Project document risk detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a project document risk detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-reviewed project document corresponding to a to-be-reviewed project, and determining the to-be-reviewed content of the to-be-reviewed project document according to the document type; wherein the document type is a project planning document or a partner response document; determining at least one risk point detection rule corresponding to the to-be-reviewed content, and performing risk point detection on the to-be-reviewed content based on each risk point detection rule; and generating a risk detection report corresponding to the to-be-examined item document based on all risk point detection results of the to-be-examined content. In order to solve the problems that in the prior art, the detection efficiency is low and errors are prone to occurring when the associated document of the to-be-examined item is detected based on a manual mode, by setting the risk point detection rules corresponding to all stages, the to-be-examined item document associated with the to-be-examined item is automatically detected, and the effect of obtaining an accurate risk detection result is achieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and storage medium for risk detection of project documents. Background Technology

[0002] When a company's business projects require the supply of project resources, it usually needs to select a legal and compliant target partner from multiple potential partners.

[0003] In this process, to ensure the compliance and legality of the business project itself and the target partners, it is necessary to conduct a risk review of the project documents associated with the business project to determine whether there are any risks in the project documents, and thus whether there are any risks in the business project itself. Currently, project document reviews are mostly conducted manually, but this method is not only inefficient but also prone to errors.

[0004] To address the above issues, the risk detection methods for project documentation need to be improved. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for risk detection of project documents, in order to solve the problems of low detection efficiency and error-proneness when detecting related documents of a project to be reviewed using manual methods in the prior art.

[0006] In a first aspect, embodiments of the present invention provide a risk detection method for project documents, including:

[0007] Obtain the project documents corresponding to the project to be reviewed, and determine the content to be reviewed in the project documents according to the document type; wherein, the document type is a project planning document or a partner response document;

[0008] Determine at least one risk point detection rule corresponding to the content to be reviewed, and perform risk point detection on the content to be reviewed based on each risk point detection rule;

[0009] Based on the detection results of all risk points in the content to be reviewed, a risk detection report corresponding to the document to be reviewed is generated.

[0010] Secondly, embodiments of the present invention also provide a risk detection device for project documents, comprising:

[0011] The module for determining the content to be reviewed is used to obtain the project document corresponding to the project to be reviewed, and to determine the content to be reviewed in the project document according to the document type; wherein, the document type is a project planning document or a partner response document;

[0012] The risk point detection module is used to determine at least one risk point detection rule corresponding to the content to be reviewed, and to perform risk point detection on the content to be reviewed based on each risk point detection rule;

[0013] The detection report generation module is used to generate a risk detection report corresponding to the project document to be reviewed, based on the detection results of all risk points of the content to be reviewed.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the risk detection method for project documents according to any embodiment of the present invention.

[0018] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the risk detection method for project documents described in any embodiment of the present invention.

[0019] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the risk detection method for project documents as described in any of the embodiments of the present invention.

[0020] The technical solution of this invention involves obtaining the project document corresponding to the project to be reviewed, and determining the content to be reviewed based on the document type; wherein the document type is a project planning document or a partner response document; determining at least one risk point detection rule corresponding to the content to be reviewed, and performing risk point detection on the content to be reviewed based on each risk point detection rule; and generating a risk detection report corresponding to the project document to be reviewed based on all risk point detection results of the content to be reviewed. In this technical solution, before and after obtaining project resources corresponding to the project to be reviewed from a partner company, the enterprise needs to perform risk detection on the project documents associated with the project to be reviewed. Based on this, this technical solution sets risk point detection rules corresponding to each review stage according to the different review stages corresponding to the project documents to be reviewed, and performs detection on the project documents to be reviewed at the corresponding stages to ensure the reasonableness and compliance of the project documents to be reviewed. This solves the problems of low detection efficiency and error-proneness when manually detecting associated documents of the project to be reviewed in the prior art. By setting risk point detection rules corresponding to each stage, it achieves automated detection of the project documents associated with the project to be reviewed, resulting in accurate risk detection results. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention 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 the content of the embodiments of the present invention and these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a risk detection method for project documents provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a risk detection method for project documents provided in Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a risk detection device for project documents provided in Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the risk detection method for project documents according to embodiments of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention. The acquisition, transmission, storage, use, and processing of data in the technical solutions of this application comply with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, certain software, components, or models and other existing solutions in the industry may be mentioned. These should be considered as exemplary, and their purpose is only to illustrate the feasibility of implementing the technical solutions of this application, but it does not mean that the applicant has or necessarily used such solutions.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0028] Before elaborating on this technical solution in detail, let's briefly introduce its application scenarios to help us understand it more clearly.

