Business linkage execution method and device based on health assessment

Abstract

The invention discloses a service linkage execution method and device based on health assessment, which can be applied to service management systems of financial science and technology, medical health care and the like, and mainly aims to solve the problem of poor linkage execution effectiveness of existing health care financial services in a complete service chain. Comprising the steps that a health assessment result of a user is acquired, and the health assessment result is obtained by dynamically assessing terminal health data, medical image data and survey text of the user based on a multi-dimensional data fusion assessment model; target service information is determined, and associated service information to be executed in a linkage manner is determined according to the key health factors of the target service information and the health assessment result; adjusting the associated service information through the processing object of the associated service information, the linkage adjustment object and the linkage adjustment model to obtain adjusted service information, and sending the adjusted service information to the user; and obtaining a user feedback result for adjusting the service information, and executing the associated service according to the user feedback result.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a business linkage execution method and apparatus based on health assessment. Background Technology

[0002] With the continuous development of fintech, the integration of financial products and technology is becoming increasingly profound. In particular, healthcare and elderly care service providers often utilize technologies such as artificial intelligence, wearable devices, and big data in financial product transactions, chronic disease management, telemedicine, or health monitoring to improve service efficiency. For example, artificial intelligence algorithms can be used for underwriting verification related to physical health status, user health assessment, and intelligent consultation.

[0003] Currently, the integration of business with artificial intelligence typically involves embedding a single business function with a single AI algorithm to obtain the processing result for each individual business function. However, since healthcare, elderly care, and financial services constitute a complete business chain, processing a single business function cannot meet the needs of handling unexpected situations or coordinated processing during business linkage. The lack of standardized processing interfaces leads to poor business interrelationships, resulting in an inability to ensure the effective linkage of different healthcare, elderly care, and financial services within the complete business chain. Summary of the Invention

[0004] In view of this, the present invention provides a business linkage execution method and apparatus based on health assessment, the main purpose of which is to solve the problem of poor linkage execution effectiveness of existing financial businesses in the complete business chain.

[0005] According to one aspect of the present invention, a business linkage execution method based on health assessment is provided, comprising:

[0006] Obtain the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model.

[0007] Identify the target business information, and determine the related business information to be executed in conjunction with the target business information based on the key health factors of the target business information and the health assessment results;

[0008] The related business information is adjusted by the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information, which is then sent to the user. The processing object includes at least one of the product object, the information object, and the evaluation object.

[0009] Obtain user feedback results on the adjusted business information, and execute related business according to the user feedback results.

[0010] Furthermore, before obtaining the user's health assessment results, the method further includes:

[0011] Acquire terminal health data, medical image data, and survey texts collected from different detection sources;

[0012] The terminal health data, the medical image data, and the survey text are preprocessed according to preset preprocessing conditions, wherein the preset preprocessing conditions are used to characterize the conditions for different processing methods of the terminal health data, the medical image data, and the survey text.

[0013] The multi-source fusion evaluation model that has been trained is retrieved, and the terminal health data, the medical image data, and the survey text are evaluated based on the multi-source fusion evaluation model to obtain the health assessment result. The multi-source fusion evaluation model is constructed based on a scorecard model, a convolutional neural network, and a decision tree network.

[0014] Furthermore, before retrieving the multi-source fusion evaluation model that has already completed model training, the method further includes:

[0015] A multi-source fusion evaluation network is constructed based on a scorecard model, a convolutional neural network, and a decision tree network, and terminal health samples, medical image samples, and survey text samples are obtained. The output layer of the multi-source fusion evaluation network is configured with multi-source dynamic weights.

[0016] The multi-source fusion evaluation network is trained based on the terminal health samples, the medical image samples, and the survey text samples to obtain the multi-source fusion evaluation model.

[0017] The multi-source dynamic weights are used to calculate the score values ​​obtained by the scorecard model, the convolutional neural network, and the decision tree network after adjusting the weight values ​​according to a preset time length.

[0018] Furthermore, the step of determining the target business information and, based on the key health factors of the target business information and the health assessment results, determining the related business information to be executed in conjunction includes:

[0019] In response to a user's business processing request, the business processing request carries multiple pieces of business information;

[0020] The target business information is determined from the business information by the business execution order and business execution conditions, and the key health factors of the target business information are determined based on the preset business health mapping relationship. The key health factors are used to characterize the health indicators that affect the target business information.

[0021] Based on the health factor relationship network, we find the associated business information corresponding to the key health factors and the health assessment results, as well as the processing objects corresponding to the associated business information. The associated business information is the associated business content that has a hierarchical relationship with the target business information. The processing objects are used to represent the objects required to execute the associated business information.

[0022] Furthermore, the step of adjusting the associated business information through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information includes:

[0023] Based on a preset adjustment strategy, the health assessment results and the corresponding linkage adjustment objects of the treatment objects are queried. The preset adjustment strategy includes the rules for determining the adjustment coefficients corresponding to different health assessment results and different treatment objects.

