A data processing method, device and equipment

Abstract

The embodiments of this specification provide a data processing method, apparatus, and device, which relate to the field of computer technology. Among them, the method includes: receiving a risk detection request for a target merchant; in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant; performing modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; according to a large language model, performing information fusion processing on the target text data to obtain target information corresponding to the target merchant; obtaining target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant; determining a risk detection result for the target merchant according to the target information and the feature information.

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular, to a data processing method, apparatus, and device. Background Art

[0002] As people pay more and more attention to their privacy data, in order to protect user privacy and ensure data security, it is necessary to detect whether the merchants providing services to users are risky merchants to ensure the data security of users. For example, the security personnel can manually analyze the merchant data to detect whether the merchant is a risky merchant.

[0003] However, due to the increasingly complex data structure and large data volume of merchant data, the detection efficiency and accuracy of risk detection by manual analysis are low. Therefore, the embodiments of this specification provide a better technical solution for risk detection of merchants. Summary of the Invention

[0004] The purpose of the embodiments of this specification is to provide a better technical solution for risk detection of merchants.

[0005] To achieve the above technical solution, the embodiments of this specification are implemented as follows:

[0006] A data processing method provided by the embodiments of this specification, the method includes: receiving a risk detection request for a target merchant; in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, the data to be detected includes multimodal data related to the business operation behavior of the target merchant; performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; obtaining target data to be detected corresponding to the risk detection requirement of the target merchant in the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant; determining a risk detection result for the target merchant according to the target information and the feature information.

[0007] A data processing device provided by an embodiment of this specification, the device includes: a request receiving module, configured to receive a risk detection request for a target merchant; a data acquisition module, configured to, in response to the risk detection request, acquire the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant; a modality alignment module, configured to perform modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; an information fusion module, configured to perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; a feature recognition module, configured to acquire target data to be detected corresponding to the risk detection requirement of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant; a risk detection module, configured to determine a risk detection result for the target merchant according to the target information and the feature information.

[0008] A data processing device provided by an embodiment of this specification, the data processing device includes: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to: receive a risk detection request for a target merchant; in response to the risk detection request, acquire the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant; perform modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; acquire target data to be detected corresponding to the risk detection requirement of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant; determine a risk detection result for the target merchant according to the target information and the feature information.

[0009] An embodiment of this specification also provides a storage medium for storing computer-executable instructions. When the executable instructions are executed by a processor, the following process is implemented: receiving a risk detection request for a target merchant; in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant; performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; obtaining target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant; and determining a risk detection result for the target merchant according to the target information and the feature information.

[0010] An embodiment of this specification also provides a computer program product, including a computer program. When the computer program is executed by a processor, the following process is implemented: receiving a risk detection request for a target merchant; in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant; performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; obtaining target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant; and determining a risk detection result for the target merchant according to the target information and the feature information. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 This is an embodiment of a data processing method in this specification;

[0013] Figure 2 This is another embodiment of a data processing method in this specification;

[0014] Figure 3It is a schematic diagram of a data processing process in this specification;

[0015] Figure 4 It is a schematic diagram of another data processing process in this specification;

[0016] Figure 5 It is an embodiment of a data processing device in this specification;

[0017] Figure 6 It is an embodiment of a data processing device in this specification. Specific implementation manners

[0018] The embodiments of this specification provide a data processing method, device and equipment.

[0019] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0020] The embodiments of this specification provide a detection mechanism for whether a merchant is a risky merchant. As people pay more and more attention to their privacy data, in order to protect user privacy and ensure data security, it is necessary to detect whether the merchants providing services to users are risky merchants to ensure the data security of users. For example, it is possible to detect whether a merchant is a risky merchant by means of manual analysis of merchant data by security personnel. However, due to the increasingly complex data structure and the increasing amount of merchant data, the detection efficiency and accuracy of risk detection by means of manual analysis are low. Therefore, the embodiments of this specification provide a better technical solution for risk detection of merchants. In this solution, a risk detection request for a target merchant is received. In response to the risk detection request, the data to be detected corresponding to the target merchant is obtained. The data to be detected includes multimodal data related to the business operation behavior of the target merchant. The data of different modalities in the data to be detected is subjected to modality alignment processing to obtain the target text data corresponding to the data to be detected. According to the large language model, information fusion processing is performed on the target text data to obtain the target information corresponding to the target merchant. The target data to be detected corresponding to the risk detection requirement of the target merchant is obtained from the data to be detected, and feature recognition processing is performed on the target data to be detected to obtain the feature information of the target merchant. According to the target information and the feature information, the risk detection result for the target merchant is determined. In this way, on the one hand, in the case of an increasingly complex data structure of merchant data, through modality alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then, by using the understanding, summarization, and reasoning capabilities of the large language model, information fusion processing is performed on the aligned data (i.e., the target text data) to obtain the target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirement of the target merchant to obtain feature information that can meet the risk detection requirement. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirement, the risk detection result for the target merchant can be quickly and accurately determined, improving the detection efficiency and accuracy of risk detection for merchants. The specific processing can refer to the specific content in the following embodiments.