[0029] In the field of enterprise project collaboration and resource acquisition management, ensuring the standardization and legality of project planning documents and partner response documents is a crucial step in preventing operational risks and maintaining a fair and orderly competitive environment. With the deepening of enterprise digital transformation, project collaboration activities are becoming more frequent, large-scale, and diversified, thus placing higher demands on the efficiency, accuracy, and comprehensiveness of the review of project-related documents.

[0030] Based on this, this technical solution proposes a risk detection method for project documents, aiming to conduct a standardized review of key documents before and after project collaboration to ensure the legality and compliance of project documents. This method uses intelligent means to perform multi-dimensional analysis of document content, identify potential risk points, and provide a reliable basis for project decision-making.

[0031] Example 1

[0032] Figure 1The flowchart of a risk detection method for project documents is provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where enterprises select resource supply partners and conduct risk detection on project documents at different stages of business projects, and promptly avoid risks in business projects based on the risk detection results. This method can be executed by a risk detection device for project documents, which can be implemented in hardware and / or software. The risk detection device for project documents can be configured in a computing device capable of executing the risk detection method for project documents.

[0033] like Figure 1 As shown, the method includes:

[0034] S110. If the project document to be reviewed is a project planning document, obtain the project document to be reviewed corresponding to the project to be reviewed, and determine the content to be reviewed in the project document according to the document type.

[0035] The "projects under review" refer to all procurement activities that require compliance review. The resource acquisition phase of these projects must meet regulatory requirements to ensure legality and fairness. If the project document under review is a project planning document, it refers to the resource requirements document that needs risk review before project cooperation. The document type refers to the project document type corresponding to different stages of the project before and after cooperation. For example, before cooperation, the document type is the project planning document; after cooperation, it is the partner's response document. In practical applications, if the review stage is before cooperation, the content to be reviewed refers to the project requirement information associated with at least one resource requirement item in the project under review, as well as the source text of the constraints of the project requirement information. For example, the content to be reviewed could be the partner's qualifications, project investment attributes, and the project cooperation period.

[0036] In a specific example, when a company needs to collaborate with other companies to acquire resources, it needs to initiate a project in advance, identify the projects to be reviewed, and prepare project documents in advance based on the project requirements before collaborating on the project. To ensure that the documents to be reviewed meet the project requirements and are legal and compliant, the specific content of the project documents needs to be reviewed.

[0037] It should be noted that the project documents to be reviewed may include text data, tabular data, and image data. For example, the text data mainly includes resource planning schemes, resource requirement approval documents, and resource requirement documents related to the project collaboration process. The tabular data mainly includes resource acquisition requirements, resource budgets, and resource constraints. The image data mainly includes qualification certificates of project partners, partner approval information, and approval results. Agent technology is used to perform text recognition on the content of the project documents to be reviewed, extracting all text data to obtain a project document containing only text data. This document is then intelligently segmented to obtain at least one piece of content to be reviewed.

[0038] Optionally, the project document to be reviewed is a project planning document. The content to be reviewed in the project document to be reviewed is determined according to the document type, including: obtaining the element review specifications corresponding to the project document to be reviewed, and performing semantic analysis on the element review specifications to obtain at least one text to be used; and locating the content to be reviewed in the project document to be reviewed corresponding to each text to be used based on the key elements in each text to be used.

[0039] The "Element Review Standards" refer to the set of rules used to conduct compliance reviews of key elements in project collaboration, such as resource requirements, partner qualifications, and budget constraints. The "Text to be Used" refers to the key text extracted from the Element Review Standards that corresponds to the rules. Key elements are the keywords contained in the text to be used.

