Claim settlement method and device based on multi-modal data, computer equipment and storage medium

Abstract

The invention relates to the field of intelligent decision making, in particular to a multi-modal data-based claim settlement method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining multi-modal claim settlement data of a target user; when the multi-modal data contains non-text data, performing text conversion processing on the non-text data to obtain a claim settlement text; performing intention recognition on the claim settlement text to obtain a real intention of the target user; and when the real intention is the claim settlement intention, obtaining a claim settlement interface corresponding to the claim settlement intention. Based on the multi-mode claim data interacted between the target user and the system in real time, a claim service entrance is provided for the user, the claim process is simplified, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent decision-making, and in particular to a claims settlement method, device, computer equipment and storage medium based on multimodal data. Background Art

[0002] At present, with the rapid development of the big data era, the business data of insurance claims services is increasing day by day, making the traditional claims management service mode that mainly relies on manual review for insurance claims services too inefficient (for example, due to the lack of understanding of claims policies and processes by customers, communication during the manual review process becomes difficult, increasing customer confusion and dissatisfaction), and it is difficult to meet the claims needs of users. Therefore, a claims service is urgently needed to solve the problem of low efficiency of existing claims services. Summary of the invention

[0003] Based on this, it is necessary to provide a claims settlement method, device, computer equipment and storage medium based on multimodal data to address the above technical issues, so as to solve the problem of low efficiency of existing claims settlement services.

[0004] A claims settlement method based on multimodal data, comprising: Obtain multimodal claims data of target users; When the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; Performing intent recognition on the claim text to obtain the real intention of the target user; When the real intention is a claim settlement intention, a claim settlement interface corresponding to the claim settlement intention is obtained.

[0005] A claims settlement device based on multimodal data, comprising: Multimodal data module, used to obtain multimodal claims data of target users; A claim text module, used for, when the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; A real intention module, used to identify the intention of the claim text and obtain the real intention of the target user; The claim interface module is used to obtain a claim interface corresponding to the claim intention when the real intention is a claim intention.

[0006] A computer device comprises a memory, a processor and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned claims settlement method based on multimodal data when executing the computer-readable instructions.

[0007] One or more readable storage media storing computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to execute the claims settlement method based on multimodal data as described above.

[0008] The above-mentioned claims method, device, computer equipment and storage medium based on multimodal data, the method includes: obtaining the multimodal claims data of the target user; when the multimodal data contains non-text data, performing text conversion processing on the non-text data to obtain a claims text; performing intent recognition on the claims text to obtain the real intention of the target user; when the real intention is a claims intention, obtaining a claims interface corresponding to the claims intention. The present invention is based on multimodal claims data in which the target user interacts with the system in real time, provides users with a claims service portal, simplifies the claims process, and improves user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0010] Figure 1 is a schematic diagram of an application environment of a claims settlement method based on multimodal data in one embodiment of the present invention; Figure 2 is a flow chart of a claims settlement method based on multimodal data in one embodiment of the present invention; Figure 3 is a schematic diagram of a structure of a claims settlement device based on multimodal data in one embodiment of the present invention; Figure 4 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] The claims settlement method based on multimodal data provided in this embodiment can be applied in the following aspects: Figure 1In an application environment, a client communicates with a server. The client includes but is not limited to various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers.

[0013] In one embodiment, if Figure 2 As shown, a claims settlement method based on multimodal data is provided, and the method is applied in Figure 1 The server in the example is used as an example to illustrate the following steps: S10. Obtain multimodal claims data of target users.

[0014] Understandably, multimodal claims data refers to claims data generated by the interaction between the target user and the system, and contains claims-related data of different types of information (such as text, images, voice, and video). For example, photos of car damage submitted by users, scanned copies of medical reports, recordings or videos of accident scenes, etc. It should be understood that multimodal claims data involves various data related to claims submitted by users during the interaction process, making the information on the mobile phone more comprehensive and helping to provide claims services to target users more accurately.

