Risk assessment method, risk assessment device and computer equipment

Abstract

This application relates to a risk assessment method, risk assessment device, and computer equipment, and pertains to the fields of data mining and information security technology. One embodiment of the method includes: acquiring data reporting information uploaded and sent by a terminal, the data reporting information including: region identifiers of a preset number of unit regions that differ from the local unit region, from multiple unit regions defined by a server; based on the data reporting information from multiple terminals, calculating a first probability value for each unit region to obtain a first probability matrix; inverting the first probability matrix to obtain a second probability matrix for each unit region; acquiring the association weights between a target point of interest and each unit region; and determining the risk assessment value of the target point of interest based on the second probability of each unit region in the second probability matrix and the association weights. This embodiment can improve the accuracy of risk assessment while ensuring the privacy and security of terminal location information.

Description

Technical Field

[0001] This application relates to the fields of data mining and information security technology, and in particular to a risk assessment method, risk assessment device, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of information security technology, risk assessment based on information security has become an important aspect of information security-related technologies. Taking the fintech field as an example, there is a need to collect location information of customers with overdue payments or other negative behaviors to identify areas with a high risk of suspected financial fraud. However, due to privacy concerns, institutions typically only collect the location information of customers at the time of application (i.e., when submitting application materials) and when using funds, but cannot collect the user's current real-time location. This lack of a timely analytical dimension affects the timeliness of risk assessment and consequently, the accuracy of the risk assessment results.

[0003] To improve the timeliness of risk assessment results while meeting privacy protection requirements, related technologies deploy pseudonym servers. After the client uploads data containing its real location information to the pseudonym server, the server protects the real location information by generating a pseudonym, and then provides the data containing the pseudonym to the business server. The business server then performs risk assessment, ensuring that the business server cannot know the actual location information of individual users during data use, thus meeting privacy protection requirements. However, in this approach, the end-user's real location information is stored on the pseudonym server. If the pseudonym server is attacked by collision attacks, differential attacks, or other malicious attacks, the real location information, despite its privacy protection, is still at risk of being leaked, posing a challenge to the privacy and security of risk assessment. Summary of the Invention

[0004] Therefore, it is necessary to provide a risk assessment method, risk assessment device, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy and privacy security of the above-mentioned technical problems.

[0005] Firstly, this application provides a risk assessment method, which includes:

[0006] Obtain data reporting information uploaded and sent by the terminal. The data reporting information includes: area identifiers of a preset number of unit areas that are different from the local unit area, which are determined from multiple unit areas divided by the server. The local unit area is the unit area to which the terminal belongs.

[0007] Based on data reporting information from multiple terminals, the first probability value of each unit area is calculated, and the first probability matrix is ​​obtained based on the first probability value of each unit area.

[0008] Invert the first probability matrix to obtain the second probability matrix for each unit region;

[0009] Obtain the association weights between the target points of interest and the corresponding unit regions;

[0010] Based on the second probability of each unit region in the second probability matrix, and the association weights of the target interest point with each unit region, the risk assessment value of the target interest point is determined.

[0011] In some embodiments, based on data reporting information from multiple terminals, the first probability value for each unit area is calculated, including:

[0012] Based on data reporting information from multiple terminals, the number of reports from each unit / region is counted.

[0013] For each unit area, based on the number of reports from the unit area, the total number of unit areas determined by the server, and a preset number, the first probability value of the unit area is calculated.

[0014] In some embodiments, the first probability value of a unit area is the ratio of the number of reports to the product of the total number of areas and a preset number.

[0015] In some embodiments, inverting the first probability matrix to obtain the second probability matrix for each unit region includes:

[0016] Based on the predetermined probability selection matrix between different unit regions, the first probability matrix is ​​inverted to obtain the second probability matrix for each unit region.

[0017] In some embodiments, the second probability matrix is ​​the product of the inverse of the first probability matrix and the probability selection matrix.

[0018] In some embodiments, obtaining the association weights between the target point of interest and each unit region includes:

[0019] The reciprocal of the distance between the location of the target point of interest and the location of the center point of the unit region is used as the association weight between the target point of interest and the corresponding unit region.

[0020] In some embodiments, the risk assessment value of the target interest point is determined based on the second probability of each unit region in the second probability matrix and the association weights corresponding to each unit region, including:

[0021] Based on the association weights of the target interest points with each unit region, the second probability of each unit region is weighted and summed to obtain the risk assessment value of the target interest points.