[0021] As Figure 1 As shown in the figure, the embodiments of this specification provide a data processing method. The execution subject of this method can be a server. The server can be an independent server or a server cluster composed of multiple servers, etc. The server can be a background server such as a financial business or an online shopping business, or a background server of a certain application program, etc. In this embodiment, the server is used as an example of the execution subject for detailed description. The method can specifically include the following steps:

[0022] In step S102, a risk detection request for a target merchant is received.

[0023] Among them, the target merchant can be any physical merchant that can provide services to users or a virtual merchant on a platform. For example, the target merchant can be a physical merchant that provides catering services to users, or the target merchant can also be a registered merchant on an online shopping platform that provides shopping services to users, etc.

[0024] In implementation, the server can regularly trigger a risk detection request for the target merchant according to a preset detection period. For example, the server can trigger a risk detection request for the target merchant every 10 days.

[0025] In addition, since the detection requirements of different types of merchants are different, such as the risk detection requirements of physical merchants are relatively low, while the risk detection requirements of virtual merchants on the platform are relatively high. Therefore, the server can set different detection periods for different types of merchants. For example, the server can trigger a risk detection request for the virtual merchant (i.e., the target merchant) on the online shopping platform every 10 days, or the server can also trigger a risk detection request for the physical merchant (i.e., the target merchant) every half month.

[0026] In addition, the server can also detect whether the merchant data of the merchant has changed, and trigger a risk detection request for the merchant (i.e., the target merchant) when it detects that the merchant data has changed. For example, when the server detects that the merchant name of a certain merchant has changed, it can determine the merchant as the target merchant and trigger a risk detection request for the target merchant.

[0027] The above method for obtaining the risk detection request for the target merchant is an optional and implementable obtaining method. In actual application scenarios, there can also be various different obtaining methods, and different obtaining methods can be selected according to different actual application scenarios. This embodiment of the specification does not make specific limitations on this.

[0028] In step S104, in response to the risk detection request, the data to be detected corresponding to the target merchant is obtained.

[0029] Among them, the data to be detected can include multimodal data related to the business operation behavior of the target merchant. For example, the data to be detected can include but is not limited to text data, image data, video data, and audio data. Specifically, the text data can include data such as the merchant name, address, and industry type of the target merchant, the image data can be the image data of the merchant logo of the target merchant, the video data can be the relevant video data of the service providing process of the target merchant, and the audio data can include the interaction data between the target merchant and the user, etc.

[0030] In step S106, perform modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected.

[0031] In implementation, the server can perform modal alignment processing on data of different modalities in the data to be detected according to a pre-trained alignment model to obtain target text data corresponding to the data to be detected. Among them, the alignment model can be a model constructed based on a preset machine learning algorithm.

[0032] In addition, the server can also determine a model according to the labels corresponding to data of different models, process data of different modalities respectively to obtain label information corresponding to data of different modalities, and then the server can determine target text data corresponding to the data to be detected according to the label information corresponding to data of different modalities. Among them, the label determination model can be a model constructed based on a preset machine learning algorithm.

[0033] For example, assume that the data to be detected includes text data and image data. Among them, the text data includes the merchant name of the target merchant, and the image data includes the merchant identifier of the target merchant. The server can determine the label type corresponding to the text data according to the label determination model corresponding to the text data, determine the label type corresponding to the image data according to the label determination model corresponding to the image data, and determine the target text data according to the label type corresponding to the text data and the label type corresponding to the image data. Among them, the label type of the text data and the label type of the image data can be used to represent the merchant type of the target merchant.

[0034] In addition, the above method for modal alignment processing is an optional and implementable processing method. In actual application scenarios, there can also be various different modal alignment processing methods, and different modal alignment processing methods can be selected according to different actual application scenarios. This specification does not make specific limitations on this.

[0035] In step S108, perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant.

[0036] Among them, large language models (LLMs) can be advanced natural language processing (NLP) models built on the basis of deep learning technology. Their underlying transformers are a set of neural networks, which can consist of an encoder and a decoder with self-attention capabilities. They can understand and generate human language by processing a large amount of text data, thereby performing various natural language processing tasks. Due to the large number of parameters and extensive training datasets of large language models, large language models can capture the richness and nuances of language expressions and can display the captured information through the powerful computing power of billions to trillions of parameters, and have strong capabilities in language understanding and generation tasks.

[0037] In implementation, after converting different modality data in the data to be detected into text description forms, the obtained target text data can be input into the large language model, and through a second prompt message, such as "Please help me integrate all the objective information of this merchant, streamline the description of transaction types, and try to expand the relationships between different merchants, especially the relationship of the same legal person", the text descriptions of each modality in the target text data can be integrated into merchant meta-tokens. The large language model can output merchant meta-descriptions (i.e., target information) containing the objective fact information of the target merchant in a relatively coherent and meaningful summary form.

[0038] The server can utilize the understanding ability of the large language model to perform information fusion processing on the target text data, that is, the server can input the target text data and the second prompt message (i.e., promot) into the large language model to obtain the target information that can be used to describe the target merchant.

[0039] For example, the target information of the target merchant output by the large language model can be "The merchant name of this merchant is 'xxx'. According to the merchant name of this merchant, the industry where this merchant is located is the catering industry. According to the image data of this merchant, the service provided by this merchant is catering service. According to the transaction behavior data of this merchant, it can be determined that the business hours of this merchant are concentrated from 3 am to 4 am."

