A credit investigation service product generation method and device, a storage medium and an equipment

Abstract

The specification provides a credit investigation service product generation method, device, storage medium and equipment. The credit investigation service product generation method comprises: acquiring business record data generated in a credit investigation business process performed by a target object; determining a credit investigation business scenario involved in the business record data, determining a construction requirement score corresponding to the credit investigation business scenario according to the occurrence frequency of the business record data in the credit investigation business scenario and the difference degree of the business scenario relative to a business scenario corresponding to an existing credit investigation service product; in the case that the construction requirement score corresponding to the credit investigation business scenario meets a credit investigation service product construction condition, generating product configuration information based on the business record data in the credit investigation business scenario; and generating a target credit investigation service product corresponding to the credit investigation business scenario according to the generated product configuration information by calling a corresponding construction component.

Description

Technical Field

[0001] This specification relates to one or more embodiments in the field of computer technology, and in particular to a method, apparatus, storage medium and device for generating credit reporting service products. Background Technology

[0002] With the rapid development of the digital economy, credit reporting services have been deeply integrated into diverse economic scenarios such as consumer finance, corporate financing, and scenario-based lending, becoming a core support for ensuring the security of financial transactions and preventing credit risks. The rise of emerging business models such as live-streaming e-commerce, flexible employment, and the sharing economy has placed higher demands on the scenario adaptability and rapid iteration capabilities of credit reporting products. Traditional credit reporting product models based on fixed scenarios are no longer sufficient to meet the market's demand for personalized and diversified credit reporting services.

[0003] However, the development of existing credit reporting products usually requires business personnel to conduct research on relevant business needs and provide corresponding product development requirements to developers. Due to the limited coverage of manual research and its susceptibility to subjective experience bias, it is difficult to accurately grasp dynamic user needs, resulting in a disconnect between product design and actual business needs. This seriously restricts the innovation and iteration of credit reporting products and the improvement of their market competitiveness. Summary of the Invention

[0004] In view of the above, one or more embodiments of this specification provide the following technical solutions: According to a first aspect of one or more embodiments of this specification, a method for generating a credit reporting service product is proposed, applied to a credit reporting system corresponding to a credit reporting agency, comprising: The system acquires business record data generated during the execution of credit reporting business by the target object; wherein the business record data includes: request data sent by the target object to the credit reporting system, and / or credit reporting data returned by the credit reporting system to the target object based on the request data; The credit reporting business scenario involved in the business record data is determined. Based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to existing credit reporting service products, the construction requirement score corresponding to the credit reporting business scenario is determined. The frequency of occurrence and the degree of difference are positively correlated with the construction requirement score. If the construction requirement score corresponding to the credit reporting business scenario meets the construction conditions of the credit reporting service product, product configuration information is generated based on the business record data under the credit reporting business scenario. Based on the generated product configuration information, the corresponding building components are invoked to generate the target credit reporting service product for the credit reporting business scenario.

[0005] According to a second aspect of one or more embodiments of this specification, an apparatus for generating a credit reporting service product is provided, comprising: The acquisition module is used to acquire business record data generated during the credit reporting process of the target object; wherein, the business record data includes: request data sent by the target object to the credit reporting system, and / or, credit reporting data returned by the credit reporting system to the target object based on the request data; The determination module is used to determine the credit reporting business scenario involved in the business record data, and to determine the construction requirement score corresponding to the credit reporting business scenario based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product; wherein, the frequency of occurrence and the degree of difference are positively correlated with the construction requirement score; The generation module is used to generate product configuration information based on business record data in the credit reporting business scenario, provided that the construction requirement score for the credit reporting business scenario meets the construction conditions for the credit reporting service product. The build module is used to call the corresponding build components to generate the target credit reporting service product corresponding to the credit reporting business scenario based on the generated product configuration information.

[0006] According to a fourth aspect of one or more embodiments of this specification, a computer-readable storage medium is provided that stores computer instructions thereon, which, when executed by a processor, implement the steps of the method described above.

[0007] According to a fifth aspect of one or more embodiments of this specification, a computer program application is provided, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0008] As described in the above embodiments, this specification collects business record data and quantifies the construction requirements based on the frequency of occurrence of data corresponding to credit reporting business scenarios and the differences between the data and existing credit reporting products. This accurately identifies the construction requirements of credit reporting service products and generates corresponding configuration information. Based on this configuration information, the corresponding construction components can be invoked to generate the target credit reporting service product. Compared to the traditional credit reporting product construction model that relies on manual research by business personnel and experience-based coding by algorithm experts, this solution eliminates the need for subjective manual analysis and experience dependence. It can automatically identify credit reporting business scenarios, generate product configurations, and complete component-based construction, effectively improving the innovation and iteration capabilities of credit reporting service products and fully meeting user needs. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the architecture of a product generation service system provided in an exemplary embodiment; Figure 2 This is a flowchart illustrating a method for generating a credit reporting service product, provided in an exemplary embodiment. Figure 3 This is a schematic diagram of the data flow path for a credit reporting service provided in an exemplary embodiment; Figure 4 This is a schematic diagram of the overall process of product generation provided in an exemplary embodiment; Figure 5 This is a schematic diagram of the structure of a device provided in an exemplary embodiment; Figure 6 This is a block diagram of a credit reporting service product generation apparatus provided in an exemplary embodiment. Detailed Implementation