[0024] The related business information is adjusted by using the trained linkage adjustment model, the processing object, and the linkage adjustment object to obtain the adjusted business information.

[0025] Furthermore, the user feedback results for obtaining the adjusted business information include:

[0026] The adjusted service information is output to the user to instruct the user to confirm the adjusted service information;

[0027] When the user feedback result is a confirmation feedback, the update parameters of the multi-dimensional data fusion evaluation model are determined, and the update parameters are updated based on the adjusted business information;

[0028] When the user feedback result is rejected, the user feedback result is statistically analyzed, and an early warning is issued when the statistical value exceeds a preset statistical threshold.

[0029] Furthermore, the method also includes:

[0030] Obtain the business result of executing the associated business, and perform an on-chain operation on the business result to store the business result in the block corresponding to the target business and the user;

[0031] The associated business is verified using smart contract technology, and the verification result is fed back to the user.

[0032] According to another aspect of the present invention, a business linkage execution device based on health assessment is provided, comprising:

[0033] The acquisition module is used to acquire the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model.

[0034] The determination module is used to determine the target business information and, based on the key health factors of the target business information and the health assessment results, determine the related business information to be executed in conjunction with the target business information.

[0035] The adjustment module is used to adjust the associated business information through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information and send it to the user. The processing object includes at least one of the product object, information object, and evaluation object.

[0036] The execution module is used to obtain user feedback results of the adjusted business information and execute related business according to the user feedback results.

[0037] Furthermore, the device also includes: a processing module and an evaluation module.

[0038] The acquisition module is also used to acquire terminal health data, medical image data and survey text collected from different detection sources;

[0039] The processing module is used to preprocess the terminal health data, the medical image data, and the survey text according to preset preprocessing conditions. The preset preprocessing conditions are used to characterize the conditions for different processing methods of the terminal health data, the medical image data, and the survey text.

[0040] The evaluation module is used to retrieve the multi-source fusion evaluation model that has been trained, and to evaluate the terminal health data, the medical image data, and the survey text based on the multi-source fusion evaluation model to obtain a health evaluation result. The multi-source fusion evaluation model is constructed based on a scoring card model, a convolutional neural network, and a decision tree network.

[0041] Furthermore, the device also includes:

[0042] The construction module is used to build a multi-source fusion evaluation network based on a scoring card model, a convolutional neural network, and a decision tree network, and to acquire terminal health samples, medical image samples, and survey text samples. The output layer of the multi-source fusion evaluation network is configured with multi-source dynamic weights.

[0043] The training module is used to train the multi-source fusion evaluation network based on the terminal health samples, the medical image samples, and the survey text samples to obtain the multi-source fusion evaluation model.

[0044] The multi-source dynamic weights are used to calculate the score values ​​obtained by the scorecard model, the convolutional neural network, and the decision tree network after adjusting the weight values ​​according to a preset time length.

[0045] Further, the determining module is specifically used to respond to a user's business processing request, which carries multiple pieces of business information; determine target business information from the business information through business execution order and business execution conditions, and determine key health factors of the target business information based on a preset business health mapping relationship. The key health factors are used to characterize health indicators affecting the target business information; and search for related business information corresponding to the key health factors and the health assessment results, as well as processing objects corresponding to the related business information, in a health factor relationship network. The related business information is related business content with a hierarchical relationship with the target business information, and the processing object is used to characterize the object required to execute the related business information.

[0046] Furthermore, the adjustment module specifically queries the health assessment results and the corresponding linkage adjustment objects of the processing objects based on a preset adjustment strategy. The preset adjustment strategy includes rules for determining the adjustment coefficients corresponding to different health assessment results and different processing objects. The related business information is adjusted through the trained linkage adjustment model, the processing objects, and the linkage adjustment objects to obtain the adjusted business information.

[0047] Furthermore, the acquisition module is specifically used to output the adjusted business information to the user to instruct the user to confirm the adjusted business information; when the user feedback result is a confirmation feedback, the update parameters of the multi-dimensional data fusion evaluation model are determined, and the update parameters are updated based on the adjusted business information; when the user feedback result is a rejection feedback, the user feedback result is statistically analyzed, and an early warning is issued when the statistical value is greater than a preset statistical threshold.

[0048] Furthermore, the device also includes:

[0049] The storage module is used to obtain the business results of the execution of the related business, and to perform on-chain operation on the business results to store the business results in the block corresponding to the target business and the user; when the related business is verified through smart contract technology, the verification result is fed back to the user.

[0050] According to another aspect of the present invention, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described business linkage execution method based on health assessment.

[0051] According to another aspect of the present invention, a computer device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0052] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-mentioned business linkage execution method based on health assessment.

[0053] By employing the above-described technical solutions, the technical solutions provided by the embodiments of the present invention have at least the following advantages:

[0054] This invention provides a method and apparatus for business linkage execution based on health assessment. Compared with the prior art, the embodiments of this invention obtain the user's health assessment results, determine the target business information, and determine the related business information to be linked and executed based on the key health factors of the target business information and the health assessment results. The related business information is adjusted using the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain adjusted business information, which is then sent to the user. User feedback results of the adjusted business information are obtained, and the related business is executed according to the user feedback results. By linking multiple businesses, the correlation and execution continuity between multiple businesses are achieved, avoiding fragmented execution between businesses, thereby satisfying the effectiveness of linkage between different financial businesses in the complete business chain.