[0040] In step S110, obtain the target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and perform feature recognition processing on the target data to be detected to obtain the feature information of the target merchant.

[0041] Among them, the risk detection requirements can include dynamic information detection requirements (such as transaction anomaly detection requirements, etc.) and static information detection requirements (such as merchant name conflict detection requirements, industry conflict detection requirements, etc.).

[0042] In implementation, for example, taking the target merchant's risk detection requirement as an industry conflict detection requirement, the server can obtain target data to be detected in the detection requirement that can be used to determine the industry in which the target merchant is located (such as text data containing the merchant name of the target merchant, and image data containing the merchant logo of the target user, etc.).

[0043] In addition, the server can also determine the incremental data in the data to be detected that corresponds to the risk detection requirements of the target merchant as the target data to be detected. For example, the server can obtain the incremental data added to the data to be detected within a preset detection cycle, and determine the data in the incremental data that corresponds to the risk detection requirements of the target merchant as the target data to be detected.

[0044] In this way, the server can use the understanding ability of the large language model to perform information fusion processing on the data to be detected with large data volume and complex data structure, and obtain target information that can comprehensively describe the target merchant. It can also perform feature recognition processing on the newly added target data to be detected that corresponds to the risk detection needs of the target merchant, and obtain the feature information of the target merchant, which can improve data utilization and risk detection efficiency.

[0045] After determining the target data to be detected, the server can perform feature recognition processing on the target data to be detected in a variety of ways. For example, the server can perform keyword recognition processing on the target data to be detected based on preset keywords, and determine the feature information of the target merchant based on the recognized keywords. Specifically, taking the above-mentioned industry conflict detection requirements as an example, the server can perform keyword recognition processing on the key words related to the industry in the target data to be detected, and determine the feature information of the target merchant based on the recognized keywords related to the industry, such as the feature information can be "shopping industry", "catering industry", etc.

[0046] Specifically, for text data, the server can directly perform keyword recognition processing on the text data. For image data, the server can identify the character information contained in the image data based on optical character recognition (OCR) technology, and perform keyword recognition processing on the recognized character information, etc., so as to determine the characteristic information of the target merchant based on the recognized keywords.

[0047] In step S112, the risk detection result for the target merchant is determined based on the target information and the feature information.

[0048] In implementation, the server can determine the risk detection result for the target merchant based on the risk detection requirements corresponding to the target merchant, the target information, and the feature information. For example, taking the risk detection requirement corresponding to the target merchant as the industry conflict detection requirement as an example, assume that the target information is "the merchant name of this merchant is 'xxx', and according to the merchant name of this merchant, the industry where this merchant is located is the catering industry, and according to the image data of this merchant, the service provided by this merchant is catering service". If the feature information of the target merchant is "catering industry", then it can be determined that there is no contradiction between the target information and the feature information, that is, the risk detection result for the target merchant can be that there is no risk. If the feature information of the target merchant is "shopping industry", then it can be determined that there is a contradiction between the target information and the feature information, that is, the risk detection result for the target merchant can be that there is a risk.

[0049] The above method for determining the risk detection result is an optional and implementable determination method. In addition, there can be various different determination methods, and different determination methods can be selected according to different actual application scenarios. The embodiments of this specification do not make specific limitations on this.

[0050] The embodiments of this specification provide a data processing method. By receiving a risk detection request for a target merchant, in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, the data to be detected includes multi-modal data related to the business operation behavior of the target merchant, performing modal alignment processing on different modal data in the data to be detected to obtain the target text data corresponding to the data to be detected, performing information fusion processing on the target text data according to the large language model to obtain the target information corresponding to the target merchant, obtaining the target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and performing feature recognition processing on the target data to be detected to obtain the feature information of the target merchant, and determining the risk detection result for the target merchant according to the target information and the feature information. In this way, on the one hand, in the case where the data structure of merchant data is becoming more and more complex, through modal alignment processing, the multi-modal data included in the data to be detected can be aligned to text data, and then by using the understanding, summarization, and reasoning capabilities of the large language model, information fusion processing is performed on the aligned data (i.e., the target text data) to obtain the target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirements of the target merchant to obtain the feature information that can meet the risk detection requirements. In this way, by being able to comprehensively and accurately describe the target information of the target merchant and the feature information that can meet the risk detection requirements, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of risk detection for merchants.

[0051] In practical applications, the specific processing method for determining the risk detection result for the target merchant according to the target information and feature information in step S112 can be diverse. The following provides an optional processing method. For example, Figure 2 as shown, it can specifically include the processing of the following steps S1122 to S1124.

[0052] In step S1122, obtain the target prompt information corresponding to the risk detection requirements of the target merchant.

[0053] In practical applications, the specific processing method for obtaining the target prompt information corresponding to the risk detection requirements of the target merchant in the above step S1122 can be diverse. The following provides an optional processing method, which can specifically include the processing of the following steps A1 to step A4.

[0054] In step A1, obtain the first prompt information corresponding to the risk detection requirements of the target merchant.

[0055] In implementation, the server can generate the first prompt information corresponding to the risk detection requirements of the target merchant according to a pre-trained generation model, where the generation model can be a model constructed according to a preset machine learning algorithm.

