A resource scheduling method, apparatus, computer device, and storage medium
By acquiring and assessing the basic, resource, and network information of small and medium-sized technology enterprises, generating profile information, and filtering it, the problem of low assessment accuracy of traditional resource scheduling platforms is solved, achieving more efficient resource scheduling and convenient resource acquisition.
Patent Information
- Application Number
- CN202211444168.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-18
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2042-11-18
AI Technical Summary
Traditional resource allocation platforms have low accuracy in assessing small and medium-sized technology enterprises, mainly due to problems such as lack of credit information, irregular management, chaotic financial systems, and high operational risks.
By acquiring basic information, resource information, and network information of the target object, and after judging the authenticity of the information, the object digital profile generation module generates profile information, and the resource scheduling description module performs filtering and resource scheduling to reduce information collection costs and improve the accuracy of assessment.
This effectively breaks down information barriers, improves the accuracy of resource allocation platforms in assessing enterprises and the convenience of resource acquisition, and lowers the financing threshold.
Smart Images

Figure CN115809919B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a resource scheduling method, apparatus, computer equipment, storage medium, and computer program product. Background Technology
[0002] With the development of computer technology, resource scheduling and evaluation technology has emerged. This technology evaluates the comprehensive credit granting, credit guarantee resource scheduling, housing purchase resource scheduling, remote joint assistance resource scheduling, and project development resource scheduling of small and medium-sized technology enterprises. When evaluating the above parameters, the staff of the resource scheduling platform need to conduct on-site inspections to obtain the corresponding information before making the evaluation.
[0003] However, traditional technologies suffer from three major drawbacks in resource allocation assessment for small and medium-sized technology enterprises (SMEs): First, SMEs generally lack credit information; second, they often suffer from irregular internal management, chaotic financial systems, and unstable business status; and third, they are characterized by knowledge-intensive, technology-intensive, asset-light, and high-risk operations. These factors contribute to the low accuracy of resource allocation platform assessments for these enterprises. Summary of the Invention
[0004] Therefore, it is necessary to provide a resource scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of resource scheduling assessment of enterprises by the resource scheduling platform, in order to address the above-mentioned technical problems.
[0005] Firstly, this application provides a resource scheduling method. The method includes: acquiring basic object information, object resource information, and object network information corresponding to each target object, and determining the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with a resource scheduling platform; when the basic object information and the object resource information are both authentic, inputting the basic object information, the object resource information, and the object network information into an object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; and then generating digital profiles of each object basic profile information and each object resource profile information. The image information and the network profile information of each object are superimposed to obtain the target object description information corresponding to each target object on the resource scheduling platform; the target object description information respectively represents the classification of each target object on the resource scheduling platform; the target object description information is input into the resource scheduling description module corresponding to the resource scheduling platform to obtain each selected target object whose target object description information meets the preset conditions; the resource scheduling details information, target object description information and object information data corresponding to each selected target object are sent to the resource scheduling platform, and the resource scheduling platform is used to schedule each target resource to each selected target object.
[0006] Secondly, this application also provides a resource scheduling device. The device includes: a target object information acquisition module, used to acquire basic object information, object resource information, and object network information corresponding to each target object, and to determine the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with the resource scheduling platform; an object profile information obtaining module, used to, when the basic object information and the object resource information are both authentic, input the basic object information, the object resource information, and the object network information to the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; and a target object description information obtaining module, used to obtain the object basic profile information, object resource profile information, and object network profile information corresponding to each target object. The object resource profile information and the object network profile information are superimposed to obtain the target object description information corresponding to each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The filtered target object acquisition module is used to input the target object description information into the resource scheduling description module corresponding to the resource scheduling platform to obtain the filtered target objects whose target object description information meets preset conditions. The target resource scheduling module is used to send the resource scheduling details information, target object description information and object information data corresponding to each filtered target object to the resource scheduling platform. The resource scheduling platform is used to schedule each target resource to the corresponding filtered target object.
