Method, device and electronic equipment for measuring business risk

Abstract

The application discloses a business risk measurement method, and belongs to the computer field. The method comprises the following steps: obtaining a text map picture and a satellite map picture of a target enterprise; obtaining a target text on the text map picture and a target object on the satellite map picture; matching the target text and the target object to determine whether the target text and the target object point to the same thing; if the target text and the target object point to the same thing, obtaining a first type to which the thing belongs; if the target text and the target object point to different things, obtaining a second type to which the target text belongs and a third type to which the target object belongs; and obtaining a business risk assessment result for the target enterprise according to at least one of the first type to which the thing belongs, the second type to which the target text belongs and the third type to which the target object belongs.

Description

Technical Field

[0001] This application belongs to the field of computer science, and specifically relates to a method, apparatus, and electronic device for measuring business risk. Background Technology

[0002] Under the new insurance logic of "underwriting + loss reduction + empowerment + claims settlement", understanding the risks that corporate clients may pose to their surroundings can enable clients to provide targeted loss reduction services and improve their ability to withstand various risks. Therefore, obtaining geographical information about the surroundings of enterprises, especially those in high-risk industries, is of paramount importance.

[0003] In related technologies, historical claims records are used to plot known risk points and risk categories on a map. For example, when a company is a chemical enterprise, surrounding buildings and rivers are easily affected by an explosion. A gridded risk map is formed by combining known risk points (such as surrounding buildings and rivers) with known risk categories (such as fire). The insured company's business risk is assessed based on the risk coefficient of the known risk grid, as the known risk grid contains various types of risk points. However, since there are many types of risk points within the known risk grid, treating different risk points with the same risk coefficient can easily lead to low accuracy in the insured company's risk coefficient. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for measuring business risk, which can solve the problem that the accuracy of the risk coefficient for insured enterprises is low because the risk grid contains many types of risk points and different risk points are treated as the same risk coefficient.

[0005] Firstly, a method for measuring business risk is provided, including:

[0006] Obtain text map images and satellite map images of the target company;

[0007] Obtain the target text on the text map image and the target object on the satellite map image;

[0008] The target text and the target object are matched to determine whether the target text and the target object refer to the same thing;

[0009] If the target text and the target object refer to the same thing, obtain the first type to which the thing belongs;

[0010] If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs;

[0011] Based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, a business risk assessment result for the target enterprise is obtained.

[0012] Secondly, a business risk measurement device is provided, comprising:

[0013] The first acquisition module is used to acquire text map images and satellite map images of the target enterprise; and to acquire target text on the text map images and target objects on the satellite map images.

[0014] The matching module is used to match the target text and the target object to determine whether the target text and the target object refer to the same thing;

[0015] The second acquisition module is used to acquire the first type of the thing if the target text and the target object point to the same thing; and to acquire the second type of the target text and the third type of the target object if the target text and the target object point to different things.

[0016] The calculation module obtains a business risk assessment result for the target enterprise based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs.

[0017] Thirdly, an electronic device is provided, comprising: a processor and a memory, the memory storing a program that, when executed by the processor, implements the steps in the method according to the first aspect.

[0018] In this embodiment, a text map image and a satellite map image of the target enterprise are obtained; target text on the text map image and target objects on the satellite map image are obtained; the target text and the target objects are matched to determine whether they point to the same thing; if the target text and the target object point to the same thing, a first type to which the thing belongs is obtained; if the target text and the target object point to different things, a second type to which the target text belongs and a third type to which the target object belongs are obtained; based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, a business risk assessment result for the target enterprise is obtained. Thus, since the business risk assessment result for the target enterprise is obtained based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, classifying the risk types surrounding the target enterprise when calculating the business risk assessment result for the target enterprise allows for a more accurate calculation of the different types of risks surrounding the target enterprise. Compared to related technologies that use gridded blurring to process various types and assign a uniform risk value to each type of risk within the grid, the embodiments of this application classify and calculate each type, which can more accurately analyze the risk brought by each type and make the business risk assessment results more accurate. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a method for measuring business risk provided in an embodiment of this application;

[0021] Figure 2 This is a flowchart of another method for measuring business risk provided in an embodiment of this application;

[0022] Figure 3 This is a flowchart of another method for measuring business risk provided in an embodiment of this application;

[0023] Figure 4 This is a flowchart of another method for measuring business risk provided in an embodiment of this application;

[0024] Figure 5 This is a structural block diagram of a business risk measurement device provided in an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of a target device provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0027] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0028] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0029] To better understand this application, some terms will be introduced before explaining the embodiments of this application.