[0056] For example, assuming that the risk detection requirement of the target merchant is the merchant name conflict detection requirement, the server can construct a generation model based on the neural network algorithm and train the generation model according to the training data to obtain the trained generation model. The server can input the merchant name conflict detection requirement into the trained generation model to obtain the first prompt information, and the first prompt information can be "Whether there is a conflict in the merchant name".

[0057] In step A2, perform feature extraction processing on the first prompt information to obtain the target vector corresponding to the first prompt information.

[0058] In step A3, determine the target risk detection rule corresponding to the first prompt information in the risk detection rule according to the similarity between the target vector and the vector corresponding to the risk detection rule.

[0059] In implementation, the server can perform feature extraction processing on the first prompt information according to a pre-trained vector extraction model to obtain the target vector, where the vector extraction model can be a model constructed according to a preset machine learning algorithm.

[0060] The server can construct a risk knowledge base according to the risk detection rules. The server can select the risk detection rules corresponding to the merchant type of the target merchant from the risk knowledge base according to the merchant type of the target merchant, and perform feature extraction processing on the determined risk detection rules through the above pre-trained vector extraction model to obtain the vector corresponding to the risk detection rule.

[0061] Alternatively, in the case of a large number of risk detection rules, the server can also perform feature extraction processing on the risk detection rules through the above-mentioned pre-trained vector extraction model to obtain the vectors corresponding to the risk detection rules. The server can construct a risk knowledge base based on the vectors corresponding to the risk detection rules and directly obtain the vectors corresponding to the risk detection rules for the target merchant from the risk knowledge base.

[0062] The server can determine the similarity between the target vector and the vectors corresponding to each risk detection rule according to a preset similarity algorithm (such as the cosine algorithm, Euclidean distance algorithm, etc.), and then select the target risk detection rule according to this similarity.

[0063] In step A4, according to the target risk detection rule and the first prompt information, the target prompt information is generated.

[0064] In implementation, the server can splice the target risk detection rule and the first prompt information to obtain the target prompt information. For example, assume that the first prompt information is "Whether there is a conflict in the merchant name", and the target risk detection rule is "If the industry corresponding to the merchant name does not match the identified industry, then there is a conflict in the merchant name". Then, the target prompt information can be "Whether there is a conflict in the merchant name. For example, if the industry corresponding to the merchant name does not match the identified industry, then there is a conflict in the merchant name".

[0065] In this way, as Figure 3 shown, through the processing of Retrieval-Augmented Generation (RAG) of the first prompt information in the above steps A2~A4, the target risk detection rule related to the first prompt information can be retrieved from the risk knowledge base, and according to the target risk detection rule and the first prompt information, the target prompt information for inputting into the large language model can be generated, which can enhance the ability of the large language model to process knowledge-intensive tasks (such as question answering, text summarization, content generation, etc.). And on the basis of taking into account the existing risk detection rules and experience, it can help to discover new authenticity risk problems. At the same time, it also reduces the query and analysis costs and improves the strategy operation efficiency.

[0066] In step S1124, based on the target prompt information, the target information and the feature information, the risk detection result for the target merchant is determined through the large language model.

[0067] In implementation, the feature information obtained from the feature recognition model with a relatively small model structure, as well as the merchant meta-description obtained based on the large language model, can be input into the large language model again, and through the target prompt information, a judgment and decision message (i.e., the risk detection result) obtained based on the large model's own understanding, summarization, and reasoning capabilities can be output.

[0068] Among them, the target prompt information can be "Please ask whether there is a conflict in the information of this merchant", and the risk detection result can be: "The merchant name is XX Restaurant. It is speculated to be in the catering industry. Its transaction time is concentrated from 1 to 6 am, and the collection amount is distributed between 800 and 10,000. From the transaction information, it does not quite conform to the regular business collection of the catering industry, and there is a risk of authenticity."

[0069] In this way, through two-stage data processing (i.e., the first stage of generating target information through modality alignment processing and information fusion processing, and the second stage of determining the risk detection result based on the feature information obtained through feature recognition processing and the target information), only the processing model in the first stage needs to be maintained in the follow-up. Then, based on the merchant meta-description (i.e., the target information) produced by it, combined with the template prompt information, the risk detection results corresponding to different risk detection requirements can be determined, reducing the operation and maintenance cost of the model.

[0070] In practical applications, the data to be detected includes image data, business operation behavior sequence data, table data, and graph structure data. The graph structure data can be constructed based on the association relationship between the target merchant and other merchants.

[0071] Among them, the image data can be image data containing the merchant identifier of the target merchant, image data of the business license of the target merchant, etc. The business operation behavior sequence data can include the transaction behavior sequence data of the target merchant, operation behavior sequence data, etc. The table data can include table data of the transaction feature data and identity feature data of the target merchant. The graph structure data can include graph structure data constructed based on the association relationship between the target merchant and other merchants, graph structure data constructed based on the association relationship between the devices of the target merchant, graph structure data constructed based on the resource flow relationship of the target merchant, and graph structure data constructed based on the legal person relationship corresponding to the target merchant. In addition, the data to be detected can also include text data such as the merchant name and address of the target merchant.

