Value data processing method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a value data processing method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: determining a similar value product information set and user group information; for each piece of similar value product information, executing a first generation step: determining a first matching information set; performing data screening on the similar risk circulation data set to generate a screened data set; for each piece of user information, determining second matching information; screening out at least one piece of user information, and generating an extended value transfer data sequence set; generating an extended data set; generating value risk information; and storing various data or information, and sending information links and link instructions to the value monitoring terminal. According to the embodiment, the value risk information for the target user can be accurately generated, and the value loss for the target user is avoided by executing the corresponding value operation on the target user.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a value data processing method, device, electronic device, and computer-readable medium. Background Art

[0002] At present, relevant value products developed by various industries will confirm the value qualifications of users to avoid value loss. The method usually adopted to generate value risk information for users using value products is to conduct value risk analysis based on the value flow data sequence of the target user and the relevant risk data set corresponding to the target value product by relevant experts to generate value risk information.

[0003] However, the inventors have found that when the above method is used to generate value risk information, the following technical problems often occur:

[0004] Manual value risk analysis is not accurate enough and inefficient, which wastes a lot of server resources and CPU resources. In addition, the confidentiality of value flow data cannot be achieved, which may lead to the leakage of value risk related information.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose value data processing methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for processing value data, including: obtaining from a target server a historical value flow data sequence for a target user and a risk flow data set corresponding to a target value product, wherein the target value product is a value product in which the target user participates in value; determining a similar value product information set corresponding to the target value product and user group information corresponding to the target user; for each similar value product information in the similar value product information set, using a central processing unit, executing a first generation step: determining a first matching information set between a similar risk flow data set corresponding to the similar value product information and the target value product; based on the first matching information set, performing data screening on the similar risk flow data set to generate a screening data group; for each user information in the user group information, determining a second matching information set between a similar historical value flow data sequence corresponding to the user information and the target user; information; filter out at least one user information whose corresponding second matching information is greater than the target value from the above user group information, and generate an extended value flow data sequence set based on at least one similar historical value flow data sequence corresponding to the above at least one user information and the above historical value flow data sequence; generate an extended data set based on the obtained screening data set and the above risk flow data set; generate value risk information characterizing the use of the above target value product by the above target user based on the above extended value flow data sequence set and the above extended data set; store the above extended value flow data sequence set, the above extended data set, the above similar value product information set, the user information corresponding to the above target user and the above user group information in the above target data storage end accordingly, and send the information link and link description corresponding to the above value risk information to the value monitoring terminal in the form of email encryption, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0009] In a second aspect, some embodiments of the present disclosure provide a value data processing device, including: an acquisition unit, configured to acquire, from a target server, a historical value flow data sequence for a target user and a risk flow data set corresponding to a target value product, wherein the target value product is a value product in which the target user participates in value; a first determination unit, configured to determine a similar value product information set corresponding to the target value product and user group information corresponding to the target user; a first execution unit, configured to, for each similar value product information in the similar value product information set, use a central processing unit to execute a first generation step: determine a first matching information set between a similar risk flow data set corresponding to the similar value product information and the target value product; perform data screening on the similar risk flow data set based on the first matching information set to generate a screened data group; a second determination unit, configured to determine, for each user information in the user group information, a second matching information set between a similar historical value flow data sequence corresponding to the user information and the target user ; A screening and generating unit is configured to screen out at least one user information whose corresponding second matching information is greater than a target value from the above user group information, and to generate an extended value circulation data sequence set according to at least one similar historical value circulation data sequence and the above historical value circulation data sequence corresponding to the above at least one user information; a first generating unit is configured to generate an extended data set according to the obtained screening data set and the above risk circulation data set; a second generating unit is configured to generate value risk information characterizing the use of the above target value product by the above target user according to the above extended value circulation data sequence set and the above extended data set; a second executing unit is configured to store the above extended value circulation data sequence set, the above extended data set, the above similar value product information set, the user information corresponding to the above target user and the above user group information in the above target data storage end, and to send the information link and link description corresponding to the above value risk information to the value monitoring terminal in the form of email encryption, so that the monitoring user can decrypt the value risk through a key and perform corresponding value operations.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the value data processing method of some embodiments of the present disclosure, the value risk information for the target user can be accurately generated, so as to avoid the value loss for the target user by performing the corresponding value operation on the target user. Specifically, the reason for the inaccuracy of the relevant value risk information is that the value risk analysis is artificially performed, and there are problems such as inaccurate value risk analysis and low efficiency. Based on this, the value data processing method of some embodiments of the present disclosure first obtains the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product from the target service end. Among them, the above-mentioned target value product is the value product in which the above-mentioned target user participates in value. Here, the obtained historical value flow data sequence and risk flow data set are used as the data basis for the generation of subsequent value risk information. Then, the similar value product information set corresponding to the above-mentioned target value product and the user group information corresponding to the above-mentioned target user are determined. Here, the data supplement of the historical value flow data sequence and the risk flow data set is realized through the similar value product information set and the user group information. Next, for each similar value product information in the above-mentioned similar value product information set, the central processor is used to perform the first generation step: the first step is to use the central processor to accurately and efficiently determine the first matching information set between the similar risk flow data set corresponding to the above-mentioned similar value product information and the above-mentioned target value product. Here, the obtained first matching information set is used to subsequently filter out the data set that matches the target value product from the similar risk flow data set, so as to serve as the data basis for the subsequent generation of value risk information. The second step is to perform data screening on the above-mentioned similar risk flow data set according to the above-mentioned first matching information set to generate a screening data group, and the obtained screening data group is a data set that has data association with the target value product. Next, for each user information in the above-mentioned user group information, the second matching information between the similar historical value flow data sequence corresponding to the above-mentioned user information and the above-mentioned target user is determined, so as to be used for the subsequent determination of the similar data set that has data association with the target user, so as to supplement the data set of the historical value flow data sequence. Next, at least one user information corresponding to the second matching information greater than the target value is screened out from the user group information, and an extended value flow data sequence set is generated based on at least one similar historical value flow data sequence corresponding to the at least one user information and the historical value flow data sequence, so as to generate a value flow data set that has a data similarity connection or data association relationship with the target user. Furthermore, an extended data set is generated based on the obtained screening data set and the risk flow data set, so as to generate a data set that has a data similarity connection or data association relationship with the target value product.Next, based on the above-mentioned extended value circulation data sequence set and the above-mentioned extended data set, the value risk information characterizing the use of the above-mentioned target value product by the above-mentioned target user can be accurately generated in the case of a large amount of data. According to the above-mentioned value risk information, the corresponding accurate value operation is performed on the above-mentioned target user. Finally, the above-mentioned extended value circulation data sequence set, the above-mentioned extended data set, the above-mentioned similar value product information set, the above-mentioned target user corresponding user information and the above-mentioned user group information are correspondingly stored in the above-mentioned target data storage end, and the information link and link description corresponding to the above-mentioned value risk information are sent to the value monitoring terminal in the form of email encryption, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation. Here, the security of the value risk related information can be greatly guaranteed by email encryption and key decryption. The storage of each information can also facilitate subsequent retrieval and use, greatly saving the use of calling resources and improving calling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the value data processing method according to the present disclosure;