[0040] Building upon the above examples, we obtain the latest element review guidelines and extract at least one text to be used from them using semantic analysis. Taking "bidding method" and "number of experts" as key elements in the text to be used as examples, we can find the source text corresponding to "bidding method" in the project document to be reviewed as the content to be reviewed. This content could be something like, "The bidding method for the project to be reviewed is open bidding." Similarly, we can find the source text corresponding to "number of experts" in the project document to be reviewed as the content to be reviewed. For example, this content could be something like, "The total number of review users for the project to be reviewed is 10, of which at least 3 are experts, and the number of experts must be an odd number."

[0041] It is understood that the key elements mentioned in this technical solution generally refer to keywords. However, when locating the content to be reviewed in the project document based on the key elements, it is possible to directly compare and locate the content based on the keywords, or to use source text content with semantic similarity to the keywords in the content to be reviewed as the content to be reviewed.

[0042] S120. Determine at least one risk point detection rule corresponding to the content to be reviewed, and perform risk point detection on the content to be reviewed based on each risk point detection rule.

[0043] Among them, the risk point detection rules refer to the risk detection conditions extracted from the element review specifications.

[0044] Optionally, at least one risk point detection rule corresponding to the content to be reviewed is determined, and risk point detection is performed on the content to be reviewed based on each risk point detection rule, including: performing thought chain deduction on each text to be used to obtain the risk point detection rule corresponding to each text to be used; and performing risk point detection on the corresponding content to be reviewed according to the risk point detection rule corresponding to each text to be used.

[0045] Before conducting risk reviews on the content to be reviewed, a thought chain deduction model can be pre-built, and historical training samples can be obtained to train the thought chain deduction model. Then, based on the trained thought chain deduction model, at least one text to be used in the element review specifications can be analyzed to obtain at least one risk point detection rule.

[0046] For example, historical training samples are input into the thought chain derivation model for training, guiding the model to reason step by step, thereby training and guiding the semantic compliance and logical consistency of the thought chain derivation model. Based on this, the element review specifications are input into the thought chain derivation model to output at least one risk point detection rule corresponding to the content to be reviewed. For example, the risk point detection rule could be: "First, determine whether the project resource requirements are clearly stated → then check whether the qualification conditions contain exclusive clauses → finally verify whether the scoring criteria are quantifiable and operable."

[0047] S130. Based on the detection results of all risk points in the content to be reviewed, generate a risk detection report corresponding to the project document to be reviewed.

[0048] Building upon the above example, if the risk detection rules include 33 items, then risk detection is performed sequentially on the corresponding content in the project document to be reviewed based on these 33 risk detection rules, yielding the risk detection results. For instance, if the risk detection rule is "determine whether the number of experts in the project to be reviewed exceeds 5 and is odd," then by detecting the corresponding content to be reviewed, if the number of experts recorded in the content to be reviewed is 3, then the risk detection result for this part of the content to be reviewed is considered unsuccessful. Based on this, a risk detection report corresponding to the risk detection results for all the content to be reviewed is generated, along with a report for the project document to be reviewed.

[0049] Understandably, the risk assessment report can also indicate the necessity or risk level of each part of the content to be reviewed, so that the reviewing user can intuitively see the risk information and risk level in the project document to be reviewed, and determine whether the project document to be reviewed needs to be revised.

[0050] The technical solution of this invention involves obtaining the project document to be reviewed if it is a project planning document prepared before cooperation between the enterprise and its partners. The review process includes: determining the content to be reviewed based on the document type; identifying at least one risk point detection rule corresponding to the content to be reviewed; performing risk point detection on the content to be reviewed based on each risk point detection rule; and generating a risk detection report corresponding to the project document to be reviewed based on all risk point detection results. In this technical solution, before cooperation between the enterprise and its partners, a project document to be reviewed needs to be prepared in advance. To ensure the legality and compliance of the project document, the element review specifications are retrieved, and semantic analysis is performed on these specifications to obtain at least one text to be used. A thought chain deduction is then performed on the text to be used to obtain at least one risk point detection rule corresponding to the project document to be reviewed. Simultaneously, the corresponding content to be reviewed in the project is located based on the key elements in the text to be used, and risk detection is performed on the corresponding content to be reviewed based on each risk point detection rule to obtain risk point detection results. This invention addresses the problems of low detection efficiency and susceptibility to errors in existing technologies that rely on manual risk assessment of project documents before a resource supply relationship is established between a company and its partners. It enables the accurate detection of risk points in project documents before the establishment of such a relationship, thereby ensuring the legality and compliance of the project documents under review.