[0030] High-risk industries: refer to industries related to the production, processing and manufacturing of hazardous chemicals, coal mines, non-coal mines, and fireworks and firecrackers.

[0031] Optical Character Recognition (OCR) component: refers to the component that extracts text information from an image, typically including text detection and text recognition.

[0032] Large language models: refer to deep neural network models built for natural language with a parameter scale of hundreds of millions or more.

[0033] Object detection model: A deep neural network model that detects specified subjects, such as people, cats, dogs, vehicles, streetlights, plants, etc., from images.

[0034] Small object detection model: A deep neural network model that detects objects that occupy a small portion of the image. In this embodiment, the object is approximately 25 pixels * 25 pixels or less.

[0035] Screenshot: Reads the current screen image and captures a rectangular area within a specified coordinate range.

[0036] Text map images: Images on the page that contain text information labeling buildings / locations.

[0037] Satellite map image: A satellite image showing a specific location.

[0038] To better address the issue of low accuracy in risk coefficients for insured enterprises in related technologies, this application proposes a risk measurement method for high-risk industry enterprises based on map text and satellite imagery. First, the target enterprise is located. Then, by acquiring text map images and satellite map images of the target enterprise, these images are processed to intelligently and efficiently determine the quantity of surrounding schools, residential areas, scenic spots, farmland, transportation routes, rivers, forests, hospitals, factories, villages, etc., and further calculate the risk coverage area of ​​the high-risk enterprise to complete the risk assessment.

[0039] The business risk measurement method provided in this application embodiment can be executed by a target device, which can be a single electronic device or multiple electronic devices. In other words, the business risk measurement method provided in this application embodiment can be executed by a single electronic device or by multiple electronic devices working together. The electronic device can be, for example, a terminal device such as a laptop or tablet, or a server.

[0040] Figure 1 This is a flowchart illustrating a method for measuring business risk provided in an embodiment of this application. For example... Figure 1 As shown in the embodiments of this application, the method for measuring business risk includes:

[0041] Step 110: Obtain text map images and satellite map images of the target company;

[0042] In this embodiment, the target enterprise can be any enterprise requiring insurance coverage, including, for example, industries related to the production, processing, and manufacturing of hazardous chemicals, coal mines, non-coal mines, and fireworks and firecrackers, as well as high-risk industries that may impact the surrounding environment or buildings. The text map image can be any map image containing textual information labeling buildings / locations, such as a city's administrative plan or a screenshot of location information from navigation software. The satellite map image can be a map image containing real-world landscapes such as villages, houses, and forests, such as a satellite image of the Earth.

[0043] Accordingly, the text map image of the target company can be a circular text map image with a radius of D centered on the target company, or a rectangular text map image with a length of H and a width of W centered on the target company, or a text map image of other shapes centered on the target company. This application embodiment does not impose specific limitations on this. The satellite map image of the target company can be a satellite map image of the same size and shape as the text map image of the target company centered on the target company.

[0044] Accordingly, obtaining text map images and satellite map images of the target company can be achieved by using external tools to take photos or screenshots and importing them into the target device. For example, a navigation map tool can be used to take a screenshot, which is then imported into the target device. Alternatively, the target device can generate these images internally. One method for internal generation is as follows: Based on a known industry list, which includes information such as latitude and longitude and the city of origin, the company name, latitude and longitude, and city of origin are individually transmitted to the target device. The target device then displays nearby map information centered on that latitude and longitude. If the map information contains text information marking buildings / locations, it can be identified as a text map image of the target company, and a screenshot can be taken to generate a text map image of the target company. If the map information contains real terrain features such as villages, houses, and forests, it can be identified as a satellite map image of the target company, and a screenshot can be taken to generate a satellite map image of the target company.

[0045] After obtaining the text map image and the satellite map image, content recognition processing can be performed on the text map image and the satellite map image.

[0046] Step 120: Obtain the target text on the text map image and the target object on the satellite map image;

[0047] In this embodiment of the application, the target text can be any field on the text map image, such as "West Chang'an Avenue" or "National Centre for the Performing Arts". The target object can be any landform on the satellite map image, such as "village" or "farmland".

[0048] The target text on the text map image and the target object on the satellite map image can be obtained by scanning and extracting using components within the target device, or by introducing an external deep neural network learning model to scan and recognize the text map image and the satellite map image, extracting and recording the content on the text map image and the satellite map image. The deep neural network learning model for extracting the target text on the text map image and the deep neural network learning model for extracting the target object on the satellite map image can be the same model or different models; this application embodiment does not impose specific limitations on this.