[0010] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0011] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties. The collection, use and processing of related data shall comply with the relevant laws, regulations and standards of the relevant regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0012] The existing credit reporting product development model still has many technical shortcomings that urgently need to be addressed: Low development efficiency: The core aspects of credit scoring products, such as the design of scoring logic and the configuration of field combinations, rely heavily on manual operation. The lack of standardized and reusable component system leads to prominent issues of repeated development, with an average development cycle of several weeks to several months, making it difficult to adapt to rapid market changes. Demand response lag: Existing technologies cannot automatically identify high-frequency behavior patterns from massive credit scoring interface call logs, and lack targeted credit scoring product solutions for emerging scenarios such as live e-commerce and flexible employment, thus failing to meet the credit assessment needs of emerging business formats in a timely manner. The technical threshold is too high: the development process of credit reporting products relies too much on the experience coding of algorithm experts, making it difficult for business personnel to participate in the product design stage, forming a "technical black box" and causing the product design to be out of touch with actual business needs; Lack of intelligent insight capabilities: It is unable to effectively perform semantic clustering and potential demand mining of user call behavior, and it is difficult to automatically identify "hidden high-demand products", which restricts the innovation and iteration of credit reporting products and the improvement of market competitiveness.

[0013] Based on this, this specification provides a method for generating credit reporting service products. By collecting business record data and combining the frequency of occurrence of data in different scenarios with the differences between the data and the scenarios corresponding to existing products, the method quantifies the construction requirements and scores them. This accurately identifies the construction requirements of credit reporting service products and generates corresponding configuration information. Then, based on the configuration information, the method calls the corresponding construction components to generate the target credit reporting service product. This achieves automatic identification and construction of credit reporting service product requirements and effectively improves the product's innovation and iteration capabilities.

[0014] Figure 1 This is a schematic diagram of the architecture of a product generation service system provided in an exemplary embodiment. For example... Figure 1 As shown, the system may include a server 11, a network 12, and several electronic devices, such as a PC (Personal Computer) 13, a mobile phone 14, etc.

[0015] Server 11 can be a physical server containing an independent host, or it can be a virtual server hosted in a host cluster. During operation, server 11 can run server-side programs for a specific application to implement the relevant functions of that application. For example, when server 11 runs a program for generating business products, it can act as a platform for generating corresponding business products.

[0016] PC13 and mobile phone14 are just some of the types of electronic devices that users can use. In reality, users can obviously also use electronic devices such as tablets, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smartwatches, etc.), etc., and one or more embodiments in this specification do not limit this. During operation, the electronic device can run a client-side program of an application to implement the relevant functions of that application. For example, when the electronic device runs a program for generating business products, it can implement a client for generating services for that business product. The application for the aforementioned business product generation service can be launched and run on the electronic device. This client-side program can be a native application installed on the electronic device, or it can be a mini-program, quick app, or other similar form. Of course, when using web technologies such as HTML5 or similar, the relevant functions can be implemented through a page displayed by a browser. This browser can be a standalone browser application or a browser module embedded in some applications.

[0017] As for the network 12 that enables interaction between electronic devices such as PC13 and mobile phone 14 and server 11, communication can be achieved using either wired or wireless networks, depending on the communication methods supported by the respective electronic devices. This specification does not impose any restrictions on this. For example, PC13 can support both wired and wireless communication, so it can use either wired or wireless networks as needed. Mobile phone 14 typically only supports wireless communication, so it can use a wireless network for communication.

[0018] Based on the aforementioned business product generation service system architecture, this specification provides a method for generating credit reporting service products, such as... Figure 2 As shown.

[0019] Figure 2 A flowchart illustrating a method for generating a credit reporting service product, as provided in this embodiment of the specification, includes the following steps: S200: Obtain business record data generated during the credit reporting process of the target object; wherein, the business record data includes: request data sent by the target object to the credit reporting system, and / or, credit reporting data returned by the credit reporting system to the target object based on the request data.

[0020] In this specification, the entity executing the method for generating credit reporting service products can be the credit reporting system corresponding to the credit reporting agency. Specifically, it can refer to the hardware or software operating platform of the credit reporting system, such as a server, cloud computing platform, distributed node, terminal device, or client deployed on these devices. For ease of description, the following will use the credit reporting system as the executing entity to illustrate the method for generating credit reporting service products provided in this specification.

[0021] Credit reporting systems can collect business record data generated by target objects during business operations. This business record data can record data generated or interacted during the data flow of the credit reporting business chain. For ease of understanding, this specification provides a schematic diagram of the data flow path of credit reporting business, such as... Figure 3 As shown.

[0022] The target audience can be the data requester in credit reporting, such as the business processing systems of financial institutions like banks, securities companies, and insurance companies, used to provide financial services like deposits and withdrawals, fund transfers, loan disbursements, securities trading, and insurance applications and claims. Alternatively, the target audience can also be the users themselves performing the corresponding business within the financial institution.

[0023] A credit reporting system is a specialized platform operated by credit reporting agencies. It is used to integrate, verify, analyze, and process relevant query requests and credit data from multiple channels (such as credit records and default information) to form standardized credit assessment results.

