Method, system and device for generating smart city checklist based on Internet of Things

Abstract

The embodiments of this specification provide a method, system and device for generating a smart city check list based on the Internet of Things. The method is executed by a check management platform. The method for generating a smart city check list based on the Internet of Things includes: obtaining a query request through a user platform based on a service platform; obtaining associated person information based on a population information platform, and the associated person information includes target object information and relationship person information; obtaining collaborative features through a collaborative platform based on the associated person information; determining a check list corresponding to the query request based on the collaborative features; and feeding back the check list to the user through a user platform based on the service platform. The smart city check list generation system based on the Internet of Things includes a user platform, a service platform and a check management platform. The method can be implemented by a smart city check list generation device based on the Internet of Things. The method can also be run after being read by computer instructions stored in a computer-readable storage medium.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things and cloud platform, and in particular to a method, system and device for generating a smart city checklist based on Internet of Things. Background Art

[0002] With the development of information science and technology, the concept of cloud platform and its application in the Internet of Things are mentioned by more and more people. There are massive data of different users in the cloud platform and the Internet of Things. When multiple users apply for business, in order to reduce risks, relevant institutions usually need to conduct risk assessment or prediction on multiple users through massive data. How to screen out users with higher risks based on massive data so that relevant institutions can further investigate users is an urgent problem to be solved.

[0003] Therefore, it is hoped to provide a method, system and device for generating a smart city checklist based on the Internet of Things, which can better determine the checklist for further investigation. Summary of the invention

[0004] One of the embodiments of this specification provides a method for generating a smart city checklist based on the Internet of Things. The method is executed by a check management platform, including: obtaining a query request through a user platform based on a service platform; obtaining associated person information based on a population information platform, the associated person information including target object information and related person information; obtaining collaborative features through a collaborative platform based on the associated person information; determining a checklist corresponding to the query request based on the collaborative features; and feeding back the checklist to the user based on the service platform through the user platform.

[0005] One of the embodiments of this specification provides a smart city checklist generation system based on the Internet of Things. The system includes a user platform, a service platform and a check management platform, and the check management platform is configured to perform the following operations: obtain a query request through the user platform based on the service platform; obtain associated person information based on the population information platform, and the associated person information includes target object information and related person information; obtain collaborative features through the collaborative platform based on the associated person information; determine a checklist corresponding to the query request based on the collaborative features; and feed back the checklist to the user through the user platform based on the service platform.

[0006] One of the embodiments of this specification provides a smart city checklist generation device based on the Internet of Things, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the smart city checklist generation method based on the Internet of Things as described in any of the above embodiments.

[0007] One of the embodiments of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any of the above-mentioned methods for generating a smart city checklist based on the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of an application scenario of a smart city checklist generation system based on the Internet of Things according to some embodiments of this specification;

[0010] Figure 2 is an exemplary schematic diagram of a smart city checklist generation system based on the Internet of Things according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for generating a smart city checklist based on the Internet of Things according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of determining cooperative features according to some embodiments of this specification;

[0013] Figure 5 It is an exemplary schematic diagram of determining a checklist based on collaborative features according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 Schematic diagram of application scenarios of the smart city checklist generation system based on the Internet of Things according to some embodiments of this specification. Figure 1 As shown, the application scenario 100 of the smart city checklist generation system based on the Internet of Things may include one or more of a processing device 110, a network 120, a storage device 130, a user terminal 140, and the like.

[0019] In some embodiments, the processing device 110 may process information and / or data related to the application scenario 100 of the smart city checklist generation system based on the Internet of Things to perform one or more functions described in the present application. For example, the processing device 110 may obtain a query request through a user platform and obtain associated person information based on a population information platform. For another example, the processing device 110 may obtain collaborative features through a collaborative platform and determine a checklist corresponding to the query request based on the collaborative features. In some embodiments, the processing device 110 may include one or more processing engines (e.g., a single-chip processing engine or a multi-chip processing engine). By way of example only, the processing device 110 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic circuit (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0020] The network 120 can connect the various components of the system and / or connect the system with external resources. The network 120 enables the various components to communicate with each other and with other parts outside the system. For example, the user terminal 140 transmits the query request to the processing device 110 through the network 120 for processing. The processing device 110 obtains the data in the storage device 130 through the network 120. The processing device 110 processes the received query request and then sends the check list to the user terminal 140 through the network 120. In some embodiments, the network 120 can be any one or more of a wired network or a wireless network. For example, the network 120 can include a cable network, an optical fiber network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network (ZigBee), a near field communication (NFC), a bus within a device, a line within a device, a cable connection, etc. or any combination thereof. The network connection between the various parts can be one of the above methods or multiple methods. In some embodiments, the network may be of various topologies such as point-to-point, shared, centralized, etc., or a combination of multiple topologies.

[0021] The storage device 130 can be used to store data and / or instructions related to the application scenario 100 of the smart city checklist generation system based on the Internet of Things. In some embodiments, the storage device 130 can store data and / or information obtained from the processing device 110, the user terminal 140, etc. For example, the storage device 130 can store associated person information, collaborative features, etc. In some embodiments, the storage device 130 may include one or more storage components, each of which may be an independent device or a part of other devices. In some embodiments, the storage device 130 may be set in the processing device 110. In some embodiments, the storage device 130 may include a random access memory (RAM), a read-only memory (ROM), a large capacity memory, a removable memory, a volatile read-write memory, etc. or any combination thereof. Exemplarily, the large capacity storage may include a magnetic disk, an optical disk, a solid-state disk, etc. In some embodiments, the storage device 130 may be implemented on a cloud platform.

[0022] The user terminal 140 may refer to a device or other entity used by a user and related to the application scenario 100 of the smart city checklist generation system based on the Internet of Things. The user may be an individual or a collective with a query request. For example, the user may include relevant institutions (such as financial institutions, etc.), individuals, enterprises, companies, etc. In some embodiments, the user terminal 140 may also be an institution that performs the query, such as a government department, etc. For example, the user terminal 140 may be used to send a query request to the processing device 110. For another example, the user terminal 140 may receive a checklist sent by the processing device 110. In some embodiments, the user terminal 140 may be one of other devices with input and / or output functions such as a mobile device 140-1, a tablet computer 140-2, a laptop computer 140-3, a desktop computer 140-4, or any combination thereof. In some embodiments, the mobile device 140-1 may include a smart phone, a smart paging device, etc., or other smart devices. In some embodiments, the user terminal 140 may include other smart terminals, such as wearable smart terminals, etc. The above examples are only used to illustrate the wide range of the user terminal 140 device range rather than to limit its range.

[0023] It should be noted that the application scenario 100 of the smart city checklist generation system based on the Internet of Things is provided for illustrative purposes only and is not intended to limit the scope of the present application. For those of ordinary skill in the art, various modifications or variations can be made according to the description of this specification. For example, the application scenario 100 of the smart city checklist generation system based on the Internet of Things can implement similar or different functions on other devices. However, these changes and modifications will not deviate from the scope of the present application.

[0024] The IoT-based smart city checklist generation system 200 can be implemented based on an IoT system.

[0025] The Internet of Things system is an information processing system that includes some or all of the user platform, service platform, and management platform. The user platform refers to a user-oriented platform that can obtain user needs and provide information feedback to users. The service platform refers to a platform that can provide input and output services to users. The management platform can realize the overall planning and coordination of the connection and collaboration between various functional platforms, gather the information of the Internet of Things operation system, and provide perception management and control management functions for the Internet of Things operation system.

[0026] Figure 22 is a system diagram of a smart city checklist generation system based on the Internet of Things according to some embodiments of the present specification. The smart city checklist generation system 200 based on the Internet of Things may include a user platform 210, a service platform 220, and a check management platform 230. In some embodiments, the smart city checklist generation system 200 based on the Internet of Things may be a part of the processing device 110 or implemented by the processing device 110.