[0022] In some embodiments, the method further includes:

[0023] Based on the risk assessment values ​​of each target point of interest within the target area, a risk target area is determined from multiple target areas.

[0024] Secondly, this application also provides a risk assessment device, the device comprising:

[0025] The data receiving module is used to obtain data reporting information uploaded and sent by the terminal. The data reporting information includes: area identifiers of a preset number of unit areas that are different from the local unit area, which are divided and determined by the server. The local unit area is the unit area to which the terminal belongs.

[0026] The statistics module is used to collect data reporting information from multiple terminals, calculate the first probability value of each unit area, and obtain the first probability matrix based on the first probability value of each unit area.

[0027] The inversion and restoration module is used to invert the first probability matrix to obtain the second probability matrix for each unit region.

[0028] The weight acquisition module is used to obtain the association weights of the target point of interest with each unit region.

[0029] The risk assessment module is used to determine the risk assessment value of the target interest point based on the second probability of each unit region in the second probability matrix and the association weights of the target interest point with each unit region.

[0030] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the risk assessment method in any of the above embodiments.

[0031] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the risk assessment method in any of the above embodiments.

[0032] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the risk assessment method in any of the above embodiments.

[0033] The aforementioned risk assessment methods, devices, computer equipment, storage media, and computer program products utilize a server that divides the server into multiple unit areas. When a terminal sends data reporting information to the server, the information included in the data reporting information is not the terminal's local unit area, but rather the area identifiers of a preset number of unit areas determined from other unit areas different from the terminal's local unit area. In other words, the location-related information reported by the terminal to the server is neither the terminal's actual location information nor its actual unit area. Therefore, based on the received data reporting information, the server cannot easily reverse engineer or infer the terminal's true location information, thus achieving accurate privacy and security protection of the terminal's location information and improving the accuracy of privacy and security protection. The server is... Based on the data reporting information uploaded by multiple terminals, statistical analysis of this data reporting information yields a first probability value for each unit area. This first probability value reflects the likelihood of the unit area being reported by terminals in other areas not belonging to that unit area; it is a false probability value. Therefore, by inverting the first probability matrix composed of the first probability values ​​of each unit area, a second probability matrix for each unit area can be obtained. The second probability value in the second probability matrix reflects the probability of terminal reporting for that unit area. Thus, based on the association weights between the target point of interest and each unit area, combined with the second probability of each unit area in the second probability matrix, the risk assessment value of the target point of interest can be determined. This improves the accuracy of risk assessment while ensuring the privacy and security of terminal location information. Attached Figure Description

[0034] Figure 1 This is a schematic diagram illustrating an application scenario of the risk assessment method in one embodiment;

[0035] Figure 2 This is a flowchart illustrating a risk assessment method in one embodiment;

[0036] Figure 3 This is a flowchart illustrating the process of determining the first probability value of a unit region in one embodiment.

[0037] Figure 4 This is a flowchart illustrating the risk assessment method in another embodiment;

[0038] Figure 5 This is a flowchart illustrating the risk assessment method in yet another embodiment;

[0039] Figure 6 This is a schematic diagram of the risk assessment device in one embodiment;

[0040] Figure 7This is a schematic diagram of the structure of a computer device in one embodiment. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0042] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0044] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0045] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0046] In the description of the embodiments in this application, the term "and / or" is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In addition, the character " / " in this document generally indicates that the related objects before and after are in an "or" relationship, and the term "multiple" refers to two or more (including two).

[0047] It should be noted that all information and data involved in this application (including but not limited to data used for analysis, stored data, and displayed data) are information and data authorized by the user or fully authorized by all parties, and the acquisition, transmission, storage, use, and processing of the relevant data comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, and their purpose is merely to illustrate the feasibility of implementing the technical solution of this application, but does not imply that the applicant has already used or necessarily used such a solution.

[0048] Currently, to improve the timeliness of risk assessment results while meeting privacy protection requirements, related technologies deploy pseudonym servers. After the client uploads data containing its real location information to the pseudonym server, the server protects the real location information by generating a pseudonym, and then provides the data containing the pseudonym to the business server. The business server then performs risk assessment, ensuring that the business server cannot know the actual location information of individual users during data use, thus meeting privacy protection requirements. However, in this approach, the end-user's real location information is stored on the pseudonym server. If the pseudonym server is attacked by collision attacks, differential attacks, or other similar attacks, the individual user's real location information, which is supposed to be protected by privacy, is still at risk of being leaked, posing a challenge to the privacy and security of risk assessment.