[0024] Data providers can be data platforms of data source institutions such as e-commerce platforms, social networks, telecommunications operators, and government departments (i.e., data providers), used to store cross-domain data such as user consumption behavior records, social interaction data, communication trajectories and locations, enterprise business information, and tax records.

[0025] For example, the data flow path for credit reporting can be as follows: Financial institutions, as data requesters, initiate data query requests (i.e., data requests) to credit reporting agencies targeting specific users. The credit reporting agency, acting as an intermediary, receives the request and, based on its own business system, connects with multiple data source institutions (data providers) to obtain various credit-related business data such as the user's credit records, repayment behavior, and performance history. The credit reporting agency can then use this data to conduct risk assessments of the user, obtain credit data, and return it to the financial institution, providing decision support for the financial institution's credit approval, risk control, and other business operations.

[0026] Based on this, the server can collect one or more business record data generated by the data requester during the credit investigation process. The data sources of this business record data may include: Data Request Log: Used to record the data requested by the data requester and the business applications that use this data; Business application form: used to associate with specific credit reporting business scenarios (such as "loan approval" and "rental review"); User feedback information; used to record users' specific business needs (such as a user wanting to obtain a rider's credit score) and their level of attention to different credit reporting business scenarios.

[0027] The credit reporting system can further obtain the business record data required to build credit reporting service products from the above data sources, which may include request data sent by the target object to the credit reporting system, and / or credit reporting data returned by the credit reporting system to the target object based on the request data.

[0028] In addition, the aforementioned business record data may also include other data such as survey questionnaires on business products, scenario demand application forms constructed by business personnel, and statistical reports on the credit reporting service industry. This manual does not make specific limitations on this.

[0029] In the credit reporting system, credit reporting service products can refer to credit reporting products that provide different credit assessment services or credit reporting data support. Specifically, they can refer to different functional modules of credit reporting services in the credit reporting platform that are adapted to different credit reporting business scenarios, such as "credit score calculation for flexible workers", "risk rating for live e-commerce merchants", and "performance record inquiry for shared economy practitioners". Of course, they can also be applications of the credit reporting platform or mini-programs deployed on the credit reporting platform.

[0030] It should be added that the aforementioned business record data can be multimodal data such as images, text, and videos. For text data, it can also include different text formats, such as structured tables, semi-structured log files, and unstructured documents (such as Word documents and PDF documents).

[0031] S202: Determine the credit reporting business scenario involved in the business record data, and determine the construction requirement score corresponding to the credit reporting business scenario based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product; wherein, the frequency of occurrence and the degree of difference are positively correlated with the construction requirement score; S204: If the construction requirement score corresponding to the credit reporting business scenario meets the construction conditions of the credit reporting service product, generate product configuration information based on the business record data under the credit reporting business scenario.

[0032] The credit reporting system can input the collected business record data into a language model-based insight engine, which will then generate product configuration information for the target credit reporting service product.

[0033] In practical applications, there are multiple opportunities to input business record data into the demand insight engine. For example, business record data can be collected at preset time intervals, and when the end of the current time interval is reached, the business record data collected within that time interval can be input into the demand insight engine. For example, each piece of business record data is collected and then input into the demand insight engine to accumulate the business record data until the target business scenario is determined based on the accumulated business record data (such as determining a credit investigation business scenario where the construction demand score is greater than a set score). For example, when the collected business record data exceeds the preset quantity, it is input into the demand insight engine.

[0034] The demand insight engine can identify key fields in business record data and standardize them to obtain a standardized field vector. The key fields can match the fields of the corresponding semantic information in the standardized field vector of the preset standard information library.

[0035] For example, in financial lending records, fields such as "credit score" and "credit rating" all match the information in the standard database. The corresponding semantics are therefore standardized to "". The corresponding standardized field vector is "F002"; for example, fields such as "loan amount" and "loan amount" all match the standardized information database. The corresponding semantics are therefore standardized to "". The corresponding standardized field vector is "F002".

[0036] After standardizing the key fields, the demand insight engine can construct a sequence of behavioral data from the data demander based on the standardized field vector. This sequence can then be used to cluster the data of each business record and determine one or more credit reporting business scenarios involved in each business record based on the clustering results.

[0037] The sequence length of the behavioral data sequence can be set based on business complexity, data granularity requirements, or the performance of the current device (such as CPU processing speed, available memory capacity, etc.), preferably 64 bytes. This behavioral data sequence is used to characterize the continuous operation trajectory and key behavioral features of a user or subject in a specific business process.

[0038] The language model corresponding to the demand insight engine can be a large language model (LLM), specifically a fine-tuned version. or The model, of course, can also be other large models. That is, the demand insight engine is a large model demand insight engine. It can take the behavioral data sequence as input to the large model. Based on the context modeling and semantic understanding capabilities of the large model, it performs semantic parsing and scenario matching on the behavioral data sequence, thereby obtaining the credit business scenario involved in the corresponding business record data.

[0039] For example, when the semantics of the input behavioral data sequence are "a certain travel platform frequently queries the stability of driver's equipment + order cancellation rate + passenger complaints", the output result is: "This behavior belongs to the 'ride-hailing driver performance evaluation' scenario".

[0040] After identifying the credit reporting business scenarios involved in each business record data, the demand insight engine can, based on a large model, determine the construction demand score for the corresponding credit reporting service product for each involved credit reporting business scenario, according to the frequency of occurrence of business record data in that credit reporting business scenario and the degree of difference from the business scenarios corresponding to existing credit reporting service products.

