US-12626312-B2 - Construction project risk assessment and mitigation

US12626312B2US 12626312 B2US12626312 B2US 12626312B2US-12626312-B2

Abstract

A computing platform is configured to (i) receive data objects related to a construction project, (ii) add the data objects to a construction knowledge graph as nodes that are connected to other nodes representing other data objects, (iii) determine, via a machine-learning model trained using historic construction project data, a first risk score for a first data object, (iv) determine, via the machine-learning model, a second risk score for a second data object, where the second risk score is based on (a) the first risk score and (b) a degree of separation between the first data object and the second data object in the construction knowledge graph, (v) based on the second risk score, automatically generate a suggested action to be taken with respect to the first data object, and (vi) cause an indication of the suggested action to be displayed at a client station of a user associated with the construction project.

Inventors

Matt Man
David Starr
Joshua Nguyen
Hesham Younes
Andrew Dunn

Assignees

Procore Technologies, Inc.

Dates

Publication Date: 20260512
Application Date: 20220606

Claims (20)

1 . A computing platform comprising: a network interface; at least one processor; non-transitory computer-readable medium; and program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to: receive one or more data objects related to a first construction project; add the received one or more data objects to a construction knowledge graph as respective nodes that are connected, via respective edges, to one or more other respective nodes that represent one or more other data objects, wherein the construction knowledge graph includes at least one path along two or more edges and at least one node between a given pair of nodes that respectively represent different construction projects; determine, via one or more machine-learning models trained using historic construction project data, a first risk score for a first data object of the received one or more data objects; determine, via the one or more machine-learning models, a second risk score for a second data object that (i) corresponds to a construction service provider and (ii) is related to a second construction project different from the first construction project, wherein the second risk score is based at least in part on (i) the first risk score for the first data object and (ii) a degree of separation between a first node in the construction knowledge graph representing the first data object and a second node in the construction knowledge graph representing the second data object, wherein the degree of separation is based on a number of edges between the first node and the second node in the construction knowledge graph; determine that the second risk score for the second data object exceeds a threshold risk score associated with the second construction project; and based on determining that the second risk score for the second data object exceeds the threshold risk score, automatically disable a client station associated with the construction service provider from performing a given function via the computing platform.
2 . The computing platform of claim 1 , wherein at least one of the one or more other data objects is related to the second construction project.
3 . The computing platform of claim 1 , wherein the first data object comprises a notice of intent to lien, wherein the construction service provider is a recipient of the notice of intent to lien, and wherein the program instructions that are executable by the at least one processor such that the computing platform is configured to automatically disable the client station associated with the construction service provider from performing a given function via the computing platform comprise program instructions that are executable by the at least one processor such that the computing platform is configured to: automatically disable the client station from submitting bids for one or more new construction projects.
4 . The computing platform of claim 1 , wherein the one or more machine-learning models comprise a second one or more machine-learning models, and wherein the program instructions that are executable by the at least one processor such that the computing platform is configured to add the received one or more data objects to the construction knowledge graph as respective nodes that are connected, via respective edges, to one or more other respective nodes that represent the one or more other data objects comprise program instructions that are executable by the at least one processor such that the computing platform is configured to: determine, via a first one or more machine-learning models, a respective physical location within the first construction project to which each of the received one or more data objects is related; associate the received one or more data objects with the respective physical locations; and based on the respective physical locations, determine respective relationships for establishing respective edges between the received one or more data objects and the one or more other data objects.
5 . The computing platform of claim 1 , further comprising program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to: determine, via the one or more machine-learning models, respective second risk scores for at least some other data objects based at least in part on (i) the first risk score for the first data object, (ii) respective degree of separation between the first node in the construction knowledge graph representing the first data object and respective other nodes in the construction knowledge graph representing the at least some other data objects within the construction knowledge graph, and (iii) one or both of a type of the first data object or respective type of respective ones of the at least some other data objects.
6 . The computing platform of claim 1 , wherein the number of edges between the first node and the second node includes: at least a first edge between the first node and a third node, and at least a second edge between either (i) the second node and the third node or (ii) the second node and another different node.
7 . The computing platform of claim 1 , wherein: the first data object is added to the construction knowledge graph after the second data object; and the first risk score determined for the first data object causes the second risk score determined for the second data object to exceed the threshold risk score.
8 . A non-transitory computer-readable medium, wherein the non-transitory computer-readable medium is provisioned with program instructions that, when executed by at least one processor, cause a computing platform to: receive one or more data objects related to a first construction project; add the received one or more data objects to a construction knowledge graph as respective nodes that are connected to one or more other respective nodes that represent one or more other data objects, wherein the construction knowledge graph includes at least one path along two or more edges and at least one node between a given pair of nodes that respectively represent different construction projects; determine, via one or more machine-learning models trained using historic construction project data, a first risk score for a first data object of the received one or more data objects; determine, via the one or more machine-learning models, a second risk score for a second data object that (i) corresponds to a construction service provider and (ii) is related to a second construction project different from the first construction project, wherein the second risk score is based at least in part on (i) the first risk score for the first data object and (ii) a degree of separation between a first node in the construction knowledge graph representing the first data object and a second node in the construction knowledge graph representing the second data object, wherein the degree of separation is based on a number of edges between the first node and the second node in the construction knowledge graph; determine that the second risk score for the second data object exceeds a threshold risk score associated with the second construction project; and based on determining that the second risk score for the second data object exceeds the threshold risk score, automatically disable a client station associated with the construction service provider from performing a given function via the computing platform.