[0049] Step 130: Match the target text and the target object to determine whether the target text and the target object refer to the same thing;

[0050] In this embodiment, the target text and the target object can be matched pairwise. For example, the phrase "West Chang'an Street" in the target text can be matched with "village" and "farmland" in the satellite map image to determine whether the target text and the target object refer to the same thing. For instance, matching "West Chang'an Street" in the target text with "street" in the satellite map image, if the match is successful, can be understood as referring to a street called West Chang'an Street.

[0051] After matching the target text and the target object to determine whether the target text and the target object refer to the same thing, different processing can be performed according to the matching results.

[0052] Step 140: If the target text and the target object point to the same thing, obtain the first type to which the thing belongs;

[0053] In this embodiment of the application, the first type to which the thing belongs can be a type that can represent the thing, such as "school", "residential area", "hospital" etc. To better understand step 140, we can further explain it using the example in step 130. When "West Chang'an Street" in the target text and "street" in the satellite map image point to the same thing, a street called West Chang'an Street, then the type of the thing can be considered as a street.

[0054] Step 150: If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs;

[0055] In this embodiment of the application, the second type to which the target text belongs can be a type that can represent the target text, such as "school", "residential area", "scenic spot" etc. The third type to which the target object belongs can be a type that can represent the target object, such as "construction area" "forest".

[0056] Accordingly, the second type to which the target text belongs can be obtained by using a deep neural network model (e.g., a large language model) to understand the meaning of the target text and classify it according to the understanding of the target text.

[0057] Step 160: Obtain a business risk assessment result for the target enterprise based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs.

[0058] In this embodiment, risk assessment results for each thing and / or each target text and each target object can be calculated based on at least one of a first type to which the thing belongs, a second type to which the target text belongs, and a third type to which the target object belongs. Risks can be marked on the text map image and / or the satellite map image based on the risk assessment results for each thing and / or each target text and each target object to obtain a business risk map for the target enterprise. Alternatively, the risk assessment results obtained from at least two of the things, target texts, and target objects can be summarized and summed to obtain a total risk value for the target enterprise, and the target texts can be recorded and classified to obtain a business risk list and a total risk value for the target enterprise. Furthermore, based on a specified list containing some of the target texts and / or target objects, the risk assessment results for each thing and / or each target text and each target object on the specified list can be processed accordingly to obtain a more accurate business risk assessment map or risk value. This embodiment does not impose specific limitations on this.

[0059] In this embodiment, a text map image and a satellite map image of the target enterprise are obtained; target text on the text map image and target objects on the satellite map image are obtained; the target text and the target objects are matched to determine whether they point to the same thing; if the target text and the target object point to the same thing, a first type to which the thing belongs is obtained; if the target text and the target object point to different things, a second type to which the target text belongs and a third type to which the target object belongs are obtained; based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, a business risk assessment result for the target enterprise is obtained. Thus, since the business risk assessment result for the target enterprise is obtained based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, classifying the risk types surrounding the target enterprise when calculating the business risk assessment result for the target enterprise allows for a more accurate calculation of the different types of risks surrounding the target enterprise. Compared to related technologies that use gridded blurring to process various types and assign a uniform risk value to each type of risk within the grid, the embodiments of this application classify and calculate each type, which can more accurately analyze the risk brought by each type and make the business risk assessment results more accurate.

[0060] Figure 2 This is a flowchart illustrating a method for measuring business risk provided in an embodiment of this application. For example... Figure 1 As shown in the embodiments of this application, the method for measuring business risk includes:

[0061] Step 210: Obtain text map images and satellite map images of the target company;

[0062] Step 220: Obtain the target text on the text map image and the target object on the satellite map image;

[0063] In this embodiment, optical character recognition software can be used to recognize the text map image to obtain the target text on the text map image. Alternatively, a target detection model and / or a small target detection model can be used to detect the satellite map image to obtain the target objects on the satellite map image, wherein the target objects are named objects.

[0064] Step 230: Obtain the first coordinates of the target text in the text map image and the second coordinates of the target object in the satellite map image;

[0065] In this embodiment, the first and second coordinates can be the center point coordinates of the target text and / or the target object, or any coordinate point of the target text and / or the target object. A rectangle or circle can also be represented by coordinates, by recording the center point and related shape data of the rectangle or circle. The rectangle or circle contains the target text and / or the target object. One specific coordinate representation of a rectangle is (x, y, width, height), where x and y are the coordinates of the top-left vertex of the rectangle relative to the target text map image and / or the target satellite map image, and width and height are the width and height of the rectangle.

