A credit information generation method, device, system and electronic device
By obtaining user data and model information, using sub-computing rules and rule coefficients of message middleware and cache side to calculate credit information dynamically, the problem of excessively rigid credit scores in the existing technology is solved, and flexible credit scores and efficient calculations are realized process.
Patent Information
- Application Number
- CN202210280723.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-21
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-03-21
AI Technical Summary
The credit scoring mechanism of the existing online payment software platform is too rigid and cannot be flexible in management for different payment scenarios, resulting in limited user payment permissions and inconvenience to users.
By obtaining user data and model information, using sub-computing rules and rule coefficients of message middleware and cache side, dynamically calculate credit information, adapt to the scoring needs of different payment scenarios, and improve the flexibility of credit scores.
It realizes the rapid switching of credit assessments based on different payment scenarios, improves the flexibility and accuracy of credit scores, avoids the step of sending all rules every time the calculation is performed, and improves the calculation efficiency.
Smart Images

Figure CN114638689B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of software systems, and in particular to a credit information generation method, device, system and electronic equipment. Background Art
[0002] At present, most online payment software platforms have established a credit scoring mechanism to evaluate the credit of users and grant them different payment permissions. However, in actual applications, there are many types of payment scenarios, such as house purchase scenarios and supermarket shopping scenarios. The existing technology does not formulate a specific scoring mechanism for each payment scenario, which makes the credit scoring too rigid, the scoring results are not applicable to the current scenario, and the management methods for user payment permissions are too single, which brings too many restrictions to users' payments and causes inconvenience to users. Therefore, how to improve the flexibility of user credit information generation is an urgent problem to be solved. Summary of the invention
[0003] In view of this, the embodiments of the present invention provide a credit information generation method, device, system and electronic device, thereby improving the flexibility of user credit information generation.
[0004] According to the first aspect, an embodiment of the present invention provides a credit information generation method, which is applied to the production end, and the method includes: obtaining user data, calculation rules and model information used to calculate credit information, wherein the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario; sending the obtained calculation rules to the cache end; sending the user data and the model information to the message middleware, so that the server reads the user data and the model information from the message middleware, and enables the server to obtain the sub-calculation rules and rule coefficient information corresponding to the model information, and then calculates the credit information of the user data through a calculation formula composed of the sub-calculation rules and the rule coefficient information, wherein the sub-calculation rules are selected and extracted by the server from the calculation rules of the cache end; receiving the credit information returned by the server.
[0005] Optionally, the method also includes: dividing the user data into multiple parts; packaging each user data and the model information to obtain multiple data packets, and sending the multiple data packets to the message middleware, so that multiple server ends respectively read the data packets from the message middleware to calculate credit information and obtain multiple credit information; receiving the multiple credit information returned by multiple server ends, and aggregating the multiple credit information to obtain total credit information.
[0006] According to the second aspect, an embodiment of the present invention provides a credit information generation method, characterized in that, when applied to a server, the method includes: reading user data and model information from a message middleware, the user data and model information are acquired by a production end and sent to the message middleware, the model information is used to describe the sub-calculation rules, user data, and rule coefficient information required for the current credit assessment scenario; selecting and extracting sub-calculation rules corresponding to the model information from the calculation rules of a cache end according to the model information, the calculation rules are acquired by the production end and sent to the cache end; acquiring corresponding rule coefficient information according to the model information; combining the sub-calculation rules and the rule coefficient information into a calculation formula, and calculating the credit information of the user data through the calculation formula; and sending the credit information to the production end.
[0007] Optionally, when the model information represents a house rental scenario, the user data includes identity information, performance information, behavior information, external credit and comprehensive evaluation information, wherein the identity information includes at least one of authorization authentication, real-name authentication, work information and educational information, the performance information includes the user's historical house rental performance and termination records, the behavior information is used to characterize the user's breach of contract behavior, the external credit is generated based on the user's social violation record and recruitment record, and the comprehensive evaluation information includes at least one of the user's cleaning, moving, maintenance and living payment times.
