Credit investigation data processing method and device

Abstract

One or more embodiments of the invention provide a credit investigation data processing method and device, and the method comprises the steps: obtaining the target identity information and target behavior characteristics of a target user; and determining target credit investigation data matched with the target user from the obtained credit investigation data set corresponding to each channel according to the target identity information and the target behavior characteristics of the target user. After target credit investigation data matched with a target user is determined, according to attribute information of field information corresponding to a target conflict field in a data item corresponding to each channel included in the target credit investigation data, determining a confidence coefficient of the field information corresponding to the target conflict field in each channel, and determining target field information of the target conflict field according to each confidence coefficient to serve as a data processing result.

Description

TECHNICAL FIELD

[0001] The one or more embodiments of the present specification relate to the technical field of credit data processing, and in particular to a credit data processing method and device. BACKGROUND

[0002] In order to ensure the reliability of credit data, credit institutions usually connect with different financial institutions and data sources, so that the credit data obtained by the credit institutions comes from different channels. Due to the non-uniform execution standards of credit data between different financial institutions, the credit data of the same user in different financial institutions has a large difference, that is, the credit institutions are difficult to obtain credit data with uniform standards from different channels.

[0003] Therefore, in the existing credit data set collection of each channel, there is a lack of effective user data association mechanism and data conflict resolution scheme, which makes it difficult for credit institutions to obtain high-quality credit data through multiple channels. SUMMARY

[0004] Therefore, the one or more embodiments of the present specification provide a credit data processing method and device.

[0005] To achieve the above-mentioned purpose, the one or more embodiments of the present specification provide technical solutions as follows: According to a first aspect of the one or more embodiments of the present specification, a credit data processing method is provided, comprising: obtaining target identity information and target behavior characteristics of a target user; determining target credit data matched with the target user from obtained credit data sets corresponding to each channel based on the target identity information and the target behavior characteristics; each credit data set corresponding to each channel includes credit data of a plurality of users; the target credit data includes data items corresponding to each channel; determining the confidence of each channel in the field information corresponding to the target conflict field based on the attribute information of the field information corresponding to the target conflict field of each channel corresponding data item, and determining the target field information of the target conflict field based on the confidence of each channel in the target conflict field as a data processing result; wherein the target field is any one of a plurality of fields included in the data item.

[0006] According to a second aspect of the one or more embodiments of the present specification, a credit data processing device is provided, comprising: an obtaining module, configured to obtain target identity information and target behavior characteristics of a target user; The determination module determines the target credit data matching the target user from the obtained credit data sets corresponding to each channel, based on the target identity information and the target behavioral characteristics; each channel's credit data set includes the credit data of multiple users; the target credit data includes data items corresponding to each channel; The conflict handling module determines the confidence level of each channel's field information corresponding to the target conflict field based on the attribute information of the field information corresponding to the target conflict field for each channel's data item, and determines the target field information of the target conflict field based on the confidence level of each channel's field information corresponding to the target conflict field, as the data processing result; wherein, the target field is any one of the multiple fields contained in the data item.

[0007] According to a third aspect of one or more embodiments of this specification, an electronic device is provided, comprising: processor; Memory used to store processor-executable instructions; The processor implements the method as described in the first aspect by running the executable instructions.

[0008] 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 as described in the first aspect.

[0009] According to a fifth aspect of one or more embodiments of this specification, a computer program product is provided, comprising: a computer program / instructions that, when executed by a processor, implement the method as described in the first aspect.

[0010] As can be seen from the above embodiments, the credit data processing method and apparatus provided in one or more embodiments of this specification first obtain the target identity information and target behavioral characteristics of the target user, and then determine the target credit data matching the target user from the obtained credit datasets corresponding to various channels based on the target identity information and target behavioral characteristics of the target user. Since the user's identity information and behavioral characteristics are considered simultaneously when determining the target credit data of the target user, the accuracy of the association between the target credit data and the target user is further guaranteed, realizing the association of credit data from multiple channels with the same target user. After determining the target credit data matching the target user, the confidence level of the field information corresponding to the target conflict field of each channel is determined based on the attribute information of the field information corresponding to the target conflict field of each data item included in the target credit data, and the target field information of the target conflict field is determined based on each confidence level. By comparing the confidence levels of each field information, the information conflict of the conflict fields is eliminated, and the quality of the target credit data is improved. Attached Figure Description

[0011] Figure 1 This is an exemplary embodiment of the architecture diagram of an application scenario for a credit data processing method.

[0012] Figure 2 This is a flowchart illustrating a credit data processing method provided in an exemplary embodiment.

[0013] Figure 3 This is a flowchart illustrating another credit data processing method provided in an exemplary embodiment.

[0014] Figure 4 This is a schematic diagram of the structure of a device provided in an exemplary embodiment.

[0015] Figure 5 This is a block diagram of a credit data processing apparatus provided in an exemplary embodiment. Detailed Implementation

[0016] 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.

[0017] The organizational information (including but not limited to organizational equipment information, organizational personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) involved in this manual are all information and data authorized by the organization or fully authorized by all parties. Furthermore, the collection, use, and processing of such data must comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation portals are provided for the organization to choose to authorize or refuse.

