Building economic risk monitoring method, electronic equipment and storage medium

Abstract

The invention provides a building economic risk monitoring method, electronic equipment and a storage medium, and the method comprises the steps: determining a first target subject, a second target subject and a third target subject according to the feature data integrity of subject feature data corresponding to each target subject included in a target building; determining a subject negative impact value of the first target subject according to the plurality of subject feature data corresponding to the first target subject; determining a subject negative impact value of the second target subject according to the impact type of the feature field of the subject feature data of the second target subject; according to the similarity between the main body feature data of the same type of main body and the main body feature data of a third target main body, determining a main body negative impact value corresponding to the third target main body; and weighting the subject negative impact value of the target subject and the building negative impact value to obtain a building economic risk value, so as to reflect a real risk condition between the target building and the target subject through the building economic risk value.

Description

Technical Field

[0001] This invention relates to the field of building economy monitoring, and in particular to a building economy risk monitoring method, electronic device and storage medium. Background Technology

[0002] In today's era of rapid economic development, the building economy, as an emerging economic form, is gradually becoming an important driving force for urban economic development. The building economy primarily uses commercial buildings, functional zones, and regional facilities as its carriers, attracting various enterprises through the development and leasing of buildings, thereby generating tax revenue and driving regional economic development. However, with the continuous development of the building economy, the risks it faces are becoming increasingly prominent. Enterprises and investors hope to accurately understand the risk status of businesses occupying the buildings in order to make reasonable investment decisions. At the same time, building managers also need effective risk monitoring methods to improve the building's operational management level and protect the interests of tenants. Therefore, there is an urgent need for an effective risk monitoring and early warning method to ensure the healthy and stable development of the building economy. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows: According to one aspect of this application, a method for monitoring building economic risks is provided, comprising: Step S100: Determine the completeness of the feature data corresponding to each target entity based on the number of feature data corresponding to each target entity included in the target building; Step S200: Based on the feature data completeness corresponding to each target subject, traverse several target subjects, determine the target subject whose feature data completeness is greater than or equal to the preset first completeness threshold as the first target subject, determine the target subject whose feature data completeness is less than the preset first completeness threshold but greater than the preset second completeness threshold as the second target subject, and determine the target subject whose feature data completeness is less than or equal to the preset second completeness threshold as the third target subject. Step S300: Based on several subject feature data corresponding to each first target subject, perform feature analysis on each first target subject to obtain the subject negative impact value corresponding to each first target subject; Step S400: Determine the adjustment coefficient corresponding to each second target subject based on the influence type of the feature field of the feature data of each subject corresponding to each second target subject; Step S500: Process and analyze the adjustment coefficient and subject feature data corresponding to each second target subject to obtain the subject negative impact value corresponding to each second target subject; Step S600: Based on the similarity between the subject feature data of the same type of subject as each third target subject and the subject feature data of each third target subject, and the subject negative impact value corresponding to the same type of subject, determine the subject negative impact value corresponding to each third target subject. Step S700: Weight the negative impact value of each target entity with the preset negative impact value of the target building to obtain the economic risk value of the target building.

[0004] According to another aspect of this application, a non-transitory computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the aforementioned building economic risk monitoring method.