[0027] The user platform 210 may refer to an IoT platform that is user-oriented, obtains user needs, and feeds information back to the user. For example, the user platform 210 may obtain a query request. The user platform 210 may feed back a checklist to the user. In some embodiments, the user platform 210 may obtain user needs and feed back information to the user through a user terminal. The user platform 210 may include Figure 1 The processing device 110 and other components in.

[0028] More details about the user platform 210 can be found in Figure 3 and its description.

[0029] The service platform 220 refers to an IoT platform that can provide input and output services to users. For example, the service platform can send a checklist to the user platform.

[0030] More details about the service platform 220 can be found in Figure 3 and its description.

[0031] The verification management platform 230 may refer to an Internet of Things platform that coordinates and coordinates the connections and collaborations between various functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management for the Internet of Things operation system. For example, the verification management platform 230 may obtain a query request through a user platform based on a service platform. The verification management platform 230 may obtain associated person information based on a population information platform. The verification management platform 230 may obtain collaborative features through a collaborative platform based on associated person information. The verification management platform 230 may determine a verification list corresponding to a query request based on collaborative features. The verification management platform 230 may include Figure 1 In some embodiments, the audit management platform 230 may be a remote platform controlled by a manager, artificial intelligence, or preset rules.

[0032] More details about the verification management platform 230 can be found in Figure 3-Figure 5 and its description.

[0033] In some embodiments, the verification management platform 230 can communicate with one or more off-network cloud platforms. The verification management platform 230 can obtain relevant auxiliary data through the off-network cloud platform. In some embodiments, the one or more off-network cloud platforms can include a population information platform, a collaboration platform, etc.

[0034] The population information platform may refer to a platform that stores population information in a certain area (e.g., nationwide, global, etc.) and provides information query for associated persons. For example, the population information platform may store population information such as gender, age, place of residence, family members, etc. of a person. In some embodiments, associated person information may be obtained through the population information platform. For example, by querying an object through the population information platform, the residence information of the object may be obtained. By querying an object whose residence is the same as that of the object on the population information platform, the associated person information of the object may be obtained.

[0035] More details about the Population Information Platform can be found at Figure 3 and its description.

[0036] A collaborative platform refers to a platform that can provide assistance information for checklist generation. For example, the collaborative platform can provide collaborative information, which can be used for checklist generation. In some embodiments, the collaborative platform can obtain collaborative features based on associated person information. In some embodiments, the collaborative platform can include at least one of a social security platform and a medical insurance platform.

[0037] For more details about the collaborative platform, see Figure 3-Figure 5 and its description.

[0038] In some embodiments, the smart city checklist generation system 200 based on the Internet of Things can be applied to various scenarios of risk prediction management. In some embodiments, the smart city checklist generation system 200 based on the Internet of Things can obtain relevant data of risk prediction in various scenarios respectively to obtain risk prediction management strategies in various scenarios. For example, relevant data on anti-fraud, anti-data falsification, credit assessment, etc. In some embodiments, the smart city checklist generation system 200 based on the Internet of Things can obtain risk prediction management strategies for the entire region (such as the whole country or the world, etc.) based on the various checklist data of risk prediction in various scenarios.

[0039] The various scenarios of risk prediction management may include anti-fraud scenarios, anti-data falsification scenarios, credit assessment scenarios, etc. For example, it may include anti-fraud risk prediction management, anti-data falsification risk prediction management, credit assessment risk prediction management, etc. It should be noted that the above scenarios are only examples and do not limit the specific application scenarios of the smart city check list generation system 200 based on the Internet of Things. Those skilled in the art can apply the smart city check list generation system 200 based on the Internet of Things to any other suitable scenarios based on the content disclosed in this embodiment.

[0040] In some embodiments, the IoT-based smart city checklist generation system 200 can be applied to anti-fraud risk prediction management. When applied to anti-fraud risk prediction management, the user platform can obtain the user's anti-fraud request. For example, anti-fraud requests for multiple target objects that meet the query conditions. The user platform can send the user's anti-fraud request to the service platform. The service platform can send the user's anti-fraud request to the verification management platform. The verification management platform can obtain relevant data (such as checklists corresponding to multiple target objects) through one or more off-network cloud platforms. Based on the processing of the checklist, policies or instructions related to anti-fraud risk prediction management are made, such as the audit intensity of multiple target objects.

[0041] In some embodiments, the IoT-based smart city checklist generation system 200 can be applied to data falsification risk prediction management. When applied to data falsification risk prediction management, the user platform can obtain the user's data falsification prevention request. For example, a data falsification prevention request for multiple target objects that meet the query conditions. The user platform can send the user's data falsification prevention request to the service platform. The service platform can send the user's data falsification prevention request to the verification management platform. The verification management platform can obtain relevant data (such as checklists corresponding to multiple target objects) through one or more off-network cloud platforms. Based on the processing of the checklist, policies or instructions related to data falsification risk prediction management are made, such as whether the data of multiple target objects are falsified.

[0042] In some embodiments, the IoT-based smart city checklist generation system 200 can be applied to credit assessment risk prediction management. When applied to credit assessment risk prediction management, the user platform can obtain the user's credit assessment request. For example, a credit assessment request for multiple target objects that meet the query conditions. The user platform can send the user's credit assessment request to the service platform. The service platform can send the user's credit assessment request to the verification management platform. The verification management platform can obtain relevant data (such as a checklist corresponding to multiple target objects) through one or more off-network cloud platforms. Make policies or instructions related to credit assessment risk prediction management based on the processing of the checklist, such as the credit of multiple target objects.

[0043] In some embodiments, the smart city checklist generation system 200 based on the Internet of Things can be composed of multiple risk prediction management subsystems, each of which can be applied to a scenario. The smart city checklist generation system 200 based on the Internet of Things can comprehensively manage and process the data obtained and output by each subsystem, and then obtain relevant strategies or instructions for assisting risk prediction management.

[0044] For example, the smart city checklist generation system 200 based on the Internet of Things may include a subsystem for anti-fraud risk prediction management, a subsystem for anti-data falsification risk prediction management, and a subsystem for credit assessment risk prediction management. The smart city checklist generation system 200 based on the Internet of Things serves as the superior system of each subsystem.

[0045] The following will be described by taking the example of the smart city checklist generation system 200 based on the Internet of Things managing each subsystem and obtaining corresponding data based on the subsystem to obtain a strategy for risk prediction management:

[0046] The smart city checklist generation system 200 based on the Internet of Things can obtain a checklist of anti-fraud, etc. of the target object based on the anti-fraud risk prediction management subsystem. The subsystem based on the anti-data fraud risk prediction management obtains a checklist of anti-data fraud, etc. of the target object. The subsystem based on the credit assessment risk prediction management obtains a checklist of credit assessment, etc. of the target object. After obtaining the above risk prediction, the smart city checklist generation system 200 based on the Internet of Things summarizes the collected checklists. The check management platform makes evaluation data related to risk prediction management based on the processing of the checklist.

[0047] For example, the verification management platform can determine the audit strength of multiple target objects based on the anti-fraud data of the target objects. The verification management platform can determine whether the data of multiple target objects is falsified based on the anti-data falsification data of the target objects. The verification management platform can determine the credit of multiple target objects based on the credit evaluation data of the target objects. The verification management platform can further determine the audit strength corresponding to the multiple target objects based on the audit strength of the multiple target objects, whether the data of the multiple target objects is falsified, and the credit of the multiple target objects.

[0048] For those skilled in the art, after understanding the principle of the system, it is possible to transfer the system to any other suitable scenario without deviating from the principle.