[0008] Optionally, calculating the credit information of the user data by using the calculation formula includes: dividing the user data into batches, and calling multiple threads from a thread pool to perform parallel calculations on the divided user data using the calculation formula to obtain multiple sub-calculation results; when all threads complete the calculations, packaging the multiple sub-calculation results to obtain the credit information.
[0009] According to the third aspect, an embodiment of the present invention provides a credit information generating device, which is applied to the production end, and the device includes: an information collection module, which is used to obtain user data, calculation rules and model information used to calculate credit information, and the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario; a first sending module, which is used to send the obtained calculation rules to the cache end; a second sending module, which is used to send the user data and the model information to the message middleware, so that the server end reads the user data and the model information from the message middleware, and enables the server end to obtain the sub-calculation rules and rule coefficient information corresponding to the model information, and then calculates the credit information of the user data through the calculation formula composed of the sub-calculation rules and the rule coefficient information, and the sub-calculation rules are selected and extracted by the server end from the calculation rules of the cache end; a receiving module, which is used to receive the credit information returned by the server end.
[0010] According to the fourth aspect, an embodiment of the present invention provides a credit information generating device, which is applied to a server, and the device includes: a first reading module, which is used to read user data and model information from a message middleware, wherein the user data and model information are acquired by a production end and sent to the message middleware, and the model information is used to describe the sub-calculation rules, user data, and rule coefficient information required for the current credit assessment scenario; a second reading module, which is used to select and extract the sub-calculation rules corresponding to the model information from the calculation rules of a cache end according to the model information, wherein the calculation rules are acquired by the production end and sent to the cache end; a third reading module, which is used to acquire the corresponding rule coefficient information according to the model information; a calculation module, which is used to combine the sub-calculation rules and the rule coefficient information into a calculation formula, and calculate the credit information of the user data through the calculation formula; and a feedback module, which is used to send the credit information to the production end.
[0011] According to the fifth aspect, an embodiment of the present invention provides a credit information generation system, characterized in that it includes a production end, a service end, a message middleware and a cache end, wherein: the production end obtains user data, calculation rules and model information for calculating credit information, and the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario; the production end sends the calculation rules to the cache end; the production end sends the user data and the model information to the message middleware; the server end reads the user data and the model information from the message middleware, and obtains the sub-calculation rules corresponding to the model information from the cache end, and then obtains the rule coefficient information corresponding to the model information; the server end calculates the credit information of the user data through a calculation formula composed of the sub-calculation rules and the rule coefficient information; the server end returns the credit information to the production end.
[0012] According to the sixth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method described in the first aspect, the second aspect, or any optional implementation manner of the first aspect or the second aspect by executing the computer instructions.
[0013] According to the seventh aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect, the second aspect, or any optional implementation manner of the first aspect or the second aspect.