[0072] In practical applications, in step S106, there are various specific processing methods for performing modality alignment processing on different modalities of data in the data to be detected to obtain the target text data corresponding to the data to be detected. The following provides an optional processing method, as Figure 2 shown, which can specifically include the processing of the following steps S1062~S1064.

[0073] In step S1062, according to the pre-trained conversion model, the data of different modalities in the data to be detected are respectively encoded to obtain feature vectors corresponding to the data to be detected of each modality.

[0074] In step S1064, according to the pre-trained conversion model, the feature vectors are decoded to obtain the target text data.

[0075] In implementation, as Figure 4 shown, the conversion model may include multiple encoders (such as text data encoder, image data encoder, table data encoder, etc.) and decoders. The server can respectively encode the data of different modalities in the data to be detected according to different encoders in the conversion model to obtain feature vectors corresponding to the data to be detected of each modality, and then decode the feature vectors through different decoders in the conversion model to obtain the target text data.

[0076] Since the data of different modalities in the data to be detected have a large difference in information density. For example, the information contained in text data is relatively rich, while the information contained in table data or business operation behavior sequence data, etc. is relatively sparse. For example, the merchant name of a certain merchant is "Ruyi Barbecue (xx West Road Store)", and it can be inferred from this merchant name alone that the industry of this merchant is the catering industry and the business form is an offline physical store. However, when the server identifies the industry, business form, etc. based on table data or operation behavior sequence data (such as transaction flow table data, merchant operation behavior sequence data, etc.), it can only play a certain role in information supplement.

[0077] Therefore, through multiple encoders in the conversion model, data of different modalities can be converted into the form of text descriptions (tokens) to obtain the target text data. On the one hand, data with different information densities can be uniformly converted into a text form with a higher information density. On the other hand, modality alignment processing can be performed through the text as a medium, which is convenient for subsequent multi-modal fusion processing.

[0078] For example, taking table data as an example, the target text data obtained by performing text conversion processing on the transaction flow table data of the target merchant within a preset detection period can be: "10% of the transaction time of this merchant in the past 1 month occurred between 4-5 o'clock, 15% occurred between 5-6 o'clock, 20% occurred between 6-7 o'clock, 25% occurred between 7-8 o'clock, and the rest occurred after 8 o'clock. The proportion of transactions after 1 o'clock in the middle of the night was <1%. The proportion of transactions with an amount <100 was 20%, the proportion of 100-200 was 30%, the proportion of 200-300 was 35%, and the transaction proportion above 500 was <2%. The maximum transaction amount was xxx yuan, and the minimum transaction amount was x yuan. The number of transaction pens in the past week decreased by 20% compared with the previous week, and the amount decreased by 10%, which was the least week within a month."

[0079] In practical applications, there are various specific processing methods for performing feature recognition processing on the target data to be detected in step S110 to obtain the feature information of the target merchant. The following provides an optional processing method, as Figure 2 shown, which may specifically include the processing of the following step S1102.

[0080] In step S1102, obtain the target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and perform behavioral feature recognition processing on the target data to be detected according to the pre-trained feature recognition model to obtain the feature information of the target merchant.

[0081] Among them, the feature recognition model can be a model constructed based on a preset machine learning algorithm.

[0082] In practical applications, the feature recognition model may include a first sub-model and a second sub-model. The first sub-model can be used to identify the industry where the target merchant is located, and the second sub-model can be used to identify whether there is a risk in the transaction behavior of the target merchant. Correspondingly, the specific processing method for performing behavioral feature recognition processing on the target data to be detected according to the pre-trained feature recognition model in the above step S1102 to obtain the feature information of the target merchant may further include the processing of the following steps B1 to B3.

[0083] In step B1, based on the pre-trained first sub-model, determine the industry feature information of the industry where the target merchant is located based on the image data and business operation behavior sequence data in the target data to be detected.

[0084] Among them, the first sub-model can be a model constructed based on a preset deep learning algorithm.

[0085] In step B2, based on the pre-trained second sub-model, determine the behavioral risk feature information of the target merchant based on the business operation behavior sequence data and the graph structure data.

[0086] In implementation, the second sub-model can be a model constructed based on a preset machine learning algorithm.

[0087] In step B3, determine the feature information of the target merchant based on the industry feature information and the behavioral risk feature information.

[0088] In practical applications, there are various specific processing methods for determining the risk detection result for the target merchant according to the target information and the feature information in step S112. The following provides an optional processing method, as Figure 2 shown, which may specifically include the processing of the following step S1126.

[0089] In step S1126, based on the pre-trained risk detection model, the risk type corresponding to the target merchant is determined based on the target information and the feature information, and the risk detection result for the target merchant is determined according to the risk type corresponding to the target merchant.

[0090] Among them, the risk detection model can be a model constructed based on a preset machine learning algorithm, and the risk types can include multiple types such as high risk, medium risk, and low risk.