[0018] As described in the background section, existing credit data collection across various channels suffers from fragmented data collection methods. This is due to differences in user identification rules across different data sources. For example, some financial institutions use the user's ID number as the core identifier, while some third-party platforms use a real-name authenticated mobile phone number or device ID as the associated field. Consequently, credit data for the same user across different channels, such as credit records, repayment behavior, and account information, is often fragmented. Credit reporting agencies struggle to accurately identify and aggregate all data belonging to the same user, leading to omissions of user credit information and impacting the comprehensiveness of credit assessments. Furthermore, differences in data collection timing, update mechanisms, and entry standards can result in different values ​​for the same attribute information of the same user across different channels. For instance, after a user's occupation changes, only some financial institutions update the occupation description field, such as changing from employee to corporate manager, while other channels retain the old occupation information. Therefore, current technologies lack effective user data association mechanisms and data conflict resolution solutions, making it difficult for credit reporting agencies to obtain high-quality credit data from multiple channels.

[0019] In summary, this specification proposes a credit data processing method. It acquires the target user's identity information and behavioral characteristics, and then determines the target credit data matching the target user from the obtained credit datasets corresponding to various channels based on these characteristics. Since both the user's identity information and behavioral characteristics are considered when determining the target credit data, the accuracy of the association between the target credit data and the target user is further ensured. This allows for the association of credit data from multiple channels with the same target user, accurately identifying and aggregating all data belonging to the same user. After determining the target credit data matching the target user, the confidence level of each channel's field information corresponding to the target conflict field is determined based on the attribute information of each data item corresponding to the target conflict field in the target credit data. The target field information of the target conflict field is then determined based on each confidence level. By comparing the confidence levels of each field, information conflicts in the conflict fields are eliminated, improving the quality of the target credit data and providing assurance for accurate decision-making using this target credit data.

[0020] Figure 1 This is an exemplary embodiment illustrating the architecture of an application scenario for a credit data processing method. For example... Figure 1 As shown, the method may include a server 34, an electronic device 35, and several data platforms, such as a first data platform 31, a second data platform 32, and a third data platform 33.

[0021] Server 34 can be a physical server containing an independent host, or it can be a virtual server hosted in a host cluster. During operation, server 34 can run server-side programs for a specific application to implement the relevant functions of that application. For example, when server 34 runs a credit data processing method program, it can act as the execution entity for the credit data processing method.

[0022] The data platform can be a platform set up by financial institutions, data operators, or social platforms to provide credit data to server 34. In some embodiments, the data platform acts as a carrier of a database and may contain a single-machine database on an independent host or a distributed database composed of multiple data nodes. Each data node can be considered an independent host, responsible for only a portion of the global data. In some embodiments, the database stores a large amount of data and can be partitioned according to different uses and data types. The sources of the data include, but are not limited to, existing databases, data crawled from the Internet, or data uploaded by users when using the client.

[0023] In some embodiments, the electronic device can be a PC (Personal Computer), tablet computer, mobile phone, or other types of electronic devices that users can use. In fact, users can obviously also use electronic devices such as laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smartwatches, etc.), etc., and one or more embodiments of 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 the program service of the aforementioned credit data processing method, it can act as a client for that program. In some embodiments, the client is used to send a data request instruction to the server 34 and obtain the credit data processed by the aforementioned data processing method from the server 34. The application of the aforementioned program service client can be launched and run on the electronic device. The 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 technologies, the relevant functions can be implemented through a page displayed by a browser. Here, the browser can be a standalone browser application or a browser module embedded in some applications.

[0024] The network for interaction between the data platform, electronic device 35, and server 31 can specifically choose to use wired or wireless networks for communication, depending on the communication methods supported by the corresponding electronic device or data platform. This specification does not impose any restrictions on this. For example, if the electronic device can support both wired and wireless communication, then wired or wireless networks can be used for communication as needed. However, if the data platform typically only supports wired communication, then a wired network can be used for communication.

[0025] refer to Figure 2 This is a flowchart of a credit data processing method provided in this specification, which includes the following steps: S202, Obtain the target user's target identity information and target behavioral characteristics.

[0026] The target user can be any one of multiple users included in the credit data sets corresponding to various channels. When starting the data processing method of the embodiments of this specification, after obtaining the credit data sets corresponding to multiple channels, any one of the users included in the credit data set corresponding to a single channel can be directly selected as the target user to begin obtaining the target user's target identity information and target behavioral characteristics. Alternatively, in some embodiments, the target user among multiple users may first issue a credit data acquisition request, and then the data processing method of the embodiments of this specification may be started according to the acquisition request, that is, after receiving the target user's credit data acquisition request, the target user's target identity information and target behavioral characteristics may be acquired first.

[0027] In some embodiments, identity information may include one or more pieces of information that can identify a user, such as name, ID card number, and mobile phone number. The target identity information refers to the identity information of the target user. In some embodiments, this target identity information can be obtained directly from the credit data of the target user in a credit data set corresponding to a specific channel. That is, a target channel can be randomly selected from multiple channels, and then a user can be randomly selected as the target user from the credit data set provided by the target channel. The target user's target identity characteristics are then determined using the credit data of that target user in the target channel. In some embodiments, the target identity information may also be provided by the target user when issuing a credit data query request.

[0028] Considering that different channels use different information for identity authentication, and that some channels may contain fraudulent or aliased user information in their credit data, this embodiment of the specification, in order to further improve the accuracy of collecting credit data for target users, acquires not only identity information but also the target user's target behavioral characteristics when obtaining the target user's identity credentials. Since different users have different behavioral habits, even if an imposter appears, and can forge the identity information of the impersonated user, their credit data can still be distinguished by differences in behavioral characteristics. In some embodiments, user behavioral characteristics can be determined by clustering each user's credit data using a preset clustering algorithm, or by extracting features from the user's credit data using a network model. It should be noted that both the preset clustering algorithm and the network model can be selected as needed and are not limited thereto.