[0066] The first and second coordinates can be obtained simultaneously when recognizing the target text and the target object. Alternatively, they can be recognized and recorded using other deep neural network models or components. This application does not impose specific limitations on this.

[0067] Step 240: Match the first coordinates and the second coordinates to determine whether the target text and the target object point to the same thing;

[0068] In this embodiment of the application, the center point coordinates and shape size of the rectangular or circular frame represented by the first coordinate and the second coordinate can be matched to determine whether the position and shape size of the first coordinate and the second coordinate are the same. In this way, it can be determined whether the target text and the target object point to the same thing.

[0069] Step 250: If the target text and the target object point to the same thing, obtain the first type to which the thing belongs;

[0070] In this embodiment of the application, if the first coordinate and the second coordinate are the same in position and shape and size, or are mostly the same in a certain controllable area, it can be considered that the target text and the target object point to the same thing, and the first type to which the thing belongs can be obtained.

[0071] Step 260: If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs;

[0072] Step 270: Based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, obtain the business risk assessment result for the target enterprise.

[0073] In this embodiment, by obtaining the first coordinates of the target text in the text map image and the second coordinates of the target object in the satellite map image, the first coordinates and the second coordinates are matched to determine whether the target text and the target object point to the same thing. Determining whether the target text and the target object point to the same thing using the first and second coordinates allows for a more objective assessment, improving the accuracy of this determination. Furthermore, it enables a more accurate understanding of the things and types surrounding the target enterprise, thereby enhancing the business risk assessment for the target enterprise.

[0074] Figure 3 This is a flowchart illustrating a method for measuring business risk provided in an embodiment of this application. For example... Figure 1 As shown in the embodiments of this application, the method for measuring business risk includes:

[0075] Step 310: Obtain text map images and satellite map images of the target company;

[0076] Step 320: Obtain the target text on the text map image and the target object on the satellite map image;

[0077] Step 330: Match the target text and the target object to determine whether the target text and the target object refer to the same thing;

[0078] Step 340: If the target text and the target object point to the same thing, obtain the first type to which the thing belongs;

[0079] Step 350: If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs;

[0080] Step 360: Based on the first type to which the thing belongs, determine the first risk weight of the first type relative to the target enterprise; based on the second type to which the target text belongs, determine the second risk weight of the second type relative to the target enterprise; based on the third type to which the target object belongs, determine the third risk weight of the third type relative to the target enterprise.

[0081] In this embodiment, the first risk weight represents the target enterprise's claim risk of the first type. It can be calculated from the cumulative claim amount caused by accidents of the first type in recent years using a normalized exponential function, or it can be manually determined as a fixed value. This embodiment does not impose specific restrictions on this. Correspondingly, the second risk weight and the third risk weight can be the same as or different from the first risk weight. This embodiment does not impose specific restrictions on this.

[0082] Step 370: Obtain a first distance between the object and the target enterprise; obtain a second distance between the target text and the target object when they point to different objects; obtain a third distance between the target object and the target enterprise when they point to different objects.

[0083] In this embodiment, the first distance can be the straight-line distance between the object and the target enterprise, calculated using the coordinates of the center point of the object and the center point of the target enterprise. It can also be the driving distance between the object and the target enterprise, etc., but this embodiment does not impose specific limitations on this.

[0084] Accordingly, the first distance can be obtained by directly measuring the straight-line distance from the text map image and / or the satellite map image, or it can be imported from other navigation software to measure the driving distance of the object relative to the target enterprise. The second distance and the third distance may or may not be equal to the first distance. This application embodiment does not impose specific limitations on this.

[0085] Step 380: Based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, obtain the business risk assessment result for the target enterprise.

[0086] In this embodiment, a business risk assessment result for the target enterprise is obtained based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance. When calculating the business risk assessment result for the target enterprise, the first distance, the second distance, and the third distance are considered, incorporating the influence of distance into the calculation based on the risk weights, thereby improving the accuracy and completeness of the calculated risk assessment result.