[0014] The technical solution provided by this application has the following advantages:
[0015] The technical solution provided by the present application first obtains user data representing various aspects of user information, all calculation rules for various application scenarios, and the preset model information corresponding to the user in the current credit evaluation scenario through the production end. The production end sends the user data and model information to the message middleware so that the server end can read the relevant data from the message middleware. The production end sends all the calculation rules to the cache end, which is convenient for the server end to extract the required calculation rules from the cache end at any time, avoiding the step of sending the calculation rules for each calculation, and improving the calculation efficiency. After the server end reads the current model information and user data from the message middleware, according to the calculation rules specified in the model information, it extracts the required sub-calculation rules from all the calculation rules of the cache end, and obtains the rule coefficient information corresponding to the sub-calculation rules from the external database or the internal database, and then the rule coefficient information and the corresponding sub-calculation rules form a calculation formula. The server end finds the part of the data involved in the calculation from the user data according to the preset provisions of the model information and inputs it into the calculation formula, thereby obtaining the user credit score (i.e. credit information) in the current scoring scenario. When the user's credit scoring scenario changes, the corresponding model can be directly switched to quickly re-evaluate the credit. When the credit assessment method of a credit scoring scenario changes, the description statement of the model information can be adjusted directly. This enables each payment scenario to quickly carry out a specific scoring process, improving the flexibility of user credit scoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings:
[0017] Figure 1 A schematic diagram of the structure of a credit information generation system in one embodiment of the present invention is shown;
[0018] Figure 2 A schematic diagram of a scoring process of a credit information generation system in one embodiment of the present invention is shown;
[0019] Figure 3 A diagram showing an example structure of a scene model in one embodiment of the present invention is shown;
[0020] Figure 4 A schematic diagram showing the steps of a credit information generation method in one embodiment of the present invention is shown;
[0021] Figure 5 A schematic diagram of the structure of a credit information generating device in one embodiment of the present invention is shown;
[0022] Figure 6 Another structural schematic diagram of a credit information generating device in one embodiment of the present invention is shown;
[0023] Figure 7 A schematic structural diagram of an electronic device in one embodiment of the present invention is shown. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0025] See also Figure 1 and Figure 2 In one embodiment, a credit information generation system includes a production end 1, a service end 2, a message middleware 3 and a cache end 4, wherein:
[0026] The production end 1 obtains user data, calculation rules and model information used to calculate credit information. The model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit scoring scenario.
[0027] The production end 1 sends the calculation rules to the cache end 4;
[0028] The production end 1 sends the user data and model information to the message middleware 3;
[0029] The server 2 reads the user data and model information from the message middleware 3, obtains the sub-calculation rules corresponding to the model information from the cache 4, and then obtains the rule coefficient information corresponding to the model information;
[0030] The server 2 calculates the credit information of the user data through a calculation formula composed of sub-calculation rules and rule coefficient information;
[0031] Server 2 returns the credit information to producer 1.
[0032] Specifically, in this embodiment, the credit score evaluation system is composed of the production end 1, the service end 2, the message middleware 3 and the cache end 4, which can be implemented by electronic devices such as personal computers, mobile phones, tablet computers and servers, and the present invention is not limited to this. However, the production end 1 is mainly used for data collection, data preprocessing and result display, so this embodiment uses small devices such as personal computers, mobile phones and tablet computers as the production end 1; the message middleware 3 includes but is not limited to message queues such as Kafka and Rabbit. Since the calculation amount and data flow of the message middleware 3 and the service end 2 are usually large, this embodiment is implemented based on a server or a server cluster; the cache end 4 needs to store a large number of calculation rules, and electronic devices of medium to large size such as personal computers or servers can be selected. This embodiment stores the calculation rules in the form of key-value based on redis cache. After collecting user data, the production end 1 first preprocesses the user data and stores the relevant information of the preprocessing in the database, mainly including labeling, deduplication, and removal of invalid data according to the data type, for example: classifying the data into friendly behavior, multi-contract calculation, real name, authorization, lease status, negative records, blacklist, etc. Then the tag information is stored in the database. Then the production end 1 sends all the collected user data to the message middleware 3, so that the server 2 can read the user data from the message middleware 3. In order to improve the flexibility of user credit information generation, Figure 3 As shown, this embodiment pre-creates multiple scenario models, each scenario model corresponds to different credit calculation rules, different user data and different rule coefficients. The scenario model of the user can flexibly adjust the rules described therein as the business of each scenario changes, and the newly added rules are directly sent to the cache end 4 for calling, without modifying the old rules. Each rule is determined by the generalized rules and specific configurations (labels, scores, weights) in the rule library. According to the rules and user data, the specific credit score of the user can be calculated. In this embodiment, the credit score is used as credit information to characterize the credit of the user. For the case where the user's evaluation scenario changes, for example: a user's credit is poor, the user's credit score in the home purchase scenario is low, thereby restricting the user's home purchase behavior. However, it is unreasonable to restrict the user's behavior of using small loans for shopping with the current credit score, so it is necessary to re-evaluate the user's credit for other scenarios. In this embodiment, corresponding scenario models are set for multiple application scenarios in advance, so that when the user's payment business scenario changes, the corresponding model is switched in time for calculation, and the corresponding score of the user under different models is obtained, so that the user's credit score is faster and more flexible.