[0049] The following will specifically illustrate the smart city check list generation system 200 based on the Internet of Things by taking the application of the smart city check list generation system 200 based on the Internet of Things in an anti-fraud risk prediction management scenario as an example.

[0050] In some embodiments, the verification management platform 230 can be configured to obtain a query request through a user platform based on a service platform. Obtain associated person information based on a population information platform, where the associated person information includes target object information and related person information. Obtain collaborative features through a collaborative platform based on the associated person information. Determine a checklist corresponding to the query request based on the collaborative features. Feedback the checklist to the user based on the service platform through a user platform.

[0051] In some embodiments, the collaboration platform may process the collaboration information of associated persons through an embedded layer to determine collaboration features.

[0052] In some embodiments, the collaborative platform may include at least one of a social security platform and a medical insurance platform. The social security platform may process the social security characteristics of the associated person through the social security embedded layer to determine the social security collaborative characteristics. The medical insurance platform may process the medical insurance characteristics of the associated person through the medical insurance embedded layer to determine the medical insurance collaborative characteristics.

[0053] In some embodiments, the social security platform can obtain the social security characteristics of the associated person through the social security knowledge graph. In some embodiments, the medical insurance platform can obtain the medical insurance characteristics of the associated person through the medical insurance knowledge graph.

[0054] In some embodiments, the social security platform can obtain the social security characteristics of the associated person through the social security knowledge graph. In some embodiments, the medical insurance platform can obtain the medical insurance characteristics of the associated person through the medical insurance knowledge graph.

[0055] In some embodiments, the verification management platform 230 may be configured to process the collaborative features based on an evaluation model to determine an evaluation value, wherein the evaluation model is a machine learning model, and determine a verification list corresponding to the query request based on the evaluation value.

[0056] In some embodiments, the input of the evaluation model may include at least one of medical insurance coordination features and social security coordination features.

[0057] In some embodiments, the verification management platform 230 may be configured to obtain an evaluation model by combining multiple embedding layers with the evaluation model through multi-party security training.

[0058] In some embodiments, the social security management platform, the medical insurance management platform, and the verification management platform can be used as one of the multiple parties to conduct collaborative training. Among them, the social security management platform can obtain the social security embedded layer. The medical insurance management platform can obtain the medical insurance embedded layer. The verification management platform can obtain the evaluation model.

[0059] It should be understood that Figure 2 The system and its platform shown can be implemented in various ways. For example, in some embodiments, the verification management platform 230 can be set in Figure 1 In the processing device 110 in.

[0060] It should be noted that the above description of the system and its components is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various components, or form a subsystem connected to other components without deviating from this principle. For example, the various components can share a storage device, or each component can have its own storage device. Such variations are all within the scope of protection of this specification.

[0061] Figure 3 is an exemplary flow chart of a method for generating a smart city checklist based on the Internet of Things according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps: In some embodiments, the process 300 may be executed by the audit management platform 230 .

[0062] Step 310: Obtain a query request through a user platform based on the service platform.

[0063] A query request may refer to information about query conditions. When a user sends a query request, he needs to provide some basic information about the query conditions. The basic information about the query conditions may include age group, gender, occupation, etc.

[0064] In some embodiments, the verification management platform 230 may obtain a query request through a user platform based on a service platform. For example, a user may input a query request through a user platform. The service platform obtains a query request input by a user through the user platform. The service platform may send the relevant query request to the verification management platform. In some embodiments, the verification management platform 230 may obtain multiple target objects that satisfy the query request based on the query request. The verification management platform may obtain information related to the target object based on multiple target objects. For example, the verification management platform may obtain associated person information based on a population information platform, and the associated person information includes target object information and related person information.

[0065] Step 320: Acquire associated person information based on the population information platform, where the associated person information includes target object information and related person information.

[0066] The associated person may include the target object and the associated person. The associated person may refer to a person who has a certain relationship with the target object. For example, the associated person is a relative of the target object, etc. The associated person information may include the target object information and the associated person information. For example, the associated person information may include the residence, relationship information, etc. of the target object and the associated person. The residence of the associated person and the target object may be the same or different. The relationship information may refer to the relationship between the associated person and the target object. For example, the relationship between the associated person and the target object may be a relative relationship (such as husband and wife, father and son, mother and daughter, brother and sister, etc.).

[0067] In some embodiments, the verification management platform 230 can obtain the associated person information through the population information platform. For example, the verification management platform can obtain multiple target objects that meet the query conditions based on the query conditions in the query request. The verification management platform can obtain the associated person information corresponding to each target object based on the multiple target objects. The verification management platform can input the query conditions (such as age group, gender, occupation, etc.) into the population information platform. The population information platform can search and query based on the above information to obtain multiple target objects that meet the query conditions, and then obtain the associated person information corresponding to each target object. Exemplarily, the population information platform can obtain the associated person with the same place of residence as each target object. The population information platform can obtain the associated person who has a kinship relationship with each target object. Through one or more associated persons, the population information platform can obtain the associated person information of each target object and the associated person. The verification management platform then obtains the associated person information through the population information platform.

[0068] Step 330: Based on the associated person information, collaborative features are obtained through the collaborative platform.

[0069] Collaborative features refer to features that can represent one or more aspects of information about the target object and the related person. For example, the multiple aspects of information may include the medical insurance information, social security information, etc. of the target object and the related person.

[0070] In some embodiments, the collaborative feature may be represented by a feature vector. The feature vector may represent the collaborative feature of a target object or a related person, etc. Different elements in the feature vector may represent relevant information of different aspects of the target object or a related person, etc.

[0071] The verification management platform can determine the credit risk of the target object through collaborative features. Collaborative features can reflect various information of the target object or related persons. For example, various information may include whether the credit card is overdue, whether social security is paid, whether there is a bad record of loan, etc. Exemplarily, the feature vector (a, b, c), the elements in the feature vector are represented by 0 or 1. 0 means no, 1 means yes. Element a indicates whether the credit card is overdue. Element b indicates whether social security is paid. Element c indicates whether there is a bad record of loan. Feature vector 1 corresponding to collaborative feature 1 of target object 1 and the related person of target object 1 is (0, 1, 0). Feature vector 1 indicates that the credit card of target object 1 and the related person of target object 1 is not overdue, social security is paid, and there is no bad record of loan. Feature vector 2 corresponding to collaborative feature 2 of target object 2 and the related person of target object 2 is (1, 1, 1). Feature vector 2 indicates that the credit card of target object 2 and the related person of target object 2 is overdue, social security is paid, and there is a bad record of loan.

[0072] In some embodiments, the collaborative features may include medical insurance collaborative features and social security collaborative features. For details on medical insurance collaborative features and social security collaborative features, please refer to Figure 4 Related description.

[0073] In some embodiments, the verification management platform 230 may obtain collaborative features through the collaborative platform based on the associated person information. For example, the verification management platform may send the associated person information to the collaborative platform through the network 120 and make a request to obtain collaborative features. The collaborative platform receives the above request and obtains the collaborative features of the target object and the associated person based on the associated person information. The collaborative platform may send the obtained collaborative features of the target object and the associated person to the verification management platform.

[0074] In some embodiments, the collaboration platform may process the collaboration information of associated persons through an embedded layer to determine collaboration features.

[0075] In some embodiments, the embedding layer may process the collaborative information of the associated person. The processed collaborative information of the associated person is transformed. Through the transformation of the embedding layer, the true value of the collaborative information of the associated person may be covered or hidden and not leaked. In some embodiments, the input of the embedding layer may include the collaborative information of the associated person. The output of the embedding layer may include collaborative features.

[0076] The collaborative information of the associated person refers to the relevant information that can reflect different aspects of the target object and the associated person. For example, the collaborative information of the associated person can reflect the social security information of the target object and the associated person, the medical insurance information of the target object and the associated person, etc.