[0055] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0056] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0057] Figure 1 This invention provides a flowchart of a business linkage execution method based on health assessment, according to an embodiment of the present invention.

[0058] Figure 2 This diagram illustrates a block diagram of a business linkage execution device based on health assessment, provided by an embodiment of the present invention.

[0059] Figure 3A schematic diagram of the structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0060] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0061] Embodiments of this invention can be applied to computer systems / servers that can operate with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems, etc.

[0062] Computer systems / servers can be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0063] In one embodiment, this invention provides a business linkage execution method based on health assessment. Taking the application of this method to computer devices such as servers as an example, the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, such as medical and health care and elderly care service platforms, and financial information management systems.

[0064] This invention provides a business linkage execution method based on health assessment, such as... Figure 1 As shown, the method includes:

[0065] 101. Obtain the user's health assessment results.

[0066] In this embodiment, the current execution terminal, as the main body for business linkage execution based on health assessment, can be a terminal server or a cloud server to obtain the user's health assessment results. The health assessment results are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model. The multi-dimensional data fusion assessment model is obtained by training a machine learning algorithm. The terminal health data is data collected by wearable devices, such as blood pressure, blood oxygen, and heart rate. The medical image data is obtained by capturing images of the user using gene detection equipment or computed tomography scanners. The survey text is the answer text obtained from asking questions to the user using a questionnaire. This embodiment does not impose specific limitations on these aspects.

[0067] It should be noted that the health assessment results are predicted by a multi-dimensional data fusion assessment model configured in the blockchain. Blockchain is a data management system based on distributed ledger technology. Its core is to form an immutable chain structure by linking data blocks in chronological order, combined with cryptography to ensure security. A blockchain network is a multi-node network system built on blockchain technology. Blockchain technology is a decentralized and immutable method for processing transaction data. Blockchain technology allows multiple participants (nodes) to jointly maintain a continuously growing list of data records, called blocks. Nodes in a blockchain network generally refer to electronic devices with data processing and communication capabilities. Therefore, nodes include, but are not limited to, personal computers, servers, mobile terminals, smart wearable devices, industrial computers, and data centers. Nodes in a blockchain network, after establishing communication connections, can build the blockchain network based on specific consensus mechanisms and smart contracts. The consensus mechanism refers to the process or algorithm for reaching agreement among multiple nodes (participants) in a distributed network. Because blockchain is a decentralized data processing network, the processing is distributed across multiple nodes, each node holding a copy of the entire ledger. Therefore, the consensus mechanism ensures that all nodes can reach a consensus on updating the ledger data. A smart contract is a computer program that automatically executes, controls, or records data processing events and actions. Smart contracts can communicate, verify, and execute data processing functions in an information-based manner.

[0068] In this embodiment, after constructing a blockchain network based on smart contracts and consensus mechanisms, any node in the blockchain network (such as a user, financial institution, or medical institution) can initiate a transaction request, such as by sending cryptocurrency or calling a smart contract. The transaction data is then signed using a private key to ensure transaction security and user authentication. The signed transaction data is then broadcast across the blockchain network, allowing worker nodes to receive the transaction information and verify it. During transaction verification, worker nodes can check the validity of the signature and whether the quantity of the underlying assets in the transaction meets the requirements. Consensus mechanisms such as Proof of Work (PoW) and Proof of Stake (PoS) are then used to reach a consensus and confirm the validity of the transaction. Verified transaction data is packaged into a new block. In blockchain networks requiring puzzle-solving or consensus-building during transaction data packaging, nodes need to solve a mathematical problem or prove their right to create a new block through other mechanisms. Simultaneously, after a block is created, it can be broadcast to the entire network. At this point, nodes in the network must verify the validity of this newly created block. For example, the block can store multi-source health data from different users. By verifying the transaction data in the new block, it is ensured that they conform to the rules and protocols of the blockchain, thus ensuring security. Once the new block is verified by a majority of nodes in the network, it is added to the blockchain, indicating that the corresponding transaction data is finalized. Then, a ledger update is performed, ensuring that all nodes' ledgers are updated to include the new block information, guaranteeing that all participants have the latest ledger state. After the ledger update, the transaction is confirmed. At this point, by executing a smart contract, the relevant assets or data can be transferred based on the blockchain network. For example, if a specific block stores a decision tree model, it can call upon a block containing multi-source health data for evaluation, and listen through a smart contract to complete the entire transaction process.

[0069] 102. Determine the target business information, and determine the related business information to be executed in conjunction with the target business information based on the key health factors of the target business information and the health assessment results.