9 . The non-transitory computer-readable medium of claim 8 , wherein at least one of the one or more other data objects is related to the second construction project.
10 . The non-transitory computer-readable medium of claim 8 , wherein the first data object comprises a notice of intent to lien, wherein the construction service provider is a recipient of the notice of intent to lien, and wherein the program instructions that, when executed by the at least one processor, cause the computing platform to automatically disable the client station associated with the construction service provider from performing a given function via the computing platform comprise program instructions that, when executed by the at least one processor, cause the computing platform to: automatically disable the client station from submitting bids for one or more new construction projects.
11 . The non-transitory computer-readable medium of claim 8 , wherein the one or more machine-learning models comprise a second one or more machine-learning models, and wherein the program instructions that, when executed by the at least one processor, cause the computing platform to add the received one or more data objects to the construction knowledge graph as respective nodes that are connected to one or more other respective nodes that represent the one or more other data objects comprise program instructions that, when executed by the at least one processor, cause the computing platform to: determine, via a first one or more machine-learning models, a respective physical location within the first construction project to which each of the received one or more data objects is related; associate the received one or more data objects with the respective physical locations; and based on the respective physical locations, determine respective relationships for establishing respective edges between the received one or more data objects and the one or more other data objects.
12 . The non-transitory computer-readable medium of claim 8 , further comprising program instructions that when executed by the at least one processor, cause the computing platform to: determine, via the one or more machine-learning models, respective second risk scores for at least some other data objects based at least in part on (i) the first risk score for the first data object, (ii) respective degree of separation between the first node in the construction knowledge graph representing the first data object and respective other nodes in the construction knowledge graph representing the at least some other data objects within the construction knowledge graph, and (iii) one or both of a type of the first data object or respective type of respective ones of the at least some other data objects.
13 . The non-transitory computer-readable medium of claim 8 , wherein the number of edges between the first node and the second node includes: at least a first edge between the first node and a third node, and at least a second edge between either (i) the second node and the third node or (ii) the second node and another different node.
14 . The non-transitory computer-readable medium of claim 8 , wherein: the first data object is added to the construction knowledge graph after the second data object; and the first risk score determined for the first data object causes the second risk score determined for the second data object to exceed the threshold risk score.
15 . A method carried out by a computing platform, the method comprising: receiving one or more data objects related to a first construction project; adding the received one or more data objects to a construction knowledge graph as respective nodes that are connected, via respective edges, to one or more other respective nodes that represent one or more other data objects, wherein the construction knowledge graph includes at least one path along two or more edges and at least one node between a given pair of nodes that respectively represent different construction projects; determining, via one or more machine-learning models trained using historic construction project data, a first risk score for a first data object of the received one or more data objects; determining, via the one or more machine-learning models, a second risk score for a second data object that (i) corresponds to a construction service provider and (ii) is related to a second construction project different from the first construction project, wherein the second risk score is based at least in part on (i) the first risk score for the first data object and (ii) a degree of separation between a first node in the construction knowledge graph representing the first data object and a second node in the construction knowledge graph representing the second data object, wherein the degree of separation is based on a number of edges between the first node and the second node in the construction knowledge graph; determining that the second risk score for the second data object exceeds a threshold risk score associated with the second construction project; and based on determining that the second risk score for the second data object exceeds the threshold risk score, automatically disabling a client station associated with the construction service provider from performing a given function via the computing platform.
16 . The method of claim 15 , wherein the one or more machine-learning models comprise a second one or more machine-learning models, and wherein causing the computing platform to add the received one or more data objects to the construction knowledge graph as respective nodes that are connected to one or more other respective nodes that represent the one or more other data objects comprises: determining, via a first one or more machine-learning models, a respective physical location within the first construction project to which each of the received one or more data objects is related; associating the received one or more data objects with the respective physical locations; and based on the respective physical locations, determining respective relationships for establishing respective edges between the received one or more data objects and the one or more other data objects.
17 . The method of claim 15 , wherein the first data object comprises a notice of intent to lien, wherein the construction service provider is a recipient of the notice of intent to lien, and wherein automatically disabling the client station associated with the construction service provider from performing a given function via the computing platform comprises: automatically disabling the client station from submitting bids for one or more new construction projects.
18 . The method of claim 15 , further comprising: determining, via the one or more machine-learning models, respective second risk scores for at least some other data objects based at least in part on (i) the first risk score for the first data object, (ii) respective degree of separation between the first node in the construction knowledge graph representing the first data object and respective other nodes in the construction knowledge graph representing the at least some other data objects within the construction knowledge graph, and (iii) one or both of a type of the first data object or respective type of respective ones of the at least some other data objects.
19 . The method of claim 15 , wherein the number of edges between the first node and the second node includes: at least a first edge between the first node and a third node, and at least a second edge between either (i) the second node and the third node or (ii) the second node and another different node.
20 . The method of claim 15 , wherein: the first data object is added to the construction knowledge graph after the second data object; and the first risk score determined for the first data object causes the second risk score determined for the second data object to exceed the threshold risk score.