[0049] Research has shown that when conducting statistical risk analysis based on information from a large number of groups, if a single terminal does not report its actual location information but instead reports information from other locations, the server can obtain the risk value of each location area by receiving data reported by multiple terminals, statistically analyzing and reversing this data. Based on this, the risk value of the point of interest can be determined, enabling risk assessment without the terminal needing to report its actual location information.

[0050] Accordingly, embodiments of this application provide a risk assessment method that can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. After dividing the evaluation area into multiple unit areas, server 104 sends the location range information and area identifiers of these unit areas to each terminal. When terminal 102 needs to report data carrying location information, it determines a preset number of area identifiers from the multiple unit areas defined by the server, different from its own local unit area, and includes these preset number of area identifiers in the data reporting information sent to the server. After receiving the data reporting information sent by multiple terminals 102, server 104 performs a series of operations such as statistics and inversion based on this data reporting information to obtain the risk probability of each unit area (i.e., the second probability in the following embodiment), and determines the risk assessment value of the target point of interest based on this, achieving risk assessment under the premise of secure privacy protection of location information. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0051] Accordingly, in one embodiment, such as Figure 2 As shown, a risk assessment method is provided, which is applied to server 104, and includes the following steps:

[0052] Step S201: Obtain the data reporting information uploaded and sent by the terminal. The data reporting information includes: the area identifiers of a preset number of unit areas that are different from the local unit area, which are determined from multiple unit areas divided by the server. The local unit area is the unit area to which the terminal belongs.

[0053] When a terminal meets the data reporting conditions, it can upload data reporting information to the server. This data reporting information may include business-related information, and to facilitate regional risk analysis and assessment, location-related information is usually also included in the data reporting information. However, since the terminal's actual location information is considered privacy-sensitive, to protect this privacy, the location information in the terminal's data reporting information is not the terminal's actual location or actual unit area information. Instead, it is a region identifier derived from a preset number of unit areas defined by the server, different from the terminal's local unit area.

[0054] The server can divide the evaluation area into multiple unit areas, set a region identifier for each unit area, determine the region location range information of each unit area, and send the region identifier and region location range information of the divided area to each terminal so that each terminal can determine its own unit area (i.e., its local unit area) and thus determine a number of other preset unit areas that are different from its local unit area.

[0055] The method of dividing the server into unit regions is not limited. In some examples, taking a rectangular region of m meters * n meters as an example, assuming the granularity of the statistical analysis is i meters * j meters, that is, the required area of ​​the unit region is i meters * j meters, then the evaluation region can be divided into K unit regions with an area of ​​i meters * j meters. For the multiple unit areas obtained, a region identifier can be assigned to each unit area. There are no restrictions on the method of assigning region identifiers. Taking the above division into K unit areas with an area of ​​i meters * j meters as an example, the region identifiers can be assigned according to the positional order of the unit areas, but it is not limited to this.

[0056] It is understood that in other embodiments, the server may also use other methods to divide the evaluation area into multiple unit areas, and each unit area is the same or approximately the same size. Other methods may also be used to determine the area identifier of each unit area, as long as it can uniquely correspond to a divided unit area.

[0057] There are no restrictions on how a terminal determines its local unit region. For example, after obtaining local location information (latitude and longitude information of the local location), the terminal compares the local location information with the regional location range information of each unit region (latitude and longitude range of the unit region). If the local location information is within the regional location range information of a certain unit region, then that unit region can be determined as the local unit region to which the terminal belongs.

[0058] The method by which the terminal selects and determines the region identifiers of a preset number of unit regions that are different from its local unit region is not limited. The specific number of preset regions is not limited; taking the above example of dividing the evaluation area into K unit regions, the value of the preset number can range from [1, K - 1]. The larger the value of the preset number, the weaker the privacy protection, and the higher the accuracy of the final statistical analysis. Therefore, in relevant embodiments, the preset number can be greater than 1 and K - 1 to balance the requirements of privacy protection and the accuracy of statistical analysis.

[0059] Step S202: Based on the data reporting information from multiple terminals, calculate the first probability value of each unit area, and obtain the first probability matrix based on the first probability value of each unit area.