[0070] In this embodiment, the target business information is a business link or node in the complete business process. For example, in the complete business chain of insurance product transactions, claims, renewals, and health and wellness services, the target business information can be the claims business of life insurance products. This embodiment does not impose specific limitations. Furthermore, key health factors are factors used to characterize those that have a critical impact on the business. Different business information corresponds to different key health factors, including but not limited to factors such as blood sugar, nodules, and tumors. The processing object of related business information is determined by combining key health factors with health assessment results. In this case, related business information refers to related business content that has a hierarchical relationship with the target business information. For example, if the target business information is life insurance claims business, the related business information is health and wellness service business.

[0071] 103. Adjust the associated business information by using the target business information processing object, the linkage adjustment object, and the linkage adjustment model to obtain adjusted business information, and send it to the user.

[0072] In this embodiment, the processing object is used to characterize the object required to execute the target business. The processing object includes at least one of a product object, an information object, and an evaluation object. The product object can be an insurance product, a futures product, etc., the information object can be information within the business, such as the business name and duration, and the evaluation object is an object used for health assessment, such as heart rate and blood pressure. This embodiment does not impose specific limitations. After determining the processing object, the associated business information is adjusted based on this processing object to make the associated business information more suitable for the target business information, achieving a linkage processing effect between businesses. Specifically, the adjustment of the associated business information can be based on the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to achieve automatic adjustment. The linkage adjustment object is used to characterize the coefficient that needs to be linked and adjusted in order to adapt to the target business in the related business. For example, in the case of insurance renewal business as the target business and health care as the linked business, when the insurance renewal period changes, the corresponding health care period also changes. Therefore, the processing object is time, the linkage adjustment object matching is time, and the linkage adjustment model is an artificial intelligence model, including but not limited to neural networks. This application embodiment does not make specific limitations.

[0073] 104. Obtain user feedback results on the adjusted business information, and execute related business according to the user feedback results.

[0074] In an embodiment of the present application, after adjustment, the adjusted service information is output to the user so that the user can confirm the adjustment content of the associated service information to obtain the user feedback result. For example, the confirmation result or rejection result of the user, etc., so as to perform the associated service according to the user feedback result. For example, when the user confirms the adjusted service information corresponding to the adjusted associated service information, it means that the user agrees to make the corresponding adjustment. Therefore, the associated service can be performed according to the adjusted service information. The embodiment of the present application does not make specific limitations.

[0075] In another embodiment of the present application, for further limitation and explanation, before the step of obtaining the health assessment result of the user, the method further includes:

[0076] Obtain terminal health data, medical image data, and survey text collected from different detection sources;

[0077] Preprocess the terminal health data, the medical image data, and the survey text respectively according to preset preprocessing conditions;

[0078] Retrieve a multi-source fusion evaluation model that has completed model training, and evaluate the terminal health data, the medical image data, and the survey text based on the multi-source fusion evaluation model to obtain a health assessment result.

[0079] In order to perform a health assessment on the collected data based on a machine learning algorithm and thus perform linkage processing between multiple services, the current execution end first obtains terminal health data, medical image data, and survey text collected from multiple detection sources. Among them, the detection sources may include wearable devices, gene detection devices, or computed tomography scanners, questionnaires, etc., to obtain the corresponding terminal health data, medical image data, and survey text. At the same time, in order to improve the effectiveness of data processing and the accuracy of model processing, the current execution end preprocesses the terminal health data, medical image data, and survey text respectively based on preset processing conditions. At this time, the preset preprocessing conditions are used to represent the condition content of different processing methods for the terminal health data, medical image data, and survey text. For example, they include threshold conditions, pixel conditions, unit conditions, or abnormal character conditions, etc., so as to preprocess the terminal health data, medical image data, and survey text according to the preset preprocessing conditions. In some instances, when the preset processing condition is a threshold condition, the corresponding preprocessing method may be data cleaning and filtering processing. When the preset processing condition is an abnormal character condition, the corresponding preprocessing method is missing value filling. For example, the mean or median is used to fill in the missing values. The embodiment of the present application does not make specific limitations.

[0080] It should be noted that the current execution stage employs a multi-source fusion evaluation model for health assessment. This model is constructed based on a scorecard model, a convolutional neural network (CNN), and a decision tree network. The scorecard model, serving as a classification and prediction algorithm, calculates the WOE (Warning of Evidence) value after feature binning and outputs a risk score through logistic regression or linear combination. The CNN, used for image feature analysis, can incorporate data augmentation techniques, including rotation, flipping, scaling, cropping, and adding noise, to generate more diverse training samples and improve the model's generalization ability. Furthermore, using a CNN model pre-trained on a large-scale public dataset (such as ImageNet), some or all pre-trained layers can be frozen, with only the top layer fine-tuned to adapt to specific medical image tasks, reducing training data requirements and improving model performance. Finally, the decision tree network, used for text analysis, requires the automated collection of customer health history and lifestyle information via Natural Language Processing (NLP) for the survey text, serving as input parameters for the decision tree network. At this point, natural language processing technology extracts key health indicators (such as hypertension, diabetes, etc.) from the customer's answers for evaluation.

