Risk assessment method and device, electronic equipment and storage medium

Abstract

The disclosure provides a risk assessment method and device, electronic equipment and storage medium, relates to the technical field of computers, and in particular to the technical field of artificial intelligence, big data and the like, and the method comprises: obtaining associated entities of a target object and entity data of the associated entities; based on the associated entities and the entity data, establishing a risk assessment graph of the target object; based on the risk assessment graph, determining target risk associated entities of the target object from the associated entities; and based on the entity data of the target risk associated entities, determining a risk coefficient of the target object. By screening the associated entities through the risk assessment graph, target risk associated entities that have a greater impact on the target object are screened out, and the risk coefficient of the target object is determined based on the entity data of the target risk entities, which can reduce the data base number for risk coefficient evaluation of the target object, improve the quality of the data, thereby reducing the cost of data processing and improving the accuracy of the finally obtained risk coefficient.

Description

Technical Field

[0001] This disclosure provides a risk assessment method, apparatus, electronic device, and storage medium, relating to the field of computer technology, specifically to the fields of artificial intelligence, big data, and other technologies. Background Technology

[0002] With the widespread application of big data technology, data has become one of the most important assets for many companies. Current privacy-protected data publishing systems only assess the risk of privacy breaches in anonymized data, neglecting to proactively assess the risk of data applicants. While malicious attackers may not be able to steal private data technically, they can use social engineering to commit data fraud, such as obtaining different data through user impersonation or group fraud, and then using data analysis techniques to extract the private data.

[0003] Knowledge graphs, as a graph-based technology, can quickly analyze the relationships between nodes. Therefore, mapping data applicants to a knowledge graph and analyzing their implicit relationships based on the knowledge graph can effectively prevent the theft of private data using social engineering. However, current rules for judging the types, names, and organizational relationships between related objects in a knowledge graph are too simplistic and apply to all related objects. Some related objects have little impact on the object being judged, thus affecting the final judgment result. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, one objective of this disclosure is to propose a risk assessment method.

[0006] The second objective of this disclosure is to provide a risk assessment device.

[0007] The third objective of this disclosure is to propose an electronic device.

[0008] The fourth objective of this disclosure is to provide a non-transitory computer-readable storage medium.

[0009] The fifth objective of this disclosure is to provide a computer program product.

[0010] To achieve the above objectives, the first aspect of this disclosure provides a risk assessment method, comprising: acquiring associated entities of a target object and entity data of the associated entities; establishing a risk assessment map of the target object based on the associated entities and entity data; determining the target risk associated entities of the target object from the associated entities based on the risk assessment map; and determining the risk coefficient of the target object based on the entity data of the target risk associated entities.

[0011] In one embodiment of this disclosure, determining the risk coefficient of a target object based on the entity data of the target risk-associated entity includes: determining violation data from the entity data of the target risk-associated entity; and determining the risk coefficient of the target object based on the violation data.

[0012] According to one embodiment of this disclosure, determining the target risk associated entity of a target object from associated entities based on a risk assessment graph includes: determining the close centrality coefficient and the betweenness centrality coefficient of all associated entities based on the risk assessment graph; and determining the target risk associated entity of the target object from all associated entities based on the close centrality coefficient and the betweenness centrality coefficient.

[0013] According to one embodiment of this disclosure, determining the target risk associated entity of a target object from all associated entities based on the close centrality coefficient and the betweenness centrality coefficient includes: determining a first determination value based on the close centrality coefficient and the first weight corresponding to the close centrality coefficient, and determining a second determination value based on the betweenness centrality coefficient and the second weight corresponding to the betweenness centrality coefficient; and determining the target risk associated entity of the target object from all associated entities based on the first determination value and the second determination value.

[0014] According to one embodiment of this disclosure, determining the target risk associated entity of a target object from all associated entities based on a first determination value and a second determination value includes: summing the first determination value and the second determination value to obtain a target determination value; comparing the target determination value with a determination threshold; and determining the associated entity corresponding to the target determination value that is greater than the determination threshold as the target risk associated entity.