[0033] Based on this, the production end 1 matches the current credit assessment scenario with the preset scenario model, obtains the model information with the highest similarity, and then sends the model information to the message middleware 3. In addition, the production end 1 also obtains all calculation rules during the initial calculation, and sends the calculation rules to the cache end 4, so that the server end 2 can directly select the calculation rules corresponding to the current credit scoring scenario from the cache end 4 in subsequent multiple calculations, thereby improving calculation efficiency.
[0034] After the server 2 obtains the model information and user data from the message middleware 3, the server 2 extracts the required sub-calculation rules from all the calculation rules of the cache 4 according to the description of the model information, and then obtains the rule coefficient information required for the calculation rules from the internal database or external database (this embodiment uses the Apollo configuration center, which is a distributed configuration center developed by the framework department of Ctrip, which can centrally manage the configuration of different application environments and different clusters. After the configuration is modified, it can be pushed to the application end in real time, and has standardized permissions, process governance and other characteristics, which is suitable for microservice configuration management scenarios). For example: Rule 1 is used in both scenario A and scenario B. Assume that the rule is c=ax+b, where a and b are rule coefficients. In actual applications, the rule coefficients corresponding to scenario A and scenario B are different. Therefore, the configuration is performed through the configuration center, and the subsequent rule coefficient information can also be modified at any time, which further increases flexibility. After that, the server 2 combines the rule coefficient information and the calculation rules according to the description of the model information to form a calculation formula that can be used for calculation. Finally, the user data is substituted into the calculation formula to obtain an accurate scoring result, and the scoring result is returned to the production end 1 to inform the user of the credit score of the current scenario.
[0035] See also Figure 4 In one embodiment, a credit information generation method, steps S101 to S104 are applied to the production end in the above system embodiment, and steps S201 to S205 are applied to the service end in the above system embodiment, and the specific steps are as follows:
[0036] Step S101: Obtain user data, calculation rules and model information used to calculate credit information, where the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario.
[0037] Step S102: Send the calculation rules to the cache end.
[0038] Step S103: Send the user data and model information to the message middleware.
[0039] Step S201: Read user data and model information from the message middleware.
[0040] Step S202: selecting and extracting sub-calculation rules corresponding to the model information from the calculation rules at the cache end according to the model information.
[0041] Step S203: Obtain corresponding rule coefficient information according to the model information.
[0042] Step S204: The sub-calculation rules and the rule coefficient information are combined into a calculation formula, and the credit information of the user data is calculated through the calculation formula.
[0043] Step S205: Send the credit information to the production end.
[0044] Step S104: Receive the credit information returned by the server.
[0045] Specifically, the specific elaboration of the above method embodiment can refer to the relevant description of the above system embodiment, which will not be repeated here.
[0046] Specifically, in one embodiment, a credit scoring method provided by an embodiment of the present invention is applied to a production end and further includes the following steps:
[0047] Step 1: Divide user data into multiple parts.
[0048] Step 2: Pack each user data and model information separately to obtain multiple data packets, and send the multiple data packets to the message middleware, so that multiple servers can read the data packets from the message middleware to calculate the credit information and obtain multiple credit information.
[0049] Step 3: Receive multiple credit information returned by multiple servers, and aggregate the multiple credit information to obtain the total credit information.
[0050] Specifically, in this embodiment, the user data is split into batches, and then each piece of split user data is packaged together with the model information and sent to the message middleware. Thus, multiple servers are used to read the data packets from the message middleware respectively, and then parallel calculations are performed. Compared with the calculation speed of a single server, a server cluster is constructed based on the idea of "divide and conquer", thereby greatly improving the calculation efficiency of the user credit score. When the amount of data is larger, the number of servers can be increased without the need to reconstruct and upgrade the entire system, which improves the convenience of system maintenance and upgrade.