[0015] S20: When the multimodal data includes non-text data, convert the non-text data into text to obtain a claim text.

[0016] It is understood that non-text data refers to data forms other than text, such as pictures, audio, video, etc. Here, non-text data includes but is not limited to photos of car damage uploaded by users, scanned copies of medical reports, recordings or videos of accident scenes, etc. Text conversion processing refers to the process of converting non-text data into text information. It should be understood that converting non-text data such as images and voice into text format allows all data to be further analyzed in a unified manner, thereby improving processing efficiency.

[0017] Optionally, the non-text data includes claim video data; the claim text includes the first video claim text; Furthermore, in step S20, the non-text data is converted into text to obtain a claim text, including: S201, performing voice character segmentation on the claim settlement video data to obtain character voice data; S202: Perform voice recognition on the character voice data to obtain the first video claim text.

[0018] Understandably, claim video data refers to video materials related to claims, including accident scene recordings, user statements, etc. For example, mobile phone videos uploaded by users. Voice role segmentation refers to the process of distinguishing the speech content of different people in the video. For example, separating the voice of each speaker in a video of a multi-person conversation. Character voice data refers to the voice clips of each character in the claim video data obtained after the claim video data is subjected to voice role segmentation. For example, a recording of the speech of a specific person A in the video. Speech recognition refers to the process of converting speech data into text data. The first video claim text refers to the text obtained by voice conversion of the claim video data. For example, the text in which the user describes the accident in the video.

[0019] Optionally, in step S201, the voice character segmentation is performed on the claim video data to obtain character voice data, including: S2011, performing video segmentation processing on the claim settlement video data to obtain a claim settlement video stream and a claim settlement audio stream; S2012. Segment the claim audio stream into voice roles to obtain the role voice data.

[0020] Understandably, through video segmentation technology, the claims video data can be decomposed into a sequence of video frames (claim video stream) and corresponding audio streams (claim audio stream). Among them, the claims video stream refers to the continuous sequence of claims video data in time; the claims audio stream refers to the audio part of the claims video data. The claims video data is divided into video and audio streams through video segmentation technology, so that each part can be processed independently, improving the flexibility and accuracy of video data processing. Voice role segmentation refers to the process of distinguishing the speech content of different people in the video. Through voiceprint recognition technology, the voices of different people in the video can be separated to obtain the voice clips of each role in the claims video data. In this way, each person's statement can be accurately identified, which helps to understand the content of the conversation in the video.

[0021] Optionally, the multimodal claim data includes claim video data; the claim text includes a second video claim text; Furthermore, in step S20, the non-text data is converted into text to obtain a claim text, including: S203, performing image content recognition on the claim video frame in the claim video stream to obtain image content text; S204: Generate the second video claim text according to the image content text and the first video claim text.

[0022] Understandably, image content recognition refers to the process of extracting text or description content from an image to obtain image content text. Image content recognition can extract useful text data from visual information, increasing the richness of claim information. In this embodiment, a second video claim text with more comprehensive information is generated by combining the image content text of the claim video data and the text obtained by voice recognition, which helps to understand and process the claim request more accurately. For example, a second video claim text is generated by combining the visible damage in the claim video data and the user's voice description.

[0023] S30: Perform intent recognition on the claim text to obtain the real intention of the target user.

[0024] Understandably, intent recognition refers to the process of determining the intent or purpose of the target user by analyzing text data. For example, determining whether the user wants to inquire about the claims process or wants to submit a claim application.

[0025] Optionally, in step S30, that is, performing intent recognition on the claim text to obtain the real intent of the target user includes: S301, identifying the claim slot of the claim text to obtain at least one claim slot; S302. Generate the real intention according to all the claim settlement slots.