[0081] In some embodiments, the health assessment results determined by the multi-source fusion evaluation model, such as low risk, medium risk, and high risk, can generate personalized or optimized health and wellness suggestions when applied to related businesses, such as health and wellness services. These suggestions may include information such as dietary habits to help customers improve their lifestyles or seek medical attention in a timely manner.

[0082] In another embodiment of this application, to further define and illustrate, before retrieving the multi-source fusion evaluation model that has completed model training, the steps further include:

[0083] A multi-source fusion evaluation network was constructed based on a scorecard model, convolutional neural network, and decision tree network, and terminal health samples, medical image samples, and survey text samples were obtained.

[0084] The multi-source fusion evaluation network is trained based on the terminal health samples, the medical image samples, and the survey text samples to obtain the multi-source fusion evaluation model.

[0085] To ensure effective fusion and accurate evaluation of multi-source data, the current execution terminal first constructs a multi-source fusion evaluation network comprising a scorecard model, a convolutional neural network, and a decision tree network. In this configuration, the scorecard model, convolutional neural network, and decision tree network operate in parallel; each has one input in the input layer, and each network has one input. After processing, they are collectively output to the output layer. In the output layer, the multi-source fusion evaluation network incorporates dynamic weights from multiple sources. These dynamic weights are used to adjust the weight values ​​according to a preset time length before calculating the scores obtained by the scorecard model, convolutional neural network, and decision tree network. The preset time length can be a multiple of the data collection time from multiple detection sources, such as 2 or 4 times, to adjust the weight values ​​upon reaching this preset time length. This embodiment does not impose a specific limitation on this limitation. In addition, when adjusting the weight values, the configuration can be based on the execution business node. The network with the largest weight and the network with the smallest weight can be selected in sequence for adjustment. For example, if the current business is insurance renewal, the corresponding support vector and convolutional neural network weight values ​​are 0.4, and the decision tree network weight value is 0.2. If the target business is claims, the corresponding convolutional neural network and decision tree network are configured to 0.4, and the scorecard model weight value is 0.2. There are no specific limitations. At this time, the adjustment mapping relationship containing different businesses and corresponding weight value adjustments can be generated in advance. This application embodiment does not make specific limitations.

[0086] Specifically, during model training, the multi-source fusion evaluation network is trained based on terminal health samples, medical image samples, and survey text samples to obtain a multi-source fusion evaluation model. During training, different loss functions and model weights can be selected based on empirical measured values ​​for different networks; this embodiment does not impose specific limitations.

[0087] In another embodiment of this application, for further definition and explanation, the steps of determining the target business information and determining the processing object of the related business information to be executed in conjunction with the target business information based on the key health factors of the target business information and the health assessment results include:

[0088] Responding to user requests for business processing;

[0089] The target business information is determined from the business information by the business execution order and business execution conditions, and the key health factors of the target business information are determined based on the preset business health mapping relationship.

[0090] Based on the health factor relationship network, we can find the associated business information corresponding to the key health factors and the health assessment results, as well as the processing objects corresponding to the associated business information.

[0091] To achieve coordinated processing of multiple services based on health assessment, the current execution end first obtains the user's service processing request. This request carries multiple service information items to identify the target service. Specifically, the target service information is determined from the service information based on the service execution order and conditions. The execution order includes the sequential order and time sequence of multiple services. The execution conditions characterize the conditions under which the user can execute the corresponding service, including but not limited to account balance and payment duration. Then, the target service information is determined based on a pre-configured service mapping relationship, which stores the correspondence between different service execution orders and conditions and the target service. Furthermore, key health factors for the target service information are determined based on a preset service health mapping relationship. These key health factors characterize health indicators affecting the target service information. The preset service health mapping relationship stores the correspondence between different service information items and different key health factors, which can be determined through a query method; this embodiment does not impose specific limitations.

[0092] It should be noted that, since the associated business information is related to the target business information in a hierarchical manner, the current execution end pre-constructs a health factor relationship network to find the associated business information and the corresponding processing objects based on the key health factors and health assessment results. The health factor relationship network includes nodes and directional lines between nodes. Nodes represent various businesses, and directional lines represent the execution order and relationship between businesses. Key health mappings and the required health assessment value ranges are marked on each directional line, allowing the query of the corresponding associated business through the directional lines and corresponding values. Simultaneously, since the processing object represents the object required to execute the associated business information, after determining the associated business information, the processing object corresponding to the associated business information is directly retrieved from the pre-configured business layer. This includes, but is not limited to, execution parameters, business names, etc., which are not specifically limited in this embodiment.

[0093] In another embodiment of this application, for further definition and explanation, the related business information is adjusted through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information, including:

[0094] Based on the preset adjustment strategy, query the health assessment results and the corresponding linkage adjustment objects of the processing object;

[0095] The related business information is adjusted by using the trained linkage adjustment model, the processing object, and the linkage adjustment object to obtain the adjusted business information.