[0005] According to another aspect of this application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0006] The present invention has at least the following beneficial effects: The building economic risk monitoring method of the present invention first determines the feature data completeness of each target entity based on the quantity of feature data corresponding to each target entity included in the target building. Feature data completeness indicates the degree of completeness of the acquired feature data of the target entity, which is used to determine the negative impact value of the target entity in subsequent processes. The higher the feature data completeness, the greater the amount of feature data acquired, and the more accurately the negative impact value determined by the feature data can reflect the feature characteristics of the target entity. After obtaining the feature data completeness of the target entities, the method iterates through several target entities based on the feature data completeness of each target entity. Target entities with feature data completeness greater than or equal to a first completeness threshold are identified as first target entities, target entities with feature data completeness less than the first completeness threshold but greater than a second completeness threshold are identified as second target entities, and target entities with feature data completeness less than or equal to the second completeness threshold are identified as third target entities. This classifies several target entities into three categories, and the feature data of these three categories of target entities are processed sequentially. That is, feature analysis is performed on each first target entity based on the number of feature data corresponding to each first target entity to obtain the feature data of each first target entity. The system calculates the corresponding negative impact value of each target entity, and determines the adjustment coefficient for each second target entity based on the impact type of the characteristic fields of each entity's characteristic data. It then processes and analyzes the adjustment coefficient and characteristic data of each second target entity to obtain the negative impact value. Finally, it determines the negative impact value of each third target entity based on the similarity between the characteristic data of entities of the same type as each third target entity and the characteristic data of each third target entity, as well as the negative impact value of the same type of entity. By applying different data processing methods to the characteristic data of the three types of target entities, the obtained negative impact value of each target entity can accurately assess the negative impact of the target entity. Finally, it weights the negative impact value of each target entity with the preset negative impact value of the target building to obtain the building economic risk value of the target building. This building economic risk value reflects the true risk situation between the target building and the target entity, achieving targeted monitoring and comprehensive risk assessment, improving the efficiency and accuracy of risk monitoring, and providing a guarantee for the healthy and stable development of the building economy. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A flowchart of a building economic risk monitoring method provided in an embodiment of the present invention. Detailed Implementation

[0009] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0010] This application proposes a method for monitoring building economic risks, such as... Figure 1 As shown, it includes: Step S100: Determine the completeness of the feature data corresponding to each target entity based on the number of feature data corresponding to each target entity included in the target building; The target entity can be a company located in the target building. The entity characteristic data is the relevant characteristic data of the company. Each entity characteristic data corresponds to a characteristic field. The characteristic field represents the information field of the corresponding entity characteristic data. The characteristic field can be a field related to the company's business situation, such as legal risks, operational risks, and regulatory risks.

[0011] Feature data completeness indicates the degree of completeness of the acquired subject feature data, which is used to determine the subject's negative impact value. The higher the feature data completeness, the greater the amount of subject feature data acquired, and the more accurately the subject's negative impact value determined by the subject feature data can reflect the subject's subject features.

[0012] Furthermore, step S100 includes steps S110-S130: Step S110: Obtain the subject feature data corresponding to each target subject within the target building to obtain several subject feature data lists A1, A2, ..., A j ,...,A k Where j = 1, 2, ..., k; k is the number of target entities included in the target building; A j This is a list of subject feature data corresponding to the j-th target subject within the target building; A j =(A j1 A j2 ,...,A jm ,...,A jn(j) ); m=1,2,...,n(j); n(j) is the number of subject feature data obtained for the j-th target subject; A jm To obtain the feature data of the m-th subject of the j-th target subject; Step S120: Traverse A j , obtain A j The preset field weights of the feature fields corresponding to each subject feature data are used to obtain the field weight list B corresponding to the j-th target subject. j =(B j1 B j2 ,...,B jm ,...,B jn(j) ); B jm For A jm The preset field weights of the corresponding feature fields; The preset field weights are the weights corresponding to the feature fields. Each feature field has a corresponding field weight, and the sum of the field weights of several feature fields is 1.

[0013] Step S130: Determine the feature data completeness C corresponding to the j-th target subject. j =∑ n(j) m=1 B jm .

[0014] Step S200: Based on the feature data completeness corresponding to each target subject, traverse several target subjects and determine the target subject whose feature data completeness is greater than or equal to the preset first completeness threshold as the first target subject; The target subject whose feature data completeness is less than a preset first completeness threshold and greater than a preset second completeness threshold is identified as the second target subject; Target subjects whose feature data completeness is less than or equal to a preset second completeness threshold are identified as third target subjects; Based on the completeness of feature data, several target subjects are divided into three categories. The first target subject has the highest feature data completeness, indicating that the first target subject has the most complete number of subject feature data. The second target subject is next, and the third target subject has the lowest feature data completeness. By dividing the target subjects into three categories, the negative impact value of the subject can be determined separately for target subjects with different feature data completeness. This ensures that the obtained negative impact value of the subject can accurately match the characteristics of the subject, without being affected by the amount of subject feature data obtained, thereby improving the accuracy of determining the negative impact value of the subject.