[0091] An embodiment of this specification provides a data processing method. By receiving a risk detection request for a target merchant, in response to the risk detection request, the data to be detected corresponding to the target merchant is obtained. The data to be detected includes multimodal data related to the business operation behavior of the target merchant. The data of different modalities in the data to be detected is subjected to modality alignment processing to obtain target text data corresponding to the data to be detected. According to the large language model, the target text data is subjected to information fusion processing to obtain the target information corresponding to the target merchant. The target data to be detected corresponding to the risk detection requirement of the target merchant is obtained from the data to be detected, and the target data to be detected is subjected to feature recognition processing to obtain the feature information of the target merchant. According to the target information and the feature information, the risk detection result for the target merchant is determined. In this way, on the one hand, in the case where the data structure of merchant data is becoming more and more complex, through modality alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then by using the understanding, summarization, and reasoning capabilities of the large language model, the aligned data (i.e., the target text data) is subjected to information fusion processing to obtain the target information corresponding to the target merchant. On the other hand, the target data to be detected corresponding to the risk detection requirement of the target merchant can be subjected to feature recognition processing to obtain feature information that can meet the risk detection requirement. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirement, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of merchant risk detection.

[0092] The above is the data processing method provided by the embodiment of this specification. Based on the same idea, the embodiment of this specification also provides a data processing device, as Figure 5 shown.

[0093] The data processing device includes: a request receiving module 501, a data obtaining module 502, a modality alignment module 503, an information fusion module 504, a feature recognition module 505, and a risk detection module 506, where:

[0094] The request receiving module 501 is configured to receive a risk detection request for a target merchant;

[0095] A data acquisition module 502, configured to obtain the data to be detected corresponding to the target merchant in response to the risk detection request, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant;

[0096] A modality alignment module 503, configured to perform modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected;

[0097] An information fusion module 504, configured to perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant;

[0098] A feature recognition module 505, configured to obtain target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant;

[0099] A risk detection module 506, configured to determine a risk detection result for the target merchant according to the target information and the feature information.

[0100] In an embodiment of the present specification, the risk detection module 506 is configured to:

[0101] Obtain target prompt information corresponding to the risk detection requirements of the target merchant;

[0102] Based on the target prompt information, the target information, and the feature information, determine a risk detection result for the target merchant through the large language model.

[0103] In an embodiment of the present specification, the risk detection module 506 is configured to:

[0104] Obtain first prompt information corresponding to the risk detection requirements of the target merchant;

[0105] Perform feature extraction processing on the first prompt information to obtain a target vector corresponding to the first prompt information;

[0106] According to the similarity between the target vector and the vector corresponding to the risk detection rule, determine a target risk detection rule in the risk detection rule corresponding to the first prompt information;

[0107] Generate the target prompt information according to the target risk detection rule and the first prompt information.

[0108] In the embodiments of this specification, the data to be detected includes image data, business operation behavior sequence data, table data, and graph structure data, and the graph structure data is constructed according to the association relationship between the target merchant and other merchants.

[0109] In the embodiments of this specification, the modality alignment module 503 is configured to:

[0110] According to a pre-trained conversion model, encode the data of different modalities in the data to be detected respectively to obtain feature vectors corresponding to the data to be detected of each modality;

[0111] According to the pre-trained conversion model, decode the feature vectors to obtain the target text data.

[0112] In the embodiments of this specification, the feature recognition module 505 is configured to:

[0113] According to a pre-trained feature recognition model, perform behavior feature recognition processing on the target data to be detected to obtain the feature information of the target merchant, and the feature recognition model is a model constructed based on a preset machine learning algorithm.

[0114] In the embodiments of this specification, the feature recognition model includes a first sub-model and a second sub-model. The first sub-model is used to identify the industry where the target merchant is located, and the second sub-model is used to identify whether there is a risk in the transaction behavior of the target merchant. The feature recognition module 505 is configured to:

[0115] According to the pre-trained first sub-model, based on the image data and business operation behavior sequence data in the target data to be detected, determine the industry feature information of the industry where the target merchant is located;

[0116] According to the pre-trained second sub-model, based on the business operation behavior sequence data and graph structure data, determine the behavior risk feature information of the target merchant;

[0117] Based on the industry feature information and the behavior risk feature information, determine the feature information of the target merchant.

[0118] In the embodiments of this specification, the risk detection module is configured to:

[0119] According to a pre-trained risk detection model, based on the target information and the feature information, determine the risk type corresponding to the target merchant, and according to the risk type corresponding to the target merchant, determine the risk detection result for the target merchant. The risk detection model is a model constructed based on a preset machine learning algorithm.

[0120] An embodiment of this specification provides a data processing device. By receiving a risk detection request for a target merchant, in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant, performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected, performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant, obtaining target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant, and determining a risk detection result for the target merchant according to the target information and the feature information. In this way, on the one hand, in the case where the data structure of merchant data is becoming more and more complex, through modal alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then by utilizing the understanding, summarization, and reasoning capabilities of the large language model, information fusion processing is performed on the aligned data (i.e., the target text data) to obtain target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirements of the target merchant to obtain feature information that can meet the risk detection requirements. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirements, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of risk detection for merchants.

[0121] The above is the data processing device provided by the embodiment of this specification. Based on the same idea, the embodiment of this specification also provides a data processing device, as Figure 6 shown.

[0122] The data processing device may be a terminal device or a server provided in the above embodiment, etc.