[0096] To achieve the goal of coordinated processing between multiple services, meet the adjustment needs of related services, and thus adapt to the execution effectiveness of related services, the current execution end queries the adjustment coefficient corresponding to the health assessment result based on a preset adjustment strategy. At this time, the preset adjustment strategy includes coordinated adjustment objects corresponding to different health assessment results and different processing objects. This strategy can be configured according to different target services and the correlation between related services; this application embodiment does not impose specific limitations. Once the value of the coordinated adjustment object is determined, the trained coordinated adjustment model and this coordinated adjustment object can be used to adjust the related service information to obtain the adjusted service information. In an insurance pricing related service scenario, the coordinated adjustment model can be a random forest model to optimize automatic premium adjustment, and the adjusted premium is used as the adjusted service information to execute the insurance pricing service. It should be noted that for different related service scenarios, artificial intelligence models can be trained for different processing objects and coordinated adjustment objects to adapt to different intelligent algorithms for adjusting related service information; this application embodiment does not impose specific limitations.

[0097] In another embodiment of this application, for further definition and explanation, the step of obtaining user feedback results for adjusting business information includes:

[0098] The adjusted service information is output to the user to instruct the user to confirm the adjusted service information;

[0099] When the user feedback result is a confirmation feedback, the update parameters of the multi-dimensional data fusion evaluation model are determined, and the update parameters are updated based on the adjusted business information;

[0100] When the user feedback result is rejected, the user feedback result is statistically analyzed, and an early warning is issued when the statistical value exceeds a preset statistical threshold.

[0101] To ensure the effectiveness of the adjusted related business information, when the current execution terminal receives user feedback, it first outputs the adjusted business information to the user to instruct the user to confirm the adjusted business information. If the received user feedback is a confirmation, it indicates that the relevant business can be executed according to the adjusted business information. Simultaneously, to ensure the effectiveness of the health assessment, update parameters for the multi-dimensional data fusion assessment model are determined. These update parameters then serve as model parameters and are updated based on the adjusted business information (e.g., increasing the weight values ​​in the model layer) to improve the accuracy of the health assessment. If the received user feedback is a rejection, the user feedback results are statistically analyzed. An alert is issued when the number of statistical occurrences exceeds a preset statistical threshold. This preset statistical threshold can be configured based on the alert precision, such as 10 times, 20 times, etc., and is not specifically limited in this embodiment.

[0102] In another embodiment of this application, for further definition and explanation, the steps also include:

[0103] Obtain the business result of executing the associated business, and perform an on-chain operation on the business result to store the business result in the block corresponding to the target business and the user;

[0104] The associated business is verified using smart contract technology, and the verification result is fed back to the user.

[0105] To ensure the security of user health data, after the current execution end performs related business, the obtained business results are then uploaded to the blockchain to store the relevant data. During the on-chain operation, to achieve multi-party collaborative security, the business results are stored in the block corresponding to the target business and the user. Simultaneously, smart contract technology is used to verify the related business. In this embodiment, after constructing a blockchain network based on smart contracts and consensus mechanisms, any node in the blockchain network (such as the user, financial institution, or medical institution) can initiate a transaction request, such as by sending cryptocurrency or calling a smart contract. The transaction data is then signed using a private key to ensure transaction security and user authentication. The signed transaction data is then broadcast across the blockchain network, allowing worker nodes in the blockchain network to receive the transaction information and verify it. During transaction verification, worker nodes in the blockchain network can check the validity of the signature and whether the quantity of the transaction's underlying assets meets the requirements. The validity of transactions is then confirmed through consensus mechanisms such as Proof of Work (PoW) and Proof of Stake (PoS). Verified transaction data is then packaged into a new block. During this packaging process, nodes in the blockchain network, which requires solving a mathematical problem or using other mechanisms to reach consensus, must prove their right to create a new block. Simultaneously, after block creation, it can be broadcast to the entire network. At this point, nodes in the network must verify the validity of the newly created block; for example, the block could store multi-source health data from different users. Verifying the transaction data in the new block ensures it conforms to the blockchain's rules and protocols, guaranteeing security. Once a new block is verified by a majority of nodes in the network, it is added to the blockchain, indicating that the corresponding transaction data is finalized. Then, a ledger update is performed, ensuring that all nodes' ledgers are updated to include the new block information, guaranteeing that all participants have the latest ledger state. Once the ledger is updated, the transaction is confirmed. At this point, by executing a smart contract, the relevant assets or data can be transferred based on the blockchain network. For example, if a decision tree model is stored in a specific block, it can be called to evaluate the block that stores multi-source health data and listen through a smart contract to complete the entire transaction process.

[0106] This invention provides a business linkage execution method based on health assessment. Compared with the prior art, this invention obtains the user's health assessment results to determine target business information, and determines related business information to be linked and executed based on the key health factors of the target business information and the health assessment results. The related business information is adjusted using the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain adjusted business information, which is then sent to the user. User feedback on the adjusted business information is obtained, and the related business is executed according to the user feedback. This linkage method enables the processing of multiple businesses, achieving correlation and execution continuity between multiple businesses, avoiding fragmented execution between businesses, and thus satisfying the effectiveness of linkage between different financial businesses in the complete business chain.