[0015] Figure 2 is a schematic diagram of the structure of some embodiments of the value data processing device according to the present disclosure;

[0016] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] refer to Figure 1 , shows a process 100 of some embodiments of the value data processing method according to the present disclosure. The value data processing method comprises the following steps:

[0024] Step 101, obtaining the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product from the target server.

[0025] In some embodiments, the execution subject of the above-mentioned value data processing method can obtain the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product through a wired connection method or a wireless connection method. Among them, the above-mentioned target value product is a value product in which the above-mentioned target user participates in value. The target user may be a user to be tested for risk. In practice, the target user may be a user to be tested for financial risk. The historical value flow data sequence may be a value flow data sequence for a historical period. In practice, the value flow data sequence may be a product consumption data sequence. Product consumption data may be product input data or product output data. The target value product may be a risk prediction product. For example, in the field of credit reporting, the target value product may be a bank credit product. The risk flow data set may be a risk data set for each product user of the target value product.

[0026] Step 102: Determine a similar value product information set corresponding to the target value product and user group information corresponding to the target user.

[0027] In some embodiments, the execution entity may determine a similar value product information set corresponding to the target value product and user group information corresponding to the target user. The similar value product information in the similar value product information set may be product information of value products whose product characteristics are similar to those of the target value product. In practice, the product information may be the product name. The user group information may be group information of a corresponding user whose characteristics are similar to those of the target user. In practice, the user group information may be group information of a user group. The user group may include: multiple users whose user characteristics are similar to those of the target user.

[0028] In some optional implementations of some embodiments, the determining of the similar value product information set corresponding to the target value product and the user group information corresponding to the target user includes:

[0029] The first step is to obtain the product display image and product display information corresponding to the above-mentioned target value product, and obtain the full product display image and full product display information corresponding to each full value product information in the above-mentioned full value product information set. Among them, the product display image can be an image that displays the product-related information corresponding to the target value product. Product-related information may include: product-related promotional information, product-related characteristic attribute information. Product display information can be text information that displays product-related characteristic attributes. The full product display image can be an image that displays product-related information corresponding to the full value product information. The full product display information can be text information that displays product-related characteristic attributes corresponding to the full value product information. Among them, the image resolution size between the product display image and the full product display image is the same.

[0030] In the second step, for each full value product information in the full value product information set, the following second generation step is performed:

[0031] Sub-step 1: extract the keyword set and corresponding keyword position information set included in the full product display picture corresponding to the full value product information. The keyword set can be the keyword set in each word set in the full product display picture. The keyword position information can be the coordinate information of the keyword in the full product display picture.

[0032] As an example, first, the above-mentioned execution entity can input the full product display picture into the image recognition model to generate a word set and a word position information set corresponding to the word set. Among them, there is a one-to-one correspondence between the words in the word set and the word position information in the word position information set. Then, the keywords corresponding to the full value product information are filtered out from the word set to obtain a keyword set. Finally, the keyword position information set corresponding to the keyword set is determined. The image recognition model can be a YOLO v5 model.

[0033] Sub-step 2: determining the word attribute information corresponding to each keyword in the above keyword set, wherein the word attribute information corresponding to the keyword may be a word attribute name with similar semantics to the keyword.

[0034] Sub-step 3: Associating each keyword in the above keyword set with the corresponding word attribute information to generate an associated word and word attribute table.

[0035] Sub-step 4, dividing the product display images into regions to obtain a divided display atlas, wherein the divided display images may be irregularly shaped images.

[0036] As an example, the execution subject may input the product display image into an image segmentation model to perform image region segmentation to obtain a segmented display image set. The image segmentation model may be a U-net model.

[0037] Sub-step 5, according to the image template corresponding to the above-mentioned product display image, determine the image content weight corresponding to each divided display image in the above-mentioned divided display image set, and obtain the image content weight set. Among them, the image template can be the initial template corresponding to the product display image. Among them, the image content weight can represent the importance of the image content in the divided display image. The image content weight can be a value between 0 and 1. Among them, the importance of the content semantics of each template module is marked in the image template.