[0029] To further improve the accuracy of user behavior characteristics, in some embodiments of this specification, the target behavior characteristics include the target user's operating habits and social relationship characteristics. Specifically, the user's operating habits may include characteristics such as transaction time, transaction amount, and transaction frequency across different channels, while the social relationship characteristics may include the user's transaction partners and request flow networks across different channels.

[0030] S204, based on the target identity information and the target behavioral characteristics, determine the target credit data matching the target user from the credit data sets corresponding to each channel; the credit data set corresponding to each channel includes the credit data of multiple users; the target credit data includes data items corresponding to each channel.

[0031] After obtaining the target user's identity information and behavioral characteristics, the target credit data matching the target user can be determined from the credit data sets corresponding to each channel. Each channel's credit data set includes the credit data of multiple users. Based on the target identity information and behavioral characteristics, users matching the target user can be identified from each channel. The credit data of this matching user in the credit data set corresponding to that channel is then determined as the target user's target credit data. Since the target user may find matching credit data in multiple channels, the target user's target credit data can include data items corresponding to each channel; that is, each data item represents the credit data matching the target user for one channel.

[0032] When determining target credit data matching a target user from the credit data sets corresponding to various channels based on target identity information and target behavioral characteristics, keyword searches or regular expression matching can be directly performed on the credit data sets corresponding to various channels to determine the target credit data matching the target user. In some embodiments, a large language model can also be used to determine target credit data matching a target user from the credit data sets corresponding to various channels based on target identity information and target behavioral characteristics.

[0033] To further improve the accuracy of determining target credit data, in some embodiments of this specification, target credit data matching the target user is determined from the obtained credit data sets corresponding to various channels based on the target identity information and the target behavioral characteristics, including: For each user's credit data in the credit data set corresponding to each channel, extract the user's identity information from the credit data, and generate the user's behavioral characteristics based on the credit data; Based on the identity information and behavioral characteristics of each user, as well as the target identity information and target behavioral characteristics, target credit data matching the target user is determined from the credit data sets corresponding to each channel.

[0034] To accurately determine the credit data matching the target user, the identity information of each user can be extracted from their credit data first, and behavioral characteristics of that user can be generated based on their credit data. In some embodiments, the user's credit data can be clustered using a preset clustering algorithm to obtain the user's behavioral characteristics, or a network model can be used to extract features from the user's credit data to obtain the user's behavioral characteristics. After determining the identity information and behavioral characteristics of each user's credit data in the credit datasets corresponding to each channel, the target credit data matching the target user can be determined from the obtained credit datasets corresponding to each channel based on the identity information and behavioral characteristics of each user, as well as the target identity information and the target behavioral characteristics. In some embodiments, the target identity information can be matched with the identity information of each user, and the target behavioral characteristics can be matched with the behavioral characteristics of each user. Finally, the credit data of users whose identity information and behavioral characteristics match simultaneously can be determined as the target credit data of the target user.

[0035] In some embodiments of this specification, target credit data matching the target user is determined from the obtained credit data sets corresponding to various channels, based on the identity information and behavioral characteristics of each user, as well as the target identity information and the target behavioral characteristics. This includes: From the identity information of each user, identify the candidate user that matches the target identity information; In response to determining that the behavioral characteristics of the candidate user match the target behavioral characteristics, the credit data of the candidate user whose behavioral characteristics match is determined as the target credit data.

[0036] To further improve the matching degree between target credit data and target users, and to avoid mismatches between identity information and credit data due to identity fraud, thereby affecting the accuracy of matching credit data for target users, this embodiment of the specification, after determining candidate users through identity information, further determines whether the behavioral characteristics of the candidate users match the target behavioral characteristics. In this way, even if the identity characteristics of a candidate user are forged, it is still possible to further determine whether the candidate user is the same user as the target user through behavioral characteristics.

[0037] In some embodiments of this specification, the identity information includes multiple sub-information, and determining candidate users matching the target identity information from the identity information of various users includes: From the identity information of multiple users, determine the first identity information that matches a preset number of sub-information among the multiple sub-information included in the target identity information, and determine the user corresponding to the first identity information as the candidate user; Alternatively, from the identity information of multiple users, determine the second identity information from which each sub-information has a similarity greater than a preset similarity with the multiple sub-informations included in the target identity information, and determine the user corresponding to the second identity information as the candidate user.