[0060] Each terminal sends data reporting information to the server, including a preset number of area identifiers. Therefore, based on the data reporting information received from multiple terminals, a first probability value for each unit area can be obtained. This first probability value reflects the reporting status of each unit area by users in other unit areas.

[0061] There are no restrictions on how the first probability value of a unit region is obtained; in some examples, refer to... Figure 3 As shown, based on data reporting information from multiple terminals, the first probability value for each unit area is calculated, including:

[0062] Step S2021: Based on the data reporting information from multiple terminals, count the number of reports from each unit / region.

[0063] Based on data reporting information from multiple terminals, the number of times each unit area is reported can be counted to obtain the number of reports for each unit area.

[0064] Step S2022: For each unit area, based on the number of reports from the unit area, the total number of unit areas determined by the server, and the preset number, calculate the first probability value of the unit area.

[0065] For each unit area, based on the number of times that unit area is reported, combined with the total number of unit areas determined by the server, and the number of unit areas contained in the data reporting information sent by the terminal (i.e., the preset number), the first probability value of the unit area can be calculated.

[0066] The specific method for obtaining the first probability value is not limited. In some specific examples, the first probability value per unit area is the ratio of the number of reported cases to the product of the total number of areas and the preset number, which can be expressed by the formula: .in, Indicates the first The first probability value for a unit region. Indicates the first Number of reports per unit area This represents the total number of regions within a given area. Indicates the preset number.

[0067] Based on the first probability values ​​of each unit region, the first probability matrix can be obtained, which can be expressed by the formula: .

[0068] Step S203: Invert the first probability matrix to obtain the second probability matrix for each unit region.

[0069] The first probability matrix can be inverted to obtain the second probability matrix for each unit region. Since the first probability value in the first probability matrix reflects the reporting status of a unit region by users in other unit regions, the second probability matrix for each unit region can be obtained by inverting it. The second probability in this second probability matrix reflects the reporting status of a unit region by users within that unit region.

[0070] Step S204: Obtain the association weights of the target interest points with each unit region.

[0071] Target points of interest (POIs) are location points for which risk analysis needs to be performed. The method for determining POIs is not limited; they can be determined manually, through statistical clustering, or other methods. This application embodiment does not impose specific limitations on this. The type of POI is not limited; it can be an abstract geographical object, such as a landmark building, or an address with a specific house number. This application embodiment does not impose specific limitations on this.

[0072] The association weight between a point of interest and a unit region reflects the importance coefficient of assessing the risk of the point of interest based on the second probability of that unit region.

[0073] There are no restrictions on the method for obtaining the association weights between the target point of interest and each unit region. In some examples, the reciprocal of the distance between the location of the target point of interest and the location of the center point of the unit region can be used as the association weight between the target point of interest and each unit region. This can be expressed by the formula: ,in, Indicates the target point of interest and the first The distance between the center points of each unit area.

[0074] Step S205: Based on the second probability of each unit region in the second probability matrix, and the association weights of the target interest point with each unit region, determine the risk assessment value of the target interest point.

[0075] Based on the obtained second probability matrix, the risk assessment value of the target interest point can be determined based on the second probability of each unit region in the second probability matrix and the association weights of the target interest point with each unit region.

[0076] In the risk assessment method of the above embodiments, the server divides the area into multiple unit regions. When the terminal sends data reporting information to the server, the information contained in the data reporting information is not the local unit region to which the terminal belongs, but rather the region identifiers of a preset number of unit regions determined from other unit regions different from the local unit region. In other words, the location-related information reported by the terminal to the server is neither the terminal's actual location information nor the actual unit region to which the terminal belongs. Therefore, based on the received data reporting information, the server finds it difficult to reverse engineer or infer the terminal's actual location information, thus achieving accurate privacy and security protection of the terminal's location information and improving the accuracy of privacy and security protection. Furthermore, the server obtains data from multiple terminals... Based on the reported information, statistical analysis of this data yields a first probability value for each unit area. This first probability value reflects the likelihood of a terminal reporting from another area that does not belong to that unit area; it is a false probability value. Therefore, by inverting the first probability matrix composed of the first probability values ​​of each unit area, a second probability matrix for each unit area can be obtained. The second probability value in the second probability matrix reflects the probability of a terminal reporting from that unit area. Thus, based on the association weights between the target point of interest and each unit area, combined with the second probability of each unit area in the second probability matrix, the risk assessment value of the target point of interest can be determined. This improves the accuracy of risk assessment while ensuring the privacy and security of terminal location information.