[0015] The negative impact value of a target entity represents the numerical value of the negative impact on the target entity determined based on the entity's characteristic data, and can be considered as the economic risk value of the enterprise.

[0016] Step S300: Based on several subject feature data corresponding to each first target subject, perform feature analysis on each first target subject to obtain the subject negative impact value corresponding to each first target subject; Furthermore, step S300 includes steps S310-S350: Step S310: Obtain the preset initial feature vector D=(D1,D2,...,D...). g ,...,D h ); where g = 1, 2, ..., h; h is the number of feature data included in the initial feature vector; D g This refers to the g-th feature data included in the initial feature vector; Step S320: Identify any first target entity as the first key entity; Step S330: Perform feature encoding on several subject feature data corresponding to the first key subject to obtain the first feature vector E=(E1,E2,...,E...). p ,...,E q ); where p=1,2,...,q; q is the number of key feature data of the first key subject; E p This refers to the feature data obtained after feature encoding the p-th subject feature data of the first key subject; Step S340: Traverse the initial feature vector D. If D g The corresponding feature fields and E p If the corresponding feature fields are the same, then D in the initial feature vector D will be... g Replace with E p ; If D g If the corresponding feature field is different from the feature field corresponding to any feature data in the first feature vector E, then the D in the initial feature vector D will be... gSet to null value to obtain the target feature vector corresponding to the first key subject; Step S350: Input the target feature vector corresponding to the first key subject into the preset influence value determination model to obtain the negative influence value of the subject corresponding to the first key subject output by the influence value determination model.

[0017] The impact value determination model is trained on historical feature data of several target subjects within a historical period. Specifically, the impact value determination model is determined according to steps S351-S354: Step S351: Encode the features of several historical feature data corresponding to each target subject within a historical time period to obtain several historical coded data corresponding to each target subject. The duration of a historical period is a preset duration, and the end time of the historical period is before the current time.

[0018] Historical feature data refers to the feature data of the target subject within a historical period.

[0019] Step S352: Integrate several historical encoded data corresponding to each target subject into the initial feature vector D according to the corresponding feature fields to obtain the historical feature vector corresponding to each target subject; Step S353: Obtain the preset historical negative impact value for each target subject within the historical time period; Step S354: Take the historical feature vector corresponding to each target subject as the input sample, and the historical negative impact value corresponding to each target subject as the output label, and perform supervised learning training on the preset initial large language model to obtain the impact value determination model.

[0020] The existing training methods can be used to train the initial large language model using samples.

[0021] Step S400: Determine the adjustment coefficient corresponding to each second target subject based on the influence type of the feature field of the feature data of each subject corresponding to each second target subject; Furthermore, step S400 includes steps S410-S450: Step S410: Identify any second target entity as the second key entity; Step S420: Perform feature encoding on several subject feature data corresponding to the second key subject to obtain the second feature vector F=(F1,F2,...,F...). a ,...,F b ); where a=1,2,...,b; b is the number of subject feature data of the second key subject; F aThis refers to the feature data obtained after feature encoding the feature data of the a-th subject of the second key subject; Step S430: Traverse the initial feature vector D. If D g The corresponding feature fields and F a If the corresponding feature fields are the same, then D in the initial feature vector D will be... g Replace with F a ; If D g If the corresponding feature field is different from the feature field corresponding to any feature data in the second feature vector F, then the D in the initial feature vector D will be... g Set to null value to obtain the target feature vector corresponding to the second key subject; Step S440: Traverse the target feature vectors corresponding to the second key subject and identify the feature data with null values ​​as missing feature data; Step S450: Determine the adjustment coefficient G corresponding to the second key subject: G = ((H1-I1)×J1+(H2-I2)×J2+(H3-I3)×J3) / (1-(I1+I2+I3)); Wherein, H1 is the sum of the preset field weights of the feature fields with positive influence among the feature fields corresponding to several feature data of the initial feature vector D; the positive type feature fields are those that can reflect the positive operation of the target entity, such as financing information, information on the number of newly added intellectual property rights, etc. H2 is the sum of the preset field weights of the neutral-type feature fields among the feature fields corresponding to several feature data of the initial feature vector D; the neutral-type feature fields are feature fields of the target entity's operating status that are neither positive nor negative, such as fields such as information on changes in key personnel, shareholder changes, and changes in business scope. H3 is the sum of the preset field weights of the feature fields with negative influence among the feature fields corresponding to several feature data of the initial feature vector D; the negative type feature fields are those that can reflect the negative operation of the target entity, such as fields such as the number of persons subject to enforcement, bill default information, and penalty information. H1+H2+H3=1; I1 is the sum of the preset field weights of the feature fields with positive influence among the feature fields corresponding to several missing feature data of the target feature vector corresponding to the second key subject; I2 is the sum of the preset field weights of the feature fields with neutral influence among the feature fields corresponding to several missing feature data of the target feature vector corresponding to the second key subject; I3 is the sum of the preset field weights of the feature fields with negative influence types among the feature fields corresponding to several missing feature data of the target feature vector corresponding to the second key subject; J1 is the preset weight coefficient of the positive feature field; J2 is the preset weight coefficient of the neutral feature field; J3 is the preset weight coefficient of the negative feature field; J1 < 1; J2 = 1; J3 > 1.