[0051] Specifically, in one embodiment, when the model information represents a house rental scenario, the user data includes identity information, performance information, behavior information, external credit and comprehensive evaluation information, wherein the identity information includes at least one of authorization authentication, real-name authentication, work information and educational information, the performance information includes the user's historical house rental performance and termination records, the behavior information is used to characterize the user's breach of contract, the external credit is generated based on the user's social violation record and recruitment record, and the comprehensive evaluation information includes at least one of the user's cleaning, moving, maintenance and living payment times.
[0052] Specifically, in this embodiment, for the special scenario of renting a house, a specific credit score calculation is performed with more targeted data, thereby further improving the accuracy of the credit score assessment. The score consists of five dimensions: identity information, performance information, behavior information, external credit, and comprehensive evaluation information, with a score range of 0 to 980 points. The page displays the score range, with the highest score being 1000 points. If the score exceeds 1000 points, the page displays 1000 points; the lowest score is 149 points. If the score is lower than 149 points, the background records the real score, and the page displays 149 points until the user score exceeds 149, then the page displays the real score. Identity information includes at least one of authorization authentication, real-name authentication, work information, and education information. In order to more accurately measure the user's credit, in this embodiment, all of the above information is involved in the calculation, for example: the software gets 100 points for the user's authorization authentication, 100 points for the user to complete the real-name authentication, and 25 points for the user to complete the work information and education information. The performance information mainly consists of performance and termination. The monthly rent performance is scored 15 points. If the user pays normally and completes the rent this month, the score will be scored. In the behavior information, if the user has been added to the blacklist by the background, the score is adjusted to a fixed score, for example, the score is directly deducted to 299 points and no longer updated. If the user's breach of contract record within the preset time is not handled, 100 points can be deducted according to one valid record, 200 points can be deducted according to two valid records, and three valid records can be added to the blacklist. The score is directly deducted to 299 points and no longer updated. External credit includes social security and recruitment records. This embodiment is based on the data of two applications, LinkedIn and Maimai, as a reference standard. For example: if the user has no illegal or disorderly behavior, the social security dimension will be added 100 points, and if there is no bad record on LinkedIn and Maimai, 10 points will be added each. Finally, the total score is adjusted by the number of cleaning, moving, maintenance and living expenses paid by the user. In this embodiment, when the user's rental time is greater than the preset time, the credit score is updated every month at a fixed interval. For example, when a user has rented for 36 months, his credit score usually reaches more than 750 points. At this time, the score is updated according to the rule of increasing 1 point per month, and the score is no longer updated according to the original points rule. Through the above calculation steps, the credit score obtained is used as information representing the user's credit, which provides the accuracy of the user's credit assessment.
[0053] Specifically, in one embodiment, the above step S204 specifically includes the following steps:
[0054] Step 4: Divide the user data into batches, and call multiple threads from the thread pool to perform parallel calculations on the divided user data using calculation formulas to obtain multiple sub-calculation results.
[0055] Step 5: When all threads finish calculating, multiple sub-calculation results are packaged to obtain credit information.
[0056] Specifically, in this embodiment, each server has a thread pool inside. After receiving user data and model information, multiple threads are called from the thread pool to further split the user data and calculate the credit score, thereby further improving the efficiency of generating credit information.
[0057] Through the above steps, the technical solution provided by the present application first obtains user data representing various aspects of user information, all calculation rules for various application scenarios, and the preset model information corresponding to the user in the current credit evaluation scenario through the production end. The production end sends the user data and model information to the message middleware so that the server can read the relevant data from the message middleware. The production end sends all calculation rules to the cache end, which is convenient for the server to extract the required calculation rules from the cache end at any time in the future, avoiding the step of sending the calculation rules for each calculation, and improving the calculation efficiency. After the server reads the current model information and user data from the message middleware, according to the calculation rules specified in the model information, it extracts the required sub-calculation rules from all calculation rules of the cache end, and obtains the rule coefficient information corresponding to the sub-calculation rules from the external database or the internal database, and then the rule coefficient information and the corresponding sub-calculation rules form a calculation formula. The server finds the part of the data involved in the calculation from the user data according to the preset provisions of the model information and inputs it into the calculation formula, thereby obtaining the user credit score (i.e. credit information) in the current scoring scenario. When the user's credit scoring scenario changes, the corresponding model can be directly switched to quickly re-evaluate the credit. When the credit assessment method of a credit scoring scenario changes, the description statement of the model information can be adjusted directly. This enables each payment scenario to quickly carry out a specific scoring process, improving the flexibility of user credit scoring.