[0077] There are no restrictions on how the second probability matrix of each unit region can be obtained by inverting the first probability matrix. In some examples, the second probability matrix of each unit region can be obtained by inverting the first probability matrix using the NSTOP-I reconstruction algorithm or the NSTOP-II reconstruction algorithm.

[0078] In other embodiments, reference is made to... Figure 4 The above step S203, which involves inverting the first probability matrix to obtain the second probability matrix for each unit region, includes:

[0079] Step 2031: Based on the predetermined probability selection matrix between different unit regions, invert the first probability matrix to obtain the second probability matrix for each unit region.

[0080] The probability selection matrix is ​​a matrix formed based on the probability that an end user in one unit area will choose the area identifier of another unit area for reporting. That is, each element in the probability selection matrix represents the probability that an end user in one unit area will choose the area identifier of another unit area for reporting. A specific example of the probability selection matrix is ​​shown below. It can be represented as:

[0081]

[0082] in, This represents the probability that an end user in the first unit area will report the area identifier of the second unit area to the server. This indicates that the terminal user in the first unit area reported the first The probability of assigning a region identifier to the server for a given unit region, and so on for others.

[0083] Probability selection matrix Each probability value in the equation can be the same, meaning that the probability of a terminal user in each unit area reporting the area identifier of another unit area to the server is the same. In other examples, the probability can be determined based on the proximity of the areas corresponding to the two area identifiers. For example, the probability can be randomly selected based on the proximity of the areas corresponding to the two area identifiers, combined with a Gaussian distribution probability, or other forms of distribution probability can be used to randomly select the corresponding probability. This application does not impose specific limitations on these embodiments.

[0084] The method for obtaining the second probability matrix for each unit region by inverting the first probability matrix based on the probability selection matrix is ​​not limited. In some examples, the second probability matrix is ​​the product of the inverse of the first probability matrix and the probability selection matrix, which can be expressed by the formula:

[0085] .in, This is the second probability matrix. This is the first probability matrix. Choose a probability matrix.

[0086] The method for determining the risk assessment value of the target interest point based on the second probability of each unit region in the second probability matrix and the association weights corresponding to each unit region is not limited. In some embodiments, reference is made to... Figure 5 As shown, it may include:

[0087] Step S2051: Based on the association weights corresponding to the target interest point and each unit region, the second probability of each unit region is weighted and summed to obtain the risk assessment value of the target interest point.

[0088] Therefore, the method for obtaining the risk assessment value of the target point of interest can be expressed by the formula:

[0089]

[0090] Where S represents the risk assessment value of the target point of interest. This represents the total number of regions within a given area. Indicates the first The second probability of a unit region Indicates the target point of interest and the first The distance between the center points of each unit area.

[0091] In some embodiments, the above-described risk assessment method further includes:

[0092] Based on the risk assessment values ​​of each target point of interest within the target area, a risk target area is determined from multiple target areas.

[0093] The target area is the area that needs to be risk-assessed. In some examples, the target area can be one of the multiple unit areas obtained by the above division. In other examples, the target area can be an area determined by a different method of dividing unit areas than described above.

[0094] Based on the geographical scope of the target area and the location information of each target point of interest, the target points of interest within the target area can be identified, and the regional risk value of the target area can be determined based on the risk assessment value of each target point of interest.

[0095] There are no restrictions on how the regional risk value of a target area is determined. In some examples, the highest risk assessment value among all target points of interest within the target area can be used as the regional risk value for that target area. In other examples, the average or weighted average of the risk assessment values ​​of all target points of interest within the target area can be used as the regional risk value for that target area, but this is not a limitation.

[0096] Based on the regional risk values ​​obtained from multiple target areas, a risk target area can be determined from among these multiple target areas.

[0097] The method for determining the risk target area from multiple target areas is not limited. In some embodiments, the target area with a regional risk value greater than a risk threshold among the multiple target areas can be determined as the risk target area. In other examples, the regional risk values ​​of multiple target areas can be sorted, and one or more target areas with the largest regional risk values ​​can be determined as the risk target areas, but this is not limited to these methods.

[0098] Based on the embodiments described above, the following detailed examples will be provided.