[0007] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program, performs the following steps: acquiring basic object information, object resource information, and object network information corresponding to each target object, and determining the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with a resource scheduling platform; when the basic object information and the object resource information are both authentic, inputting the basic object information, the object resource information, and the object network information into the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; and then... The basic profile information of the objects, the resource profile information of each object, and the network profile information of each object are superimposed to obtain the target object description information corresponding to each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The target object description information is input into the resource scheduling description module corresponding to the resource scheduling platform to obtain each selected target object whose target object description information meets the preset conditions. The resource scheduling details information, target object description information, and object information data corresponding to each selected target object are sent to the resource scheduling platform, which is used to schedule each target resource to the selected target object.
[0008] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps: acquiring basic object information, object resource information, and object network information corresponding to each target object, and determining the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with a resource scheduling platform; when the basic object information and the object resource information are both authentic, inputting the basic object information, the object resource information, and the object network information into an object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; and then... Basic profile information, resource profile information, and network profile information of each object are superimposed to obtain target object description information corresponding to each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The target object description information is input into the resource scheduling description module corresponding to the resource scheduling platform to obtain each selected target object whose target object description information meets preset conditions. The resource scheduling details, target object description information, and object information data corresponding to each selected target object are sent to the resource scheduling platform, which is used to schedule each target resource to the corresponding selected target object.
[0009] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps: acquiring basic object information, object resource information, and object network information corresponding to each target object, and determining the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with a resource scheduling platform; when the basic object information and the object resource information are both authentic, inputting the basic object information, the object resource information, and the object network information into an object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; and then... The profile information, resource profile information, and network profile information of each object are superimposed to obtain the target object description information corresponding to each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The target object description information is input into the resource scheduling description module corresponding to the resource scheduling platform to obtain each selected target object whose target object description information meets preset conditions. The resource scheduling details, target object description information, and object information data corresponding to each selected target object are sent to the resource scheduling platform, which is used to schedule each target resource to the corresponding selected target object.
[0010] The aforementioned resource scheduling method, apparatus, computer equipment, storage medium, and computer program product acquire basic object information, object resource information, and object network information corresponding to each target object, and determine the authenticity of the basic object information and object resource information; the target object has a resource scheduling relationship with the resource scheduling platform; when the basic object information and object resource information are both authentic, the basic object information, object resource information, and object network information are input into the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information corresponding to each target object; the basic object information is then processed. The situation profile information, resource profile information of each object, and network profile information of each object are overlaid to obtain the target object description information corresponding to each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The target object description information is input into the resource scheduling description module of the resource scheduling platform to obtain the selected target objects whose target object description information meets the preset conditions. The resource scheduling details information, target object description information, and object information data corresponding to each selected target object are sent to the resource scheduling platform, which is used to schedule each target resource to the corresponding selected target object.
[0011] By employing a system where target entities submit applications and the resource allocation platform makes judgments, information collection costs are reduced, effectively breaking down information barriers between target entities and the resource allocation platform, and improving the directness and convenience of resource acquisition for target entities. Simultaneously, through data services such as enterprise digital profiling and resource allocation model calculations, the platform analyzes and portrays small and medium-sized technology target entities from multiple perspectives, including their basic information, intangible assets, and public opinion, thereby lowering the financing threshold for target entities and effectively improving the accuracy of resource allocation assessments of enterprises by the resource allocation platform. Attached Figure Description
[0012] Figure 1 This is a diagram illustrating the application environment of a resource scheduling method in one embodiment.
[0013] Figure 2 This is a flowchart illustrating a resource scheduling method in one embodiment;
[0014] Figure 3 This is a flowchart illustrating the method for obtaining image information in one embodiment;
[0015] Figure 4 This is a flowchart illustrating a method for obtaining basic profile information of each object in one embodiment.