[0038] Sub-step 6: determining the position weight corresponding to each keyword position information in the keyword position information set according to the image content weight set to obtain a position weight set.

[0039] Alternatively, the execution entity may determine the image content weight of the same corresponding template module as each keyword position information in the keyword position information set as the position weight corresponding to the keyword position information, and obtain a position weight set.

[0040] Sub-step 7: adding the keyword position information set and the position weight set to the associated word and word attribute table to generate an information association table.

[0041] The third step is to determine the product information association table corresponding to the product display diagram. The generation method of the product information association table can refer to the generation method of the information association table.

[0042] The fourth step is to determine the table content difference information corresponding to each information association table in the obtained information association table set and the product information association diagram to generate difference information. The difference information can be a value between 0 and 1, and the larger the value, the greater the difference in the table content.

[0043] Step 5: determine the full value product information in the full value product information set whose corresponding difference information meets the preset information condition as similar value product information to obtain a similar value product information set. The preset information condition may be full value product information whose difference information is less than 30%.

[0044] Optionally, the above-mentioned determination of the similar value product information set corresponding to the above-mentioned target value product and the user group information corresponding to the above-mentioned target user further includes the following steps:

[0045] The first step is to determine the object feature information group corresponding to the target user. The object feature information group may be the feature value of each object feature corresponding to the target user. For example, each object feature may include but is not limited to at least one of the following: object name, object assets, object work information.

[0046] The second step is to determine the user characteristic information group corresponding to each user information in the initial user group information, and obtain the user characteristic information group set. The initial user group information may be group information corresponding to the initial user group. The initial user group information may be a group identifier. The initial user group may be a traceability group of a user group that has a user characteristic association relationship with the target user.

[0047] The third step is to obtain the selected feature attribute information set and clustering purpose information. The feature attribute information may be an attribute identifier corresponding to the feature attribute. The clustering purpose information may represent the association between the determined user group information and the target user. For example, the clustering target information may be the information of the consumption level clustering purpose, or the level of the asset-similar clustering purpose.

[0048] In the fourth step, according to the above clustering purpose information, each feature attribute information in the above feature attribute information set is assigned an information weight to generate weight information and obtain a weight information set. The information size corresponding to the weight information is between -1 and 1. A higher weight is assigned to the feature attribute information that is closely related to the clustering target information, and a lower weight is assigned to the feature attribute information that is not closely related to the clustering target information.

[0049] As an example, first, the above-mentioned execution entity can input the clustering purpose information and each feature attribute information in the feature attribute information set into the convolutional neural network model to generate weight information and obtain the weight information set.

[0050] The fifth step is to filter out a first feature attribute information subset whose corresponding weight information has an information size greater than 0 from the above feature attribute information set, and to filter out a second feature attribute information subset whose corresponding weight information has an information size less than 0.

[0051] In the sixth step, based on the first feature attribute information subset and the corresponding first weight information subset, the object feature information group and the user feature information group set are used as clustering data sets, and user information sets corresponding to the target user and the initial user group information are clustered to generate a first user information cluster. The user information clustering method can be a K-means algorithm based on weight information. That is, in the process of generating vector distance, the influence of weight information needs to be considered.

[0052] The seventh step is to use the object feature information group and the user feature information group set as clustering data sets based on the second feature attribute information subset and the corresponding second weight information subset, and to cluster the user information sets corresponding to the target user and the initial user group information to generate a second user information cluster set.

[0053] In step 8, cluster verification is performed on each cluster in the first user information cluster set using each cluster in the second user information cluster set to generate verification results, wherein the verification results include: the result that the first user information cluster set passes the cluster verification and the result that the first user information cluster set fails the cluster verification.

[0054] As an example, first, a first user information cluster including user information corresponding to a target user is screened out from a first user information cluster set as a first target user information cluster. Then, a second user information cluster including user information corresponding to a target user is screened out from a second user information cluster set as a second target user information cluster. Next, a user information difference rate between each user information in the first target user information cluster and each user information in the second target user information cluster is determined. Finally, in response to determining that the user information difference rate is greater than or equal to a fixed value, a result that the first user information cluster set fails the cluster check is generated. In response to determining that the user information difference rate is less than a fixed value, a result that the first user information cluster set passes the cluster check is generated.

[0055] The ninth step is to determine the user group information corresponding to the target user according to the verification result.

[0056] As an example, in response to determining that the verification result is that the first user information cluster set passes the cluster verification, the group information of the user group corresponding to the first user information cluster where the target user in the first user information cluster set is located is used as the user group information. In response to determining that the verification result is that the first user information cluster set fails the cluster verification, the same user information as the second target user information cluster is removed from the first target user information cluster to obtain the first target user information cluster after removal as the user group information.

[0057] Step 103, for each similar value product information in the similar value product information set, using a central processing unit, executes a first generation step:

[0058] Step 1031, determining a first matching information set between the similar risk transfer data set corresponding to the similar value product information and the target value product.

[0059] In some embodiments, the execution entity may determine a first matching information set between the similar risk flow data set corresponding to the similar value product information and the target value product. There is corresponding similar risk flow data for the first matching information in the first matching information set. That is, there is a one-to-one correspondence between the first matching information in the first matching information set and the similar risk flow data in the similar risk flow data set. The first matching information may be a matching score. The first matching information may represent the degree of matching between the similar risk flow data and the target value product. The larger the corresponding numerical value of the first matching information, the higher the corresponding matching degree.