[0058] like Figure 5 As shown, this embodiment also provides a credit information generation device, which is applied to the production end, and the device includes:
[0059] The information collection module 101 is used to obtain user data, calculation rules and model information for calculating credit information. The model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario. For details, please refer to the relevant description of step S101 in the above method embodiment, which will not be repeated here.
[0060] The first sending module 102 is used to send the obtained calculation rule to the cache end. For details, please refer to the relevant description of step S102 in the above method embodiment, which will not be repeated here.
[0061] The second sending module 103 is used to send the user data and model information to the message middleware, so that the server can read the user data and model information from the message middleware, and obtain the sub-calculation rules and rule coefficient information corresponding to the model information, and then calculate the credit information of the user data by the calculation formula composed of the sub-calculation rules and rule coefficient information, and the sub-calculation rules are selected and extracted by the server from the calculation rules of the cache. For details, please refer to the relevant description of step S103 in the above method embodiment, which will not be repeated here.
[0062] The receiving module 104 is used to receive the credit information returned by the service end. For details, please refer to the relevant description of step S104 in the above method embodiment, which will not be repeated here.
[0063] like Figure 6 As shown, this embodiment also provides a credit information generation device, which is applied to the server, and the device includes:
[0064] The first reading module 201 is used to read user data and model information from the message middleware. The user data and model information are obtained by the production end and sent to the message middleware. The model information is used to describe the calculation rules, user data and rule coefficient information required for the current credit assessment scenario. For details, please refer to the relevant description of step S201 in the above method embodiment, which will not be repeated here.
[0065] The second reading module 202 is used to select and extract the sub-calculation rules corresponding to the model information from the calculation rules of the cache end according to the model information. The calculation rules are obtained by the production end and sent to the cache end. For details, please refer to the relevant description of step S202 in the above method embodiment, which will not be repeated here.
[0066] The third reading module 203 is used to obtain corresponding rule coefficient information according to the model information. For details, please refer to the relevant description of step S203 in the above method embodiment, which will not be repeated here.
[0067] The calculation module 204 is used to combine the sub-calculation rules and the rule coefficient information into a calculation formula, and calculate the credit information of the user data through the calculation formula. For details, please refer to the relevant description of step S204 in the above method embodiment, which will not be repeated here.
[0068] Feedback module 205 is used to send the credit information to the production end. For details, please refer to the relevant description of step S205 in the above method embodiment, which will not be repeated here.
[0069] A credit scoring device provided in an embodiment of the present invention is used to execute a credit scoring method provided in the above embodiment. Its implementation method and principle are the same. For details, please refer to the relevant description of the above method embodiment, which will not be repeated here.
