the timbre characteristics of different speakers in the audio of the evaluation process; Based on the timbre characteristics, the audio of the evaluation process is transcribed into text to obtain the dialogue content text corresponding to the target speaker, wherein the target speaker is the target object and / or the target object's family member; A reliability assessment is performed based on the dialogue text to obtain the second assessment result.

4. The method as described in claim 3, characterized in that, The step of performing a reliability assessment based on the dialogue content text to obtain the second assessment result includes: Determine the matching result between the dialogue text and the information in the medical record photo; Based on the content matching results, the second evaluation result is determined.

5. The method as described in claim 3, characterized in that, The step of performing a reliability assessment based on the dialogue content text to obtain the second assessment result includes: Obtain the context consistency verification result of the dialogue content text; Based on the consistency verification results of the preceding and following text, the second evaluation result is determined.

6. The method as described in claim 1, characterized in that, The step of issuing a fraud risk warning based on the first assessment result and the second assessment result includes: Based on the first assessment result, a first warning value is determined; Based on the second assessment results, a second warning value is determined; A fraud risk warning is issued based on the first warning value and the second warning value.

7. A fraud risk early warning device for assessing disability levels in long-term care insurance, characterized in that, include: The determination module is used to determine the data to be analyzed, wherein the data to be analyzed includes medical record photos of the target object and audio of the evaluation process; The first assessment module is used to assess the rationality of the disability level based on the medical record photos, so as to obtain the first assessment result; The second evaluation module is used to perform a reliability evaluation based on the audio of the evaluation process to obtain a second evaluation result; The early warning module is used to issue fraud risk warnings based on the first assessment result and the second assessment result.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images