[0077] In some embodiments, the collaboration platform may process the collaboration information of the associated persons through the embedding layer to determine the collaboration features. For example, the collaboration platform may input the collaboration information of the associated persons into the embedding layer, and the embedding layer may output the collaboration features.

[0078] In some embodiments, the verification management platform 230 can obtain different collaborative features through different collaborative platforms. The collaborative platforms can include social security platforms, medical insurance platforms, etc. The social security platform can process the social security features of the associated person through the social security embedded layer to determine the social security collaborative features. The medical insurance platform can process the medical insurance features of the associated person through the medical insurance embedded layer to determine the medical insurance collaborative features. For details on determining the social security collaborative features and the medical insurance collaborative features, see Figure 4 The related descriptions will not be repeated here.

[0079] In some embodiments of this specification, the collaborative platform processes the collaborative information of the associated persons through the embedded layer to determine the collaborative features. The relevant information of the target object and the associated persons can be changed, and the real value of the relevant information can be covered or hidden to avoid being leaked. This ensures the security and confidentiality of the relevant information of the target object and the associated persons.

[0080] Step 340 , determining a checklist corresponding to the query request based on the collaborative features.

[0081] In some embodiments, the verification management platform 230 can determine the evaluation value of each target object based on the collaborative features corresponding to the multiple target objects. The evaluation value refers to the credit risk that can reflect the target object. In some embodiments, the evaluation value can be represented by a numerical value or text. For example, the evaluation value is represented by a numerical value of 0-10. The closer the evaluation value is to 10, the higher the credit risk is and the worse the credit of the target object is. The closer the evaluation value is to 0, the lower the credit risk is and the better the credit of the target object is. For another example, the evaluation value is represented by text. The text may include low credit risk, average credit risk, high credit risk, etc. Low credit risk means that the target object has a good credit. Average credit risk means that the target object has an average credit. High credit risk means that the target object has a poor credit.

[0082] In some embodiments, the verification management platform 230 can determine the evaluation value based on the collaborative feature. For example, the collaborative feature reflects that the target object 1 and the person related to the target object 1 have good credit and no bad records. The verification management platform 230 can determine that the evaluation value of the target object 1 is low (such as the evaluation value is 2). For another example, the collaborative feature reflects that the target object 2 and one or more of the persons related to the target object 2 have poor credit and their credit cards are overdue. The verification management platform 230 can determine that the evaluation value of the target object 2 is high (such as the evaluation value is 8).

[0083] In some embodiments, the verification management platform 230 may determine an evaluation value based on collaborative features and collaborative feature thresholds. The collaborative feature threshold may refer to a threshold value on collaborative features pre-set by the verification management platform. The collaborative feature threshold may include 10 collaborative feature thresholds. Different collaborative feature thresholds may correspond to different evaluation values. For example, an evaluation value less than or equal to collaborative feature threshold 1 corresponds to 1. An evaluation value greater than collaborative threshold 1 and less than or equal to collaborative feature threshold 2 corresponds to 2. An evaluation value greater than collaborative threshold 7 and less than or equal to collaborative feature threshold 8 corresponds to 8, and so on. As described in the above example, the collaborative features of target object 1 and the person related to target object 1 are greater than collaborative feature threshold 1 and less than collaborative feature threshold 2, and the verification management platform 230 may determine that the evaluation value of target object 1 is 2.

[0084] In some embodiments, the verification management platform 230 may process the collaborative features based on the evaluation model to determine the evaluation value. The evaluation model is a machine learning model. The verification management platform 230 may determine the verification list corresponding to the query request based on the evaluation value. For details on determining the verification list corresponding to the query request based on the evaluation value, see Figure 5 The related descriptions will not be repeated here.

[0085] In some embodiments, the verification management platform 230 may determine a verification list corresponding to the query request based on the evaluation values ​​corresponding to the multiple target objects. The verification list may refer to the results of the verification of the multiple target objects that meet the query conditions. The verification management platform may sort the evaluation values ​​corresponding to each target object and generate a verification list. The sorting may be sorted according to the size of the evaluation value, for example, the smaller the evaluation value, the higher the ranking. The verification list may reflect the credit risks corresponding to the multiple target objects that meet the query conditions. The verification list may include multiple relevant information about the multiple target objects. For example, the verification list may include at least one of the evaluation value of each target object that meets the query conditions, the ranking of each target object among the multiple target objects, annotations about each target object, and reference content about the evaluation of each target object. Exemplarily, the relevant information about target object A in the verification list is the evaluation value 3, the ranking 2, the annotation that the target object has a high risk and needs to be paid special attention to, the reference content credit card overdue times 5 times, the loan bad record 1 time, etc.

[0086] Step 350: Feedback the checklist to the user through the user platform based on the service platform.

[0087] Relevant institutions can send query requests to the verification management platform. Relevant institutions can refer to institutions with query needs, such as financial institutions. Relevant institutions can determine the audit intensity of multiple target objects based on the verification list fed back by the verification management platform (the verification list includes the ranking of the evaluation values ​​corresponding to multiple target objects). For example, the audit intensity may include no audit required, normal audit, key audit, etc. Exemplarily, the verification list shows that a certain target object has a low credit risk and good credit, and the relevant institution can determine the audit intensity as no audit required. The verification list shows that a certain target object has a high credit risk and poor credit, and the relevant institution can determine the audit intensity as key audit.

[0088] In some embodiments, the relevant institutions may determine the audit intensity by presetting preset standards. For example, the preset standard is that the evaluation value in the verification list is less than or equal to 3, and the audit intensity is no audit required. The preset standard is that the evaluation value in the verification list is greater than 3 and less than or equal to 7, and the audit intensity is normal audit. The preset standard is that the evaluation value in the verification list is greater than 7 and less than or equal to 10, and the audit intensity is key audit.

[0089] In some embodiments, the verification management platform may send the verification list to the user platform through the service platform. The user platform feeds back the verification list to the user. For example, the verification management platform sends the verification list (the ranking of the evaluation values ​​of multiple target objects) to the service platform. The service platform sends the verification list to the user platform. The user platform may send the verification list to the user. The user may determine the further review intensity of the multiple target objects based on the verification list.

[0090] In some embodiments of this specification, through the massive data, the verification management platform can determine a verification list, which is more consistent with the rules of historical data. Users can determine the further review intensity of multiple target objects based on the verification list. Through the above method, it is helpful for users to understand the credit status of multiple target objects and reduce the risk of fraud. Users can save the pre-sequence analysis of massive data.

[0091] Figure 4 FIG. 1 is an exemplary schematic diagram of determining cooperative features according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps: In some embodiments, the process 400 may be executed by the audit management platform 230 .

[0092] In some embodiments, the collaborative platform 401 may include at least one of a social security platform 4011 and a medical insurance platform 4012 .

[0093] In step 410, the social security platform processes the social security characteristics of the associated person through the social security embedding layer to determine the social security collaborative characteristics.

[0094] The social security platform 4011 refers to a platform that can provide assistance information about social security. The social security platform can include social security information of people from one or more social security agencies.

[0095] In some embodiments, the social security embedding layer 412 may process the social security features 411 of the associated person. The processed social security features of the associated person are transformed. Through the transformation of the social security embedding layer, the true value of the social security features of the associated person may be covered or hidden and not leaked. In some embodiments, the input of the social security embedding layer 412 may include the social security features 411 of the associated person. The output of the social security embedding layer may include the social security collaborative features 413.