[0022] Step S500: Process and analyze the adjustment coefficient and subject feature data corresponding to each second target subject to obtain the subject negative impact value corresponding to each second target subject; Furthermore, step S500 includes steps S510-S520: Step S510: Input the target feature vector corresponding to the second key subject into the influence value determination model to obtain the initial negative impact value M corresponding to the second key subject output by the influence value determination model; Step S520: Determine the negative impact value L=M×G corresponding to the second key subject.

[0023] Step S600: Based on the similarity between the subject feature data of the same type of subject as each third target subject and the subject feature data of each third target subject, and the subject negative impact value corresponding to the same type of subject, determine the subject negative impact value corresponding to each third target subject. Furthermore, step S600 includes steps S610-S680: Step S610: Identify any third target entity as the third key entity; Step S620: Among the preset key subjects, the key subjects with the same subject type as the third key subject are identified as subjects of the same type; The key subject is the subject whose feature data completeness is greater than the first completeness threshold.

[0024] Step S630: Traverse the feature fields of the main feature data of the same type of subject and the feature fields of the main feature data of the third key subject, and determine the feature fields that are common to both the same type of subject and the third key subject as common fields; Step S640: Compare the similarity of the subject feature data of the common fields corresponding to the same type of subject with the subject feature data of the common fields corresponding to the third key subject to obtain the feature similarity of the same type of subject. Step S650: If the feature similarity of the subject of the same type is greater than the preset similarity threshold, then the subject of the same type is identified as the target subject of the same type. Step S660: Obtain the preset negative impact value of each target of the same type corresponding to the third key subject, so as to obtain the impact value list N=(N1,N2,...,N...). c ,...,N d ); where c = 1, 2, ..., d; d is the number of target entities of the same type corresponding to the third key entity; N c The negative impact value of the target entity of the c-th type corresponding to the third key entity; Step S670: Obtain the feature similarity between the third key subject and each corresponding target subject of the same type, to obtain a feature similarity list T=(T1,T2,...,T...). c ,...,T d ); where T c The feature similarity between the third key subject and the corresponding c-th target subject of the same type; Step S680: Determine the negative impact value R corresponding to the third key subject. d c=1 (T c / (∑ d c=1 T c ))×N c .

[0025] Step S700: Weight the negative impact value of each target entity with the preset negative impact value of the target building to obtain the economic risk value of the target building. Furthermore, step S700 includes steps S710-S720: Step S710: Obtain the preset negative building impact value V corresponding to the target building; Step S720: Determine the economic risk value of the target building, Z = Y1 × V + Y2 × Q; Where Q is the sum of the negative impact values ​​of several target entities; Y1 is the preset first risk value coefficient; Y2 is the preset second risk value coefficient; Y1+Y2=1; Y2=(S1 / Q)×W1+(S2 / Q)×W2+(S3 / Q)×W3; S1 is the sum of the negative impact values ​​of several first target entities; S2 is the sum of the negative impact values ​​of several second target entities; S3 is the sum of the negative impact values ​​of several third target entities; S1 + S2 + S3 = Q; W1 is the preset first influence value coefficient; W2 is the preset second influence value coefficient; W3 is the preset third influence value coefficient; 0 < W3 < W2 < W1 < 1.