[0016] Figure 5This is a flowchart illustrating a method for obtaining the object correlation coefficient matrix in one embodiment;
[0017] Figure 6 This is a flowchart illustrating a method for obtaining basic profile information of each object in one embodiment.
[0018] Figure 7 This is a flowchart illustrating a method for obtaining network profile information of each object in one embodiment.
[0019] Figure 8 This is a flowchart illustrating a method for obtaining news description information of a target object in one embodiment;
[0020] Figure 9 This is a flowchart illustrating a method for obtaining target object description information in one embodiment;
[0021] Figure 10 A flowchart illustrating the method for obtaining basic profile information of an object in another embodiment;
[0022] Figure 11 A flowchart illustrating the method for obtaining object network profile information in another embodiment;
[0023] Figure 12 This is a structural block diagram of a resource scheduling device in one embodiment;
[0024] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0026] The resource scheduling method provided in this application embodiment can be applied to, for example, Figure 1The application environment shown is illustrated. Terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. The system acquires basic object information, resource information, and network information for each target object, and verifies the authenticity of the basic object information and resource information. The target objects have a resource scheduling relationship with the resource scheduling platform. If the basic object information and resource information are authentic, they are input into the object digital profile generation module of the resource scheduling platform to obtain basic object profile information, resource profile information, and network profile information for each target object. These profiles are then overlaid to obtain the target object description information for each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. This description information is input into the resource scheduling description module of the resource scheduling platform to obtain the selected target objects whose descriptions meet preset conditions. The resource scheduling details, target object description information, and object information data for each selected target object are sent to the resource scheduling platform, which then schedules each target resource to the selected target object. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0027] In one embodiment, such as Figure 2 As shown, a resource scheduling method is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps are included:
[0028] Step 202: Obtain the basic information, resource information and network information of each target object, and determine the authenticity of the basic information and resource information.
[0029] The target object can be an object that needs to obtain resources from the resource scheduling method. Generally speaking, the target object can be a company in society, such as a small or medium-sized technology company.
[0030] Among them, the basic information of the object can be the tangible asset information carried by the object that obtains resources through operation, such as: financial information, fixed asset information, and the proportion between various assets in the enterprise.
[0031] Among them, object resource information can be the intangible asset information carried by the object that acquires the resource through operation, such as software copyrights, qualifications, patents, etc. in an enterprise.
[0032] Among them, object network information can be information generated on the network by the object that obtains resources through its operation, such as news in enterprises, credit information of enterprise personnel, etc.
[0033] Specifically, the first step is to obtain the basic information, resource information, and network information of each target entity. This involves using the enterprise information submission function. For enterprises with financing needs, this means preparing relevant materials and certificates, logging into the system, and following the system prompts to fill in the relevant enterprise information and upload supporting documents. This mainly includes basic enterprise information, resource information (intangible asset information), and network information (enterprise public opinion information). Basic enterprise information includes, but is not limited to, the basic information of the legal representative and key leaders, business license, real estate certificate, net profit, income tax, financial expenses, fixed assets, and main business revenue. Intangible asset information includes, but is not limited to, software copyright information, qualifications, and patent information. Enterprise public opinion information includes the credit information of the legal representative and key leaders, and news related to the enterprise, its legal representative, and key leaders on the internet over the past three years.
[0034] The second step involves verifying the authenticity of the basic information and resource information of the object. This verification function uses supporting documents uploaded by the company to assess the accuracy of the information provided. For example, it first checks for inconsistencies in image clarity, consistency of item boundaries, and image attributes to determine if the uploaded images have been edited. Then, it uses OCR technology to identify image information in the supporting documents and compares this information with the information submitted by the company to determine its authenticity.
[0035] Step 204: If the object basic information and object resource information are both true, input the object basic information, object resource information and object network information into the object digital profile generation module corresponding to the resource scheduling platform to obtain the object basic information profile, object resource information profile and object network information profile corresponding to each target object.