[0041] The frequency of occurrence is used to characterize the frequency of actual business needs in the credit reporting business scenario. That is, when there are N business record data belonging to the credit reporting business scenario, the corresponding frequency of occurrence is N. The difference degree is used to characterize the degree of differentiation and innovation of the credit reporting business scenario compared to existing credit reporting service products. The demand insight engine can determine the scenario description information corresponding to the credit reporting business scenario based on business record data, and then calculate the difference degree between the scenario description information and the scenario description information corresponding to existing credit reporting service products in the preset product library. Among them, the frequency of occurrence and the difference degree are positively correlated with the construction of demand scores. In practical applications, in addition to frequency and novelty, the demand insight engine can also calculate the construction demand score based on other information. Specifically, it can calculate the construction demand score by weighting and summing the frequency and difference of the business record data corresponding to the credit reporting business scenario, the number of data demanders involved in the business record data in the credit reporting business scenario, the user attention reflected by the business record data in the credit reporting business scenario, and their respective weights.

[0042] The number of data demanders involved in the business record data under this credit reporting business scenario is used to reflect the application scope and practical value of the credit reporting business scenario. The more data demanders involved, the wider the application scope and the higher the practical value of the credit reporting business scenario. Therefore, the greater the demand for building credit reporting service products corresponding to the credit reporting business scenario. User attention can be quantified based on users' query data of relevant business records and suggestions from users. It is used to represent the urgency of users' actual needs for the credit reporting business scenario. The more relevant quantitative indicators there are, the higher the user attention is, and the higher the priority of building credit reporting service products.

[0043] For example, the build requirements score can be calculated using the following formula: Requirement score = 0.4 × frequency of occurrence + 0.3 × number of data requesters involved + 0.2 × degree of difference + 0.1 × user attention.

[0044] After determining the construction requirement score for each credit reporting business scenario, the demand insight engine can sort the credit reporting business scenarios in descending order of the construction requirement score for the corresponding credit reporting service products. The credit reporting business scenarios ranked before the preset position are identified as target business scenarios, or the credit reporting business scenarios with a construction requirement score greater than the preset threshold are identified as target business scenarios.

[0045] In other words, for any credit reporting business scenario, the construction requirement score corresponding to the credit reporting business scenario can be determined based on the frequency of occurrence of business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product. If the construction requirement score corresponding to the credit reporting business scenario meets the construction conditions of the credit reporting service product (the construction requirement score is greater than the preset score or the corresponding ranking is before the preset position), product configuration information is generated based on the business record data in the credit reporting business scenario.

[0046] The demand insight engine can then generate structured product configuration information for the target credit reporting service product based on the business record data under the credit reporting business scenario (target business scenario). This product configuration information may include the business scenario type, application cases, key fields, and adaptation models corresponding to the target credit reporting service product. Of course, it may also include other information such as core functional requirements, evaluation indicators, data feature description information, and business rule constraints, but this specification does not specify these limitations.

[0047] For example, the product configuration information of the target credit reporting service product is shown below: json { “recommended_product”: “Livestream host credit score” "use_case (application case)": "MCN agency cooperation evaluation, platform onboarding review", "key_fields": "[Login frequency, live stream duration, complaint rate, rent payment]" "suitable_model": "XGBoost".

[0048] } S204: Based on the generated product configuration information, call the corresponding building components to generate the target credit reporting service product corresponding to the credit reporting business scenario.

[0049] In this manual, in addition to the demand insight engine, the server also deploys a product building engine. This product building engine provides a variety of building components. The server can call the corresponding building components according to the product configuration information, thereby generating the target credit scoring service product through the building components.

[0050] The build components provided by this product's build engine may include: Basic Information Configurator: Input product metadata in a form, such as name, scenario, and update frequency; Output template generator: Automatically generates report structure and style code; Business rule configurator: A graphical "condition-action" logic block that supports nesting and priority settings; Algorithm Model Library: Provides optional model components and supports click-to-insert orchestration processes; Product component library: Pre-packaged field combinations according to scenarios, supporting one-click reuse.

[0051] Specifically, the product building engine can call the basic information configurator, which will configure the basic information of the target credit reporting service product according to the product configuration information, and obtain the metadata structure of the target credit reporting service product.

[0052] The basic information configurator can automatically generate basic information for the target credit reporting service product in the configuration form based on the product configuration information. Users can also fill in or modify this basic information in the configuration form (e.g., user-initiated entry, selection via drop-down menu, etc.). Input items for this basic information can include: the target credit reporting service product name, business scenario type, data subject type (individual / enterprise / new citizen), and information output format (JSON / HTML / PDF), etc.

[0053] The basic information configurator can generate the metadata structure of the target credit reporting service product based on the basic information in the configuration form.

[0054] The product building engine can call the business rule configurator to configure the business rules corresponding to the target credit reporting service product.

[0055] The business rule configurator can automatically generate default business rules for the target credit reporting service product based on the product configuration information. It also provides "condition-action" logic blocks that support graphical splicing, making it easy for users to set up business rules themselves.