[0038] Considering that the user identification rules for credit data sets corresponding to different channels may differ, leading to variations in the identity information contained in the credit data sets across different channels, or the absence of identity information in some channels, or changes in identity information such as name and mobile phone number over time. For example, the identity information entered by the same user at institution A includes name, ID card number, and mobile phone number, while the identity information entered by the same user at institution B includes name and ID card number. Therefore, the identity information entered by the user at the two different institutions is not entirely the same. In this case, if we want to simultaneously aggregate the user's credit data from institutions A and B, we need to consider that the mobile phone number sub-information is missing from institution B. Therefore, in the embodiments of this specification, in order to ensure that all credit data belonging to the same user is collected as completely as possible, the matching criteria can be relaxed when determining candidate users. That is, the first identity information of the candidate user only needs to match a preset number of sub-information among the multiple sub-information included in the target identity information, rather than matching all sub-information. It should be noted that the above-mentioned preset data can be set as needed and is not limited thereto. For example, the above-mentioned preset number can be set to any number less than the total number of multiple sub-information. In some embodiments, considering that different channels and corresponding institutions may have some discrepancies when entering user identity information, such as entering "Wang Ri" as "Wang Yue" or entering a digit of the ID number incorrectly, in order to still collect all credit data of the same user in the event of such errors, when determining whether each piece of sub-information matches, the similarity between two pieces of sub-information can be determined to be greater than a preset similarity. It should be noted that this preset similarity can be set as needed and is not limited thereto. However, the closer the preset similarity is to 100%, the higher the requirements for the user's entered identity information.

[0039] In some embodiments, to collect credit data of the same user from different channels as much as possible, a second identity information can be identified from the identity information of multiple users. The similarity between each piece of information and the multiple pieces of information included in the target identity information is greater than a preset similarity. The user corresponding to the second identity information is then identified as a candidate user. It should be noted that the preset similarity can be set as needed and is not limited thereto. For example, if the preset similarity is 90%, when a piece of information is exactly the same as the pieces of information included in the target identity information (i.e., the similarity is 100%), the preset similarity requirement is met. Simultaneously, if the pieces of information in a user's identity information are not completely identical to their corresponding pieces of information in the target identity information, but the error is within a reasonable range (i.e., the preset similarity is met), the user can still be identified as a candidate user matching the target user's identity information. This further expands the scope of credit data collection for the target user and avoids omissions of credit data from the target credit data.

[0040] In some embodiments of this specification, target credit data matching the target user is determined from the obtained credit data sets corresponding to various channels, based on the identity information and behavioral characteristics of each user, as well as the target identity information and the target behavioral characteristics. This includes: For each user, the user's identification information is generated based on the user's identity information and behavioral characteristics; Generate the target user's target identification information based on the target identity information and the target behavioral characteristics; From the identification information of each user, determine the alternative identification information that matches the target identification information, and determine the credit data corresponding to the alternative identification information as the target credit data.

[0041] To further improve the efficiency and accuracy of identity information matching, in this embodiment, identification information for each user can be generated first based on their identity information and behavioral characteristics. Then, target identification information for the target user can be generated based on the target user's target identity information and target behavioral characteristics. Finally, by comparing the matching information with the target identification information, candidate users matching the target user in each channel can be determined. In some embodiments, when generating identification information from identity information and behavioral characteristics, the identity information and behavioral characteristics can be directly combined, or they can be encoded using a preset encoding method to obtain the corresponding identification information, or other methods can be used to generate the identification information; this is not limited. It should be noted that the preset encoding method can be selected as needed and is not limited. For example, in some embodiments, one-hot encoding can be used.

[0042] S206, based on the attribute information of the field information corresponding to the target conflict field for each channel's data item, determine the confidence level of the field information corresponding to the target conflict field for each channel, and determine the target field information of the target conflict field based on the confidence level of each channel corresponding to the target conflict field, as the data processing result; wherein, the target field is any one of the multiple fields contained in the data item.

[0043] Considering the potential conflicts between credit data collected from different channels—for example, regarding the user's occupation field, since a user may engage in different jobs at different times, the same user can easily have different occupation information recorded in the credit data corresponding to different channels—to further improve the quality of the target credit data corresponding to the target user and reduce data conflicts, after obtaining the target credit data corresponding to the target user, the confidence level of each channel's field information corresponding to the target conflict field is determined based on the attribute information of the data item corresponding to each channel in the target conflict field. In some embodiments, the aforementioned attribute information may include at least one of the channel source, generation time, and information occurrence frequency; or, in some embodiments, other information that can represent the attribute characteristics of the field information may be included as needed, without limitation. The confidence level of each field information, i.e., the degree of trustworthiness of the field information, can be determined through the attribute information of each field information. Generally, the more recent the generation time of the field information, the higher the confidence level of the field information. Similarly, the higher the frequency of occurrence of the information, the higher the confidence level of the field information. Furthermore, the more reliable the source of the field information, the higher the confidence level of the field information. For example, in one scenario, the confidence level of the UnionPay authentication channel is higher than that of the telecom operator authentication channel, which is higher than that of the social media platform authentication channel. In some embodiments, to further improve the accuracy of confidence level determination, the attribute information may include multiple sub-attribute information that can represent the attribute characteristics of the field information. The confidence level of the field information is then obtained by weighted summation of the confidence levels corresponding to each sub-attribute information.

[0044] After determining the confidence level of the field information corresponding to the target conflict field for each channel, the target field information of the target conflict field can be determined based on the confidence level of each channel in the target conflict field, and used as the data processing result. In some embodiments, the field information with the highest confidence level can be determined from the field information corresponding to the target conflict field for each channel as the target field information.

[0045] Table 1

[0046] In some embodiments of this specification, referring to Table 1, a table corresponding to target credit data is provided. In Table 1, channel number, name, age, occupation, and transaction records represent various fields. Name, age, and occupation are conflicting fields, while channel number and transaction records are non-conflicting fields. Each row under a field represents a data item corresponding to a channel, and each data item includes multiple field information. As can be seen from Table 1, data items corresponding to different channels may have data conflicts in certain conflicting fields, requiring further filtering to extract target field information that can represent the target user's current true information.