[0026] Understandably, claim slots refer to key information points related to claims in the claim text, and claim slots are crucial to understanding claim requests. For example, claim slots include "accident type", "extent of damage", "claim amount", "time of accident", "location", "lost items", etc. The true intent refers to the fundamental purpose of the user's conversation or submission of data. In the claim scenario, the true intent includes "submitting claim review", "submitting claim application", "inquiring about claim progress", "routine inquiries", etc. The true intent of the user is determined by all identified claim slots. For example, if "accident type", "extent of damage" and "claim amount" are identified, it can be judged that the user's intention is to "submit a claim application".

[0027] Optionally, after step S30, that is, after performing intent recognition on the claim text to obtain the real intent of the target user, the following steps are included: S31, generating slot confirmation information according to the claim text and the claim slot, so that the target user can confirm the claim slot; S32: After the user confirms the claim slot, the real intention is updated.

[0028] Understandably, slot confirmation information refers to information generated by the system for users to confirm the accuracy of slot information. For example, when the claim slot includes "accident type" and "damage degree", slot confirmation information of "Your accident type is a car accident, right?" will be generated to further confirm the accident type. After the user confirms the slot information, the true intention is updated based on the user's feedback. For example, if the user confirms all slot information, the system can confirm that the user's intention is to submit a claim. In this way, claim requests can be processed more reliably, improving user satisfaction and claim efficiency.

[0029] S40: When the real intention is a claim settlement intention, obtain a claim settlement interface corresponding to the claim settlement intention.

[0030] Understandably, the claim interface refers to a service interface for processing claim requests, for example, a web form or API for submitting a claim application online. It should be understood that when the user's real intention is to make a claim, the system will guide the user to the corresponding claim processing process or interface. For example, if the target user's real intention is to submit a claim, an online claim form will be provided to the target user. In this way, a claim service entrance is provided to the user, which simplifies the claim process and improves the user experience.

[0031] In steps S10-S40, the multimodal claims data of the target user is obtained; when the multimodal data includes non-text data, the non-text data is converted into text to obtain a claims text; The claim text is subjected to intent recognition to obtain the target user's real intent; when the real intent is a claim intention, a claim interface corresponding to the claim intention is obtained. This embodiment provides users with a claim service portal based on multimodal claim data of real-time interaction between the target user and the system, simplifies the claim process, and improves user experience.

[0032] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0033] In one embodiment, a claims settlement device based on multimodal data is provided, and the claims settlement device based on multimodal data corresponds one-to-one to the claims settlement method based on multimodal data in the above embodiment. Figure 3 As shown, the multimodal data-based claims settlement device includes a multimodal data module 10, a claims settlement text module 20, a true intention module 30 and a claims settlement interface module 40. The functional modules are described in detail as follows: The multimodal data module 10 is used to obtain the multimodal claims data of the target user; A claim text module 20, for converting the non-text data into text when the multimodal data includes non-text data, to obtain a claim text; A real intention module 30 is used to identify the intention of the claim text to obtain the real intention of the target user; The claim settlement interface module 40 is used to obtain a claim settlement interface corresponding to the claim settlement intention when the real intention is a claim settlement intention.

[0034] Optionally, the non-text data includes claim video data; the claim text includes the first video claim text; The claim text module includes: A character voice data unit, used for performing voice character segmentation on the claim video data to obtain character voice data; The first video claim text unit is used to perform voice recognition on the character voice data to obtain the first video claim text.

[0035] Optionally, the character voice data unit includes: A segmentation unit, used for performing video segmentation processing on the claim video data to obtain a claim video stream and a claim audio stream; The role segmentation unit is used to perform voice role segmentation on the claim audio stream to obtain the role voice data.

[0036] Optionally, the multimodal claim data includes claim video data; the claim text includes a second video claim text; Furthermore, the claim text module 20 includes: An image content recognition unit, used for performing image content recognition on the claim video frame in the claim video stream to obtain image content text; The second video claim text unit is used to generate the second video claim text according to the image content text and the first video claim text.

[0037] Optionally, the real intention module 30 includes: A claim slot unit, used to identify the claim slot of the claim text to obtain at least one claim slot; The real intention unit is used to generate the real intention according to all the claim slots.