[0036] The object digital portrait generation module can be a module within the resource scheduling platform used to generate object digital portraits from input information. A digital portrait, also known as a digital image or digitized image, is a two-dimensional image represented using a finite number of digital pixels. It is represented by an array or matrix, and its illumination position and intensity are discrete. A digital image is an image obtained by digitizing an analog image, using pixels as its basic element, and can be stored and processed by a digital computer or digital circuit. Digital portraiture is a technology; applying digital portraiture to education is an art.
[0037] Among them, the basic information profile of the object can be the profile information obtained by the object's basic information through the object digital profile generation module.
[0038] Among them, the object resource status profile information can be the profile information obtained by the object resource information through the object digital profile generation module.
[0039] Among them, the object network situation profile information can be the profile information obtained by the object network information through the object digital profile generation module.
[0040] Specifically, assuming the basic information and resource information of the target object are accurate, it is necessary to analyze the target object's basic situation, especially its profitability, solvency, asset structure, growth potential, and operational capabilities. These aspects play a crucial role in determining whether the resource allocation platform will allocate resources. These five aspects are closely related to numerous parameters such as the target object's return on assets, current ratio, fixed asset ratio, average total asset growth rate, and current asset turnover. To better analyze and characterize the target object's basic situation, the basic information, resource information, and network information are input into the corresponding object digital profile generation module of the resource allocation platform. This yields separate profiles for each target object: basic information, resource information, and network information. The corresponding operational logic involves first using principal component analysis to reduce the dimensionality of the numerous parameters, and then calculating the target object's basic situation score. For example... Figure 9 As shown, the specific steps are as follows:
[0041] Step 1: Collect a large amount of relevant data on technology targets in recent years, including but not limited to indicators such as total loan amount, total assets, net profit, operating income, financial expenses, income tax expenses, return on assets, net profit margin of main business, current ratio, debt-to-equity ratio, quick ratio, interest coverage ratio, fixed asset ratio, average total asset growth rate, average main business growth rate, current asset turnover, total asset turnover, etc.
[0042] Step 2: Preprocess the collected sample data. Missing, redundant, and outlier data are deleted and corrected to obtain data for each technology target, with each target having a specific indicator, thus generating an initial data matrix.
[0043]
[0044] The initial data matrix B is standardized using the following method:
[0045]
[0046] in:
[0047]
[0048] The object correlation coefficient matrix of the standardized data is then:
[0049]
[0050] in:
[0051]
[0052] Using principal component analysis, calculate the object eigenvalues (λ1, λ2, ..., λ) of the object correlation coefficient matrix G. m ) and the corresponding object feature vector α i =(α i1 ,α i2 ,...α im ), i = 1, 2, ..., m. Select the top k principal components whose cumulative contribution rate reaches 85% or higher. The formula for calculating the contribution t of each principal component is:
[0053]
[0054] Calculate the principal component description information F of the target entity, assuming the indicators of the applicant company are:
[0055]
[0056] Then the descriptive information F of each principal component is:
[0057]
[0058] Calculate the Basic Profile Information (BI) of the target object: Add the components of each principal component description information to obtain the Basic Profile Information (BI) of the target object: BI = F1 + F2 + ... + F k By executing the above method on any target object, we can obtain basic profile information of each target object.
[0059] The third step is to analyze the target asset's resource information to obtain a profile of the target asset's resources. Evaluating a company's intangible assets (such as software copyrights, qualifications, patents, etc.) presents certain difficulties, such as determining the transaction price and economic benefits of intangible assets. Therefore, expert review is used to evaluate intangible assets.
[0060] The specific steps are as follows:
[0061] ① The system sends the company's intangible assets to five random experts in the corresponding field. The experts score the assets based on factors such as technology, economic benefits, practicality, competitiveness, application prospects, development difficulty, and legal status. ② The average score from the five experts is used as the company's object resource profile information (IA).