[0047] To further improve the accuracy of target field information, in some embodiments of this specification, the target field information of the target conflict field is determined based on the confidence level of each channel corresponding to the target conflict field, including: Based on the confidence level of each channel in the target conflict field, determine the first field information with the highest confidence level from the field information of each channel in the target conflict field; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is greater than a preset threshold, the first field information is determined as the target field information; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is not greater than a preset threshold, a manual review interface for determining the target field information is provided, and the target field information is determined based on the user instructions returned by the manual review interface.

[0048] Considering that in some embodiments, there may be two or more channels with small differences in confidence levels between the field information corresponding to the target field, meaning that the field information corresponding to two or more channels may all reflect the current real situation of the target user, thus making it impossible to directly determine the target field information through confidence level. Therefore, in the embodiments of this specification, when determining the target field information, it is first determined whether the difference in confidence level between the first field information with the highest confidence level and any other field information under the target conflict field (excluding the first field information) is greater than a preset threshold. If it is greater, it indicates that the difference in confidence level between the first field information with the highest confidence level and other field information is large, and the first field information can be directly determined as the target field information. If it is determined that the difference in confidence level between the first field information and any other field information under the target conflict field (excluding the first field information) is not greater than the preset threshold, it indicates that the target field information cannot be directly determined through confidence level. Therefore, it is necessary to determine the target field information through manual review, that is, to provide a manual review interface for determining the target field information, and to determine the target field information based on the user instructions returned by the manual review interface.

[0049] In some embodiments of this specification, the credit data processing method further includes: Determine whether the data items for each channel have the same field information corresponding to the target conflict field; In response to the fact that the data items corresponding to various channels have the same field information in the target conflict field, the field information of any data item corresponding to the target conflict field is determined as the target field information.

[0050] It should be noted that the aforementioned conflicting fields generally refer to fields in credit data that may conflict. These conflicting fields typically correspond to unique field information, such as a user's gender, occupation, and age. Therefore, a conflict arises when the field information under a certain field differs between different channels. In some embodiments, credit data may include non-conflicting fields in addition to conflicting fields, such as a user's transaction records and credit inquiry records. To further improve the efficiency of determining the target field information, when determining the target field information, it can be first determined whether the field information corresponding to the data items of each channel is the same as that corresponding to the target conflicting field. If they are the same, the field information of any data item corresponding to the data item of any channel corresponding to the target conflicting field can be directly determined as the target field information. If they are different, the target field information of the target conflicting field can be determined based on the confidence level of each channel corresponding to the target conflicting field.

[0051] In some embodiments of this specification, the credit data processing method further includes: Expand the target conflict field to obtain a set of expanded fields corresponding to the target conflict field; Based on the expanded field set, determine the field information corresponding to the target conflict field for each channel's corresponding data item.

[0052] Considering the different data standards for credit data across different channels—for example, the field "phone number" might be stored as "mobile" or "phone" in different channels—directly determining the matching field information for each channel's data item based on the target conflict field may not yield valid results. Therefore, in this embodiment, the target conflict field can be expanded to obtain an expanded field set, and then the field information for each channel's data item corresponding to the target conflict field can be determined based on the expanded field set. In some embodiments, a preset expanded field set can be pre-set for each field in the credit data. Then, during the expansion process, the preset expanded field set corresponding to the target conflict field can be directly determined as the expanded field set for that target conflict field. In some embodiments, prompt words can also be generated based on the target conflict field and input into a large language model, which then generates the expanded field set corresponding to the target conflict field.

[0053] In some embodiments of this specification, the method further includes: The target conflict field is semantically parsed using a large language model to obtain the semantic parsing result of the target conflict field; Based on the semantic parsing results, the field information corresponding to the data items of each channel in the target conflict field is determined.

[0054] Considering that although the data standards for each field in the credit data corresponding to different channels are different, the meaning of the same field is the same. For example, in the example above, "mobile" and "phone" can both mean mobile phone. Therefore, in order to improve the matching accuracy of the target conflict field, a large language model can be used to perform semantic parsing on the target conflict field to obtain the semantic parsing result of the target conflict field. Then, based on the semantic parsing result, the field information corresponding to the data item of each channel in the target conflict field can be determined. In some embodiments, a large language model can be used to perform semantic parsing on each field of the data item corresponding to each channel to accurately determine the target conflict field from each field.

[0055] In some embodiments of this specification, the credit data processing method further includes: Encrypt the field information corresponding to the target field in the data items for each channel.

[0056] To further protect user data security and privacy, in the embodiments of this specification, the field information corresponding to the target field in the data item corresponding to each channel can also be encrypted. The target field can be a field with high privacy or security requirements, and the specific target field can be set as needed, without limitation. For example, in some embodiments, fields related to identity information can be determined as target fields.

[0057] In some embodiments of this specification, the credit data processing method further includes: In response to an information query request for the target user, reliable credit data of the target user is generated based on the target field information. The reliable credit data is sent to the party requesting the information query.

[0058] To further enhance the user experience and ensure that users can directly obtain high-quality credit data when querying information without needing secondary processing such as conflict resolution, this embodiment of the specification describes a method where, upon receiving an information query request for the target user, reliable credit data for the target user can be generated based on the target field information obtained in the aforementioned steps. In other words, reliable credit data for the target user can be obtained through the above data processing results and then sent to the information query requester. In some embodiments, the information query requester may be the target user or an organization associated with the target user; this is not limited.