[0060] As an example, first, the execution subject may perform data encoding on each similar risk flow data to generate encoding vector information and obtain an encoding vector information set. Then, the encoding vector information in the encoding vector information set is spliced ​​to generate a splicing vector. Next, the product attribute information set corresponding to the target value product is encoded to generate an attribute encoding vector. Finally, the vector cosine distance between the attribute encoding vector and the splicing vector is determined as the first matching information.

[0061] Here, using the central processing unit to execute the first generation step can achieve advance arrangement of computing resources and improve the processing efficiency corresponding to the generation step.

[0062] Step 1032: Screen the similar risk flow data set based on the first matching information set to generate a screened data set.

[0063] In some embodiments, the execution entity may perform data screening on the similar risk flow data set according to the first matching information set to generate a screening data group.

[0064] As an example, the execution subject may filter out similar risk flow data corresponding to the first matching information greater than a preset value from the similar risk flow data set to obtain a filtered data set. For example, the preset value may be 0.7.

[0065] Step 104: for each user information in the user group information, determine the second matching information between the similar historical value transfer data sequence corresponding to the user information and the target user.

[0066] In some embodiments, the execution entity may determine, for each user information in the user group information, the second matching information between the similar historical value flow data sequence corresponding to the user information and the target user. The second matching information in the second matching information set has corresponding similar risk flow data. That is, there is a one-to-one correspondence between the first matching information in the first matching information set and the similar risk flow data in the similar risk flow data set. The first matching information may be a matching score. The first matching information may represent the degree of matching between the similar risk flow data and the target value product. The larger the corresponding numerical value of the first matching information, the higher the corresponding matching degree.

[0067] As an example, first, the execution subject may perform data encoding on each similar historical value flow data in the similar historical value flow data sequence to generate a value flow encoding vector and obtain a value flow encoding vector sequence. Then, each value flow encoding vector in the value flow encoding vector sequence is vector-fused to generate a fusion vector. Next, the user attribute feature information set corresponding to the target user is vector-converted to generate an attribute fusion feature vector. Finally, the vector cosine distance between the fusion vector and the attribute fusion feature vector is determined as the second matching information.

[0068] Step 105, filter out at least one user information whose corresponding second matching information is greater than the target value from the above user group information, and generate an extended value flow data sequence set based on at least one similar historical value flow data sequence corresponding to the above at least one user information and the above historical value flow data sequence.

[0069] In some embodiments, the execution subject may filter out at least one user information whose corresponding second matching information is greater than a target value from the user group information, and generate an extended value flow data sequence set based on at least one similar historical value flow data sequence corresponding to the at least one user information and the historical value flow data sequence. The target value may be a preset value.

[0070] Step 106: Generate an extended data set based on the obtained screening data set and the risk transfer data set.

[0071] In some embodiments, the execution entity may generate an extended data set based on the obtained screening data set and the risk transfer data set. In practice, the extended data set includes: each screening data set in the screening data set and the risk transfer data set.

[0072] As an example, the execution entity may combine the screening data set and the risk transfer data set to generate a combined data set as an extended data set.

[0073] Step 107: Generate value risk information representing the target user's use of the target value product based on the extended value circulation data sequence set and the extended data set.

[0074] In some embodiments, the execution subject may generate value risk information representing the target user's use of the target value product based on the extended value circulation data sequence set and the extended data set, wherein the value risk information may be the value risk that the target user may bring when using the target value product.

[0075] In some optional implementations of some embodiments, generating the value risk information characterizing the target user's use of the target value product according to the extended value circulation data sequence set and the extended data set may include the following steps:

[0076] The first step is to obtain a first value-risk characteristic attribute group based on the product perspective and a second value-risk characteristic attribute group based on the user perspective. Among them, the first value-risk characteristic attribute in the first value-risk characteristic attribute group based on the product perspective can be a characteristic attribute that is closely related to the value-risk information from the product perspective. The first value-risk characteristic attribute in the first value-risk characteristic attribute group based on the user perspective can be a characteristic attribute that is closely related to the value-risk information from the user perspective.

[0077] The second step is to extract the first value-risk characteristic attribute information group set for the first value-risk characteristic attribute group from the above-mentioned extended value circulation data sequence set, and to extract the second value-risk characteristic attribute information group set for the second value-risk characteristic attribute group from the above-mentioned extended value circulation data sequence set.

[0078] The third step is to extract a third value-risk characteristic attribute information group set for the first value-risk characteristic attribute group from the extended data set, and to extract a fourth value-risk characteristic attribute information group set for the second value-risk characteristic attribute group from the extended data set.

[0079] The fourth step is to generate the first candidate value-risk information based on the first value-risk characteristic attribute information set and the third value-risk characteristic attribute information set.

[0080] As an example, the above-mentioned execution entity can input the above-mentioned first value-risk characteristic attribute information set and the above-mentioned third value-risk characteristic attribute information set into a parallel-connected convolutional neural network model + a multi-layer serially connected convolutional neural network model to generate a first candidate value-risk information.

[0081] The fifth step is to generate second candidate value risk information based on the second value risk characteristic attribute information set and the fourth value risk characteristic attribute information set.

[0082] As an example, the above-mentioned execution entity can input the above-mentioned second value-risk characteristic attribute information set and the above-mentioned fourth value-risk characteristic attribute information set into a parallel-connected convolutional neural network model + a multi-layer serially connected convolutional neural network model to generate a second candidate value-risk information.

[0083] The sixth step is to determine the information level corresponding to the first candidate value risk information and the information level corresponding to the second candidate value risk information, as the first information level and the second information level respectively.