[0056] For example, the business rules configured by the business rule configurator are as follows: "If the number of queries in the past 3 months is greater than 5, a high-risk warning will be triggered"; "If there is no credit history, an alternative data model will be used"; "If the credit score is less than 600 and the age is less than 25, a manual review will be triggered."

[0057] In addition, users can nest different business rules and set corresponding priorities for different business rules through the business rule configurator.

[0058] The product building engine can call the output template generator, which will generate a template structure corresponding to the output content of the target credit reporting service product based on the product type reflected in the product configuration information.

[0059] The output template generator can automatically generate template structures based on product type. It also supports users to drag and adjust the display order of different modules (e.g., display risk level first, then list details).

[0060] In addition, the output template generator can also generate template configuration information such as Markdown structure, HTML / CSS styles, and PDF layout suggestions by taking product configuration information as input from template generation models (such as LLM).

[0061] Furthermore, the algorithm model library stores various algorithm models that can be used to build credit scoring service products. For example, the implementation methods and core characteristics of each model are shown in Table 1: Table 1

[0062] In practical applications, the product configuration information generated by the demand insight engine can directly contain the model type that is compatible with it. At this time, the product building engine can directly call the algorithm model of that type from the algorithm model library to build the target credit reporting service product. Of course, the configuration information generated by the demand insight engine can also contain data feature description information (such as data type, feature dimension, data volume, etc.) and credit reporting business scenario type. The product building engine can further match the corresponding algorithm model from the algorithm model library based on the data feature description information and the credit reporting business scenario type.

[0063] For example, when the data features are described as "high-dimensional discrete features + tens of millions of samples" and the credit reporting business scenario type is "credit risk assessment", the product building engine will match "XG Boost machine learning model".

[0064] Of course, users can also choose the algorithm models provided by the algorithm model library. In practical applications, only one algorithm model can be set as the main model of the target credit scoring service product. Alternatively, multiple algorithm models can be integrated (e.g., 70% XGBoost + 30% rule engine).

[0065] The product component library stores reusable code corresponding to the built product components. For example, the functions and adaptation scenarios of each product component are shown in Table 2: Table 2

[0066] The product building engine can determine the reusable code that matches the credit investigation business scenarios and core functional requirements contained in the product configuration information from the product component library.

[0067] For example, when the credit reporting business scenario is "tenant qualification verification on rental platforms" and the core functional requirement is "performance capability assessment", the product building engine will match the reusable code of the "performance stability package" (including functions related to water and electricity payment and rent payment); when the credit reporting business scenario is "fraud verification of credit applications" and the core functional requirement is "related risk identification", it will match the reusable code corresponding to the "relationship network package".

[0068] Of course, users can also choose the algorithm model provided by the product component library themselves. For example, the product building engine can provide reusable field combination modules that support drag-and-drop into the canvas. When a user drags any product component into the canvas, it is automatically mapped to the data source interface, thereby obtaining the reusable code of the corresponding product component.

[0069] Furthermore, the product build engine can display a product orchestration canvas to users and, in response to the target operations performed by users on each build component in the product orchestration canvas, adjust the automated build data generated by each build component based on product configuration information, so as to build the target credit scoring service product based on the adjusted automated build data. The automated data construction includes at least one of the following: the metadata structure, template structure, business rules, at least one algorithm model, and reusable code.

[0070] In practical applications, the product's orchestration canvas is a visual process design interface. Users can drag and drop data source components, product component features, algorithm models, rule blocks, output templates, etc., and can also define the execution order by connecting lines to form a "product pipeline".

[0071] For example, users can drag the "Behavioral Activity Package" from the product component library into the product orchestration canvas, which will be automatically mapped to the "Login Frequency" field. They can then select the "XGBoost Model" as the main model and add the rule: "If there is no rent payment record in the past 3 months → deduct 20 points and prompt for manual review".

[0072] Based on the automated data generated above, the product building engine can further generate configuration files for the target credit scoring service product. For example, this configuration file can be in YAML format, and its content is shown below: product_id: CR001-LIVE; Name: Live Streamer's Credit Score; version: 1.0; Description: Used by MCN agencies to assess the commercial credibility of livestreamers; fields: - F101: Login frequency (last 30 days); - F205: Average live stream duration; - F309: Rental payment records; - F402: Platform complaint rate; Model: XG Boost; scoring_logic: score = 0.5 × login frequency + 0.3 × live stream duration + 0.2 × rent payment; If rent payment == 0: score -= 20; output_template: live_host_report_v1.html; generated_by:LLM-Product-Engine / v2.1.

[0073] The server can further submit the aforementioned configuration file, thereby building and publishing the target credit reporting service product in the credit reporting system.

[0074] Specifically, the server can generate interface documentation that conforms to the API (such as Swagger / Open API) interface specifications of the credit reporting system, and register the interface documentation with the API gateway of the credit reporting system to deploy the target credit reporting service product to the credit reporting system and update the product catalog of the credit reporting service products provided by the credit reporting system.

[0075] In practical applications, the product building engine can deploy the target credit reporting service product to the credit reporting system through Docker / Kubernetes. After deployment, the credit reporting system can automatically perform syntax verification on the product code, as well as canary releases and tests on the target credit reporting service product.

[0076] Once the target credit reporting service product is deployed, the credit reporting system can then perform corresponding credit reporting business based on that target credit reporting service product.