[0096] The social security characteristics 411 of the associated person refer to the characteristics that can represent the social security related information of the target object and the associated person. The social security related information may include the social security related information of the target object and the associated person. The social security related information may include the number of participating areas, the social security payment information of each participating area, etc. The number of participating areas may refer to the areas in which the target object or the associated person has participated in social security. The social security payment information of each participating area may include the total number of social security payment months, the current number of consecutive social security payment months, the payment type, the payment base, the account balance, the number of applications for low-income subsidies, the number of rejections of low-income subsidies, the existence of low-rent housing, the number of unemployment insurance collections, the amount of unemployment insurance collection, etc. The payment type may include personal payment or company payment, etc.

[0097] The social security collaborative feature 413 may refer to the social security feature after being processed by the social security embedding layer. For example, the social security feature 1 of the associated person is (3, 86, 17, A, 4000, ...). The social security feature 1 of the associated person indicates that the number of participating areas of the target object is 3. The total number of social security payment months of the target object is 86 months. The current number of consecutive social security payment months of the target object is 17 months. The payment type of the target object is Class A. The payment base of the target object is 4000, etc. The social security collaborative feature 1 corresponding to the social security feature 1 of the associated person may be (a, b, c, d, e, ...). a in the social security collaborative feature 1 indicates that the number of participating areas of the target object is 3. b indicates that the total number of social security payment months of the target object is 86 months. c indicates that the current number of consecutive social security payment months of the target object is 17 months. d indicates that the payment type of the target object is Class A. e indicates that the payment base of the target object is 4000, etc.

[0098] In some embodiments, the social security platform 241 may process the social security features 411 of the associated person through the social security embedding layer 412 to determine the social security collaborative features 413. For example, the social security platform may input the social security features of the associated person into the social security embedding layer, and the social security embedding layer may output the social security collaborative features.

[0099] For details about the training process of the social security embedding layer, please refer to Figure 5Related description.

[0100] In some embodiments, the social security platform can obtain the social security characteristics of associated persons through the social security knowledge graph.

[0101] The social security knowledge graph may reflect the relationship between multiple people and multiple social security institutions. In some embodiments, the social security knowledge graph may include nodes and edges. The edges of the social security knowledge graph may refer to the relationship between nodes. Nodes may include person nodes and social security institution nodes, etc. The node attributes of a person node may include address information, bank flow, income information, credit data, etc. The node attributes of a social security institution node may include address information, etc.

[0102] In some embodiments, the edges of the social security knowledge graph may include multiple types of edges. For example, the direct relative type, the same address type, the social security related type, etc. The direct relative type edge is an edge between people, which can reflect the relationship between people. The direct relative type edge attributes may include husband and wife, father and son, mother and daughter, brother and sister, etc. The same address type edge is also an edge between people.

[0103] For example, by querying the address information of two people A and B, it is determined that A and B have the same address. Then there is an edge between A and B called "A-same address-B". The edge of social security related type is the edge between a person and a social security agency, which can reflect the relationship between the person and the social security agency. For example, the edge of social security related type can be used to describe the social security related information of a person. The edge attributes of social security related type may include the total number of months of social security payment, the number of consecutive months of social security payment, the payment type (such as personal payment or company payment), the payment base, the account balance, the number of applications for low-income subsidies, the number of rejections of low-income subsidies, the existence of low-rent housing, the number of unemployment insurance collections, the amount of unemployment insurance collection, etc.

[0104] In some embodiments, the social security platform can obtain the social security characteristics of associated persons through the social security knowledge graph.

[0105] The social security characteristics of the associated person may include the social security characteristics of the target object and the social security characteristics of the related person. In some embodiments, the social security characteristics of the target object may be obtained through the number of insured areas of the target object, the social security payment information of each insured area, and other related information. The social security platform may determine the number of insured areas by the number of edges between the target object and the social security structure. For example, in the social security knowledge graph, there is one edge between the target object and each of the three social security structures. The social security platform may determine that the number of insured areas of the target object is three.

[0106] The social security platform can determine the social security payment information of each participating area through the attributes of the edge between the target object and the corresponding social security agency. For example, the social security platform can query the edge attributes of the target object with a neighbor degree of 1 and an edge type of social security-related type through the social security knowledge graph. The social security platform can then determine the social security payment information of each participating area corresponding to the target object.

[0107] Neighborhood refers to the distance between two nodes. For example, neighborhood can include 1, 2, 5, etc. A neighborhood of 1 means that two nodes are directly connected. For example, the target object is directly connected to a social security agency. A neighborhood of 2 means that two nodes are connected through another node. For example, the target object is A, the target object's wife is B, and the wife's brother is C. The connection method of A, B and C3 individual nodes is ABC. The neighborhood of the target object A and his wife's brother C is 2.

[0108] In some embodiments, the social security platform can input the obtained information such as the number of participating areas of the target object, the social security payment information of each participating area, etc. into the social security embedding layer. The social security embedding layer outputs the social security feature vector of the target object. The social security feature vector can represent the social security characteristics of the target object or related person.

[0109] Different elements in the social security feature vector can represent different social security related information of the target object or related person, etc. For example, in the social security feature vector (a, b, c, ...), element a can represent the number of participating areas of the target object; b can represent the social security payment information of one participating area; c can represent the social security payment information of another participating area different from b, etc.

[0110] In some embodiments, the social security platform can determine the target object's related persons through the proximity between different people and the target object. The social security characteristics of the related person can be obtained through the number of insurance regions of the target object's related person, the social security payment information of each insurance region, and other related information. For example, the social security platform can set a maximum proximity. The maximum proximity can refer to the maximum proximity between the related person and the target object. For example, the maximum proximity can be 3, 5, etc.

[0111] For example, the maximum neighbor degree is 3. The social security platform can obtain the related persons of the target object through the social security knowledge graph. The social security platform can obtain edges with a neighbor degree less than or equal to 3 and an edge type of the same type as the direct relative type or the address. The social security platform can obtain the person node connected to the edge. The person corresponding to the person node is the related person of the target object. The social security platform can obtain relevant information such as the number of participating areas, social security payment information of each participating area, etc.

[0112] In some embodiments, the social security platform can input the obtained related information such as the number of participating areas of the related person, the social security payment information of each participating area, etc. into the social security embedding layer. The social security embedding layer outputs the social security feature vector of the related person.

[0113] In some embodiments, the social security platform can obtain social security collaborative features by means of neighbor degree weighting. Neighbor degree weighting can mean that the weight of the social security related information of the relationship person connected by the edge with a larger neighbor degree value is smaller. For example, the social security platform can weight the social security feature vectors of the target object and the relationship person to determine the social security collaborative features. Exemplarily, the social security feature vector of the target object is A1, and the corresponding weight is 0.4. The social security feature vector of relationship person 1 is A2, and the neighbor degree with the target object is 1, and the corresponding weight is 0.3. The social security feature vector of relationship person 2 is A3, and the neighbor degree with the target object is 2, and the corresponding weight is 0.2. The social security feature vector of relationship person 3 is A4, and the neighbor degree with the target object is 3, and the corresponding weight is 0.1. The social security collaborative features are A1*0.4+A2*0.3+A3*0.2+A4*0.1. The social security platform can pre-set the size of the weight according to actual needs.

[0114] In some embodiments of this specification, the social security characteristics of the target object and the related person are obtained through the social security knowledge graph, and then the social security collaborative characteristics are obtained. Through the above method, the relevant social security information of the target object and the related person can be comprehensively considered from multiple aspects, eliminating the need for the user to conduct a pre-analysis of the massive data on social security, which is conducive to improving the accuracy of the subsequent verification list. By generating a verification list based on the massive data on social security, a verification list that is more consistent with the rules of historical data on social security can be obtained.

[0115] In step 420, the medical insurance platform processes the medical insurance characteristics of the associated person through the medical insurance embedding layer to determine the medical insurance coordination characteristics.

[0116] The medical insurance platform 4012 refers to a platform that can provide assistance information about medical insurance. The medical insurance platform can include medical insurance information of people from one or more medical insurance institutions.