[0084] In the seventh step, the value risk information is generated according to the first information level, the second information level, the first threshold for the first candidate value risk information and the second threshold for the second candidate value risk information.

[0085] In some optional implementations of some embodiments, generating the value risk information characterizing the target user's use of the target value product according to the extended value circulation data sequence set and the extended data set may include the following steps:

[0086] In the first step, for each extended value flow data sequence in the above extended value flow data sequence set, the following third generation step is performed:

[0087] Sub-step 1: extracting the first value flow feature information set corresponding to the extended value flow data sequence. The first value flow feature information set is an information set corresponding to the user value flow feature set. The first value flow feature information set can be a feature content set of the extended value flow data sequence under the user value flow feature set.

[0088] Sub-step 2: Input the first value flow feature information set into a product type information classification model to generate product type information. The product type information classification model may be a neural network model for generating product type information. The product type information may be a type identifier corresponding to the product type. In practice, the product type information classification model may be a multi-layer series of convolutional layers.

[0089] Sub-step 3, obtaining a first product feature information set corresponding to the above product type information.

[0090] Sub-step 4: for each extended data in the above extended data set, perform the following fourth generation step:

[0091] The first sub-step is to extract the second product feature information set corresponding to the extended data, wherein the second product feature information set is an information set corresponding to the product value circulation feature set.

[0092] The second sub-step is to determine the feature information similarity between the first product feature information set and the second product feature information set as the first feature similarity. The feature information similarity can represent the degree of information similarity between the two product feature information. The feature information similarity can be a value between 0 and 1. The higher the value, the more similar the representation.

[0093] As an example, the execution entity may determine the feature information similarity between the first product feature information set and the second product feature information set by means of cosine distance as the first feature similarity.

[0094] The third sub-step is to determine the first data similarity between the extended value circulation data sequence and the historical value circulation data sequence, wherein the first data similarity can represent the data similarity between the extended value circulation data sequence and the historical value circulation data sequence.

[0095] The fourth sub-step is to determine the similarity of the second data corresponding to the extended data.

[0096] The fifth sub-step is to generate a first initial risk similarity based on the first feature similarity, the first data similarity and the second data similarity.

[0097] As an example, the execution entity may add the first feature similarity, the first data similarity, and the second data similarity to generate a first initial risk similarity.

[0098] As another example, the execution entity may perform weighted sum processing on the first feature similarity, the first data similarity, and the second data similarity to generate the first initial risk similarity.

[0099] The second step is to generate the first initial risk information according to the obtained first initial risk similarity set.

[0100] As an example, the execution entity may add up the first initial risk similarities in the first initial risk similarity set to generate the first initial risk information.

[0101] The third step is to generate the above-mentioned value risk information based on the above-mentioned first initial risk information.

[0102] Optionally, the generating of the value risk information according to the first initial risk information may include the following steps:

[0103] In the first step, for each extended data in the above extended data set, the following fifth generation step is performed:

[0104] Sub-step 1: determine the second product feature information set corresponding to the above-mentioned extended data as the target second product feature information set.

[0105] Sub-step 2, inputting the above-mentioned target second product feature information set into the user type information classification model to generate user type information. The user type information classification model may be a neural network model for generating user type information. The user type information may be a type identifier corresponding to the user type. In practice, the user type information classification model may be a multi-layer series of convolutional layers.

[0106] Sub-step 3: obtaining a first user characteristic information set corresponding to the above user type information.

[0107] Sub-step 4: for each extended value circulation data sequence in the extended value circulation data sequence set, execute the following sixth generation step:

[0108] The first sub-step is to determine the user feature information set corresponding to the above-mentioned extended value circulation data sequence as the second user feature information set.

[0109] The second sub-step is to determine the feature information similarity between the first user feature information set and the second user feature information set as the second feature similarity.

[0110] The third sub-step is to determine the third data similarity corresponding to the extended data.

[0111] The fourth sub-step is to determine the fourth data similarity corresponding to the above-mentioned extended value flow data sequence.

[0112] The fifth sub-step is to generate a second initial risk similarity according to the second feature similarity, the third data similarity and the fourth data similarity. For the specific implementation method, please refer to the generation of the first initial risk similarity.

[0113] The second step is to generate the second initial risk information according to the obtained second initial risk similarity set. The specific implementation method can refer to the generation of the first initial risk information.

[0114] The third step is to generate the above-mentioned value risk information based on the above-mentioned second initial risk information and the above-mentioned first initial risk information.

[0115] As an example, the execution entity may perform weighted processing on the second initial risk information and the first initial risk information to generate value risk information.

[0116] Optionally, the generating of the value risk information according to the second initial risk information and the first initial risk information may include the following steps:

[0117] The first step is to determine the value risk tendency information, wherein the value risk tendency information includes: information representing the tendency from the user risk perspective and information representing the tendency from the product risk perspective.

[0118] The second step is to generate the above-mentioned value risk information based on the above-mentioned value risk tendency information, the above-mentioned second initial risk information and the above-mentioned first initial risk information.

[0119] As an example, the execution entity may perform weighted processing on the value risk tendency information, the second initial risk information and the first initial risk information to generate value risk information.

[0120] Optionally, as one of the invention points, another technical problem "the generation of value risk information is not accurate enough" is solved. Based on this, the present disclosure can generate the first initial risk information and the second initial risk information from the perspective of user type and product type respectively, thereby accurately and comprehensively generating value risk information.