[0015] According to one embodiment of this disclosure, determining the close centrality coefficient of all associated entities includes: for the i-th associated entity, obtaining the node distances between the i-th associated entity and the other n-1 associated entities in the risk assessment graph, where i is an integer, n is the number of associated entities, and 1≤i≤n; based on the node distances, determining the average distance between the i-th associated entity and the other n-1 associated entities in the risk assessment graph; and using the reciprocal of the average distance as the close centrality coefficient of the i-th associated entity.

[0016] According to one embodiment of this disclosure, determining the betweenness centrality coefficient of all associated entities includes: for the j-th associated entity, obtaining the target number of times any two of the other n-1 associated entities pass through the j-th associated entity in the risk assessment graph, where j is an integer, n is the number of associated entities, and 1≤j≤n; and determining the betweenness centrality coefficient of the j-th associated entity based on the target number of times.

[0017] To achieve the above objectives, a second aspect of this disclosure provides a risk assessment apparatus, comprising: an acquisition module for acquiring associated entities of a target object and entity data of the associated entities; an assessment module for establishing a risk assessment map of the target object based on the associated entities and entity data; determining a target risk associated entity of the target object from the associated entities based on the risk assessment map; and determining a risk coefficient of the target object based on the entity data of the target risk associated entity.

[0018] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement the risk assessment method as described in the first aspect of this disclosure.

[0019] To achieve the above objectives, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the risk assessment method as described in the first aspect of this disclosure.

[0020] To achieve the above objectives, a fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the risk assessment method as described in the first aspect of this disclosure.

[0021] By filtering related entities through the risk assessment map to identify those with a significant impact on the target object, and then determining the risk coefficient of the target object based on the entity data of these risk entities, the data base for assessing the risk coefficient of the target object can be reduced, data quality can be improved, thereby reducing data processing costs and increasing the accuracy of the final risk coefficient. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of a risk assessment method according to one embodiment of the present disclosure;

[0023] Figure 2 This is a schematic diagram of a knowledge graph of a risk assessment method according to one embodiment of the present disclosure;

[0024] Figure 3 This is a schematic diagram of another risk assessment method according to one embodiment of the present disclosure;

[0025] Figure 4 This is a schematic diagram of another risk assessment method according to one embodiment of the present disclosure;

[0026] Figure 5 This is a schematic diagram of a risk assessment device according to one embodiment of the present disclosure;

[0027] Figure 6 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure. Detailed Implementation

[0028] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0029] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of national laws and regulations.

[0030] Figure 1 This is a schematic diagram illustrating an exemplary implementation of a risk assessment method proposed in this disclosure, such as... Figure 1 As shown, this risk assessment method includes the following steps:

[0031] S101, obtain the associated entities of the target object and the entity data of the associated entities.

[0032] In this embodiment of the disclosure, the target object is the object that needs to be risk assessed. The target object can be of various types. For example, the target object can be an organization, personnel, etc., without any limitation.

[0033] It should be noted that an associated entity is an object that has a relationship with the target object. This relationship can be an affiliated unit, friend, relative, etc., without any restrictions here.

[0034] Optionally, the associated entity can also be another individual that has no direct association with the target object but is associated with the target object.

[0035] Optionally, the associated entity can also be a non-entity, such as an event, mobile phone number, or account associated with the target object. Taking an event as an example, an event can be a violation event involving various institutions in the information record, such as a suspended promotion, non-performing loans, or involvement in a case.

[0036] It should be noted that the associated entities can be different for different target objects. For example, the associated entities of an organization can be its employees, partner organizations, etc., while the associated entities of an individual can be their employer, borrowing unit, relatives, etc.

[0037] In this embodiment of the disclosure, after the target object is determined, the associated entities can be determined according to the items for risk assessment as needed. For example, if it is necessary to conduct a risk assessment on the health status of the target object, the target object's immediate family members, hospitals where the target object has previously received medical treatment, etc. can be used as associated entities.