[0051] Example 2

[0052] Figure 2 The flowchart below shows a risk detection method for project documents provided in Embodiment 2 of the present invention. Optionally, if the project document to be reviewed is a response document from a partner, the project document to be reviewed corresponding to the project to be reviewed is obtained, and the content to be reviewed in the project document to be reviewed is determined according to the document type. At least one risk point detection rule corresponding to the content to be reviewed is determined, and risk point detection is performed on the content to be reviewed based on each risk point detection rule. Based on all the risk point detection results of the content to be reviewed, a risk detection report corresponding to the project document to be reviewed is generated.

[0053] like Figure 2 As shown, the method includes:

[0054] S210. If the project document to be reviewed is a response document from a partner, obtain the project document to be reviewed corresponding to the project to be reviewed, and determine the content to be reviewed in the project document according to the document type.

[0055] Optionally, if the project document to be reviewed is a partner response document, and there are multiple partner response documents, then the content to be reviewed is at least one partner entity information contained in the partner response document. The content to be reviewed for the project document is determined according to the document type, including: for each project document to be reviewed, entity extraction is performed on the project document to be reviewed to obtain at least one entity to be used; based on the detailed data corresponding to each entity to be used in the project document to be reviewed, the content to be reviewed corresponding to the project document to be reviewed is generated.

[0056] The collaborating party information refers to the identifying and contact data of legal entities and their affiliates directly related to the project under review. This includes, but is not limited to, legally and business-essential data such as company qualification information, authorized representative information, contact channel information, and information on related personnel involved in project execution. For example, collaborating party information may include the collaborating party's company name, legal representative, contact information, address, project bidding users, contact information and email addresses of project bidding users, and employee information.

[0057] In practical applications, when enterprises need to collaborate with other companies to acquire project resources, there are usually multiple bidders. To verify the authenticity and legality of each bidder, the correlation between their entity information can be used to determine whether the bidding process was conducted legally and compliantly. The response documents provided by each bidder (i.e., the project documents to be reviewed) generally need to record the entity information of the corresponding enterprise. Therefore, by extracting entities from each project document to be reviewed, at least one entity to be used can be obtained. The detailed data corresponding to each entity to be used can then be associated with that entity to obtain the dataset to be reviewed (i.e., the content to be reviewed) corresponding to each bidder.

[0058] Based on the above, a target knowledge graph is constructed based on at least one entity to be used in each project document to be reviewed and the detailed data corresponding to each entity to be used (i.e., the content to be reviewed). The target knowledge graph is then visualized so that review users can intuitively see whether there are any relationships between the cooperating responders through the target knowledge graph.

[0059] By exemplarily employing Neo4J technology, entity extraction is performed based on the response documents of potential partners to obtain at least one entity to be used. For instance, this entity could be a multi-layered enterprise bidding information knowledge graph comprising three main entities: bidding users, tendering users, and external related enterprises. This effectively connects scattered information points to form a network structure that comprehensively reflects the characteristics of enterprise bidding behavior, thus obtaining the target knowledge graph. Furthermore, visualization technology is used to visualize the target knowledge graph, improving readability and comprehensibility. This assists review users in quickly understanding the complex relationships between potential partners and rapidly discovering their connections, providing strong support for risk assessment.

[0060] S220. Determine at least one risk point detection rule corresponding to the content to be reviewed, and perform risk point detection on the content to be reviewed based on each risk point detection rule.

[0061] Optionally, at least one risk point detection rule corresponding to the content to be reviewed is determined, and risk point detection is performed on the content to be reviewed based on each risk point detection rule, including: determining the risk contribution of each partner entity information for at least one partner entity information in the content to be reviewed; setting corresponding explicit risk detection rules and / or implicit risk detection rules for each partner entity information according to the risk contribution; and performing risk point detection on the corresponding partner entity information based on the explicit risk detection rules and / or implicit risk detection rules.