[0026] The building economic risk monitoring method of the present invention first determines the feature data completeness of each target entity based on the quantity of feature data corresponding to each target entity included in the target building. Feature data completeness indicates the degree of completeness of the acquired feature data of the target entity, which is used to determine the negative impact value of the target entity in subsequent processes. The higher the feature data completeness, the greater the amount of feature data acquired, and the more accurately the negative impact value determined by the feature data can reflect the feature characteristics of the target entity. After obtaining the feature data completeness of the target entities, the method iterates through several target entities based on the feature data completeness of each target entity. Target entities with feature data completeness greater than or equal to a first completeness threshold are identified as first target entities, target entities with feature data completeness less than the first completeness threshold but greater than a second completeness threshold are identified as second target entities, and target entities with feature data completeness less than or equal to the second completeness threshold are identified as third target entities. This classifies several target entities into three categories, and the feature data of these three categories of target entities are processed sequentially. That is, feature analysis is performed on each first target entity based on the number of feature data corresponding to each first target entity to obtain the feature data of each first target entity. The system calculates the corresponding negative impact value of each target entity, and determines the adjustment coefficient for each second target entity based on the impact type of the characteristic fields of each entity's characteristic data. It then processes and analyzes the adjustment coefficient and characteristic data of each second target entity to obtain the negative impact value. Finally, it determines the negative impact value of each third target entity based on the similarity between the characteristic data of entities of the same type as each third target entity and the characteristic data of each third target entity, as well as the negative impact value of the same type of entity. By applying different data processing methods to the characteristic data of the three types of target entities, the obtained negative impact value of each target entity can accurately assess the negative impact of the target entity. Finally, it weights the negative impact value of each target entity with the preset negative impact value of the target building to obtain the building economic risk value of the target building. This building economic risk value reflects the true risk situation between the target building and the target entity, achieving targeted monitoring and comprehensive risk assessment, improving the efficiency and accuracy of risk monitoring, and providing a guarantee for the healthy and stable development of the building economy.

[0027] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0028] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0029] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0030] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0031] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as “circuit,” “module,” or “system.”

[0032] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.

[0033] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0034] The storage device stores program code that can be executed by the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.

[0035] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0036] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0037] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0038] Electronic devices can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable users to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (such as routers, modems, etc.). This communication can be performed through input / output (I / O) interfaces. Furthermore, electronic devices can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters.

[0039] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section of this specification.

[0040] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0041] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0042] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0043] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0044] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0045] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0046] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring building economic risks, characterized in that, include: Step S100: Determine the completeness of the feature data corresponding to each target entity based on the number of feature data corresponding to each target entity included in the target building; Step S200: Based on the feature data completeness corresponding to each target subject, traverse several target subjects, determine the target subject whose feature data completeness is greater than or equal to a preset first completeness threshold as the first target subject, determine the target subject whose feature data completeness is less than the preset first completeness threshold but greater than a preset second completeness threshold as the second target subject, and determine the target subject whose feature data completeness is less than or equal to the preset second completeness threshold as the third target subject. Step S300: Based on several subject feature data corresponding to each first target subject, perform feature analysis on each first target subject to obtain the subject negative impact value corresponding to each first target subject; Step S400: Determine the adjustment coefficient corresponding to each second target subject based on the influence type of the feature field of each subject feature data corresponding to each second target subject; Step S500: Process and analyze the adjustment coefficient and subject feature data corresponding to each second target subject to obtain the subject negative impact value corresponding to each second target subject; Step S600: Based on the similarity between the subject feature data of the same type of subject as each third target subject and the subject feature data of each third target subject, and the subject negative impact value corresponding to the same type of subject, determine the subject negative impact value corresponding to each third target subject; Step S700: Weight the negative impact value of each target entity with the preset negative impact value of the target building to obtain the economic risk value of the target building.