[0087] Figure 4 This is a flowchart illustrating a method for measuring business risk provided in an embodiment of this application. For example... Figure 1 As shown in the embodiments of this application, the method for measuring business risk includes:

[0088] Step 410: Obtain text map images and satellite map images of the target company;

[0089] Step 420: Use OCR software to recognize the text map image to obtain the target text on the text map image; use an object detection model to detect the satellite map image to obtain the target objects on the satellite map image, wherein the target objects are objects with names;

[0090] Step 430: Determine the first text box where the target text is located; use the coordinates corresponding to the first text box as the first coordinates of the target text in the text map image; determine the second text box where the target object is located; use the coordinates corresponding to the second text box as the second coordinates of the target object in the satellite map image;

[0091] In this embodiment, the first text box can be a rectangle, a circle, or other shapes; this embodiment does not impose specific limitations on this. The first text box contains the target text. When the first text box is a rectangle, a specific method for representing the first coordinates can be found in the description of step 230.

[0092] Step 440: Calculate the overlap between the first text box and the second text box. The overlap is the ratio of the overlapping area of ​​the first text box and the second text box to the total area. The total area is the sum of the areas of the first text box and the second text box.

[0093] In this embodiment of the application, the overlap between the first text box and the second text box is calculated in pairs.

[0094] Step 450: If the overlap is greater than a threshold, determine that the target text and the target object refer to the same thing; if the overlap is less than or equal to the threshold, determine that the target text and the target object refer to different things.

[0095] Step 460: If the target text and the target object refer to the same thing, obtain the type to which the target text belongs and the type to which the target object belongs; according to the specified rules, merge the type to which the target text belongs and the type to which the target object belongs to obtain the target type, and use the target type as the first type to which the target object belongs;

[0096] In this embodiment of the application, the specified rule includes the merging relationship between the type to which the target text belongs and the type to which the target object belongs. For example, when the type to which the target text belongs is "community" and the type to which the target object belongs is "building", "community" and "building" are merged according to the specified rule to obtain the target type "community".

[0097] Step 470: If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs;

[0098] Step 480: Based on the first type to which the thing belongs, determine the first risk weight of the first type relative to the target enterprise; based on the second type to which the target text belongs, determine the second risk weight of the second type relative to the target enterprise; based on the third type to which the target object belongs, determine the third risk weight of the third type relative to the target enterprise.

[0099] Step 490: Obtain the first distance of the object relative to the target enterprise; obtain the second distance of the target text relative to the target enterprise when the target text and the target object point to different objects; obtain the third distance of the target object relative to the target enterprise when the target text and the target object point to different objects.

[0100] Step 495: Determine the risk assessment result of the target company using the following formula:

[0101] estimate_result=∑estimate(d n )

[0102] estimate(d n )=est_base*w class-n *(std_dis / dis n )

[0103] dis n =((x) n -x c ) 2 +(y n -y c ) 2 ) 1 / 2

[0104] Where, estimate_result is the risk assessment result of the target company; estimate(dn) is the risk assessment result for each of the items, the target text that failed to match, and the target object that failed to match; est_base is the risk base value, which is determined by the industry type of the target company and the registered capital of the target company, and is a constant; w class-n The risk weight is one of the first risk weight, the second risk weight, and the third risk weight; std_dis is the risk diffusion reference distance, which is a constant given a fixed map scale; dis n It is one of the first distance, the second distance, and the third distance; (x c ,y c (x) represents the coordinates of the target company; n ,y n The coordinates are obtained from either the first coordinate or the second coordinate. For example, if the first coordinate and the second coordinate are the center point coordinates of the target text and the target object, respectively, then (x...) n ,y n (x) can be either the first coordinate or the second coordinate. If the first coordinate and the second coordinate are arbitrary coordinate points of the target text and the target object, respectively, then (x) n ,y n The coordinates can be the target text and the target point where the target object is located, such as the coordinates of the center point.

[0105] In this embodiment of the application, when the target text and the target object are determined to be the same thing, the (x) n ,y n The coordinates can be determined by the type of the object. When the type of the object is the same as the type of the target text, the coordinates of the object can be the first coordinate. For example, when the type of the target text is "residential area" and the type of the target object is "building", and the combined type of the object is "residential area", the coordinates of the object can be the first coordinate.

[0106] To better understand the embodiments of this application, a specific implementation of an embodiment of this application is listed below. It should be understood that the example is not a limitation.

[0107] Locate the target company: Based on the known list of high-risk industries L, which includes information such as latitude and longitude and the city where the company is located, the company name, latitude and longitude, and the city where the company is located are entered into the map tool one by one according to the list L. The map tool displays a map within a radius D centered on the latitude and longitude, and the map screen includes map text, generating a screenshot S1.