[0099] For servers that need to perform risk assessments, the assessment area is divided into K unit areas based on the unit area size information corresponding to the assessment requirements. For example, if the unit area size information is i meters * j meters, then the assessment area can be divided into K unit areas with an area size of i meters * j meters.

[0100] After dividing the region into K unit regions, the server sets the region identifiers for the K unit regions and determines the latitude and longitude information of each of the K unit regions based on the latitude and longitude information of the evaluation area. Then, the server sends the region identifiers and latitude and longitude information of the K unit regions to the terminal.

[0101] The terminal receives the region identifiers and latitude and longitude information of K unit regions sent by the server, and stores the region identifiers and latitude and longitude information of K unit regions locally for later use.

[0102] When a terminal needs to report data, it obtains its current location information and determines the local unit area to which its current location information belongs based on the latitude and longitude information of each unit area; it then randomly selects a preset number of unit area identifiers from unit areas outside its local unit area; and sends data reporting information to the server, which includes the region identifiers of the preset number of unit areas selected above.

[0103] The server receives data reports from each terminal, calculates the first probability value for each unit region based on the data reports from each terminal, and obtains the first probability matrix based on the first probability value for each unit region. Based on the predetermined probability selection matrix between different unit regions, the server inverts the first probability matrix to obtain the second probability matrix for each unit region.

[0104] For a given target point of interest, the reciprocal of the distance between the target point of interest and the center point of the unit region is calculated to obtain the association weights of the target point of interest with the unit region respectively. Based on the association weights of the target point of interest with each unit region respectively, the second probability of each unit region is weighted and summed to obtain the risk assessment value of the target point of interest.

[0105] Based on the risk assessment values ​​of the target points of interest, and considering the regional scope of the target area, the location information of each target point of interest can be used to determine the target points of interest within the target area. Based on the risk assessment values ​​of each target point of interest, the regional risk value of the target area can be determined.

[0106] Finally, based on the regional risk value of the determined target area, the risk target area can be identified from multiple target areas.

[0107] The identified risk target areas can serve as a reference factor in subsequent business processing. For example, in the field of fintech, when a financial institution's server receives a business application request, such as a loan request, it can determine whether the location information of the terminal initiating the application is within the risk target area. If it is, the application can be rejected or the review process can be strengthened, but this is not the only possibility.

[0108] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0109] Accordingly, this application also provides a risk assessment apparatus for implementing the risk assessment method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more risk assessment apparatus embodiments provided below can be found in the limitations of the risk assessment method described above, and will not be repeated here.

[0110] In one embodiment, reference Figure 6 As shown, a risk assessment device is provided, including: a data receiving module 601, a statistics module 602, an inversion and restoration module 603, a weight acquisition module 604, and a risk assessment module 605, wherein:

[0111] The data receiving module 601 is used to obtain data reporting information uploaded and sent by the terminal. The data reporting information includes: a preset number of unit area identifiers that are different from the local unit area among multiple unit areas determined by the server. The local unit area is the unit area to which the terminal belongs.

[0112] The statistics module 602 is used to collect data reporting information from multiple terminals, calculate the first probability value of each unit area, and obtain the first probability matrix based on the first probability value of each unit area.

[0113] The inversion and restoration module 603 is used to invert the first probability matrix to obtain the second probability matrix for each unit region.

[0114] The weight acquisition module 604 is used to acquire the association weights of the target interest points with each unit region.

[0115] The risk assessment module 605 is used to determine the risk assessment value of the target interest point based on the second probability of each unit region in the second probability matrix and the association weights of the target interest point with each unit region.

[0116] In some embodiments, the statistics module 602 is used to count the number of reports for each unit area based on the data reporting information of multiple terminals; and for each unit area, based on the number of reports for the unit area, the total number of unit areas determined by the server, and a preset number, calculate the first probability value of the unit area.

[0117] In some embodiments, the first probability value of a unit area is the ratio of the number of reports to the product of the total number of areas and a preset number.

[0118] In some embodiments, the inversion and restoration module 603 is used to invert the first probability matrix based on a predetermined probability selection matrix between different unit regions to obtain the second probability matrix of each unit region.

[0119] In some embodiments, the second probability matrix is ​​the product of the inverse of the first probability matrix and the probability selection matrix.

[0120] In some embodiments, the weight acquisition module 604 is used to take the reciprocal of the distance between the location of the target interest point and the location of the center point of the unit region as the association weight between the target interest point and the unit region respectively.