[0038] In this embodiment of the disclosure, the entity data of the associated entity may include various types, and the specific entity data to be obtained can be determined according to the project for which risk assessment is required. For example, if the project for risk assessment is financial status, the associated entity may be a lending bank, and the corresponding entity data may include the loan date, bank name, loan amount, and whether there is any default, etc.

[0039] S102, Based on related entities and entity data, establish a risk assessment map of the target object.

[0040] In this embodiment of the disclosure, after obtaining the associated entities and entity data, the associated entities and target objects can be displayed and located in the graph, and a risk assessment graph can be determined based on the relationship between the associated entities.

[0041] It should be noted that the risk assessment graph in this embodiment is a knowledge graph, used to display a series of different graphics representing the development process and structural relationships of knowledge. It uses visualization technology to describe knowledge resources and their carriers, mining, analyzing, constructing, drawing, and displaying knowledge and the interrelationships between them. The target object and related entities are connected by relationship lines; different related entities can also be connected by relationship lines. For example, such as... Figure 2 As shown, the target entity and its associated entities A, B, C, D, and E can be directly connected through relationship lines, such as A, B, C, and D, or indirectly connected through other nodes, such as E.

[0042] S103, Based on the risk assessment diagram, identify the target risk associated entities of the target object from the associated entities.

[0043] In this embodiment of the disclosure, there are various methods for determining the target risk associated entity of the target object from the associated entities based on the risk assessment graph, and no limitation is made here.

[0044] Optionally, the target risk associated entity can be determined based on the risk assessment map and its locational relationship with related entities. For example, the associated entity closest to the target object can be used as the target risk associated entity. Figure 2 As shown, A, B, C, and D can be considered as target risk-related entities.

[0045] Optionally, based on the risk assessment map, the associated entity with the most connections to other associated entities can be selected as the target risk associated entity. For example, such as Figure 2 As shown, D can be considered as the target risk associated entity.

[0046] S104, Based on the entity data of the target risk-related entities, determine the risk coefficient of the target object.

[0047] In this embodiment of the disclosure, after identifying the target risk-related entity, the entity data of the target risk-related entity can be filtered to identify the violation data, and this data can be used as the assessment data for evaluating the risk coefficient of the target risk object.

[0048] It should be noted that the data on violations can be of various types, such as the overdue period, the amount owed, and whether there is a criminal record, etc., without any restrictions here.

[0049] In this example, the risk coefficient of the target object can be determined by a risk coefficient algorithm. It should be noted that the risk coefficient algorithm can be pre-set and can be changed according to actual design needs.

[0050] Optionally, the risk coefficient of each associated entity to the target object can be determined based on the positional relationship and association relationship between the target object and associated entities in the risk assessment map, for example, by the distance between the target object and associated entities, and then based on the association data of the associated entities, thus determining the risk coefficient of all associated entities to the target object.

[0051] Optionally, since not all related entities affect the risk coefficient of the target object, the related entities that pose a risk to the target object can be identified from the risk assessment diagram first, and then the risk coefficient of the target object can be determined through these risky related entities.

[0052] In this embodiment, the risk coefficient of the target object is first determined. Then, a risk assessment map of the target object is established based on associated entities and entity data. Next, based on the risk assessment map, target risk associated entities of the target object are identified from the associated entities. Finally, the risk coefficient of the target object is determined based on the entity data of the target risk associated entities. Therefore, by filtering associated entities through the risk assessment map to identify target risk associated entities with a significant impact on the target object, and determining the risk coefficient of the target object based on the entity data of these target risk entities, the data base for assessing the risk coefficient of the target object can be reduced, data quality can be improved, thereby reducing data processing costs and improving the accuracy of the final obtained risk coefficient.

[0053] In the above embodiments, based on the risk assessment graph, the target risk associated entity of the target object is determined from the associated entities. This can also be achieved through... Figure 3 To further explain, the method includes:

[0054] S301, based on the risk assessment diagram, determine the close centrality coefficient and between centrality coefficient of all related entities.

[0055] Closeness centrality utilizes the local characteristics of a risk assessment graph, namely the number of connections between related entities. However, a high number of connections for an entity does not necessarily mean it is at the core of the network. A node has high closeness centrality if the shortest distances from a node to other nodes in the graph are all small.