[0077] To facilitate understanding, this manual provides a schematic diagram of the overall product manufacturing process, such as... Figure 4 As shown.

[0078] The process involves inputting business record data into a language model-based demand insight engine (i.e., a large-scale demand insight engine). The demand insight engine can then perform data cleaning and vectorization of key fields to construct a behavioral data virtual column. Based on this behavioral data sequence, the business record data is clustered to determine the credit reporting business scenario corresponding to each business record data. Subsequently, the construction demand score corresponding to each credit reporting business scenario is calculated. Based on this construction demand score, the target business scenario is selected and the corresponding product configuration information is generated.

[0079] The product configuration information is then input into the product building engine, which generates a configuration file for the target credit reporting service product through the various product building components in the engine. The target credit reporting service product is then deployed and released based on the configuration file (including API gateway registration, access to the credit reporting platform, and gray-scale testing).

[0080] As can be seen from the above methods, this solution can utilize the semantic parsing capabilities provided by the large language model to analyze call logs in real time. Through semantic clustering and recommendation of credit reporting scenarios, it can automatically identify high-demand products and automatically generate logic, thereby discovering emerging scenario demands in advance. Through component-based combination and unique scenario customization, it can support products in various subdivided scenarios, significantly shortening the development cycle of credit reporting products.

[0081] Figure 5 This is a schematic structural diagram of a device provided in an exemplary embodiment. For example... Figure 5 As shown, device 500 mainly consists of a communication interface 502, a user interface 504, a processor 506, and a data storage 508. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 510. The communication interface 502 enables device 500 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 502 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 502 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 502 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 502 may also include multiple physical communication interfaces, such as Wi-Fi interfaces, Bluetooth interfaces, and wide-area wireless interfaces.

[0082] User interface 504 includes receiving user input and providing output to the user. Therefore, user interface 504 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 504 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 504 may include software, circuitry, or other forms of logic capable of transmitting and receiving data from external user input / output devices. Additionally or alternatively, device 500 may support remote access from other devices via communication interface 502 or another physical interface (not shown). User interface 504 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 504 may also be configured as a display device for rendering or displaying text fragments.

[0083] Processor 506 may contain one or more general-purpose processors and / or special-purpose processors.

[0084] Data storage 508 may include one or more volatile and / or non-volatile storage components and may be integrated wholly or partially with processor 506. Data storage 508 may include removable and non-removable components.

[0085] Processor 506 is capable of executing program instructions 518 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 508 to perform the various functions described herein. Data storage 508 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 500, enable device 500 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 518 by processor 506 may result in processor 506 using data 512.

[0086] For example, program instructions 518 may include an operating system 522 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 500 and one or more applications 520 (e.g., a browser, social application, or game application). Similarly, data 512 may include operating system data 516 and application data 514. Operating system data 516 is primarily accessible to the operating system 522, while application data 514 is primarily accessible to one or more applications 520. Application data 514 may reside in a file system visible or hidden from the user of device 500.

[0087] Application 520 can communicate with operating system 522 through one or more application programming interfaces (APIs). These APIs help application 520 read and / or write application data 514, transmit or receive information via communication interface 502, receive or display information on user interface 504, etc.

[0088] In some terminology, application 520 may be simply referred to as "app". Furthermore, application 520 can be downloaded to device 500 through one or more online app stores or app markets. However, applications can also be installed on device 500 in other ways, such as through a web browser or a physical interface on device 500 (e.g., a USB port).

[0089] Please refer to Figure 6 The credit reporting service product generation device can be applied to, for example... Figure 5 The device shown is used to implement the technical solution described in this specification. The credit reporting service product generation device may include: The acquisition module 600 is used to acquire business record data generated during the credit reporting business performed by the target object; wherein, the business record data includes: request data sent by the target object to the credit reporting system, and / or, credit reporting data returned by the credit reporting system to the target object based on the request data; The determining module 602 is used to determine the credit reporting business scenario involved in the business record data, and to determine the construction requirement score corresponding to the credit reporting business scenario based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product; wherein, the frequency of occurrence and the degree of difference are positively correlated with the construction requirement score; The generation module 604 is used to generate product configuration information based on the business record data in the credit reporting business scenario, provided that the construction requirement score corresponding to the credit reporting business scenario meets the construction conditions of the credit reporting service product. Module 606 is used to call the corresponding build components to generate the target credit reporting service product corresponding to the credit reporting business scenario based on the generated product configuration information.

[0090] Optionally, the determining module 602 is further configured to input multiple business record data generated during the credit investigation business of the target object into a demand insight engine based on a language model, so as to perform clustering processing on each business record data through the demand insight engine, and to determine at least one business scenario involved in each business record data based on the clustering processing results.

[0091] Optionally, the determining module 602 is specifically used to identify key fields in each business record data through the demand insight engine, and to standardize the key fields to obtain a standardized field vector; wherein, the key field is the field whose expressed semantic information matches the standardized field vector in the preset standard information library; based on the standardized field vector, construct the behavioral data sequence of the target object, so as to perform clustering processing on each business record data through the behavioral data sequence; The generation module 604 is specifically used to generate product configuration information based on business record data in the credit reporting business scenario through the demand insight engine.