[0059] In some embodiments of this specification, when a new credit data set corresponding to a new channel is connected to the execution body of the credit data processing method of this specification, the credit data of each user can be merged into the corresponding credit data that has already undergone the above-mentioned credit data processing, based on the identity information of each user in the new channel's credit data set. Furthermore, the target field information of the target conflict field is re-determined based on the confidence level of the field information corresponding to the target conflict field of that channel. It should be noted that the specific process of merging the credit data of each user into the corresponding credit data that has already undergone the above-mentioned credit data processing can be referred to the embodiment corresponding to step S204 above, and will not be repeated here. The specific process of re-determining the target field information of the target conflict field can be referred to the embodiment corresponding to step S206 above, and will not be repeated here.

[0060] In some embodiments of this specification, the credit data processing method further includes recording each step of the credit data processing method and generating an operation log for storage. This allows for recording the complete change chain of the credit data, further enabling traceability of field information for each field.

[0061] refer to Figure 3 This is a flowchart of a credit data processing method provided in this specification, which includes the following steps: S302, receives an information query request for the target user.

[0062] In some embodiments, the aforementioned information query request generally refers to a query request to obtain the credit data of the target user. The information query request may be issued directly by the target user or by other relevant institutions that want to obtain the credit data of the target user, and there is no limitation on this.

[0063] S304, Obtain the target user's target identity information and target behavioral characteristics.

[0064] Target identity information may include the target user's name, mobile phone number, ID card number, etc., and target behavioral characteristics may include the target user's operating habits and social relationship characteristics.

[0065] S306, determine the target credit data that matches the target user from the credit data sets corresponding to multiple channels.

[0066] Since target users may have corresponding credit data in credit datasets across multiple channels, in order to provide more comprehensive credit data for target users, target credit data matching the target user can be determined from the credit datasets across multiple channels by using the target user's target identity information and target behavioral characteristics.

[0067] S308, eliminate data conflicts in target credit data.

[0068] Due to differences in data standards or recording times among various credit reporting channels, the same field may contain conflicting information recorded in different channels. For example, regarding a target user's occupation information, channel A might record the occupation as a doctor, while channel B might record it as a programmer. However, a target user cannot simultaneously hold both professions. Therefore, it is necessary to resolve the conflict and determine the target user's true current occupation. In some embodiments, the target field information for each conflicting field can be determined based on the confidence level corresponding to each conflicting field across different channels.

[0069] S310 returns the target credit data to the target user to eliminate the conflict.

[0070] After eliminating data conflicts in the target credit data, the conflict-free target credit data can be returned to the target user so that subsequent calculations or judgments can be made more accurately based on the conflict-free target credit data.

[0071] The credit data processing method provided in this specification first obtains the target user's target identity information and target behavioral characteristics. Then, based on the target user's target identity information and target behavioral characteristics, it determines the target credit data matching the target user from the obtained credit datasets corresponding to various channels. Since the user's identity information and behavioral characteristics are considered simultaneously when determining the target credit data, the accuracy of the association between the target credit data and the target user is further ensured, enabling the association of credit data from multiple channels with the same target user. After determining the target credit data matching the target user, the confidence level of each channel's field information corresponding to the target conflict field is determined based on the attribute information of the data items corresponding to each channel in the target credit data. The target field information of the target conflict field is then determined based on each confidence level. By comparing the confidence levels of each field information, information conflicts in the conflict fields are eliminated, improving the quality of the target credit data.

[0072] Figure 4 This is a schematic structural diagram of a device provided in an exemplary embodiment. For example... Figure 4 As shown, device 400 mainly consists of a communication interface 402, a mechanism interface 404, a processor 406, and a data storage 408. These components are interconnected and communicate with each other via a method bus, network, or other connection mechanism 410. Communication interface 402 enables device 400 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, communication interface 402 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, communication interface 402 can be a wired interface such as Ethernet, Token Ring, or USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or wide area wireless interface (e.g., WiMAX or LTE). Of course, communication interface 402 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. Communication interface 402 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide area wireless interfaces.

[0073] Mechanism interface 404 includes receiving mechanism input and providing output to the mechanism. Therefore, mechanism interface 404 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. Mechanism interface 404 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, mechanism interface 404 may include software, circuitry, or other forms of logic capable of transmitting and receiving data from external mechanism input / output devices. Additionally or alternatively, device 400 may support remote access from other devices via communication interface 402 or another physical interface (not shown). Mechanism interface 404 may be configured to receive mechanism input, the position and movement of which may be indicated by an indicator or cursor described herein. Mechanism interface 404 may also be configured as a display device for rendering or displaying text fragments.

[0074] Processor 406 may contain one or more general-purpose processors and / or special-purpose processors.

[0075] Data storage 408 may include one or more volatile and / or non-volatile storage components and may be integrated wholly or partially with processor 406. Data storage 408 may include removable and non-removable components.

[0076] Processor 406 is capable of executing program instructions 418 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 408 to perform the various functions described herein. Data storage 408 may comprise a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 400, enable device 400 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Processor 406 executing program instructions 418 may result in processor 406 using data 412.