[0108] Map text recognition and classification: Use the optical character recognition component to recognize all map text in screenshot S1, generate a set {Word} and the coordinate position loc_i(x,y,width,height) of each text word_i in screenshot S1, classify each text word_i using a large language model, and classify categories such as school, residential area, scenic spot, shopping mall, road, hospital, factory, company, etc., generate a classification result set {R}, associate the classification result r_i of each text word_i with the coordinate position loc_i and record it.

[0109] Small target detection satellite image: Switch the map tool display mode to satellite mode, generate screenshot S2, perform small target detection on screenshot S2, automatically detect main objects such as buildings, rivers, lakes, forests, farmland, traffic arteries, and mountainous areas in S2, generate a set of main objects {Iden} and the coordinate position loc_j(x,y,width,height) of each main object iden_j in S2, form associations and record them.

[0110] Surrounding information integration: Calculate the Intersection over Union (IOU) for each pair of loc_i and loc_j (i.e., the ratio of the overlapping area to the sum of the areas). For r_i and iden_j with an IOU greater than the threshold TD1, they are considered the same object. Merge relevant information according to the specified rule_set, such as merging communities and buildings into communities, scenic spots and forests into forests, etc. After merging, generate a merged information set {Merge}. Add the merged information set {Merge}, the remaining unmerged map text classification result set {R}_left, and the remaining unmerged small target subject set {Iden}_left to the integration result set {Final_Set}.

[0111] Risk assessment calculation: Complete the risk assessment of the target high-risk enterprise according to the following formula, and generate the assessment result estimate_result, where d n For the nth element of {Final_Set}, including element information info n and element coordinates (x) n ,y n ); est_base is the base risk value, which is determined by the industry type and registered capital of the company; w class-n For element information info n The risk weight is calculated using softmax (normalized exponential function) based on the cumulative compensation amount from accidents in the past three years for the element's type (school, residential area, hospital, etc.); std_dis is the risk diffusion reference distance, which is a constant given a fixed map scale; disn The straight-line distance between the nth element and the target company; (x c ,y c ) represents the coordinates of the center points of S1 and S2, i.e., the coordinates of the target company.

[0112] estimate_result=∑estimate(d n )

[0113] estimate(d n )=est_base*w class-n *(std_dis / dis n )

[0114] dis n =((x) n -x c ) 2 +(y n -y c ) 2 ) 1 / 2

[0115] Where, estimate_result is the risk assessment result of the target company; estimate(dn) is the risk assessment result for each of the items, the target text that failed to match, and the target object that failed to match; est_base is the risk base value, which is determined by the industry type of the target company and the registered capital of the target company, and is a constant; w class-n The risk weight is one of the first risk weight, the second risk weight, and the third risk weight; std_dis is the risk diffusion reference distance, which is a constant given a fixed map scale; dis n It is one of the first distance, the second distance, and the third distance; (x c ,y c (x) represents the coordinates of the target company; n ,y n It is obtained from either the first coordinate or the second coordinate.

[0116] Figure 5 This is a structural block diagram of a business risk measurement device provided in an embodiment of this application. The business risk measurement device 500 provided in this embodiment of the application includes a first acquisition module 510, a matching module 520, a second acquisition module 530, and a calculation module 540.

[0117] The first acquisition module 510 is used to acquire a text map image and a satellite map image of the target enterprise; and to acquire the target text on the text map image and the target object on the satellite map image.

[0118] The matching module 520 is used to match the target text and the target object to determine whether the target text and the target object refer to the same thing;

[0119] The second acquisition module 530 is used to acquire the first type to which the object belongs if the target text and the target object point to the same thing; and to acquire the second type to which the target text belongs and the third type to which the target object belongs if the target text and the target object point to different things.

[0120] The calculation module 540 is used to obtain a business risk assessment result for the target enterprise based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs.

[0121] Optionally, in the process of acquiring the target text on the text map image and the target object on the satellite map image, the first acquisition module 510 is specifically used for:

[0122] The text map image is identified using optical character recognition software to obtain the target text on the text map image;

[0123] The satellite map image is detected using a target detection model to obtain target objects on the satellite map image, wherein the target objects are objects with names.

[0124] Optionally, in the process of matching the target text and the target object to determine whether the target text and the target object refer to the same thing, the matching module 520 is specifically used for:

[0125] Obtain the first coordinates of the target text in the text map image, and the second coordinates of the target object in the satellite map image;

[0126] The first coordinate and the second coordinate are matched to determine whether the target text and the target object point to the same thing.