[0092] Optionally, the determining module 602 is specifically used to: determine the scenario description information corresponding to the credit reporting business scenario based on the business record data under the credit reporting business scenario; and determine the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product based on the scenario description information corresponding to the credit reporting business scenario and the scenario description information of the business scenario corresponding to the existing credit reporting service product.

[0093] Optionally, the determining module 602 is specifically used to perform a weighted summation based on the frequency of occurrence, the degree of difference, the number of data demanders involved in the business record data under the credit reporting business scenario, the user attention reflected by the business record data under the credit reporting business scenario, and their respective weights, to obtain the construction demand score.

[0094] Optionally, the construction conditions for the credit reporting service product include: the construction requirement score is greater than a preset score, or, after sorting each credit reporting business scenario according to the construction requirement score corresponding to each credit reporting business scenario in descending order, the ranking corresponding to this business scenario is located before a preset position.

[0095] Optionally, the building components include: a basic information configurator, an output template generator, and a business rule configurator; The construction module 606 is specifically used to: call the basic information configurator so that the basic information configurator configures the basic information of the target credit reporting service product according to the product configuration information to obtain the metadata structure of the target credit reporting service product; call the output template generator so that the output template generator generates a template structure corresponding to the output content of the target credit reporting service product according to the product type reflected by the product configuration information; and call the business rule configurator so as to configure the business rules corresponding to the target credit reporting service product through the business rule configurator.

[0096] Optionally, the building components include: an algorithm model library and a product component library; the algorithm model library stores a variety of algorithm models that can be used to build credit scoring service products, and the product component library stores reusable code corresponding to the built product components; The construction module 606 is specifically used to determine at least one algorithm model that matches the target credit reporting service product in the algorithm model library, and to determine reusable code corresponding to the product component that matches the product configuration information in the product component library.

[0097] Optionally, the building components are provided by a preset product building engine, which is used to display a product arrangement canvas to the user; The construction module 606 is specifically used to adjust the automated construction data generated by each construction component based on the product configuration information in response to the target operation performed by the user on each construction component in the product orchestration canvas, so as to construct the target credit scoring service product according to the adjusted automated construction data; wherein, the automated construction data includes at least one of the metadata structure, the template structure, the business rules, the at least one algorithm model, and the reusable code.

[0098] Optionally, the device further includes: The deployment module 608 is used to generate an interface document that conforms to the API interface specification of the credit reporting system, and register the interface document with the API gateway of the credit reporting system to deploy the target credit reporting service product to the credit reporting system, and update the product catalog of the credit reporting service products provided by the credit reporting system.

[0099] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0100] Based on the same concept as the methods described above, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor performs the steps of the method as described in any of the above embodiments by executing the executable instructions.

[0101] Based on the same concept as the methods described above, this specification also provides a computer-readable storage medium having computer instructions stored thereon that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0102] Based on the same concept as the methods described above, this specification also provides a computer program application, including a computer program / instructions that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0103] What those skilled in the art will understand is: In this specification, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, application, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, application, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, application, or apparatus that includes said elements is not excluded.

[0104] In this specification, “a,” “an,” and “the” do not specifically refer to the singular, but may also include the plural.

[0105] In this specification, ordinal numbers such as "first," "second," etc., do not necessarily indicate order; they are often used to distinguish between objects. For example, "first server" and "second server" usually refer to two servers. To differentiate between these two servers, they are described as "first server" and "second server." Of course, sometimes these two servers may be the same server.

[0106] In this specification, unless explicitly stated otherwise, "receiving and sending data" does not necessarily mean direct receiving and sending; it can also mean indirect receiving and sending. For example, A receiving data sent by B can be understood as A directly receiving the data sent by B, or it can be understood as A indirectly receiving the data sent by B through other entities such as C. Similarly, B sending data to A can be understood as B sending the data directly to A, or it can be understood as B indirectly sending the data to A through other entities such as C. Here, C can be one entity, or it can be two or more entities.

[0107] In this specification, unless explicitly stated otherwise, the relationships between structures can be direct or indirect. For example, when describing "A is connected to B," unless it is explicitly stated that A and B are directly connected, it should be understood that A can be directly connected to B or indirectly connected to B. Similarly, when describing "A is on top of B," unless it is explicitly stated that A is directly above B (AB is adjacent and A is above B), it should be understood that A can be directly above B or indirectly above B (AB is separated by other elements, and A is above B). And so on.

[0108] This specification uses specific terms to describe embodiments thereof. Terms such as "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those different embodiments or examples, without contradiction.

[0109] Although one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is only one of many possible execution orders and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims.

Claims

1. A method for generating a credit reporting service product, applied to a credit reporting system corresponding to a credit reporting agency, comprising: The system acquires business record data generated during the execution of credit reporting business by the target object; wherein the business record data includes: request data sent by the target object to the credit reporting system, and / or credit reporting data returned by the credit reporting system to the target object based on the request data; The credit reporting business scenario involved in the business record data is determined. Based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to existing credit reporting service products, the construction requirement score corresponding to the credit reporting business scenario is determined. The frequency of occurrence and the degree of difference are positively correlated with the construction requirement score. If the construction requirement score corresponding to the credit reporting business scenario meets the construction conditions of the credit reporting service product, product configuration information is generated based on the business record data under the credit reporting business scenario. Based on the generated product configuration information, the corresponding building components are invoked to generate the target credit reporting service product corresponding to the credit reporting business scenario; wherein, reusable code corresponding to the built product components that match the product configuration information is determined in the product component library; and, a product orchestration canvas is displayed to the user, and in response to the user's target operation on each building component in the product orchestration canvas, the automated building data generated by each building component based on the product configuration information is adjusted, so as to build the target credit reporting service product according to the adjusted automated building data; wherein, the automated building data also includes the reusable code.