[0121] In some embodiments, the risk assessment module 605 is used to perform a weighted summation of the second probabilities of each unit region based on the association weights corresponding to the target interest point and each unit region, so as to obtain the risk assessment value of the target interest point.

[0122] In some embodiments, the risk assessment module 605 is used to determine a risk target area from multiple target areas based on the risk assessment values ​​of each target point of interest within the target area.

[0123] Each module in the aforementioned risk assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0124] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals or servers via a network connection. When the computer program is executed by the processor, it implements a risk assessment method.

[0125] Those skilled in the art will understand that the structure of the computer device described above is only a partial structure related to the solution of this application and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0126] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the risk assessment method in any of the above embodiments.

[0127] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the risk assessment method in any of the above embodiments.

[0128] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the risk assessment method in any of the above embodiments.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0130] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A risk assessment method, characterized in that, The method includes: Obtain data reporting information uploaded and sent by the terminal. The data reporting information includes: a preset number of unit area identifiers that are different from the local unit area, which are determined from multiple unit areas divided by the server. The local unit area is the unit area to which the terminal belongs. Based on data reporting information from multiple terminals, a first probability value for each unit region is calculated, and a first probability matrix is ​​obtained based on the first probability value of each unit region. The first probability value reflects the situation where the unit region is reported by terminals in other unit regions that do not belong to that unit region. Invert the first probability matrix to obtain the second probability matrix for each of the unit regions; Obtain the association weights between the target points of interest and each of the unit regions, where the target points of interest are the location points for which risk analysis needs to be performed. Based on the association weights corresponding to the target interest points and the respective unit regions, the second probabilities of each unit region in the second probability matrix are weighted and summed to obtain the risk assessment value of the target interest points.

2. The method according to claim 1, characterized in that, The data reporting information based on multiple terminals, and the statistical calculation of the first probability value for each unit area, include: Based on data reporting information from multiple terminals, the number of reports for each unit area is counted. For each of the aforementioned unit regions, a first probability value for the unit region is calculated based on the number of reports made by the unit region, the total number of unit regions determined by the server, and the preset number.

3. The method according to claim 2, characterized in that, The first probability value of the unit area is the ratio of the number of reports to the product of the total number of areas and the preset number.

4. The method according to claim 1, characterized in that, The step of inverting the first probability matrix to obtain the second probability matrix for each of the unit regions includes: Based on the predetermined probability selection matrix between different unit regions, the first probability matrix is ​​inverted to obtain the second probability matrix for each unit region.

5. The method according to claim 4, characterized in that, The second probability matrix is ​​the product of the inverse of the first probability matrix and the probability selection matrix.

6. The method according to claim 1, characterized in that, The acquisition of the association weights between the target points of interest and each of the unit regions includes: The reciprocal of the distance between the location of the target point of interest and the location of the center point of the unit region is used as the association weight between the target point of interest and the unit region.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Based on the risk assessment values ​​of each target point of interest within the target area, a risk target area is determined from multiple target areas.

8. The method according to claim 7, characterized in that, The process of determining the risk target area from multiple target areas includes: Among multiple target regions, the target regions whose regional risk values ​​are greater than the risk threshold are included. or The regional risk values ​​of multiple target areas are sorted, and one or more target areas with the highest regional risk values ​​are identified as risk target areas.

9. A risk assessment device, characterized in that, The device includes: The data receiving module is used to acquire data reporting information uploaded and sent by the terminal. The data reporting information includes: a preset number of area identifiers from multiple unit areas determined by the server that are different from the local unit area, wherein the local unit area is the unit area to which the terminal belongs. The statistics module is used to calculate the first probability value of each unit area based on the data reporting information of multiple terminals, and obtain a first probability matrix based on the first probability value of each unit area. The first probability value reflects the situation where the unit area is reported by terminals of other unit areas that do not belong to the unit area. The inversion and restoration module is used to invert the first probability matrix to obtain the second probability matrix for each of the unit regions. The weight acquisition module is used to acquire the association weights of the target interest points with each of the unit regions, where the target interest points are the location points for which risk analysis needs to be performed. The risk assessment module is used to perform a weighted summation of the second probabilities of each unit region in the second probability matrix based on the association weights corresponding to the target interest point and each of the unit regions, so as to obtain the risk assessment value of the target interest point.

10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images