[0121] Step 108, the above-mentioned extended value flow data sequence set, the above-mentioned extended data set, the above-mentioned similar value product information set, the above-mentioned target user corresponding user information and the above-mentioned user group information are correspondingly stored in the above-mentioned target data storage end, and the information link and link description corresponding to the above-mentioned value risk information are sent to the value monitoring terminal in the form of encrypted email, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0122] In some embodiments, the above-mentioned execution entity may store the above-mentioned extended value flow data sequence set, the above-mentioned extended data set, the above-mentioned similar value product information set, the above-mentioned target user corresponding user information and the above-mentioned user group information correspondingly at the above-mentioned target data storage end, and send the information link and link description corresponding to the above-mentioned value risk information in the form of encrypted email to the value monitoring terminal, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0123] In some optional implementations of some embodiments, after step 108, the steps further include:

[0124] The first step is to determine the value risk execution result corresponding to the target user. The value risk execution result may be the result after the value operation is performed on the target user. For example, the value operation may be an interest rate increase operation, and the corresponding value risk execution result may be the interest rate corresponding to the target user after the interest rate increase.

[0125] In the second step, the above-mentioned value risk execution results, the value risk information corresponding to the above-mentioned target users, the above-mentioned extended value flow data sequence set and the above-mentioned extended data set are distributed and stored in each first-level product deployment terminal. In practice, each product deployment terminal stores the product data under each product. The product deployment terminal can be divided into multiple levels of product terminals, and the first-level product deployment terminal can be a product deployment terminal in a city with a volume greater than a preset volume. For example, the first-level product deployment terminal can be a product deployment terminal deployed at the provincial capital level. The remaining product terminals can be product terminals distributed in various small cities.

[0126] The third step is to determine whether the target terminal is a first-level product deployment terminal in response to receiving the value risk appeal information initiated by the target user at the target terminal. The value risk appeal information may be a request information for re-appealing the value risk. For example, the value risk appeal information may be information for appealing the interest rate reduction.

[0127] In a fourth step, in response to determining that the target terminal is not the target terminal, a first-level product deployment terminal corresponding to the target terminal is determined as the target first-level product deployment terminal.

[0128] The fifth step is to determine the user level corresponding to the target user. The user level can represent the importance of the target user. The higher the corresponding user level, the more efficient the selected information transmission method is.

[0129] The sixth step is to determine the information transmission mode corresponding to the above user level as the target information transmission mode.

[0130] The seventh step is to use the above-mentioned target information transmission method to send the above-mentioned value risk execution results stored in the above-mentioned target first-level product deployment terminal, the value risk information corresponding to the above-mentioned target user, the above-mentioned extended value flow data sequence set and the above-mentioned extended data set to the above-mentioned target terminal, so that the above-mentioned target terminal can review the above-mentioned value risk complaint information.

[0131] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the value data processing method of some embodiments of the present disclosure, the value risk information for the target user can be accurately generated, so as to avoid the value loss for the target user by performing the corresponding value operation on the target user. Specifically, the reason for the inaccuracy of the relevant value risk information is that the value risk analysis is artificially performed, and there are problems such as inaccurate value risk analysis and low efficiency. Based on this, the value data processing method of some embodiments of the present disclosure first obtains the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product from the target service end. Among them, the above-mentioned target value product is the value product in which the above-mentioned target user participates in value. Here, the obtained historical value flow data sequence and risk flow data set are used as the data basis for the generation of subsequent value risk information. Then, the similar value product information set corresponding to the above-mentioned target value product and the user group information corresponding to the above-mentioned target user are determined. Here, the data supplement of the historical value flow data sequence and the risk flow data set is realized through the similar value product information set and the user group information. Next, for each similar value product information in the above-mentioned similar value product information set, the central processor is used to perform the first generation step: the first step is to use the central processor to accurately and efficiently determine the first matching information set between the similar risk flow data set corresponding to the above-mentioned similar value product information and the above-mentioned target value product. Here, the obtained first matching information set is used to subsequently filter out the data set that matches the target value product from the similar risk flow data set, so as to serve as the data basis for the subsequent generation of value risk information. The second step is to perform data screening on the above-mentioned similar risk flow data set according to the above-mentioned first matching information set to generate a screening data group, and the obtained screening data group is a data set that has data association with the target value product. Next, for each user information in the above-mentioned user group information, the second matching information between the similar historical value flow data sequence corresponding to the above-mentioned user information and the above-mentioned target user is determined, so as to be used for the subsequent determination of the similar data set that has data association with the target user, so as to supplement the data set of the historical value flow data sequence. Next, at least one user information corresponding to the second matching information greater than the target value is screened out from the user group information, and an extended value flow data sequence set is generated based on at least one similar historical value flow data sequence corresponding to the at least one user information and the historical value flow data sequence, so as to generate a value flow data set that has a data similarity connection or data association relationship with the target user. Furthermore, an extended data set is generated based on the obtained screening data set and the risk flow data set, so as to generate a data set that has a data similarity connection or data association relationship with the target value product.Next, based on the above-mentioned extended value circulation data sequence set and the above-mentioned extended data set, the value risk information characterizing the use of the above-mentioned target value product by the above-mentioned target user can be accurately generated in the case of a large amount of data. According to the above-mentioned value risk information, the corresponding precise value operation is performed on the above-mentioned target user. Finally, the above-mentioned extended value circulation data sequence set, the above-mentioned extended data set, the above-mentioned similar value product information set, the above-mentioned target user corresponding user information and the above-mentioned user group information are correspondingly stored in the above-mentioned target data storage end, and the information link and link description corresponding to the above-mentioned value risk information are sent to the value monitoring terminal in the form of encrypted email, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0132] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a value data processing device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the value data processing device can be specifically applied to various electronic devices.