[0056] In this embodiment of the disclosure, for the i-th associated entity, the node distance between the i-th associated entity and the other n-1 associated entities in the risk assessment graph is obtained, where i is an integer, n is the number of associated entities, 1≤i≤n. Based on the node distance, the average distance between the i-th associated entity and the other n-1 associated entities in the risk assessment graph is determined. Finally, the reciprocal of the average distance is used as the compact centrality coefficient of the i-th associated entity.

[0057] The formula for calculating the compact centrality coefficient is as follows:

[0058]

[0059] Among them, F i Let be the compact centrality coefficient of the i-th associated entity, n be the number of associated entities, and d be the coefficient of compact centrality. j Let be the distance between the i-th associated entity and the j-th associated entity.

[0060] Betweenness centrality is a method for detecting the degree of influence of a node on the information flow in a graph. It involves calculating all shortest paths between any two nodes in the network; if many of these shortest paths pass through a certain node, then that node is considered to have high Betweenness Centrality.

[0061] The formula for calculating the compact centrality coefficient is as follows:

[0062]

[0063] Among them, C B (j) represents the betweenness centrality coefficient of the j-th associated entity, and σst(v) represents the number of shortest paths from the s-th associated entity to the t-th associated entity via j. σst represents the total number of shortest paths from the s-th associated entity to the t-th associated entity.

[0064] S302, based on the close centrality coefficient and the betweenness centrality coefficient, identifies the target risk associated entity of the target object from all associated entities.

[0065] After obtaining the tight centrality coefficient and the betweenness centrality coefficient, the importance of the corresponding related entities can be determined through these coefficients. It should be noted that the higher the importance coefficient, the greater the influence on the target object, and the more the corresponding entity data reflects the risk level of the target object.

[0066] Alternatively, the tight centrality coefficient and the intermediate centrality coefficient can be compared with the tight centrality coefficient threshold and the intermediate centrality coefficient threshold, respectively. When the tight centrality coefficient and the intermediate centrality coefficient are greater than the tight centrality coefficient threshold and the intermediate centrality coefficient threshold, respectively, the target object can be considered as a target risk-related entity.

[0067] In this embodiment, firstly, based on the risk assessment graph, the tight centrality coefficient and association centrality coefficient of all related entities are determined. Then, based on the tight centrality coefficient and association centrality coefficient, the target risk related entities of the target object are identified from all related entities. Therefore, by calculating the tight centrality coefficient and association centrality coefficient of related entities, the target risk related entities with the greatest impact on the target object can be screened out, thereby enabling more accurate positioning of related entities and improving the accuracy of subsequent risk coefficient calculations.

[0068] In the above embodiments, based on the close centrality coefficient and the association centrality coefficient, the target risk associated entity of the target object is determined from all associated entities. This can also be achieved through... Figure 4 To further explain, the method includes:

[0069] S401, a first judgment value is determined based on the tight centrality coefficient and the first weight corresponding to the tight centrality coefficient, and a second judgment value is determined based on the intermediary centrality coefficient and the second weight corresponding to the intermediary centrality coefficient.

[0070] In this embodiment, the first weight and the second weight are pre-set and can be changed according to actual design needs, without any limitation.

[0071] It should be noted that the allocation of the first and second weights may differ for different target objects, and no restrictions are imposed here. For example, when assessing the physical health risk of a target object, emphasis may be placed on the close centrality coefficient, in which case the first weight should be greater than the second weight; when assessing the financial risk of a target object, emphasis may be placed on the intermediary centrality coefficient, in which case the second weight should be greater than the first weight.

[0072] S402, Based on the first judgment value and the second judgment value, determine the target risk associated entity of the target object from all associated entities.

[0073] In this embodiment, the first determination value and the second determination value can be summed to obtain the target determination value. Then, the target determination value is compared with a determination threshold. Finally, the associated entity corresponding to the target determination value that is greater than the determination threshold is determined as the target risk associated entity. It should be noted that the determination threshold is a critical value for determining whether the target object is a target risk associated entity. This determination threshold can be changed according to actual design needs, and no limitation is made here.