[0070] Through the collaboration of the above components,
[0071] The technical solution provided by the present application first obtains user data representing various aspects of user information, all calculation rules for various application scenarios, and the preset model information corresponding to the user in the current credit evaluation scenario through the production end. The production end sends the user data and model information to the message middleware so that the server end can read the relevant data from the message middleware. The production end sends all the calculation rules to the cache end, which is convenient for the server end to extract the required calculation rules from the cache end at any time, avoiding the step of sending the calculation rules for each calculation, and improving the calculation efficiency. After the server end reads the current model information and user data from the message middleware, according to the calculation rules specified in the model information, it extracts the required sub-calculation rules from all the calculation rules of the cache end, and obtains the rule coefficient information corresponding to the sub-calculation rules from the external database or the internal database, and then the rule coefficient information and the corresponding sub-calculation rules form a calculation formula. The server end finds the part of the data involved in the calculation from the user data according to the preset provisions of the model information and inputs it into the calculation formula, thereby obtaining the user credit score (i.e. credit information) in the current scoring scenario. When the user's credit scoring scenario changes, the corresponding model can be directly switched to quickly re-evaluate the credit. When the credit assessment method of a credit scoring scenario changes, the description statement of the model information can be adjusted directly. This enables each payment scenario to quickly carry out a specific scoring process, improving the flexibility of user credit scoring.
[0072] Figure 7 An electronic device according to an embodiment of the present invention is shown, the device includes a processor 901 and a memory 902, which can be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.
[0073] The processor 901 may be a central processing unit (CPU). The processor 901 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.
[0074] The memory 902 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above method embodiments. The processor 901 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 902, that is, implementing the methods in the above method embodiments.
[0075] The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 901, etc. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 902 may optionally include a memory remotely arranged relative to the processor 901, and these remote memories may be connected to the processor 901 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0076] One or more modules are stored in the memory 902 , and when executed by the processor 901 , the method in the above method embodiment is executed.
[0077] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the above method embodiments, and will not be repeated here.
[0078] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the implemented program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.
[0079] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A credit information generation method, characterized in that: Applied to the production end, the method includes: Obtaining user data, calculation rules, and model information for calculating credit information, wherein the model information is used to describe the sub-calculation rules, user data, and rule coefficient information required for the current credit assessment scenario; Sending the obtained calculation rule to a cache end; Sending the user data and the model information to the message middleware, so that the server reads the user data and the model information from the message middleware, and the server obtains the sub-calculation rules and rule coefficient information corresponding to the model information, and then calculates the credit information of the user data by a calculation formula composed of the sub-calculation rules and the rule coefficient information, wherein the sub-calculation rules are selected and extracted by the server from the calculation rules of the cache end; Receiving the credit information returned by the server; The method further comprises: Dividing the user data into multiple parts; Packing each user data and the model information respectively to obtain multiple data packets, and sending the multiple data packets to the message middleware, so that multiple service ends read the data packets from the message middleware respectively to calculate the credit information and obtain multiple credit information; The multiple credit information returned by the multiple service ends are received, and the multiple credit information are aggregated to obtain the total credit information.
2. A credit information generation method, characterized in that: Including multiple servers, the method applied to one of the servers includes: Reading user data and model information from the message middleware, wherein the user data and model information are obtained by the production end and sent to the message middleware, and the model information is used to describe the sub-calculation rules, user data, and rule coefficient information required for the current credit assessment scenario; Selecting and extracting sub-calculation rules corresponding to the model information from calculation rules at the cache end according to the model information, wherein the calculation rules are obtained by the production end and sent to the cache end; Acquire corresponding rule coefficient information according to the model information; Combining the sub-calculation rules and the rule coefficient information into a calculation formula, and calculating the credit information of the user data by using the calculation formula; Sending the credit information to the production end; Among them, the user data read from the message middleware is one of the multiple copies divided by the production end. The production end packages each user data and the model information to obtain multiple data packets, and sends the multiple data packets to the message middleware, so that each server end respectively executes the steps from reading the user data and model information from the message middleware to sending the credit information to the production end, so that the production end obtains multiple credit information, and then the production end summarizes the multiple credit information to obtain the total credit information.
3. The method according to claim 2, characterized in that When the model information represents a house rental scenario, the user data includes identity information, performance information, behavior information, external credit and comprehensive evaluation information, wherein the identity information includes at least one of authorization authentication, real-name authentication, work information and educational information; the performance information includes the user's historical house rental performance and termination records; the behavior information is used to characterize the user's breach of contract; the external credit is generated based on the user's social violation record and recruitment record; and the comprehensive evaluation information includes at least one of the user's cleaning, moving, maintenance and living payment times.