[0127] Optionally, in obtaining the first coordinates of the target text in the text map image and the second coordinates of the target object in the satellite map image, the matching module 520 is specifically used for:

[0128] Determine the first text box where the target text is located; use the coordinates corresponding to the first text box as the first coordinates of the target text in the text map image;

[0129] Determine the second text box where the target object is located; use the coordinates corresponding to the second text box as the second coordinates of the target object in the satellite map image.

[0130] Optionally, in the process of matching the first coordinates and the second coordinates to determine whether the target text and the target object point to the same thing, the matching module 520 is specifically used for:

[0131] Calculate the overlap between the first text box and the second text box. The overlap is the ratio of the overlapping area of ​​the first text box and the second text box to the total area. The total area is the sum of the areas of the first text box and the second text box.

[0132] If the overlap is greater than a threshold, it is determined that the target text and the target object refer to the same thing;

[0133] If the overlap is less than or equal to the threshold, it is determined that the target text and the target object refer to different things.

[0134] Optionally, in the process of obtaining the type of the item, the second obtaining module 530 is specifically used for:

[0135] Obtain the type of the target text and the type of the target object;

[0136] According to the specified rules, the type to which the target text belongs and the type to which the target object belongs are merged to obtain the target type, and the target type is used as the first type to which the target object belongs.

[0137] Optionally, in the process of obtaining the business risk assessment result for the target enterprise based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, the calculation module 540 is specifically used for:

[0138] Based on the first type to which the thing belongs, determine the first risk weight of the first type relative to the target enterprise;

[0139] Based on the second type to which the target text belongs, determine the second risk weight of the second type relative to the target enterprise;

[0140] Based on the third type to which the target object belongs, determine the third risk weight of the third type relative to the target enterprise;

[0141] Obtain the first distance of the object relative to the target enterprise;

[0142] When the target text and the target object point to different things, the second distance of the target text relative to the target enterprise is obtained;

[0143] When the target text and the target object point to different things, the third distance of the target object relative to the target enterprise is obtained;

[0144] Based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, a business risk assessment result for the target enterprise is obtained.

[0145] Optionally, in the process of obtaining the business risk assessment result for the target enterprise based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, the calculation module 540 is specifically used for:

[0146] The risk assessment result of the target company is determined using the following formula:

[0147] estimate_result=∑estimate(d n )

[0148] estimate(d n )=est_base*w class-n *(std_dis / dis n )

[0149] dis n =((x) n -x c ) 2 +(y n -y c ) 2 ) 1 / 2

[0150] Where, estimate_result is the risk assessment result of the target company; estimate(dn) is the risk assessment result for each of the items, the target text that failed to match, and the target object that failed to match; est_base is the risk base value, which is determined by the industry type of the target company and the registered capital of the target company, and is a constant; w class-n The risk weight is one of the first risk weight, the second risk weight, and the third risk weight; std_dis is the risk diffusion reference distance, which is a constant given a fixed map scale; dis n It is one of the first distance, the second distance, and the third distance; (x c,y c (x) represents the coordinates of the target company; n ,y n It is obtained from either the first coordinate or the second coordinate.

[0151] Figure 6 This is a schematic diagram of an electronic device provided in an embodiment of this application. For example... Figure 6 As shown, the electronic device 600 provided in this application embodiment may include a processor 610 and a memory 620. The memory stores a computer program, which, when executed, implements any of the business risk measurement methods provided in this application embodiment (e.g., ...). Figures 1 to 4 The steps in the method for measuring business risk shown in any of the figures.

[0152] Memory is used to store programs or data. Memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc.

[0153] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0154] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0155] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0156] This application provides a computer program product that is stored in a storage medium and executed by at least one processor to implement the various processes of the above method embodiments and achieve the same technical effects. To avoid repetition, further details are omitted here.

[0157] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0159] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for measuring business risk, characterized in that, include: Obtain text map images and satellite map images of the target company; Obtain the target text on the text map image and the target object on the satellite map image; The target text and the target object are matched to determine whether the target text and the target object refer to the same thing; If the target text and the target object refer to the same thing, obtain the first type to which the thing belongs; If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs; Based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs, a business risk assessment result for the target enterprise is obtained, including: Based on the first type to which the thing belongs, determine the first risk weight of the first type relative to the target enterprise; Based on the second type to which the target text belongs, determine the second risk weight of the second type relative to the target enterprise; Based on the third type to which the target object belongs, determine the third risk weight of the third type relative to the target enterprise; Obtain the first distance of the object relative to the target enterprise; When the target text and the target object point to different things, the second distance of the target text relative to the target enterprise is obtained; When the target text and the target object point to different things, the third distance of the target object relative to the target enterprise is obtained; Based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, a business risk assessment result for the target enterprise is obtained.