[0062] Among them, explicit risk detection rules refer to the detection conditions used to detect whether there is directly related information about potential partners.

[0063] For example, explicit risk detection rules are used to detect identical entity information, such as legal person information, company name, or email address, between partners A and B. Implicit risk detection rules, on the other hand, are used to detect whether there are indirectly related entity information among potential partners. For instance, given partners A, B, and C, if detection determines that there is a relationship between the entity information of partners A and B, no relationship between the entity information of partners A and C, but a relationship between the entity information of partners B and C, then implicit risk detection rules can be used to detect whether there is a relationship between the entity information of partners A and C.

[0064] In other words, by identifying the main information of potential partners, if identical main information is detected between partners, a significant relationship is determined between the corresponding partners. If a significant relationship is detected between two partners and a third partner, a latent relationship is determined between the two partners.

[0065] The advantage of this setup is that by identifying and analyzing the corresponding entity information of all potential partners, it is possible to quickly detect whether there are significant or implicit relationships between the partners. This not only improves the efficiency of risk identification but also enhances the accuracy of identifying the entity risks of the partners.

[0066] S230. Based on the detection results of all risk points in the content to be reviewed, generate a risk detection report corresponding to the project document to be reviewed.

[0067] Optionally, after generating a risk detection report corresponding to the project document to be reviewed based on the detection results of all risk points of the content to be reviewed, the process may further include: identifying the target partner corresponding to the project to be reviewed; obtaining the supply performance data of the target partner in at least one evaluation indicator, and determining the evaluation attributes to be used corresponding to each supply performance data; and performing a weighted average of the weights to be used and the evaluation attributes to be used corresponding to all evaluation indicators to obtain the target evaluation attributes corresponding to the target partner.

[0068] The target partner refers to an independent and compliant partner selected by the company for the project under review. Evaluation indicators are metrics used to assess the target partner's performance during the project resource supply phase. These indicators may include the supply cycle of project resources, delivery timeliness, quality of project resources, and the reasonableness of the value attributes of the project resources proposed by the target partner to the company. Evaluation attributes to be used refer to the evaluation attributes resulting from the assessment of the target partner's actual performance on the evaluation indicators. Target evaluation attributes are used to systematically quantify the target partner's performance during the project supply phase, based on a comprehensive evaluation of all evaluation indicators.

[0069] For example, an evaluation system corresponding to the project to be reviewed is established in advance, and the evaluation system includes at least one evaluation indicator. After the target partner is determined, the performance of the target partner in the performance process is evaluated based on each evaluation indicator to obtain the evaluation attributes to be used under the corresponding evaluation indicators. In order to improve the rationality of the evaluation of the target partner, the target evaluation attributes are obtained by weighted averaging of the evaluation attributes to be used and the weights to be used for each evaluation indicator.

[0070] The technical solution of this invention involves obtaining the project document to be reviewed if it is a response document from a partner during the establishment of a cooperative relationship between the enterprise and the partner. The review process includes: obtaining the project document to be reviewed and determining the content to be reviewed based on the document type; determining at least one risk point detection rule corresponding to the content to be reviewed and performing risk point detection on the content to be reviewed based on each risk point detection rule; and generating a risk detection report corresponding to the project document to be reviewed based on all risk point detection results of the content to be reviewed. In this technical solution, during the establishment of a cooperative relationship between the enterprise and potential partners, multiple potential partners need to submit partner response documents to the enterprise. To verify the standardization and independence of the relationship between the potential partners, the entity identification information of each potential partner needs to be extracted from the partner response documents, and the presence of explicit or implicit association characteristics between these entity identification information is detected. If association characteristics are detected, it is determined that there is entity risk between potential partners; if no association characteristics are detected, it is confirmed that each potential partner meets the independence requirements, and the enterprise can then establish a resource collaboration relationship with the corresponding potential partner. This technology solves the problem that existing technologies, which rely on manual methods, are not easy to identify the correlation characteristics between potential partners. It enables the automatic identification of whether there are correlation characteristics between potential partners based on the response documents provided by the potential partners, thereby ensuring the independence and compliance of potential partners who supply project resources to enterprises.