[0077] For example, program instructions 418 may include an operation method 422 (e.g., an operation method kernel, device driver, and / or other modules) installed on device 400 and one or more applications 420 (e.g., a browser, social application, or game application). Similarly, data 412 may include operation method data 416 and application data 414. Operation method data 416 is primarily accessible to operation method 422, while application data 414 is primarily accessible to one or more applications 420. Application data 414 may reside in file methods visible or hidden from the device 400.

[0078] Application 420 can communicate with operation method 422 through one or more application programming interfaces (APIs). These APIs help application 420 read and / or write application data 414, transmit or receive information via communication interface 402, receive or display information on mechanism interface 404, etc.

[0079] In some terminology, application 420 may be simply referred to as "app". Furthermore, application 420 can be downloaded to device 400 through one or more online app stores or app markets. However, applications can also be installed on device 400 in other ways, such as through a web browser or a physical interface on device 400 (e.g., a USB port).

[0080] Please refer to Figure 5 It includes credit data processing devices that can be applied to, for example Figure 4 The device shown implements the technical solution described in this specification. The credit data processing apparatus may include: Module 502 acquires the target user's target identity information and target behavioral characteristics; The determination module 504 determines the target credit data matching the target user from the obtained credit data sets corresponding to each channel based on the target identity information and the target behavioral characteristics; each channel's credit data set includes the credit data of multiple users; the target credit data includes data items corresponding to each channel; The conflict handling module 506 determines the confidence level of the field information corresponding to the target conflict field for each channel based on the attribute information of the field information corresponding to the target conflict field for each channel, and determines the target field information of the target conflict field based on the confidence level of each channel corresponding to the target conflict field, as the data processing result; wherein, the target field is any one of the multiple fields contained in the data item.

[0081] In some embodiments of this specification, the determining module includes: The feature extraction unit extracts the user's identity information from the credit data of each user in the credit data dataset corresponding to each channel, and generates the user's behavioral features based on the credit data. The matching unit determines the target credit data that matches the target user from the credit data sets corresponding to each channel, based on the identity information and behavioral characteristics of each user, as well as the target identity information and the target behavioral characteristics.

[0082] In some embodiments of this specification, the matching unit includes: An identity matching component identifies candidate users from the identity information of each user who match the target identity information. A behavior matching component, in response to determining that the behavioral characteristics of the candidate user match the target behavioral characteristics, identifies the credit data of the candidate user whose behavioral characteristics match as the target credit data.

[0083] In some embodiments of this specification, the identity information includes multiple sub-information, and the identity matching component is specifically used for: From the identity information of multiple users, determine the first identity information that matches a preset number of sub-information among the multiple sub-information included in the target identity information, and determine the user corresponding to the first identity information as the candidate user; Alternatively, from the identity information of multiple users, determine the second identity information from which each sub-information has a similarity greater than a preset similarity with the multiple sub-informations included in the target identity information, and determine the user corresponding to the second identity information as the candidate user.

[0084] In some embodiments of this specification, the matching unit is specifically used for: For each user, the user's identification information is generated based on the user's identity information and behavioral characteristics; Generate the target user's target identification information based on the target identity information and the target behavioral characteristics; From the identification information of each user, determine the alternative identification information that matches the target identification information, and determine the credit data corresponding to the alternative identification information as the target credit data.

[0085] In some embodiments of this specification, the credit data processing device further includes a conflict verification module, used for: Determine whether the data items for each channel have the same field information corresponding to the target conflict field; In response to the fact that the data items corresponding to various channels have the same field information in the target conflict field, the field information of any data item corresponding to the target conflict field is determined as the target field information.

[0086] In some embodiments of this specification, the conflict handling module is specifically used for: Based on the confidence level of each channel in the target conflict field, determine the first field information with the highest confidence level from the field information of each channel in the target conflict field; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is greater than a preset threshold, the first field information is determined as the target field information; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is not greater than a preset threshold, a manual review interface for determining the target field information is provided, and the target field information is determined based on the user instructions returned by the manual review interface.

[0087] In some embodiments of this specification, the credit data processing device further includes a word expansion module, used for: Expand the target conflict field to obtain a set of expanded fields corresponding to the target conflict field; Based on the expanded field set, determine the field information corresponding to the target conflict field for each channel's corresponding data item.

[0088] In some embodiments of this specification, the credit data processing apparatus further includes a semantic module, used for: The target conflict field is semantically parsed using a large language model to obtain the semantic parsing result of the target conflict field; Based on the semantic parsing results, the field information corresponding to the data items of each channel in the target conflict field is determined.

[0089] In some embodiments of this specification, the attribute information includes at least one of the following: channel source, generation time, and information occurrence frequency.

[0090] In some embodiments of this specification, the target behavioral characteristics include the target user's operating habits and social relationship characteristics.

[0091] In some embodiments of this specification, the credit data processing device further includes an encryption module for: Encrypt the field information corresponding to the target field in the data items for each channel.

[0092] In some embodiments of this specification, the credit data processing apparatus further includes a request module for: In response to an information query request for the target user, reliable credit data of the target user is generated based on the target field information. The reliable credit data is sent to the party requesting the information query.

[0093] 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 method, or some features may be ignored or not executed.

[0094] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor executes the executable instructions to implement the steps of the credit data processing method as described in any of the above embodiments.

[0095] Based on the same concept as the above method, 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 credit data processing method as described in any of the above embodiments.

[0096] Based on the same concept as the methods described above, this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the credit data processing method as described in any of the above embodiments.

[0097] 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, product, 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, product, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded.