2. The method according to claim 1, characterized in that, The step of obtaining the target text on the text map image and the target object on the satellite map image includes: The text map image is identified using optical character recognition software to obtain the target text on the text map image; The satellite map image is detected using a target detection model to obtain target objects on the satellite map image, wherein the target objects are objects with names.

3. The method according to claim 1, characterized in that, The step of matching the target text and the target object to determine whether the target text and the target object refer to the same thing includes: Obtain the first coordinates of the target text in the text map image, and the second coordinates of the target object in the satellite map image; The first coordinate and the second coordinate are matched to determine whether the target text and the target object point to the same thing.

4. The method according to claim 3, characterized in that, The step of obtaining the first coordinates of the target text in the text map image and the second coordinates of the target object in the satellite map image includes: Determine the first text box where the target text is located; use the coordinates corresponding to the first text box as the first coordinates of the target text in the text map image; Determine the second text box where the target object is located; use the coordinates corresponding to the second text box as the second coordinates of the target object in the satellite map image.

5. The method according to claim 4, characterized in that, The step of matching the first coordinates and the second coordinates to determine whether the target text and the target object point to the same thing includes: Calculate the overlap between the first text box and the second text box. The overlap is the ratio of the overlapping area of ​​the first text box and the second text box to the total area. The total area is the sum of the areas of the first text box and the second text box. If the overlap is greater than a threshold, it is determined that the target text and the target object refer to the same thing; If the overlap is less than or equal to the threshold, it is determined that the target text and the target object refer to different things.

6. The method according to claim 1, characterized in that, The process of obtaining the type of the item includes: Obtain the type of the target text and the type of the target object; According to the specified rules, the type to which the target text belongs and the type to which the target object belongs are merged to obtain the target type, and the target type is used as the first type to which the target object belongs.

7. The method according to claim 3, characterized in that, The business risk assessment result for the target enterprise is obtained based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, including: The risk assessment result of the target company is determined using the following formula: estimate_result = ∑ estimate(d n ) estimate(d n ) = is_base w class-n (std_dis / dis n ) dis n = ((x n - x c ) 2 + (y n - y c ) 2 ) 1 / 2 Where, estimate_result is the risk assessment result of the target company; estimate(d n The risk assessment results for each of the stated items, the target text that failed to match, and the target object that failed to match; est_base is the risk base value, which is determined by the industry type of the target company and the registered capital of the target company, and is a constant; w class-n The risk weight is one of the first risk weight, the second risk weight, and the third risk weight; std_dis is the risk diffusion reference distance, which is a constant given a fixed map scale; dis n It is one of the first distance, the second distance, and the third distance; (x c ,y c (x) represents the coordinates of the target company; n ,y n It is obtained from either the first coordinate or the second coordinate.

8. A device for measuring business risk, characterized in that, include: The first acquisition module is used to acquire text map images and satellite map images of the target company; Obtain the target text on the text map image and the target object on the satellite map image; The matching module is used to match the target text and the target object to determine whether the target text and the target object refer to the same thing; The second acquisition module is used to acquire the first type to which the object belongs if the target text and the target object point to the same thing; If the target text and the target object point to different things, obtain the second type to which the target text belongs and the third type to which the target object belongs; The calculation module obtains a business risk assessment result for the target enterprise based on at least one of the first type to which the thing belongs, the second type to which the target text belongs, and the third type to which the target object belongs; The calculation module is specifically used to determine a first risk weight of the first type relative to the target enterprise based on the first type to which the thing belongs. Based on the second type to which the target text belongs, determine the second risk weight of the second type relative to the target enterprise; Based on the third type to which the target object belongs, determine the third risk weight of the third type relative to the target enterprise; Obtain the first distance of the object relative to the target enterprise; When the target text and the target object point to different things, the second distance of the target text relative to the target enterprise is obtained; When the target text and the target object point to different things, the third distance of the target object relative to the target enterprise is obtained; Based on the first risk weight, the second risk weight, the third risk weight, the first distance, the second distance, and the third distance, a business risk assessment result for the target enterprise is obtained.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that run on the processor, the program or instructions which, when executed by the processor, implement the steps of the method as described in any one of claims 1-7.

Images