[0107] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this embodiment of the invention provides a business linkage execution device based on health assessment, such as... Figure 2 As shown, the device includes:

[0108] The acquisition module 21 is used to acquire the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data and survey text based on a multi-dimensional data fusion assessment model.

[0109] The determination module 22 is used to determine the target business information and, based on the key health factors of the target business information and the health assessment results, determine the related business information to be executed in conjunction with the target business information.

[0110] The adjustment module 23 is used to adjust the associated business information through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information and send it to the user. The processing object includes at least one of the product object, the information object, and the evaluation object.

[0111] The execution module 24 is used to obtain user feedback results of the adjusted business information and execute related business according to the user feedback results.

[0112] Furthermore, the device also includes: a processing module and an evaluation module.

[0113] The acquisition module is also used to acquire terminal health data, medical image data and survey text collected from different detection sources;

[0114] The processing module is used to preprocess the terminal health data, the medical image data, and the survey text according to preset preprocessing conditions. The preset preprocessing conditions are used to characterize the conditions for different processing methods of the terminal health data, the medical image data, and the survey text.

[0115] The evaluation module is used to retrieve the multi-source fusion evaluation model that has been trained, and to evaluate the terminal health data, the medical image data, and the survey text based on the multi-source fusion evaluation model to obtain a health evaluation result. The multi-source fusion evaluation model is constructed based on a scoring card model, a convolutional neural network, and a decision tree network.

[0116] Furthermore, the device also includes:

[0117] The construction module is used to build a multi-source fusion evaluation network based on a scoring card model, a convolutional neural network, and a decision tree network, and to acquire terminal health samples, medical image samples, and survey text samples. The output layer of the multi-source fusion evaluation network is configured with multi-source dynamic weights.

[0118] The training module is used to train the multi-source fusion evaluation network based on the terminal health samples, the medical image samples, and the survey text samples to obtain the multi-source fusion evaluation model.

[0119] The multi-source dynamic weights are used to calculate the score values ​​obtained by the scorecard model, the convolutional neural network, and the decision tree network after adjusting the weight values ​​according to a preset time length.

[0120] Further, the determining module is specifically used to respond to a user's business processing request, which carries multiple pieces of business information; determine target business information from the business information through business execution order and business execution conditions, and determine key health factors of the target business information based on a preset business health mapping relationship. The key health factors are used to characterize health indicators affecting the target business information; and search for related business information corresponding to the key health factors and the health assessment results, as well as processing objects corresponding to the related business information, in a health factor relationship network. The related business information is related business content with a hierarchical relationship with the target business information, and the processing object is used to characterize the object required to execute the related business information.

[0121] Furthermore, the adjustment module specifically queries the health assessment results and the corresponding linkage adjustment objects of the processing objects based on a preset adjustment strategy. The preset adjustment strategy includes rules for determining the adjustment coefficients corresponding to different health assessment results and different processing objects. The related business information is adjusted through the trained linkage adjustment model, the processing objects, and the linkage adjustment objects to obtain the adjusted business information.

[0122] Furthermore, the acquisition module is specifically used to output the adjusted business information to the user to instruct the user to confirm the adjusted business information; when the user feedback result is a confirmation feedback, the update parameters of the multi-dimensional data fusion evaluation model are determined, and the update parameters are updated based on the adjusted business information; when the user feedback result is a rejection feedback, the user feedback result is statistically analyzed, and an early warning is issued when the statistical value is greater than a preset statistical threshold.

[0123] Furthermore, the device also includes:

[0124] The storage module is used to obtain the business results of the execution of the related business, and to perform on-chain operation on the business results to store the business results in the block corresponding to the target business and the user; when the related business is verified through smart contract technology, the verification result is fed back to the user.

[0125] This invention provides a business linkage execution device based on health assessment. Compared with the prior art, this invention obtains the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model. It then determines target business information and, based on the key health factors of the target business information and the health assessment results, determines the processing objects for related business information. These processing objects include at least one of product objects, information objects, and assessment objects. After adjusting the related business information based on the processing objects, it obtains user feedback on the adjusted business information and executes the related business according to the user feedback. This linkage method enables the coordinated processing of multiple businesses, achieving correlation and execution continuity between multiple businesses, avoiding fragmented execution between businesses, and thus ensuring the effectiveness of linkage between different financial businesses in the complete business chain.

[0126] According to one embodiment of the present invention, a storage medium is provided, the storage medium storing at least one executable instruction, which can execute the business linkage execution method based on health assessment in any of the above method embodiments.

[0127] Figure 3The diagram illustrates a structural schematic of a computer device according to an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computer device.

[0128] like Figure 3 As shown, the computer device may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0129] The processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308.

[0130] Communication interface 304 is used to communicate with other network elements such as clients or other servers.

[0131] The processor 302 is used to execute program 310, specifically to execute the relevant steps in the above-described embodiment of the business linkage execution method based on health assessment.