4. The method according to claim 2 or 3, characterized in that: The calculating the credit information of the user data by the calculation formula includes: Divide the user data into batches, and call multiple threads from the thread pool to perform parallel calculations on the divided user data using the calculation formula to obtain multiple sub-calculation results; When all thread calculations are completed, the multiple sub-calculation results are packaged to obtain the credit information.
5. A credit information generating device, characterized in that: Applied to the production end, the device includes: An information collection module is used to obtain user data, calculation rules and model information used to calculate credit information, wherein the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario; and divide the user data into multiple parts; A first sending module, used for sending the obtained calculation rule to a cache end; The second sending module is used to send the user data and the model information to the message middleware, so that the server reads the user data and the model information from the message middleware, and the server obtains the sub-calculation rules and rule coefficient information corresponding to the model information, and then calculates the credit information of the user data by the calculation formula composed of the sub-calculation rules and the rule coefficient information, wherein the sub-calculation rules are selected and extracted by the server from the calculation rules of the cache end; each user data and the model information are packaged to obtain multiple data packets, and the multiple data packets are sent to the message middleware, so that multiple servers read the data packets from the message middleware to calculate the credit information and obtain multiple credit information; The receiving module is used to receive the credit information returned by the server; receive the multiple credit information returned by multiple servers, and aggregate the multiple credit information to obtain total credit information.
6. A credit information generating device, characterized in that: The invention comprises a plurality of servers, and a device applied to one of the servers comprises: A first reading module is used to read user data and model information from the message middleware, wherein the user data and model information are obtained by the production end and sent to the message middleware, and the model information is used to describe the sub-calculation rules, user data, and rule coefficient information required for the current credit assessment scenario; A second reading module, configured to select and extract sub-calculation rules corresponding to the model information from calculation rules of the cache end according to the model information, wherein the calculation rules are obtained by the production end and sent to the cache end; A third reading module, used for acquiring corresponding rule coefficient information according to the model information; A calculation module, used to combine the sub-calculation rules and the rule coefficient information into a calculation formula, and calculate the credit information of the user data through the calculation formula; A feedback module, used for sending the credit information to the production end; Among them, the user data read from the message middleware is one of the multiple copies divided by the production end. The production end packages each user data and the model information to obtain multiple data packets, and sends the multiple data packets to the message middleware, so that each server end executes the steps from the first reading module to the feedback module respectively, so that the production end obtains multiple credit information, and then the production end summarizes the multiple credit information to obtain the total credit information.
7. A credit information generation system, characterized in that: It includes the production side, the server side, the message middleware and the cache side, among which: The production end obtains user data, calculation rules and model information for calculating credit information, wherein the model information is used to describe the sub-calculation rules, user data and rule coefficient information required for the current credit assessment scenario; the production end divides the user data into multiple parts; The production end sends the calculation rule to the cache end; The production end sends the user data and the model information to the message middleware; each user data and the model information are packaged to obtain multiple data packets, and the multiple data packets are sent to the message middleware, so that multiple service ends read the data packets from the message middleware to calculate the credit information and obtain multiple credit information; The server reads the user data and the model information from the message middleware, obtains the sub-calculation rules corresponding to the model information from the cache, and then obtains the rule coefficient information corresponding to the model information; The server calculates the credit information of the user data by using a calculation formula composed of the sub-calculation rule and the rule coefficient information; The service end returns the credit information to the production end; The production end receives the multiple credit information returned by multiple service ends, and aggregates the multiple credit information to obtain total credit information.
8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 or 2-4 by executing the computer instructions.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 or 2-4.
Citation Information
Patent Citations
Concurrent program developing method for processing of large-scale data based on small memory
CN104572106A
Message congestion control method, system and equipment, and storage medium
CN109347757A
Data processing method, real-time computing system and information system
CN110347399A
Computing task processing method, device and system, server and storage medium
CN110955461A
Credit score calculation method and device and storage medium
CN114202384A