[0133] like Figure 2As shown, a value data processing device 200 includes: an acquisition unit 201, a first determination unit 202, a first execution unit 203, a second determination unit 204, a screening generation unit 205, a first generation unit 206, a second generation unit 207 and a second execution unit 208. Among them, the acquisition unit 201 is configured to obtain the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product from the target server, wherein the above-mentioned target value product is the value product in which the above-mentioned target user participates in value; the first determination unit 202 is configured to determine the similar value product information set corresponding to the above-mentioned target value product and the user group information corresponding to the above-mentioned target user; the first execution unit 203 is configured to, for each similar value product information in the above-mentioned similar value product information set, use the central processor to execute the first generation step: determine the first matching information set between the similar risk flow data set corresponding to the above-mentioned similar value product information and the above-mentioned target value product; based on the above-mentioned first matching information set, perform data screening on the above-mentioned similar risk flow data set to generate a screening data group; the second determination unit 204 is configured to determine the second matching information between the similar historical value flow data sequence corresponding to the above-mentioned user information and the above-mentioned target user for each user information in the above-mentioned user group information; the screening generation unit 205 is configured The first generation unit 206 is configured to generate an extended data set based on the obtained screening data set and the risk flow data set; the second generation unit 207 is configured to generate value risk information characterizing the use of the target value product by the target user according to the extended value flow data set and the extended data set; the second execution unit 208 is configured to store the extended value flow data set, the extended data set, the similar value product information set, the target user's corresponding user information and the user group information in the target data storage end, and send the information link and link description corresponding to the value risk information to the value monitoring terminal in the form of email encryption, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0134] It is understood that the various units recorded in the value data processing device 200 and the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the value data processing device 200 and the units included therein, and will not be described in detail here.

[0135] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0136] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0137] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0138] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0139] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0140] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0141] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently and not be installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the historical value flow data sequence for the target user and the risk flow data set corresponding to the target value product from the target server, wherein the above-mentioned target value product is the value product in which the above-mentioned target user participates in value; determines the similar value product information set corresponding to the above-mentioned target value product and the user group information corresponding to the above-mentioned target user; for each similar value product information in the above-mentioned similar value product information set, uses the central processing unit to execute the first generation step: determines the first matching information set between the similar risk flow data set corresponding to the above-mentioned similar value product information and the above-mentioned target value product; based on the above-mentioned first matching information set, performs data screening on the above-mentioned similar risk flow data set to generate a screening data group; for each user information in the above-mentioned user group information, determines the similar historical value flow data sequence corresponding to the above-mentioned user information and the above-mentioned target value product. the second matching information between users; filtering out at least one user information whose corresponding second matching information is greater than the target value from the above user group information, and generating an extended value circulation data sequence set based on at least one similar historical value circulation data sequence corresponding to the above at least one user information and the above historical value circulation data sequence; generating an extended data set based on the obtained screening data set and the above risk circulation data set; generating value risk information characterizing the use of the above target value product by the above target user based on the above extended value circulation data sequence set and the above extended data set; storing the above extended value circulation data sequence set, the above extended data set, the above similar value product information set, the user information corresponding to the above target user and the above user group information in the above target data storage end in a corresponding manner, and sending the information link and link description corresponding to the above value risk information to the value monitoring terminal in the form of email encryption, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

[0142] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0144] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a first determination unit, a first execution unit, a second determination unit, a screening generation unit, a first generation unit, a second generation unit, and a second execution unit. Among them, the names of these units do not constitute a limitation on the units themselves in certain circumstances. For example, the acquisition unit may also be described as "a unit for acquiring a historical value flow data sequence for a target user and a risk flow data set corresponding to a target value product from a target server."

[0145] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0146] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for processing valuable data, comprising: Acquire a historical value transfer data sequence for a target user and a risk transfer data set corresponding to a target value product from a target server, wherein the target value product is a value product in which the target user participates in value; Determine a similar value product information set corresponding to the target value product and user group information corresponding to the target user; For each similar value product information in the similar value product information set, a first generation step is performed using a central processing unit: Determine a first matching information set between a similar risk transfer data set corresponding to the similar value product information and the target value product; According to the first matching information set, the similar risk flow data set is screened to generate a screened data set; For each user information in the user group information, determine the second matching information between the similar historical value flow data sequence corresponding to the user information and the target user; filter out at least one user information whose corresponding second matching information is greater than the target value from the user group information, and generate an extended value flow data sequence set according to at least one similar historical value flow data sequence corresponding to the at least one user information and the historical value flow data sequence; generating an extended data set based on the obtained screening data set and the risk transfer data set; Generating value risk information characterizing the target user's use of the target value product according to the extended value circulation data sequence set and the extended data set; The extended value circulation data sequence set, the extended data set, the similar value product information set, the target user's corresponding user information and the user group information are correspondingly stored in the target data storage end, and the information link and link description corresponding to the value risk information are sent to the value monitoring terminal in the form of encrypted email, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

2. The method according to claim 1, wherein: The determining of the similar value product information set corresponding to the target value product and the user group information corresponding to the target user includes: Obtaining a product display image and product display information corresponding to the target value product, and obtaining a full product display image and full product display information corresponding to each full value product information in the full value product information set; For each full-value product information in the full-value product information set, the following second generation step is performed: Extracting a keyword set and a corresponding keyword position information set included in the full product display image corresponding to the full value product information; Determine word attribute information corresponding to each keyword in the keyword set; Associating each keyword in the keyword set with corresponding word attribute information to generate an associated word and word attribute table; Dividing the product display image into regions to obtain a divided display image set, wherein the divided display image may be an image of an irregular shape; Determine, according to the image template corresponding to the product display image, the image content weight corresponding to each divided display image in the divided display image set, and obtain an image content weight set; Determine, according to the image content weight set, a position weight corresponding to each keyword position information in the keyword position information set to obtain a position weight set; Adding the keyword position information set and the position weight set to the associated word and word attribute table to generate an information association table; Determine a product information association table corresponding to the product display image; Determine table content difference information corresponding to the product information association table and each information association table in the obtained information association table set to generate difference information; The full value product information whose corresponding difference information in the full value product information set meets the preset information condition is determined as similar value product information to obtain a similar value product information set.