[0132] Specifically, program 310 may include program code that includes computer operation instructions.

[0133] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computer device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0134] Memory 306 is used to store program 310. Memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0135] Specifically, program 310 can be used to cause processor 302 to perform the following operations:

[0136] Obtain the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model.

[0137] Identify the target business information, and determine the related business information to be executed in conjunction with the target business information based on the key health factors of the target business information and the health assessment results;

[0138] The related business information is adjusted by the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information, which is then sent to the user. The processing object includes at least one of the product object, the information object, and the evaluation object.

[0139] Obtain user feedback results on the adjusted business information, and execute related business according to the user feedback results.

[0140] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0141] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A business collaboration execution method based on health assessment, characterized in that, include: Obtain the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model. Identify the target business information, and determine the related business information to be executed in conjunction with the target business information based on the key health factors of the target business information and the health assessment results; The related business information is adjusted by the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information, which is then sent to the user. The processing object includes at least one of the product object, the information object, and the evaluation object. Obtain user feedback results on the adjusted business information, and execute related business according to the user feedback results.

2. The method according to claim 1, characterized in that, Before obtaining the user's health assessment results, the method further includes: Acquire terminal health data, medical image data, and survey texts collected from different detection sources; The terminal health data, the medical image data, and the survey text are preprocessed according to preset preprocessing conditions, wherein the preset preprocessing conditions are used to characterize the conditions for different processing methods of the terminal health data, the medical image data, and the survey text. The multi-source fusion evaluation model that has been trained is retrieved, and the terminal health data, the medical image data, and the survey text are dynamically evaluated based on the multi-source fusion evaluation model to obtain the health evaluation result. The multi-source fusion evaluation model is constructed based on the scorecard model, convolutional neural network, and decision tree network.

3. The method according to claim 2, characterized in that, Before retrieving the multi-source fusion evaluation model that has already completed model training, the method further includes: A multi-source fusion evaluation network is constructed based on a scorecard model, a convolutional neural network, and a decision tree network, and terminal health samples, medical image samples, and survey text samples are obtained. The output layer of the multi-source fusion evaluation network is configured with multi-source dynamic weights. The multi-source fusion evaluation network is trained based on the terminal health samples, the medical image samples, and the survey text samples to obtain the multi-source fusion evaluation model. The multi-source dynamic weights are used to calculate the score values ​​obtained by the scorecard model, the convolutional neural network, and the decision tree network after adjusting the weight values ​​according to a preset time length.

4. The method according to claim 1, characterized in that, The process of determining the target business information and, based on the key health factors of the target business information and the health assessment results, determining the related business information to be executed in conjunction includes: In response to a user's business processing request, the business processing request carries multiple pieces of business information; The target business information is determined from the business information by the business execution order and business execution conditions, and the key health factors of the target business information are determined based on the preset business health mapping relationship. The key health factors are used to characterize the health indicators that affect the target business information. Based on the health factor relationship network, we find the associated business information corresponding to the key health factors and the health assessment results, as well as the processing objects corresponding to the associated business information. The associated business information is the associated business content that has a business hierarchy with the target business information, and the processing object is used to represent the object required to execute the associated business information.

5. The method according to claim 1, characterized in that, The process of adjusting the associated business information through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information includes: Based on a preset adjustment strategy, the health assessment results and the corresponding linkage adjustment objects of the treatment objects are queried. The preset adjustment strategy includes the rules for determining the adjustment coefficients corresponding to different health assessment results and different treatment objects. The related business information is adjusted by using the trained linkage adjustment model, the processing object, and the linkage adjustment object to obtain the adjusted business information.

6. The method according to claim 5, characterized in that, The user feedback results for obtaining the adjusted service information include: The adjusted service information is output to the user to instruct the user to confirm the adjusted service information; When the user feedback result is a confirmation feedback, the update parameters of the multi-dimensional data fusion evaluation model are determined, and the update parameters are updated based on the adjusted business information; When the user feedback result is rejected, the user feedback result is statistically analyzed, and an early warning is issued when the statistical value exceeds a preset statistical threshold.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Obtain the business result of executing the associated business, and perform an on-chain operation on the business result to store the business result in the block corresponding to the target business and the user; The associated business is verified using smart contract technology, and the verification result is fed back to the user.

8. A business linkage execution device based on health assessment, characterized in that, include: The acquisition module is used to acquire the user's health assessment results, which are obtained by dynamically evaluating the user's terminal health data, medical image data, and survey text based on a multi-dimensional data fusion assessment model. The determination module is used to determine the target business information and, based on the key health factors of the target business information and the health assessment results, determine the related business information to be executed in conjunction with the target business information. The adjustment module is used to adjust the associated business information through the processing object of the target business information, the linkage adjustment object, and the linkage adjustment model to obtain the adjusted business information and send it to the user. The processing object includes at least one of the product object, information object, and evaluation object. The execution module is used to obtain user feedback results of the adjusted business information and execute related business according to the user feedback results.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method of claim 1.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method of claim 1.

Images