[0117] In some embodiments, the medical insurance embedding layer 422 may process the medical insurance features 421 of the associated person. The processed medical insurance features of the associated person are transformed. Through the transformation of the medical insurance embedding layer, the true value of the medical insurance features of the associated person may be covered or hidden and not leaked. In some embodiments, the input of the medical insurance embedding layer 422 may include the medical insurance features 421 of the associated person. The output of the medical insurance embedding layer may include the medical insurance collaborative features 423.

[0118] The medical insurance feature 421 of the associated person refers to a feature that can represent the medical insurance related information of the target object and the associated person. The medical insurance related information may include the medical insurance related information of the target object and the associated person. The medical insurance related information may include the number of participating areas, the medical insurance related information of each participating area, etc. The number of participating areas may refer to the areas in which the target object or the associated person has participated in medical insurance. The medical insurance related information of each participating area may include the number of visits to the doctor, the number of serious illnesses, the severity, the number of medical insurance reimbursements, the total amount of medical insurance reimbursement, etc.

[0119] The medical insurance collaborative feature 423 may refer to the medical insurance feature processed by the medical insurance embedding layer. For example, the medical insurance feature 1 of the associated person is (2, 10, 2, 1, 5, ...). The medical insurance feature 1 of the associated person indicates that the number of insured areas of the target object is 2. The number of times the target object has visited the doctor is 10 times. The number of major illnesses of the target object is 2 times. The severity of the target object is level 1. The number of medical insurance reimbursements for the target object is 5 times, etc. The medical insurance collaborative feature 1 corresponding to the medical insurance feature 1 of the associated person may be (A, B, C, D, E, ...). A in the medical insurance collaborative feature 1 indicates that the number of insured areas of the target object is 2. B indicates that the number of times the target object has visited the doctor is 10 times. C indicates that the number of major illnesses of the target object is 2 times. D indicates that the severity of the target object is level 1. E indicates that the number of medical insurance reimbursements for the target object is 5 times, etc.

[0120] In some embodiments, the medical insurance platform 4012 may process the medical insurance features 421 of the associated person through the medical insurance embedding layer 422 to determine the medical insurance collaborative features 423. For example, the medical insurance platform may input the medical insurance features of the associated person into the medical insurance embedding layer, and the medical insurance embedding layer may output the medical insurance collaborative features.

[0121] For details about the training process of the medical insurance embedding layer, please refer to Figure 5 Related description.

[0122] In some embodiments, the medical insurance platform can obtain the medical insurance characteristics of associated persons through the medical insurance knowledge graph.

[0123] The medical insurance knowledge graph may reflect the relationship between multiple people and multiple medical insurance institutions. In some embodiments, the medical insurance knowledge graph may include nodes and edges. The edges of the medical insurance knowledge graph may refer to the relationship between nodes. Nodes may include person nodes and medical insurance institution nodes, etc. The node attributes of a person node may include address information, bank flow, income information, credit data, etc. The node attributes of a medical insurance institution node may include address information, etc.

[0124] In some embodiments, the edges of the medical insurance knowledge graph may include multiple types of edges. For example, the type of direct relatives, the type of the same address, the type related to medical insurance, etc. The edge of the medical insurance related type is the edge between a person and a medical insurance institution, which can reflect the relationship between the person and the medical insurance institution. For example, the edge of the medical insurance related type can be used to describe the medical insurance related information of a person. The edge attributes of the medical insurance related type may include the number of visits to the doctor, the number of major illnesses, the severity, the number of medical insurance reimbursements, the total amount of medical insurance reimbursement, etc. Regarding the type of direct relatives and the type of the same address, please refer to the relevant description in step 410 for details.

[0125] In some embodiments, the medical insurance platform can obtain the medical insurance characteristics of associated persons through the medical insurance knowledge graph.

[0126] The medical insurance characteristics of the associated person may include the medical insurance characteristics of the target object and the medical insurance characteristics of the related person. In some embodiments, the medical insurance characteristics of the target object can be obtained through the number of insured areas of the target object, the medical insurance related information of each insured area, etc. The medical insurance platform can determine the number of insured areas by the number of edges between the target object and the medical insurance structure. The medical insurance platform can determine the medical insurance related information of each insured area by the attributes of the edge between the target object and the corresponding medical insurance institution. For example, the medical insurance platform can query the edge attributes of the target object with a neighbor degree of 1 and an edge type of a medical insurance related type through the medical insurance knowledge graph. The medical insurance platform can further determine the medical insurance related information of each insured area corresponding to the target object.

[0127] In some embodiments, the medical insurance platform can input the acquired number of participating regions of the target object, medical insurance related information of each participating region, etc. into the medical insurance embedding layer. The medical insurance embedding layer outputs the medical insurance feature vector of the target object.

[0128] In some embodiments, the medical insurance platform can determine the target object's related persons through the proximity of different people to the target object. The medical insurance characteristics of the related persons can be obtained through the number of insured areas of the target object's related persons, the medical insurance related information of each insured area, etc.

[0129] In some embodiments, the medical insurance platform can input the acquired number of participating areas of the related person, relevant information of each participating area, etc. into the medical insurance embedding layer. The medical insurance embedding layer outputs the medical insurance feature vector of the related person.

[0130] In some embodiments, the medical insurance platform can obtain the medical insurance collaborative feature by neighbor degree weighting. The acquisition of medical insurance collaborative features is similar to the acquisition of social security collaborative features. The only difference is that the acquisition of medical insurance collaborative features is that the medical insurance platform performs neighbor degree weighting on the medical insurance feature vector. The acquisition of social security collaborative features is that the social security platform performs neighbor degree weighting on the social security feature vector. Therefore, for more information about obtaining medical insurance collaborative features, please refer to the acquisition of social security collaborative features, which will not be repeated here.

[0131] In some embodiments of this specification, the medical insurance characteristics of the target object and the related person are obtained through the medical insurance knowledge graph, and then the medical insurance collaborative characteristics are obtained. Through the above method, the relevant medical insurance information of the target object and the related person can be comprehensively considered from multiple aspects, eliminating the user's pre-analysis of massive data on medical insurance, which is conducive to improving the accuracy of the subsequent verification list. By generating a verification list based on massive data on medical insurance, a verification list that is more consistent with the rules of historical data on medical insurance can be obtained.

[0132] In some embodiments of this specification, different collaborative platforms process different features of associated persons through different embedding layers to determine different collaborative features. The relevant information of target objects and associated persons corresponding to different collaborative platforms can be changed, and the real value of the relevant information is covered or hidden to avoid being leaked, thereby ensuring the security and confidentiality of the relevant information of target objects and associated persons.

[0133] Figure 5 FIG. 1 is an exemplary schematic diagram of determining a checklist based on collaborative features according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following steps: In some embodiments, the process 500 may be executed by the audit management platform 230 .

[0134] Step 510, processing the collaborative features based on the evaluation model to determine the evaluation value 530, the evaluation model is a machine learning model.

[0135] In some embodiments, the audit management platform 230 may process the collaborative feature 511 based on the evaluation model 512 to determine the evaluation value 513 .

[0136] Evaluation model 512 refers to a model that can determine the evaluation value of the target object. In some embodiments, the evaluation model can be a machine learning model. In some embodiments, the type of evaluation model can include a neural network model, a deep neural network, etc., and the choice of model type can be determined according to the specific situation.

[0137] In some embodiments, the input of the evaluation model may include one or more collaborative features. The output of the evaluation model may include an evaluation value of the target object. For example, the evaluation value of the target object is determined based on the evaluation model processing one or more collaborative features.