[0071] Example 3

[0072] Figure 3 This is a schematic diagram of a risk detection device for project documents provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a content to be reviewed determination module 310, a risk point detection module 320, and a detection report generation module 330.

[0073] The module 310 for determining the content to be reviewed is used to obtain the project document corresponding to the project to be reviewed, and to determine the content to be reviewed in the project document according to the document type; wherein the document type is a project planning document or a partner response document.

[0074] The risk point detection module 320 is used to determine at least one risk point detection rule corresponding to the content to be reviewed, and to perform risk point detection on the content to be reviewed based on each risk point detection rule;

[0075] The detection report generation module 330 is used to generate a risk detection report corresponding to the project document to be reviewed, based on the detection results of all risk points in the content to be reviewed.

[0076] The technical solution of this invention involves obtaining the project document corresponding to the project to be reviewed, and determining the content to be reviewed based on the document type; wherein the document type is a project planning document or a partner response document; determining at least one risk point detection rule corresponding to the content to be reviewed, and performing risk point detection on the content to be reviewed based on each risk point detection rule; and generating a risk detection report corresponding to the project document to be reviewed based on all risk point detection results of the content to be reviewed. In this technical solution, before and after obtaining project resources corresponding to the project to be reviewed from a partner company, the enterprise needs to perform risk detection on the project documents associated with the project to be reviewed. Based on this, this technical solution sets risk point detection rules corresponding to each review stage according to the different review stages corresponding to the project documents to be reviewed, and performs detection on the project documents to be reviewed at the corresponding stages to ensure the reasonableness and compliance of the project documents to be reviewed. This solves the problems of low detection efficiency and error-proneness when manually detecting associated documents of the project to be reviewed in the prior art. By setting risk point detection rules corresponding to each stage, it achieves automated detection of the project documents associated with the project to be reviewed, resulting in accurate risk detection results.

[0077] Optionally, the module for determining the content to be reviewed includes: a unit for determining the text to be used, which is used to obtain the element review specifications corresponding to the project document to be reviewed if the project document to be reviewed is a project planning document, and to perform semantic analysis on the element review specifications to obtain at least one text to be used;

[0078] The first content determination unit is used to locate the content to be reviewed in the project document to be reviewed, based on the key elements in each text to be used.

[0079] Optionally, the risk point detection module includes: a first detection rule determination unit, used to perform thought chain deduction on each text to be used to obtain the risk point detection rule corresponding to each text to be used;

[0080] The first risk detection unit is used to detect risk points in the corresponding content to be reviewed according to the risk point detection rules for each text to be used.

[0081] Optionally, the module for determining the content to be reviewed includes: a unit for determining entities to be used, which is used when the project document to be reviewed is a response document from a partner, and there are multiple response documents from partners. For each project document to be reviewed, entity extraction is performed on the project document to be reviewed to obtain at least one entity to be used.

[0082] The second content determination unit is used to generate the content to be reviewed corresponding to the project document to be reviewed, based on the detailed data of each entity to be used in the project document to be reviewed.

[0083] Optionally, the risk point detection module includes: a risk contribution determination unit, used to determine the risk contribution of each partner entity information for at least one partner entity information in the content to be reviewed;

[0084] The second detection rule determination unit is used to set corresponding explicit risk detection rules and / or implicit risk detection rules for each partner entity information based on the risk contribution level.

[0085] The second risk detection unit is used to detect risk points in the relevant partner entity information based on explicit risk detection rules and / or implicit risk detection rules.

[0086] Optionally, the risk detection device for project documents is also used to construct a target knowledge graph based on at least one entity to be used in each project document to be reviewed and the detailed data corresponding to each entity to be used, and to visualize the target knowledge graph.

[0087] Optionally, the risk detection device for project documents may also include: a target partner determination module, used to determine the target partners corresponding to the project to be reviewed;

[0088] The module for determining the evaluation attributes to be used is used to obtain the supply performance data of the target partner in at least one evaluation indicator and determine the evaluation attributes to be used corresponding to each supply performance data.

[0089] The target evaluation attribute determination module is used to perform weighted average processing on the weights and evaluation attributes to be used for all evaluation indicators to obtain the target evaluation attributes corresponding to the target partners.