[0074] In this embodiment, a first determination value is first determined based on the tight centrality coefficient and the first weight corresponding to the tight centrality coefficient, and a second determination value is determined based on the betweenness centrality coefficient and the second weight corresponding to the betweenness centrality coefficient. Then, based on the first and second determination values, the target risk associated entity of the target object is determined from all associated entities. By setting a determination threshold, the accuracy of determining the target risk associated entity of the target object can be adjusted according to its own needs, thereby increasing the practicality of this disclosure.

[0075] Corresponding to the risk assessment methods provided in the above embodiments, one embodiment of this disclosure also provides a risk assessment device. Since the risk assessment device provided in this disclosure corresponds to the risk assessment methods provided in the above embodiments, the implementation methods of the above risk assessment methods are also applicable to the risk assessment device provided in this disclosure, and will not be described in detail in the following embodiments.

[0076] Figure 5 This is a schematic diagram of a risk assessment device proposed in this disclosure, such as... Figure 5 As shown, the risk assessment device 500 includes: an acquisition module 510, an assessment module 520, a determination module 530, and a generation module 540.

[0077] The acquisition module 510 is used to acquire the associated entities of the target object and the entity data of the associated entities.

[0078] Assessment module 520 is used to create a risk assessment map of the target object based on related entities and entity data.

[0079] The determination module 530 is used to determine the target risk associated entities of the target object from the associated entities based on the risk assessment map.

[0080] The generation module 540 is used to determine the risk coefficient of the target object based on the entity data of the target risk-related entity.

[0081] In one embodiment of this disclosure, the generation module 540 is further configured to: determine violation data from the entity data of the target risk-associated entity; and determine the risk coefficient of the target object based on the violation data.

[0082] In one embodiment of this disclosure, the determining module 530 is further configured to: determine the close centrality coefficient and the betweenness centrality coefficient of all associated entities based on the risk assessment graph; and determine the target risk associated entity of the target object from all associated entities based on the close centrality coefficient and the betweenness centrality coefficient.

[0083] In one embodiment of this disclosure, the determining module 530 is further configured to: determine a first determination value based on the close centrality coefficient and the first weight corresponding to the close centrality coefficient, and determine a second determination value based on the betweenness centrality coefficient and the second weight corresponding to the betweenness centrality coefficient; and determine the target risk associated entity of the target object from all associated entities based on the first determination value and the second determination value.

[0084] In one embodiment of this disclosure, the determining module 530 is further configured to: sum the first determination value and the second determination value to obtain a target determination value; compare the target determination value with a determination threshold; and determine the associated entity corresponding to the target determination value that is greater than the determination threshold as the target risk associated entity.

[0085] In one embodiment of this disclosure, the determining module 530 is further configured to: for the i-th associated entity, obtain the node distances between the i-th associated entity and the other n-1 associated entities in the risk assessment graph, where i is an integer, n is the number of associated entities, and 1≤i≤n; based on the node distances, determine the average distance between the i-th associated entity and the other n-1 associated entities in the risk assessment graph; and use the reciprocal of the average distance as the compact centrality coefficient of the i-th associated entity.

[0086] In one embodiment of this disclosure, the determining module 530 is further configured to: for the j-th associated entity, obtain the target number of times any two of the other n-1 associated entities pass through the j-th associated entity in the risk assessment graph, where j is an integer, n is the number of associated entities, and 1≤j≤n; and determine the betweenness centrality coefficient of the j-th associated entity based on the target number of times.

[0087] Therefore, by filtering related entities through the risk assessment map to identify target risk-related entities that have a significant impact on the target object, and determining the risk coefficient of the target object based on the entity data of the target risk entities, the data base for assessing the risk coefficient of the target object can be reduced, the data quality can be improved, thereby reducing the cost of data processing and improving the accuracy of the final risk coefficient.

[0088] To implement the above embodiments, this disclosure also proposes an electronic device 600, such as... Figure 6As shown, the electronic device 600 includes a processor 601 and a memory 602 communicatively connected to the processor. The memory 602 stores instructions executable by at least one processor. The instructions are executed by at least one processor 601 to implement the risk assessment method as described in the first aspect of this disclosure.