2. The method according to claim 1, characterized in that, Step S100 includes: Step S110: Obtain the subject feature data corresponding to each target subject included in the target building, so as to obtain several subject feature data lists A1, A2, ..., A j ,...,A k Where j = 1, 2, ..., k; k is the number of target entities included in the target building; A j This is a list of subject feature data corresponding to the j-th target subject included in the target building; A j =(A j1 A j2 ,...,A jm ,...,A jn(j) ); m=1,2,...,n(j); n(j) is the number of subject feature data obtained for the j-th target subject; A jm To obtain the feature data of the m-th subject of the j-th target subject; Step S120: Traverse A j , obtain A j The preset field weights of the feature fields corresponding to each of the aforementioned subject feature data are used to obtain the field weight list B corresponding to the j-th target subject. j =(B j1 B j2 ,...,B jm ,...,B jn(j) ); B jm For A jm The preset field weights of the corresponding feature fields; Step S130: Determine the feature data completeness C corresponding to the j-th target subject. j =∑ n(j) m=1 B jm .

3. The method according to claim 2, characterized in that, Step S300 includes: Step S310: Obtain the preset initial feature vector D=(D1,D2,...,D...). g ,...,D h ); where g = 1, 2, ..., h; h is the number of feature data included in the initial feature vector; D g The g-th feature data included in the initial feature vector; Step S320: Determine any one of the first target entities as the first key entity; Step S330: Perform feature encoding on several subject feature data corresponding to the first key subject to obtain a first feature vector E=(E1,E2,...,E...). p ,...,E q ); where p = 1, 2, ..., q; q is the number of main feature data of the first key subject; E p The feature data is obtained by feature encoding the p-th subject feature data of the first key subject; Step S340: Traverse the initial feature vector D. If D g The corresponding feature fields and E p If the corresponding feature fields are the same, then D in the initial feature vector D will be... g Replace with E p ; If D g If the corresponding feature field is different from the feature field corresponding to any feature data in the first feature vector E, then D in the initial feature vector D will be... g Set to null value to obtain the target feature vector corresponding to the first key entity; Step S350: Input the target feature vector corresponding to the first key subject into a preset influence value determination model to obtain the negative influence value of the subject corresponding to the first key subject output by the influence value determination model; The influence value determination model is obtained by training on historical feature data corresponding to several target subjects within a historical period.

4. The method according to claim 3, characterized in that, The influence value determination model is based on the following steps: Step S351: Encode the historical feature data corresponding to each target subject within a historical time period to obtain several historical encoded data corresponding to each target subject; the duration of the historical time period is a preset duration, and the end time of the historical time period is before the current time. Step S352: Integrate several historical encoded data corresponding to each target subject into the initial feature vector D according to the corresponding feature fields to obtain the historical feature vector corresponding to each target subject; Step S353: Obtain the preset historical negative impact value corresponding to each target subject within the historical time period; Step S354: Take the historical feature vector corresponding to each target subject as the input sample, and the historical negative impact value corresponding to each target subject as the output label, and perform supervised learning training on the preset initial large language model to obtain the impact value determination model.