[0090] The project document risk detection device provided in this embodiment of the invention can execute the project document risk detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0091] Example 4

[0092] Figure 4 A schematic diagram of the structure of an electronic device 10 according to an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0093] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0094] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0095] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as risk detection methods for project documents.

[0096] In some embodiments, the risk detection method for project documents may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the risk detection method for project documents described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the risk detection method for project documents by any other suitable means (e.g., by means of firmware).

[0097] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] Computer programs used to implement the risk detection method for project documents of this invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0099] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0101] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0102] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0103] Example 5

[0104] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the risk detection method for project documents as provided in any embodiment of this application.

[0105] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0107] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A risk detection method for project documents, characterized in that, include: Obtain the project documents corresponding to the project to be reviewed, and determine the content to be reviewed in the project documents according to the document type; wherein, the document type is a project planning document or a partner response document; Determine at least one risk point detection rule corresponding to the content to be reviewed, and perform risk point detection on the content to be reviewed based on each risk point detection rule; Based on the detection results of all risk points in the content to be reviewed, a risk detection report corresponding to the document to be reviewed is generated.

2. The method according to claim 1, characterized in that, The project document to be reviewed is the project planning document. Determining the content to be reviewed in the project document based on the document type includes: Obtain the element review specifications corresponding to the project document to be reviewed, and perform semantic analysis on the element review specifications to obtain at least one text to be used; Based on the key elements in each text to be used, locate the content to be reviewed corresponding to each text to be used in the project to be reviewed.

3. The method according to claim 2, characterized in that, The step of determining at least one risk point detection rule corresponding to the content to be reviewed, and performing risk point detection on the content to be reviewed based on each risk point detection rule, includes: By performing thought chain deduction on each text to be used, the risk point detection rules corresponding to each text to be used are obtained; Risk points are detected in the corresponding content to be reviewed based on the risk point detection rules for each text to be used.

4. The method according to claim 1, characterized in that, The project document to be reviewed is the response document of the partner, and there are multiple partner response documents. The content to be reviewed is at least one partner entity information contained in the partner response document. Determining the content to be reviewed of the project document according to the document type includes: For each project document to be reviewed, entity extraction is performed to obtain at least one entity to be used. Based on the detailed data corresponding to each entity to be used in the project document to be reviewed, the content to be reviewed corresponding to the project document to be reviewed is generated.

5. The method according to claim 4, characterized in that, The step of determining at least one risk point detection rule corresponding to the content to be reviewed, and performing risk point detection on the content to be reviewed based on each risk point detection rule, includes: For at least one partner entity information in the content to be reviewed, determine the risk contribution level corresponding to each partner entity information. Based on the risk contribution level, set corresponding explicit risk detection rules and / or implicit risk detection rules for each partner entity information; Based on the explicit risk detection rules and / or the implicit risk detection rules, risk points are detected in the relevant partner entity information.

6. The method according to claim 4, characterized in that, Also includes: Based on at least one entity to be used in each project document to be reviewed and the detailed data corresponding to each entity to be used, a target knowledge graph is constructed, and the target knowledge graph is visualized.

7. The method according to claim 1, characterized in that, After generating a risk detection report corresponding to the project document to be reviewed based on the detection results of all risk points in the content to be reviewed, the process further includes: Identify the target partners corresponding to the projects under review; Obtain the supply fulfillment data of the target partner in at least one evaluation indicator, and determine the evaluation attributes to be used for each supply fulfillment data. The weighted average of the weights and evaluation attributes to be used for all the evaluation indicators is used to obtain the target evaluation attribute corresponding to the target partner.

8. A risk detection device for project documents, characterized in that, include: The module for determining the content to be reviewed is used to obtain the project document corresponding to the project to be reviewed, and to determine the content to be reviewed in the project document according to the document type; wherein, the document type is a project planning document or a partner response document; The risk point detection module is used to determine at least one risk point detection rule corresponding to the content to be reviewed, and to perform risk point detection on the content to be reviewed based on each risk point detection rule; The detection report generation module is used to generate a risk detection report corresponding to the project document to be reviewed, based on the detection results of all risk points of the content to be reviewed.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the risk detection method for project documents according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the risk detection method for project documents according to any one of claims 1-7.

Images