[0062] By executing the above method on any target object, you can obtain the object resource profile information corresponding to each target object.
[0063] Step 4: Analyze the company's public opinion information. This analysis includes not only the company itself, but also the analysis of its legal representative and key leaders. For example... Figure 10 As shown, the specific steps are as follows:
[0064] ① Check the credit history of the company's legal representative and key leaders; calculate their credit scores based on the credit history: For each legal representative and key leader, first set an initial credit score. If their credit history includes instances of being a loan user, having no credit history, having accumulated three or six consecutive loan applications, bad debts, being a defaulter, or having frequent loan inquiries, a certain number of points will be deducted. Then, calculate the average credit score as the descriptive data R for the company leaders' target personnel.
[0065] ② Collect news related to the company, its legal representative, and key leaders from the internet over the past three years; process the collected news: categorize news into positive and negative news, and determine the impact coefficient of each news item. For positive news, the impact coefficient is +1, and for negative news, it is -1. Calculate the news's popularity based on comments, reposts, and other data, and track the duration the news maintains a certain level of popularity; calculate the score for each news item = impact coefficient * popularity * duration. Use the average score of all news items as the target audience status news description information U for the company.
[0066] ③ Calculate the public opinion information score PS of the reporting enterprise: Add the target personnel description data R of the enterprise leader and the target status news description information U to obtain the target network situation profile information of the enterprise PS = R + U.
[0067] By executing the above method on any target object, you can obtain object network profile information corresponding to each target object.
[0068] Step 206: Overlay the basic profile information, resource profile information, and network profile information of each object to obtain the target object description information corresponding to each target object on the resource scheduling platform.
[0069] The target object description information can be the overall profile information of any target object, used to represent the specific situation of the current target object.
[0070] Specifically, the target entity's digital profile is characterized by three parts: basic information about the enterprise, intangible assets, and public opinion information. The enterprise's overall score S is obtained by adding the scores of these three parts: basic information, intangible assets, and public opinion information. That is, the target entity's descriptive information S = BI + IA + PS = F1 + F2 + ... + F k +IA+U+R.
[0071] Step 208: Input the description information of each target object into the resource scheduling description module corresponding to the resource scheduling platform to obtain each screened target object whose description information meets the preset conditions.
[0072] The resource scheduling description module can be based on a neural network algorithm, using enterprise digital profiles to train a resource scheduling model and calculate the resource scheduling details of the resource scheduling platform.
[0073] Among them, the screened target objects can be target objects that meet at least one condition in the resource scheduling module.
[0074] Specifically, the description information of each target object in the application is input into the resource scheduling description module of the resource scheduling platform. The output is the selected target objects whose description information meets the preset conditions. This includes the recommended resource scheduling details suitable for the application target object, including resource scheduling amount, resource scheduling interest rate, resource scheduling period, and reverse resource scheduling method.
[0075] Step 210: Send the resource scheduling details, target object descriptions, and object information data corresponding to each selected target object to the resource scheduling platform.
[0076] Among them, the resource scheduling details can be detailed information about the resource scheduling platform's resource scheduling to the target object, including the resource scheduling amount, resource scheduling method, resource scheduling time, etc.
[0077] The object information data can be the basic information of the target object, used to trigger the resource scheduling platform to transfer resources to the target object. For example, a bank needs a company's corporate account information to transfer a loan to the company's corporate account.
[0078] Specifically, based on the resource allocation amount in the recommended resource allocation details, the system determines whether the target applicant can obtain resources from the resource allocation platform. If the target applicant can obtain resources from the resource allocation platform, the system sends the applicant information, target applicant description, and resource allocation details to the resource allocation platform, and the platform assigns a dedicated person to liaise with the target applicant. If the target applicant cannot obtain resources from the resource allocation platform, the system indicates that the resource allocation has failed, and the target applicant can resubmit the resource allocation application after modifying or supplementing the relevant materials within a certain period of time.