[0123] The data processing device may vary greatly due to configuration or performance differences, and may include one or more processors 601 and a memory 602. One or more application programs or data may be stored in the memory 602. Among them, the memory 602 may be short-term storage or persistent storage. The application programs stored in the memory 602 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the data processing device. Further, the processor 601 may be set to communicate with the memory 602 and execute a series of computer-executable instructions in the memory 602 on the data processing device. The data processing device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input / output interfaces 605, and one or more keyboards 606.

[0124] Specifically, in this embodiment, the data processing device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs may include one or more modules. Each module may include a series of computer-executable instructions in the data processing device and is configured to be executed by one or more processors. The one or more programs include the following computer-executable instructions for:

[0125] Receiving a risk detection request for a target merchant;

[0126] In response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant;

[0127] Performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected;

[0128] According to the large language model, performing information fusion processing on the target text data to obtain target information corresponding to the target merchant;

[0129] Obtaining target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant;

[0130] Determining a risk detection result for the target merchant according to the target information and the feature information.

[0131] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the data processing device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, reference can be made to the description of the method embodiment.

[0132] An embodiment of this specification provides a data processing device. By receiving a risk detection request for a target merchant, in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant, performing modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected, performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant, obtaining target data to be detected corresponding to the risk detection requirements of the target merchant in the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant, and determining a risk detection result for the target merchant according to the target information and the feature information. In this way, on the one hand, in the case where the data structure of merchant data is becoming more and more complex, through modal alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then by using the understanding, summarization, and reasoning capabilities of the large language model, information fusion processing is performed on the aligned data (i.e., the target text data) to obtain the target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirements of the target merchant to obtain feature information that can meet the risk detection requirements. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirements, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of risk detection for merchants.

[0133] Further, based on the above Figures 1 to 5 shown method, one or more embodiments of this specification also provide a storage medium for storing computer-executable instruction information. In a specific embodiment, the storage medium can be a USB flash drive, an optical disc, a hard disk, etc. When the computer-executable instruction information stored in the storage medium is executed by a processor, the following process can be implemented:

[0134] Receive a risk detection request for a target merchant;

[0135] In response to the risk detection request, obtain the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant;

[0136] Perform modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected;

[0137] Perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant;

[0138] Obtain the target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain the feature information of the target merchant;

[0139] Determine the risk detection result for the target merchant according to the target information and the feature information.

[0140] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the above-mentioned storage medium embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0141] The embodiments of this specification provide a storage medium. By receiving a risk detection request for a target merchant, in response to the risk detection request, obtain the data to be detected corresponding to the target merchant. The data to be detected includes multimodal data related to the business operation behavior of the target merchant. Perform modal alignment processing on the data of different modalities in the data to be detected to obtain the target text data corresponding to the data to be detected. According to the large language model, perform information fusion processing on the target text data to obtain the target information corresponding to the target merchant. Obtain the target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain the feature information of the target merchant. Determine the risk detection result for the target merchant according to the target information and the feature information. In this way, on the one hand, in the case of the increasingly complex data structure of merchant data, through modal alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then by using the understanding, summarization, and reasoning capabilities of the large language model, perform information fusion processing on the aligned data (i.e., the target text data) to obtain the target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirements of the target merchant to obtain feature information that can meet the risk detection requirements. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirements, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of merchant risk detection.

[0142] Further, based on the above Figures 1 to 5 shown method, one or more embodiments of this specification also provide a computer program product, including a computer program. When the computer program in this computer program product is executed by a processor, it can implement the following process:

[0143] Receive a risk detection request for a target merchant;

[0144] In response to the risk detection request, obtain the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant;

[0145] Perform modal alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected;

[0146] According to the large language model, perform information fusion processing on the target text data to obtain the target information corresponding to the target merchant;

[0147] Obtain the target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain the feature information of the target merchant;

[0148] Determine the risk detection result for the target merchant according to the target information and the feature information.

[0149] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between each embodiment, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the above embodiment of a computer program product, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0150] An embodiment of this specification provides a computer program product. By receiving a risk detection request for a target merchant, in response to the risk detection request, obtaining the data to be detected corresponding to the target merchant, where the data to be detected includes multimodal data related to the business operation behavior of the target merchant, performing modal alignment processing on the data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected, performing information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant, obtaining target data to be detected corresponding to the risk detection requirements of the target merchant from the data to be detected, and performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant, and determining a risk detection result for the target merchant according to the target information and the feature information. In this way, on the one hand, in the case where the data structure of merchant data is becoming increasingly complex, through modal alignment processing, the multimodal data included in the data to be detected can be aligned to text data, and then, by utilizing the understanding, summarization, and reasoning capabilities of the large language model, information fusion processing is performed on the aligned data (i.e., target text data) to obtain target information corresponding to the target merchant. On the other hand, feature recognition processing can be performed on the target data to be detected corresponding to the risk detection requirements of the target merchant to obtain feature information that can meet the risk detection requirements. In this way, through the target information that can comprehensively and accurately describe the target merchant and the feature information that can meet the risk detection requirements, the risk detection result for the target merchant can be determined quickly and accurately, improving the detection efficiency and detection accuracy of merchant risk detection.