[0089] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to implement the risk assessment method as described in the first aspect of this disclosure.

[0090] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the risk assessment method as described in the first aspect of this disclosure.

[0091] In the description of this disclosure, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this disclosure.

[0092] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise expressly specified.

[0093] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0094] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A risk assessment method, characterized by, include: Obtain the associated entities of the target object and the entity data of the associated entities; Based on the associated entities and the entity data, a risk assessment map of the target object is established; Based on the risk assessment diagram, determining the target risk associated entity of the target object from the associated entities includes: determining the close centrality coefficient and the betweenness centrality coefficient of all the associated entities based on the risk assessment diagram; determining a first judgment value based on the close centrality coefficient and the first weight corresponding to the close centrality coefficient, and determining a second judgment value based on the betweenness centrality coefficient and the second weight corresponding to the betweenness centrality coefficient, wherein when judging the physical health risk of the target object, the close centrality coefficient is emphasized, so the first weight needs to be greater than the second weight; when judging the financial risk of the target object, the betweenness centrality coefficient is emphasized, so the second weight needs to be greater than the first weight; and determining the target risk associated entity of the target object from all the associated entities based on the first judgment value and the second judgment value. Based on the entity data of the target risk-related entity, the risk coefficient of the target object is determined.

2. The method of claim 1, wherein, Determining the risk coefficient of the target object based on the entity data of the target risk-related entity includes: Identify the violation data from the entity data of the target risk-related entity; Based on the violation data, the risk coefficient of the target object is determined.

3. The method of claim 1, wherein, The step of determining the target risk associated entity of the target object from all the associated entities based on the first determination value and the second determination value includes: The first determination value and the second determination value are summed to obtain the target determination value; The target determination value is compared with the determination threshold; The associated entities corresponding to the target judgment value that is greater than the judgment threshold are identified as the target risk associated entities.

4. The method according to any one of claims 1 or 3, characterized in that, Determine the tight centrality coefficients of all the associated entities, including: For the i-th associated entity, obtain the node distance between the i-th associated entity and the other n-1 associated entities in the risk assessment graph, where i is an integer, n is the number of associated entities, and 1≤i≤n; Based on the node distance, determine the average distance between the i-th associated entity and the other n-1 associated entities in the risk assessment map; The reciprocal of the average distance is used as the compact centrality coefficient of the i-th associated entity.

5. The method according to any one of claims 1 or 3, characterized in that, Determine the betweenness centrality coefficients of all the aforementioned associated entities, including: For the j-th associated entity, obtain the target number of times any two of the other n-1 associated entities pass through the j-th associated entity in the risk assessment graph, where j is an integer, n is the number of associated entities, and 1≤j≤n; The betweenness centrality coefficient of the j-th associated entity is determined based on the target number.

6. A risk assessment apparatus, characterized by, include: The acquisition module is used to acquire the associated entities of the target object and the entity data of the associated entities; The assessment module is used to establish a risk assessment map of the target object based on the associated entities and the entity data; A determination module is used to determine the target risk associated entity of the target object from the associated entities based on the risk assessment graph, including: determining the close centrality coefficient and the betweenness centrality coefficient of all the associated entities based on the risk assessment graph; determining a first judgment value based on the close centrality coefficient and the first weight corresponding to the close centrality coefficient, and determining a second judgment value based on the betweenness centrality coefficient and the second weight corresponding to the betweenness centrality coefficient, wherein when judging the physical health risk of the target object, the close centrality coefficient is emphasized, so the first weight needs to be greater than the second weight; when judging the financial risk of the target object, the betweenness centrality coefficient is emphasized, so the second weight needs to be greater than the first weight; and determining the target risk associated entity of the target object from all the associated entities based on the first judgment value and the second judgment value. The generation module is used to determine the risk coefficient of the target object based on the entity data of the target risk-related entity.

7. An electronic device, characterized in that, Including memory and processor; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-5.

Images