[0138] In some embodiments, the verification management platform 230 may input multiple collaborative features of the target object and the related person into the evaluation model. The evaluation model processes the multiple collaborative features and outputs the evaluation value of the target object. The verification management platform 230 obtains the evaluation value of the target object output by the evaluation model.

[0139] In some embodiments, the input of the evaluation model may also include at least one of the social security collaborative feature 413 and the medical insurance collaborative feature 423. For details about the social security collaborative feature and the medical insurance collaborative feature, please refer to Figure 4 Related description.

[0140] In some embodiments, the verification management platform 230 may input the medical insurance collaborative features and / or social insurance collaborative features of the target object and the related person into the evaluation model. The evaluation model processes the medical insurance collaborative features and / or social insurance collaborative features and outputs the evaluation value of the target object. The verification management platform 230 obtains the evaluation value of the target object output by the evaluation model.

[0141] In some embodiments of the present specification, the verification management platform 230 determines the evaluation value of the target object through the evaluation model. The verification management platform 230 can comprehensively consider the relevant conditions of the medical insurance and / or social insurance of the target object and the related person, which is conducive to improving the accuracy of the evaluation value of the target object.

[0142] In some embodiments, the evaluation model may be trained based on multiple sets of training samples and labels.

[0143] In some embodiments, the training sample includes multiple groups of sample collaborative features. The label is the sample evaluation value of the target object. The training sample can be obtained based on historical data. For example, the verification management platform can use the collaborative features of a target object in the historical data and the collaborative features of the target object's related persons as a group of sample collaborative features. The historical data includes multiple target objects. Each target object has its own corresponding collaborative features of the target object and the collaborative features of the target object's related persons. The verification management platform can obtain multiple groups of sample collaborative features. The label of the training sample can be determined by manual labeling or automatic labeling. For example, the verification management platform can mark the actual evaluation value of the target object as the label of the training sample.

[0144] In some embodiments, the evaluation model can be obtained by combining multiple embedding layers with the evaluation model through multi-party security training.

[0145] The multiple embedding layers may refer to respective embedding layers of multiple collaborative platforms. Joint multi-party security training refers to the training of the evaluation model by multiple participants.

[0146] In some embodiments, the verification management platform can obtain collaborative features through multiple collaborative platforms. Multiple collaborative platforms can process different features of target objects and related persons through their respective embedded layers to determine different collaborative features. In some embodiments, the verification management platform can obtain an evaluation model through multiple embedded layers and combined multi-party security training with the evaluation model.

[0147] In some embodiments, the evaluation model may be trained based on multiple sets of training samples and labels.

[0148] In some embodiments, the training sample includes multiple groups of sample collaborative features. The label is the sample evaluation value of the target object. The training sample can be obtained through the data of multiple different people. For example, the verification management platform can obtain the data of multiple people. The multiple people can include people with no fraud records, people with fraud records, etc. The verification management platform can determine the above different people as multiple sample target objects. The verification management platform can send the information of the multiple sample target objects to multiple different collaborative platforms.

[0149] Different collaborative platforms obtain collaborative features of different aspects of sample target objects and persons related to sample target objects through their corresponding embedding layers. For example, the medical insurance platform obtains medical insurance collaborative features. Different collaborative platforms send the acquired collaborative features of different aspects of sample target objects and persons related to sample target objects to the verification management platform.

[0150] The verification management platform can use the collaborative features of a sample target object and the person related to the sample target object as a set of sample collaborative features. Each sample target object has its own corresponding collaborative features of the sample target object and the collaborative features of the person related to the sample target object. The verification management platform can obtain multiple sets of sample collaborative features.

[0151] The labels of training samples can be determined by manual labeling or automatic labeling. For example, the verification management platform can manually label based on other information of the sample target object and its related persons. Exemplarily, for sample target objects and their related persons with no fraud records, the verification management platform can mark the labels of the training samples corresponding to the sample target objects as normal values. For sample target objects and their related persons with fraud records, the verification management platform can mark the labels of the training samples corresponding to the sample target objects as higher evaluation values. For sample target objects and their related persons who have performed heroic acts and / or have been commended, the verification management platform can mark the labels of the training samples corresponding to the sample target objects as very low evaluation values.

[0152] In some embodiments of the present specification, through multi-party security training, it can be ensured that different information of the target object and the related person is not leaked, and the security of the information of the target object and the related person can be ensured.

[0153] In some embodiments, the social security management platform, the medical insurance management platform, and the verification management platform can be used as one of the multiple parties to conduct collaborative training. The social security management platform can obtain the social security embedding layer. The medical insurance management platform can obtain the medical insurance embedding layer. The verification management platform can obtain the evaluation model. For details about the social security embedding layer and the medical insurance embedding layer, please refer to Figure 4 Related description.

[0154] Multiple parties can refer to the management platforms corresponding to multiple collaborative platforms. For example, the management platform corresponding to the social security collaborative platform is the social security management platform. For another example, the management platform corresponding to the medical insurance platform is the medical insurance management platform.

[0155] The social security management platform can refer to an IoT platform that manages multiple social security institutions in a coordinated manner. The medical insurance management platform can refer to an IoT platform that manages multiple medical insurance institutions in a coordinated manner.

[0156] Collaborative training can refer to multiple management platforms working together to train. Through collaborative training, different management platforms can obtain their own models. For example, the social security management platform can obtain the social security embedding layer. The medical insurance management platform can obtain the medical insurance embedding layer. The verification management platform can obtain the evaluation model.

[0157] In some embodiments, a social security embedding layer, a medical insurance embedding layer and an evaluation model can be obtained based on multiple groups of training samples and label training.

[0158] In some embodiments, the training samples include multiple groups of sample target objects and related persons of the sample target objects. The labels are sample evaluation values ​​of the target objects. The training samples can be obtained through data of multiple different persons. For example, the verification management platform can obtain data of multiple persons. The verification management platform can determine the above different persons as multiple sample target objects.

[0159] The verification management platform can send the information of multiple sample target objects to the social security management platform and the medical insurance management platform. The social security embedding layer can obtain the social security collaborative characteristics of the sample target objects and the social security collaborative characteristics of the sample target objects' related persons based on the information of the sample target objects. The medical insurance embedding layer can obtain the medical insurance collaborative characteristics of the sample target objects and the social security collaborative characteristics of the sample target objects' related persons based on the information of the sample target objects.

[0160] The verification management platform can treat the same sample target object and the related person of the sample target object as a group of sample target objects and the related persons of the sample target object. Each sample target object has its own corresponding related person of the sample target object. The verification management platform can obtain multiple groups of sample target objects and the related persons of the sample target objects.

[0161] In some embodiments, different collaborative platforms send the acquired collaborative features of different aspects of sample target objects and persons related to the sample target objects to the verification management platform. The verification management platform can input the collaborative features of the sample target objects and persons related to the sample target objects into the evaluation model. The labels of the training samples can be determined by manual or automatic labeling.

[0162] The training of the social security embedding layer, the medical insurance embedding layer, and the evaluation model may include one or more iterative updates. Each iterative update may include updating the model parameters of the social security embedding layer, the medical insurance embedding layer, and the evaluation model based on the training samples. The social security embedding layer with updated parameters may obtain updated social security collaborative features. The medical insurance embedding layer with updated parameters may obtain updated medical insurance collaborative features. The evaluation model with updated parameters may obtain updated evaluation values.

[0163] In some embodiments, the optimization objectives of the social security embedding layer, the medical insurance embedding layer, and the evaluation model training may include adjusting the model parameters so that the value of the corresponding loss function becomes smaller. The loss function can be used to characterize the difference between the evaluation value predicted by the model and the sample evaluation value. In some embodiments, when the social security embedding layer, the medical insurance embedding layer, and the evaluation model meet the termination conditions in a certain iterative update, the training can be stopped. For example, when the difference between the evaluation value predicted by the model and the sample evaluation value is less than a preset threshold, the training is stopped. The social security management platform can obtain the social security embedding layer. The medical insurance management platform can obtain the medical insurance embedding layer. The verification management platform can obtain the evaluation model.