[0038] Optionally, the claims settlement device based on multimodal data further includes: A confirmation unit, configured to generate slot confirmation information according to the claim text and the claim slot, so that the target user can confirm the claim slot; An updating unit is used to update the real intention after the user confirms the claim slot.

[0039] For the specific limitations of the claims settlement device based on multimodal data, please refer to the limitations of the claims settlement method based on multimodal data above, which will not be repeated here. Each module in the above-mentioned claims settlement device based on multimodal data can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0040] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer-readable instructions and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database of the computer device is used to store data involved in a claims settlement method based on multimodal data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a claims settlement method based on multimodal data is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0041] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer-readable instructions to implement the following steps: Obtain multimodal claims data of target users; When the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; Performing intent recognition on the claim text to obtain the real intention of the target user; When the real intention is a claim settlement intention, a claim settlement interface corresponding to the claim settlement intention is obtained.

[0042] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media store computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the following steps are implemented: Obtain multimodal claims data of target users; When the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; Performing intent recognition on the claim text to obtain the real intention of the target user; When the real intention is a claim settlement intention, a claim settlement interface corresponding to the claim settlement intention is obtained.

[0043] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0044] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0045] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A claims settlement method based on multimodal data, characterized in that: include: Obtain multimodal claims data of target users; When the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; Performing intent recognition on the claim text to obtain the real intention of the target user; When the real intention is a claim settlement intention, a claim settlement interface corresponding to the claim settlement intention is obtained.

2. The claims settlement method based on multimodal data according to claim 1, characterized in that: The non-text data includes claim video data; the claim text includes the first video claim text; The text conversion process of the non-text data to obtain the claim text includes: Performing voice character segmentation on the claim video data to obtain character voice data; Perform voice recognition on the character voice data to obtain the first video claim text.

3. The claims settlement method based on multimodal data according to claim 2, characterized in that: The step of performing voice character segmentation on the claim video data to obtain character voice data includes: Performing video segmentation processing on the claim video data to obtain a claim video stream and a claim audio stream; The claim audio stream is segmented into voice roles to obtain the role voice data.

4. The claims settlement method based on multimodal data according to claim 3, characterized in that: The multimodal claim data includes claim video data; the claim text includes a second video claim text; The text conversion process of the non-text data to obtain the claim text includes: Performing image content recognition on the claim video frame in the claim video stream to obtain image content text; The second video claim text is generated according to the image content text and the first video claim text.

5. The claims settlement method based on multimodal data according to claim 1, characterized in that: The performing intention recognition on the claim text to obtain the real intention of the target user includes: Identifying a claim slot of the claim text to obtain at least one claim slot; The true intent is generated based on all the claim slots.

6. The claims settlement method based on multimodal data according to claim 5, characterized in that: After the intention of the claim text is recognized to obtain the real intention of the target user, the method includes: Generate slot confirmation information according to the claim text and the claim slot, so that the target user can confirm the claim slot; After the user confirms the claim slot, the true intention is updated.

7. A claims settlement device based on multimodal data, characterized in that: include: Multimodal data module, used to obtain multimodal claims data of target users; A claim text module, used for, when the multimodal data includes non-text data, performing text conversion processing on the non-text data to obtain a claim text; A real intention module, used to identify the intention of the claim text and obtain the real intention of the target user; The claim interface module is used to obtain a claim interface corresponding to the claim intention when the real intention is a claim intention.

8. The claims settlement device based on multimodal data according to claim 7, characterized in that: The non-text data includes claim video data; the claim text includes the first video claim text; The claim text module includes: A character voice data unit, used for performing voice character segmentation on the claim video data to obtain character voice data; The video claim text unit is used to perform voice recognition on the character voice data to obtain the first video claim text.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the claims settlement method based on multimodal data as described in any one of claims 1 to 6 is implemented.

10. One or more computer-readable storage media storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the claims settlement method based on multimodal data as described in any one of claims 1 to 6.

Images