5. The method according to claim 4, characterized in that, Step S400 includes: Step S410: Identify any of the second target entities as the second key entity; Step S420: Perform feature encoding on several subject feature data corresponding to the second key subject to obtain a second feature vector F=(F1,F2,...,F...). a ,...,F b ); where a=1,2,...,b; b is the number of subject feature data of the second key subject; F a The feature data is obtained after feature encoding the a-th subject feature data of the second key subject; Step S430: Traverse the initial feature vector D. If D g The corresponding feature fields and F a If the corresponding feature fields are the same, then D in the initial feature vector D will be... g Replace with F a ; If D g If the corresponding feature field is different from the feature field corresponding to any feature data in the second feature vector F, then D in the initial feature vector D will be... g Set to null value to obtain the target feature vector corresponding to the second key subject; Step S440: Traverse the target feature vector corresponding to the second key subject and determine the feature data with null values ​​as missing feature data; Step S450: Determine the adjustment coefficient G corresponding to the second key subject: G = ((H1-I1)×J1+(H2-I2)×J2+(H3-I3)×J3) / (1-(I1+I2+I3)); Wherein, H1 is the sum of preset field weights of the feature fields with positive influence among the feature fields corresponding to the feature data of the initial feature vector D; H2 is the sum of preset field weights of the feature fields with neutral influence among the feature fields corresponding to the feature data of the initial feature vector D; H3 is the sum of preset field weights of the feature fields with negative influence among the feature fields corresponding to the feature data of the initial feature vector D; H1+H2+H3=1; I1 is the sum of preset field weights for the feature fields with a positive influence type among the feature fields corresponding to the missing feature data of the target feature vector corresponding to the second key subject; I2 is the sum of preset field weights for the feature fields with a neutral influence type among the feature fields corresponding to the missing feature data of the target feature vector corresponding to the second key subject; I3 is the sum of preset field weights for the feature fields with a negative influence type among the feature fields corresponding to the missing feature data of the target feature vector corresponding to the second key subject. J1 is the preset weight coefficient of the positive feature field; J2 is the preset weight coefficient of the neutral feature field; J3 is the preset weight coefficient of the negative feature field; J1 < 1; J2 = 1; J3 > 1.

6. The method according to claim 5, characterized in that, Step S500 includes: Step S510: Input the target feature vector corresponding to the second key subject into the influence value determination model to obtain the initial negative influence value M corresponding to the second key subject output by the influence value determination model; Step S520: Determine the negative impact value L=M×G corresponding to the second key subject.

7. The method according to claim 6, characterized in that, Step S600 includes: Step S610: Determine any of the aforementioned third target entities as the third key entity; Step S620: Among the preset number of key subjects, the key subjects that have the same subject type as the third key subject are determined as subjects of the same type; the key subject is a subject whose feature data completeness is greater than the first completeness threshold. Step S630: Traverse the feature fields of the main feature data of the same type of subject and the feature fields of the main feature data of the third key subject, and determine the feature fields that are common to both the same type of subject and the third key subject as common fields; Step S640: Compare the similarity of the subject feature data of the common fields corresponding to the same type of subject with the subject feature data of the common fields corresponding to the third key subject to obtain the feature similarity of the same type of subject. Step S650: If the feature similarity corresponding to the same type of subject is greater than the preset similarity threshold, then the same type of subject is determined as the target same type subject; Step S660: Obtain the preset negative impact value of each target subject of the same type corresponding to the third key subject, so as to obtain the impact value list N=(N1,N2,...,N...). c ,...,N d ); where c=1,2,...,d; d is the number of target entities of the same type corresponding to the third key entity; N c The negative impact value of the c-th target of the same type corresponding to the third key subject; Step S670: Obtain the feature similarity between the third key subject and each corresponding target subject of the same type, to obtain a feature similarity list T=(T1,T2,...,T...). c ,...,T d ); where T c The feature similarity between the third key subject and the corresponding c-th target subject of the same type; Step S680: Determine the negative impact value R corresponding to the third key entity, i.e., R=∑ d c=1 (T c / (∑ d c=1 T c ))×N c .

8. The method according to claim 7, characterized in that, Step S700 includes: Step S710: Obtain the preset negative building impact value V corresponding to the target building; Step S720: Determine the economic risk value of the target building, Z = Y1 × V + Y2 × Q; Where Q is the sum of the negative impact values ​​of the target entities; Y1 is the preset first risk value coefficient; Y2 is the preset second risk value coefficient; Y1+Y2=1; Y2=(S1 / Q)×W1+(S2 / Q)×W2+(S3 / Q)×W3; S1 is the sum of the negative impact values ​​corresponding to several first target entities; S2 is the sum of the negative impact values ​​corresponding to several second target entities; S3 is the sum of the negative impact values ​​corresponding to several third target entities; S1 + S2 + S3 = Q; W1 is the preset first influence value coefficient; W2 is the preset second influence value coefficient; W3 is the preset third influence value coefficient; 0 < W3 < W2 < W1 < 1.

9. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the method as described in any one of claims 1-8.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images