Description

BACKGROUND Software applications are used on a regular basis to perform and manage tasks in users' personal and professional capacities. As some examples, software applications may assist users with managing tasks related to email communications, customer relationship management, billing and payroll processing, human resources management, and construction project design and management. Many other types of software applications exist. Software applications handle a large volume of information and can be complex. It is therefore desirable for software applications to provide sophisticated features and tools which can enhance a user's ability to interact with the software application, obtain desired information, and improve the overall user experience. Thus, any tool that can improve a user's interaction with a software application is desired. Overview A construction project often involves the creation of an immense amount of information, involving a large number of different stakeholders that may be creators or consumers—often both—of such information. At the inception of a construction project an owner may coordinate with planners, architects, and engineers in a planning and design phase to define the scope and develop the design for the project (e.g., a new building). This phase may take months or years depending on the size of the project, and may result in the creation of project-specific design specifications, architectural plans, engineering plans, etc. These various different plans generally comprise visual representations of the construction project that visually communicate information about the construction project, such as how to assemble or construct different parts of the project. Such visual representations tend to take one of at least two different forms. One form may be a two-dimensional technical drawing in which two-dimensional line segments of the drawing represent certain physical elements of the construction project like walls and ducts. In this respect, a two-dimensional technical drawing could be embodied either in paper form or in a computerized form, such as an image file (e.g., a PDF, JPEG, etc.), or via software for viewing a two-dimensional drawing model. As another possibility, a construction project's design plans may be represented by a three-dimensional model that is embodied in a computerized form, such as in a building information model (BIM) file, with three-dimensional meshes visually representing the physical elements of the construction project (e.g., walls, ducts, etc.). Specialized software is configured to edit and access the BIM file and render a three-dimensional view of the construction project from one or more perspectives. Following the planning and design phase, a preconstruction phase may introduce additional stakeholders such as project managers, general contractors, and subcontractors, each of whom may work with estimators to prepare cost estimates for the project in order to prepare corresponding bids (e.g., bids to perform work on a certain portion of the project). During this phase, stakeholders may also go through one or more pre-qualification processes to evaluate their financial stability, insurance information, prior work history, safety violations, etc. In turn, the owner may award contracts to construct the project, and these contracts may contain additional terms and expectations regarding the project's construction, including a project budget and contingencies. Thereafter, the construction managers and/or contractors may generate still further information for the project, including additional bidding and selection of subcontractors within different trades (e.g., concrete, masonry, carpentry, plumbing, etc.), risk management plans, safety plans, and work breakdown structures, which include a listing of activities (e.g., pouring a foundation, installing a door, etc.) and the tasks required to complete each activity. In this regard, a typical construction project may include thousands of such activities that may need to be broken down in order to create a clear roadmap for the construction process. Relatedly, a scheduler may develop a project schedule that orders all of the activities in the work breakdown structure(s) and establishes the timing of construction. For instance, a project schedule may establish a critical path of activities that dictates the longest time to project completion, may identify activities that can be performed in parallel, and may include milestones for certain activities to assist project managers with assessing whether a project is on schedule. The construction phase may follow, sometimes referred to as the execution phase. During this phase, contractors and subcontractors order and take delivery of materials, update their individual budgets, establish labor management plans and monthly, weekly, or daily schedules, and generally construct the project. Once construction is underway, a project manager or general contractor may