3. The method according to claim 2, wherein: The step of determining the similar value product information set corresponding to the target value product and the user group information corresponding to the target user also includes: Determine an object feature information group corresponding to the target user; Determine the user characteristic information group corresponding to each user information in the initial user group information to obtain a user characteristic information group set; Obtain the selected feature attribute information set and clustering purpose information; According to the clustering purpose information, assign information weight to each feature attribute information in the feature attribute information set to generate weight information and obtain a weight information set, wherein the information size corresponding to the weight information is between -1 and 1; Filter out a first feature attribute information subset whose information size of corresponding weight information is greater than 0 from the feature attribute information set, and filter out a second feature attribute information subset whose information size of corresponding weight information is less than 0; According to the first feature attribute information subset and the corresponding first weight information subset, the object feature information group and the user feature information group set are used as clustering data sets, and user information clustering is performed on the user information set corresponding to the target user and the initial user group information to generate a first user information cluster set; According to the second feature attribute information subset and the corresponding second weight information subset, the object feature information group and the user feature information group set are used as clustering data sets, and user information clustering is performed on the user information set corresponding to the target user and the initial user group information to generate a second user information cluster set; Using each cluster in the second user information cluster set, performing cluster verification on each cluster in the first user information cluster set to generate a verification result; According to the verification result, user group information corresponding to the target user is determined.

4. The method according to claim 3, wherein: The generating, according to the extended value circulation data sequence set and the extended data set, value risk information characterizing the target user's use of the target value product includes: Obtaining a first value-risk characteristic attribute group based on a product perspective and a second value-risk characteristic attribute group based on a user perspective; Extracting a first value-risk characteristic attribute information group set for the first value-risk characteristic attribute group from the extended value circulation data sequence set, and extracting a second value-risk characteristic attribute information group set for the second value-risk characteristic attribute group from the extended value circulation data sequence set; Extracting a third value-risk characteristic attribute information group set for the first value-risk characteristic attribute group from the extended data set, and extracting a fourth value-risk characteristic attribute information group set for the second value-risk characteristic attribute group from the extended data set; Generate first candidate value-risk information according to the first value-risk characteristic attribute information set and the third value-risk characteristic attribute information set; generating second candidate value-risk information according to the second value-risk characteristic attribute information set and the fourth value-risk characteristic attribute information set; Determine an information level corresponding to the first candidate value risk information and an information level corresponding to the second candidate value risk information, as a first information level and a second information level, respectively; The value-risk information is generated according to the first information level, the second information level, a first threshold for the first candidate value-risk information, and a second threshold for the second candidate value-risk information.

5. The method according to claim 1, wherein: The method further comprises: Determine the value risk execution result corresponding to the target user; Distribute and store the value risk execution result, the value risk information corresponding to the target user, the extended value circulation data sequence set and the extended data set in each first-level product deployment terminal; In response to receiving value risk appeal information initiated by a target user at a target terminal, determining whether the target terminal is a first-level product deployment terminal; In response to determining that it is not, determining a first-level product deployment terminal corresponding to the target terminal as a target first-level product deployment terminal; Determine a user level corresponding to the target user; Determine an information transmission mode corresponding to the user level as a target information transmission mode; Utilizing the target information transmission method, the value risk execution result stored in the target first-level product deployment terminal, the value risk information corresponding to the target user, the extended value flow data sequence set and the extended data set are sent to the target terminal, so that the target terminal can review the value risk complaint information.

6. A value data processing device, comprising: An acquisition unit is configured to acquire, from a target server, a historical value transfer data sequence for a target user and a risk transfer data set corresponding to a target value product, wherein the target value product is a value product in which the target user participates in value; A first determining unit is configured to determine a similar value product information set corresponding to the target value product and user group information corresponding to the target user; The first execution unit is configured to, for each similar value product information in the similar value product information set, use a central processor to execute a first generation step: determine a first matching information set between a similar risk flow data set corresponding to the similar value product information and the target value product; and perform data screening on the similar risk flow data set according to the first matching information set to generate a screening data set; A second determination unit is configured to determine, for each user information in the user group information, second matching information between a similar historical value transfer data sequence corresponding to the user information and the target user; a screening and generating unit configured to screen out at least one user information whose corresponding second matching information is greater than a target value from the user group information, and generate an extended value flow data sequence set according to at least one similar historical value flow data sequence corresponding to the at least one user information and the historical value flow data sequence; A first generating unit is configured to generate an extended data set according to the obtained screening data set and the risk transfer data set; A second generating unit is configured to generate value risk information characterizing the target user's use of the target value product according to the extended value circulation data sequence set and the extended data set; The second execution unit is configured to store the extended value flow data sequence set, the extended data set, the similar value product information set, the target user's corresponding user information and the user group information in the target data storage end, and send the information link and link description corresponding to the value risk information to the value monitoring terminal in the form of encrypted email, so that the monitoring user can decrypt the value risk through the key and perform the corresponding value operation.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images