2. The method as described in claim 1, further comprising, before determining the construction requirement score corresponding to the credit reporting business scenario: Multiple business record data generated during the credit investigation process of the target object are input into a demand insight engine based on a language model. The demand insight engine then performs clustering processing on each business record data to determine at least one business scenario involved in each business record data based on the clustering results.

3. The method as described in claim 2, wherein clustering processing is performed on the business record data, specifically including: The demand insight engine identifies key fields in each business record data and standardizes these key fields to obtain a standardized field vector. The key fields are fields whose semantic information matches the standardized field vector in a preset standard information database. Based on the standardized field vector, a behavioral data sequence of the target object is constructed, so as to perform clustering processing on the business record data through the behavioral data sequence; Product configuration information is generated based on business record data in this credit reporting scenario, specifically including: The demand insight engine generates product configuration information based on business record data in this credit reporting business scenario.

4. The method as described in claim 1, further comprising, before determining the construction requirement score corresponding to the credit reporting business scenario: Based on the business record data in this credit reporting business scenario, determine the scenario description information corresponding to this credit reporting business scenario; Based on the scenario description information corresponding to the credit reporting business scenario and the scenario description information corresponding to the existing credit reporting service product, the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product is determined.

5. The method as described in claim 1, determining the construction requirement score corresponding to the credit reporting business scenario, specifically includes: The construction requirement score is obtained by weighting and summing the occurrence frequency, the degree of difference, the number of data demanders involved in the business record data in the credit reporting business scenario, the user attention reflected by the business record data in the credit reporting business scenario, and their respective weights.

6. The method as described in claim 1, wherein the conditions for constructing the credit reporting service product include: If the construction requirement score is greater than a preset score, or if the credit reporting business scenarios are sorted in descending order of the construction requirement scores corresponding to each credit reporting business scenario, the sorting of the business scenario will be placed before the preset position.

7. The method of claim 1, wherein the building component comprises: Basic information configurator, output template generator, and business rule configurator; Based on the generated product configuration information, the corresponding build components are invoked to generate the target credit reporting service product for this credit reporting business scenario, specifically including: The basic information configurator is invoked to configure the basic information of the target credit reporting service product according to the product configuration information, thereby obtaining the metadata structure of the target credit reporting service product. The output template generator is invoked to generate a template structure corresponding to the output content of the target credit reporting service product based on the product type reflected in the product configuration information. Finally, the business rule configurator is invoked to configure the business rules corresponding to the target credit reporting service product.

8. The method of claim 7, wherein the building component comprises: Algorithm model library; The algorithm model library stores a variety of algorithm models that can be used to build credit reporting service products; Based on the generated product configuration information, the corresponding build components are invoked to generate the target credit reporting service product for this credit reporting business scenario, specifically including: The algorithm model library determines at least one algorithm model that matches the target credit reporting service product, and the product component library determines reusable code corresponding to the product component that matches the product configuration information.

9. The method of claim 8, wherein the building component is provided by a preset product building engine, the product building engine being used to display the product arrangement canvas to the user; in, The automated data construction includes the metadata structure, the template structure, the business rules, the at least one algorithm model, and the reusable code.

10. The method of claim 1, further comprising: Generate an interface document that conforms to the API interface specification of the credit reporting system, and register the interface document with the API gateway of the credit reporting system to deploy the target credit reporting service product to the credit reporting system, and update the product catalog of the credit reporting service products provided by the credit reporting system.

11. A device for generating a credit reporting service product, comprising: The acquisition module is used to acquire business record data generated during the credit reporting business performed by the target object; wherein, the business record data includes: request data sent by the target object to the credit reporting system, and / or, credit reporting data returned by the credit reporting system to the target object based on the request data; The determination module is used to determine the credit reporting business scenario involved in the business record data, and to determine the construction requirement score corresponding to the credit reporting business scenario based on the frequency of occurrence of the business record data in the credit reporting business scenario and the degree of difference between the business scenario and the business scenario corresponding to the existing credit reporting service product; wherein, the frequency of occurrence and the degree of difference are positively correlated with the construction requirement score; The generation module is used to generate product configuration information based on business record data in the credit reporting business scenario, provided that the construction requirement score for the credit reporting business scenario meets the construction conditions for the credit reporting service product. A construction module is used to generate a target credit reporting service product corresponding to the credit reporting business scenario by calling the corresponding construction components based on the generated product configuration information; wherein, it determines reusable code corresponding to the already constructed product components that match the product configuration information in the product component library; and displays a product orchestration canvas to the user, and adjusts the automated construction data generated by each construction component based on the product configuration information in response to the user's target operation on each construction component in the product orchestration canvas, so as to construct the target credit reporting service product according to the adjusted automated construction data; wherein, the automated construction data also includes the reusable code.

12. An electronic device, comprising: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method as described in any one of claims 1-10 by executing the executable instructions.

13. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1-10.

Images