[0098] In this specification, “a,” “an,” and “the” do not specifically refer to the singular, but may also include the plural.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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 processing credit data, comprising: Obtain the target user's target identity information and target behavioral characteristics; Based on the target identity information and the target behavioral characteristics, target credit data matching the target user is determined from the credit data sets corresponding to each channel; each channel's credit data set includes the credit data of multiple users; the target credit data includes data items corresponding to each channel; Based on the attribute information of the field information corresponding to the target conflict field for each channel's data item, the confidence level of the field information corresponding to the target conflict field for each channel is determined, and the target field information of the target conflict field is determined based on the confidence level of each channel corresponding to the target conflict field, as the data processing result; wherein, the target field is any one of the multiple fields contained in the data item.

2. The method according to claim 1, wherein the target credit data matching the target user is determined from the obtained credit data sets corresponding to various channels based on the target identity information and the target behavioral characteristics, comprising: For each user's credit data in the credit data set corresponding to each channel, extract the user's identity information from the credit data, and generate the user's behavioral characteristics based on the credit data; Based on the identity information and behavioral characteristics of each user, as well as the target identity information and target behavioral characteristics, target credit data matching the target user is determined from the credit data sets corresponding to each channel.

3. The method according to claim 2, wherein target credit data matching the target user is determined from the obtained credit data sets corresponding to each channel based on the identity information and behavioral characteristics of each user, as well as the target identity information and the target behavioral characteristics, comprising: From the identity information of each user, identify the candidate user that matches the target identity information; In response to determining that the behavioral characteristics of the candidate user match the target behavioral characteristics, the credit data of the candidate user whose behavioral characteristics match is determined as the target credit data.

4. The method according to claim 3, wherein the identity information includes multiple sub-information, and determining a candidate user matching the target identity information from the identity information of each user includes: From the identity information of multiple users, determine the first identity information that matches a preset number of sub-information among the multiple sub-information included in the target identity information, and determine the user corresponding to the first identity information as the candidate user; Alternatively, from the identity information of multiple users, determine the second identity information from which each sub-information has a similarity greater than a preset similarity with the multiple sub-informations included in the target identity information, and determine the user corresponding to the second identity information as the candidate user.

5. The method according to claim 2, wherein target credit data matching the target user is determined from the obtained credit data sets corresponding to each channel based on the identity information and behavioral characteristics of each user, and the target identity information and the target behavioral characteristics, comprising: For each user, the user's identification information is generated based on the user's identity information and behavioral characteristics; Generate the target user's target identification information based on the target identity information and the target behavioral characteristics; From the identification information of each user, determine the alternative identification information that matches the target identification information, and determine the credit data corresponding to the alternative identification information as the target credit data.

6. The method according to claim 1, further comprising: Determine whether the data items for each channel have the same field information corresponding to the target conflict field; In response to the fact that the data items corresponding to various channels have the same field information in the target conflict field, the field information of any data item corresponding to the target conflict field is determined as the target field information.

7. The method according to claim 1, wherein determining the target field information of the target conflict field based on the confidence level of each channel corresponding to the target conflict field includes: Based on the confidence level of each channel in the target conflict field, determine the first field information with the highest confidence level from the field information of each channel in the target conflict field; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is greater than a preset threshold, the first field information is determined as the target field information; In response to determining that the confidence difference between the first field information and any field information other than the first field information under the target conflict field is not greater than a preset threshold, a manual review interface for determining the target field information is provided, and the target field information is determined based on the user instructions returned by the manual review interface.

8. The method according to claim 1, further comprising: Expand the target conflict field to obtain a set of expanded fields corresponding to the target conflict field; Based on the expanded field set, determine the field information corresponding to the target conflict field for each channel's corresponding data item.

9. The method according to claim 1, further comprising: The target conflict field is semantically parsed using a large language model to obtain the semantic parsing result of the target conflict field; Based on the semantic parsing results, the field information corresponding to the data items of each channel in the target conflict field is determined.

10. The method according to claim 1, wherein the attribute information includes at least one of channel source, generation time, and information occurrence frequency.

11. The method according to claim 1, wherein the target behavioral characteristics include the target user's operating habits and social relationship characteristics.

12. The method according to claim 1, further comprising: Encrypt the field information corresponding to the target field in the data items for each channel.

13. The method according to claim 1, further comprising: In response to an information query request for the target user, reliable credit data of the target user is generated based on the target field information. The reliable credit data is sent to the party requesting the information query.

14. A credit data processing apparatus, comprising: The acquisition module obtains the target user's target identity information and target behavioral characteristics; The determination module determines the target credit data matching the target user from the obtained credit data sets corresponding to each channel, based on the target identity information and the target behavioral characteristics; each channel's credit data set includes the credit data of multiple users; the target credit data includes data items corresponding to each channel; The conflict handling module determines the confidence level of each channel's field information corresponding to the target conflict field based on the attribute information of the field information corresponding to the target conflict field for each channel's data item, and determines the target field information of the target conflict field based on the confidence level of each channel's field information corresponding to the target conflict field, as the data processing result; wherein, the target field is any one of the multiple fields contained in the data item.

15. An electronic device comprising: processor; Memory used to store processor-executable instructions; The processor executes the executable instructions to implement the method as described in any one of claims 1-13.

16. 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 1-13.

17. A computer program product comprising: A computer program / instruction that, when executed by a processor, implements the method as described in any one of claims 1-13.

Images