[0151] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0152] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by a user's programming of the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL), and there is not just one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0153] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0154] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0155] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0156] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0157] Embodiments of the present specification are described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present specification. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable parallel and serial devices for fraud cases to generate a machine, such that the instructions executed by the processors of the computer or other programmable parallel and serial devices for fraud cases generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0158] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable parallel and serial devices for fraud cases to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0159] These computer program instructions can also be loaded onto a computer or other programmable parallel and serial devices for fraud cases, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0160] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0161] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0162] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0163] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0164] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, one or more embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Furthermore, one or more embodiments of this specification may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0166] The various embodiments in this specification are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiments.

[0167] The above description is only for the embodiments of this specification and is not intended to limit this document. For those skilled in the art, various changes and modifications can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims of this specification.

Claims

1. A data processing method, comprising: Receive risk detection requests for target merchants; In response to the risk detection request, obtaining the to-be-detected data corresponding to the target merchant, wherein the to-be-detected data includes multimodal data related to the business operation behavior of the target merchant; Performing modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; According to the large language model, information fusion processing is performed on the target text data to obtain target information corresponding to the target merchant; Acquire target data to be detected that corresponds to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant; A risk detection result for the target merchant is determined according to the target information and the characteristic information.

2. The method according to claim 1, wherein determining the risk detection result for the target merchant according to the target information and the feature information comprises: Obtaining target prompt information corresponding to the risk detection requirements of the target merchant; Based on the target prompt information, the target information and the feature information, a risk detection result for the target merchant is determined by the large language model.

3. According to the method of claim 2, the step of obtaining target prompt information corresponding to the risk detection requirements of the target merchant comprises: Acquire first prompt information corresponding to the risk detection requirement of the target merchant; Performing feature extraction processing on the first prompt information to obtain a target vector corresponding to the first prompt information; Determining a target risk detection rule corresponding to the first prompt information in the risk detection rules according to the similarity between the target vector and the vector corresponding to the risk detection rule; The target prompt information is generated according to the target risk detection rule and the first prompt information.

4. According to the method of claim 3, the data to be detected includes image data, business operation behavior sequence data, table data, and graph structure data, and the graph structure data is constructed according to the association relationship between the target merchant and other merchants.

5. According to the method of claim 4, the step of performing modality alignment processing on the data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected comprises: According to the pre-trained conversion model, encoding processing is performed on the data of different modes in the data to be detected respectively to obtain feature vectors corresponding to the data to be detected of each mode; According to the pre-trained conversion model, the feature vector is decoded to obtain the target text data.

6. The method according to claim 4, wherein the step of performing feature recognition processing on the target data to be detected to obtain feature information of the target merchant comprises: According to a pre-trained feature recognition model, the target data to be detected is processed for behavioral feature recognition to obtain feature information of the target merchant, wherein the feature recognition model is a model constructed based on a preset machine learning algorithm.

7. The method according to claim 6, wherein the feature recognition model comprises a first sub-model and a second sub-model, wherein the first sub-model is used to identify the industry in which the target merchant is located, and the second sub-model is used to identify whether the transaction behavior of the target merchant is risky, and the target data to be detected is subjected to behavioral feature recognition processing according to the pre-trained feature recognition model to obtain feature information of the target merchant, including: Determine, according to the pre-trained first sub-model, industry characteristic information of the industry in which the target merchant is located based on the image data and the business operation behavior sequence data in the target data to be detected; Determining the behavior risk characteristic information of the target merchant according to the pre-trained second sub-model and based on the business operation behavior sequence data and the graph structure data; Based on the industry characteristic information and the behavior risk characteristic information, characteristic information of the target merchant is determined.

8. The method according to claim 1, determining the risk detection result for the target merchant according to the target information and the characteristic information, comprising: According to a pre-trained risk detection model, based on the target information and the feature information, the risk type corresponding to the target merchant is determined, and according to the risk type corresponding to the target merchant, the risk detection result for the target merchant is determined, and the risk detection model is a model constructed based on a preset machine learning algorithm.

9. A data processing device, comprising: A request receiving module, used to receive a risk detection request for a target merchant; A data acquisition module, configured to acquire, in response to the risk detection request, the to-be-detected data corresponding to the target merchant, wherein the to-be-detected data includes multimodal data related to the business operation behavior of the target merchant; A modality alignment module, used for performing modality alignment processing on data of different modalities in the data to be detected, so as to obtain target text data corresponding to the data to be detected; An information fusion module, used to perform information fusion processing on the target text data according to a large language model to obtain target information corresponding to the target merchant; A feature recognition module is used to obtain target data to be detected that corresponds to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant; The risk detection module is used to determine the risk detection result for the target merchant according to the target information and the characteristic information.

10. A data processing device, comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Receive risk detection requests for target merchants; In response to the risk detection request, obtaining the to-be-detected data corresponding to the target merchant, wherein the to-be-detected data includes multimodal data related to the business operation behavior of the target merchant; Performing modality alignment processing on data of different modalities in the data to be detected to obtain target text data corresponding to the data to be detected; According to the large language model, information fusion processing is performed on the target text data to obtain target information corresponding to the target merchant; Acquire target data to be detected that corresponds to the risk detection requirements of the target merchant from the data to be detected, and perform feature recognition processing on the target data to be detected to obtain feature information of the target merchant; A risk detection result for the target merchant is determined according to the target information and the characteristic information.

Images