[0164] In some embodiments of the present specification, different management platforms can obtain different corresponding models through multi-party collaborative training, which is conducive to further improving the accuracy of subsequent verification lists.

[0165] Step 520: Determine a checklist corresponding to the query request based on the evaluation value.

[0166] In some embodiments, the verification management platform 230 may determine the evaluation value corresponding to each target object based on the evaluation model. The verification management platform may sort the evaluation values ​​corresponding to each target object and generate a verification list corresponding to the query request. For example, the verification management platform may sort the evaluation values ​​from small to large to generate a verification list based on the size of the evaluation values. The verification management platform then obtains the verification list sorted from small to large in the evaluation value, and the verification list corresponds to the query request of the user.

[0167] In some embodiments of the present specification, by determining the evaluation value through the evaluation model, and determining the checklist corresponding to the query request based on the evaluation value, the accuracy of the evaluation value of the target object can be improved, and the accuracy of the checklist can be further ensured. By generating a checklist with massive data on social security and / or medical insurance, a checklist that is more consistent with the rules of historical data on social security and / or medical insurance can be obtained.

[0168] It should be noted that the above description of the relevant processes is only for example and explanation, and does not limit the various modifications and changes of this specification. However, these modifications and changes are still within the scope of this specification.

[0169] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0170] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0171] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0172] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0173] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0174] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0175] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for generating a smart city checklist based on the Internet of Things, characterized in that: The method is executed by a verification management platform, and the method includes: Obtaining query requests through the user platform based on the service platform; Acquire associated person information based on the population information platform, wherein the associated person information includes target object information and related person information; Based on the associated person information, a collaborative feature is obtained through a collaborative platform, wherein the collaborative feature includes a social security collaborative feature and a medical insurance collaborative feature; the collaborative platform includes at least one of a social security platform and a medical insurance platform, including: The social security platform processes the social security characteristics of the associated person through the social security embedding layer to determine the social security collaborative characteristics. The social security characteristics of the associated person are obtained through the social security knowledge graph. The social security knowledge graph includes nodes and edges. The nodes include person nodes and social security agency nodes. The node attributes of the person nodes include address information, bank flow, income information and credit data. The node attributes of the social security agency nodes include address information. The edges of the social security knowledge graph include multiple types of edges. The types of edges of the social security knowledge graph include direct relative type, same address type and social security related type. The social security characteristics of the associated person include the social security characteristics of the target object and the social security characteristics of the related person. The social security platform determines the related person of the target object through the neighbor degree of different people with the target object. The social security characteristics of the target object or the social security characteristics of the related person are respectively obtained through the number of insured areas of the target object or the related person of the target object and the social security payment information of each insured area. The social security platform determines the number of insured areas through the number of edges between the target object or the related person and the social security structure. The social security platform searches the edge between the target object with a neighbor degree of 1 and the corresponding social security agency through the social security knowledge graph to determine the social security payment information of each participating area; the social security platform weights the social security feature vectors of the target object and the related person by neighbor degree weighting to obtain the social security collaborative feature; the neighbor degree weighting means that the weight of the social security related information of the related person connected by the edge with a larger neighbor degree value is smaller; The medical insurance platform processes the medical insurance characteristics of the associated person through the medical insurance embedding layer to determine the medical insurance collaborative characteristics, and the medical insurance characteristics of the associated person are obtained through the medical insurance knowledge graph, the medical insurance knowledge graph includes nodes and edges, the nodes of the medical insurance knowledge graph include the person nodes and medical insurance institution nodes; the node attributes of the medical insurance institution nodes include address information; the edges of the medical insurance knowledge graph include multiple types of edges, and the types of the edges of the medical insurance knowledge graph include direct relative type, same address type and medical insurance related type; Determining a checklist corresponding to the query request based on the collaborative feature; the determining the checklist corresponding to the query request based on the collaborative feature includes: The collaborative features are processed based on an evaluation model to determine an evaluation value, wherein the evaluation model is a machine learning model; the evaluation model is obtained by performing multi-party security training on the social security embedding layer, the medical insurance embedding layer and the evaluation model; the training samples include multiple groups of sample collaborative features, and the labels of the training samples are sample evaluation values ​​of sample target objects; Based on the evaluation value, determining a checklist corresponding to the query request; The checklist is fed back to the user through the user platform based on the service platform.

2. A smart city checklist generation system based on the Internet of Things, characterized in that: The system includes a user platform, a service platform and a verification management platform, and the verification management platform is configured to perform the following operations: Obtaining query requests through the user platform based on the service platform; Acquire associated person information based on the population information platform, wherein the associated person information includes target object information and related person information; Based on the associated person information, a collaborative feature is obtained through a collaborative platform, wherein the collaborative feature includes a social security collaborative feature and a medical insurance collaborative feature; the collaborative platform includes at least one of a social security platform and a medical insurance platform, including: The social security platform processes the social security characteristics of the associated person through the social security embedding layer. Determine the social security collaborative characteristics, the social security characteristics of the associated person are obtained through the social security knowledge graph, The social security knowledge graph includes nodes and edges, and the nodes include person nodes and social security agency nodes; the node attributes of the person nodes include address information, bank flow, income information and credit data; the node attributes of the social security agency nodes include address information; the edges of the social security knowledge graph include multiple types of edges, and the types of edges of the social security knowledge graph include direct relative type, same address type and social security related type; the social security characteristics of the associated persons include the social security characteristics of the target object and the social security characteristics of the related persons; the social security platform determines the related persons of the target object through the neighbor degree of different people with the target object; the social security characteristics of the target object or the social security characteristics of the related persons are respectively obtained through the number of insured areas of the target object or the related persons of the target object and the social security payment information of each insured area; the social security platform determines the number of insured areas through the number of edges between the target object or the related persons and the social security structure; The social security platform searches the edge between the target object with a neighbor degree of 1 and the corresponding social security agency through the social security knowledge graph to determine the social security payment information of each participating area; the social security platform weights the social security feature vectors of the target object and the related person by neighbor degree weighting to obtain the social security collaborative feature; the neighbor degree weighting means that the weight of the social security related information of the related person connected by the edge with a larger neighbor degree value is smaller; The medical insurance platform processes the medical insurance characteristics of the associated person through the medical insurance embedding layer. Determine the medical insurance collaborative feature, the medical insurance feature of the associated person is obtained through a medical insurance knowledge graph, the medical insurance knowledge graph includes nodes and edges, the nodes of the medical insurance knowledge graph include the person node and the medical insurance institution node; the node attribute of the medical insurance institution node includes address information; the edge of the medical insurance knowledge graph includes multiple types of edges, and the types of the edges of the medical insurance knowledge graph include direct relative type, same address type and medical insurance related type; Determining a checklist corresponding to the query request based on the collaborative feature; the determining the checklist corresponding to the query request based on the collaborative feature includes: The collaborative features are processed based on an evaluation model to determine an evaluation value, wherein the evaluation model is a machine learning model; the evaluation model is obtained by performing multi-party security training on the social security embedding layer, the medical insurance embedding layer and the evaluation model; the training samples include multiple groups of sample collaborative features, and the labels of the training samples are sample evaluation values ​​of sample target objects; Based on the evaluation value, determining a checklist corresponding to the query request; The checklist is fed back to the user through the user platform based on the service platform.

3. A smart city checklist generation device based on the Internet of Things, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the method for generating a smart city checklist based on the Internet of Things as described in claim 1.

4. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the method for generating a smart city checklist based on the Internet of Things as described in claim 1.

Images