[0079] In the aforementioned resource scheduling method, basic object information, resource information, and network information corresponding to each target object are obtained, and the authenticity of the basic object information and resource information is judged. The target objects have a resource scheduling relationship with the resource scheduling platform. If the basic object information and resource information are both authentic, the basic object information, resource information, and network information are input into the object digital profile generation module corresponding to the resource scheduling platform to obtain basic object profile information, resource profile information, and network profile information for each target object. The basic object profile information and the digital profile information for each target object are then used to generate digital profiles of the target objects. Resource profile information and network profile information for each object are overlaid to obtain target object description information for each target object on the resource scheduling platform. The target object description information represents the classification of each target object on the resource scheduling platform. The target object description information is input into the resource scheduling description module of the resource scheduling platform to obtain each selected target object whose target object description information meets the preset conditions. The resource scheduling details, target object description information, and object information data corresponding to each selected target object are sent to the resource scheduling platform, which is used to schedule each target resource to the corresponding selected target object.
[0080] By employing a system where target entities submit applications and the resource allocation platform makes judgments, information collection costs are reduced, effectively breaking down information barriers between target entities and the resource allocation platform, and improving the directness and convenience of resource acquisition for target entities. Simultaneously, through data services such as enterprise digital profiling and resource allocation model calculations, the platform analyzes and portrays small and medium-sized technology target entities from multiple perspectives, including their basic information, intangible assets, and public opinion, thereby lowering the financing threshold for target entities and effectively improving the accuracy of resource allocation assessments of enterprises by the resource allocation platform.
[0081] In one embodiment, such as Figure 3 As shown, the basic information of the object, the object resource information, and the object network information are input into the object digital profile generation module of the resource scheduling platform to obtain the basic object profile information, object resource profile information, and object network profile information corresponding to each target object, including:
[0082] Step 302: Input the basic information of the object into the object basic information analysis submodule to obtain the basic profile information of each target object.
[0083] Among them, the object basic information analysis submodule can be an algorithm that generates object basic information profile information from the object's basic information.
[0084] Specifically, we collect a large amount of relevant data on technology targets in recent years, including but not limited to indicators such as total loans, total assets, net profit, operating income, financial expenses, income tax expenses, return on assets, net profit margin of main business, current ratio, debt-to-equity ratio, quick ratio, interest coverage ratio, fixed asset ratio, average total asset growth rate, average main business growth rate, current asset turnover, total asset turnover, etc.
[0085] The collected sample data is preprocessed. Missing, redundant, and outlier data are deleted and corrected to obtain data for each technology target, with each target having a specific indicator, thus generating an initial data matrix.
[0086]
[0087] The initial data matrix B is standardized using the following method:
[0088]
[0089] in:
[0090]
[0091] The object correlation coefficient matrix of the standardized data is then:
[0092]
[0093] in:
[0094]
[0095] Using principal component analysis, calculate the object eigenvalues (λ1, λ2, ..., λ) of the object correlation coefficient matrix G. m ) and the corresponding object feature vector α i =(αi1 ,α i2 ,...α im ), i = 1, 2, ..., m. Select the top k principal components whose cumulative contribution rate reaches 85% or higher. The formula for calculating the contribution t of each principal component is:
[0096]
[0097] Calculate the principal component description information F of the target entity, assuming the indicators of the applicant company are:
[0098]
[0099] Then the descriptive information F of each principal component is:
[0100]
[0101] Calculate the Basic Profile Information (BI) of the target object: Add the components of each principal component description information to obtain the Basic Profile Information (BI) of the target object: BI = F1 + F2 + ... + F k By executing the above method on any target object, we can obtain basic profile information of each target object.
[0102] Step 304: Input the object resource information into the object resource information analysis submodule to obtain the object resource profile information corresponding to each target object.
[0103] The object resource information analysis submodule can be an algorithm that generates object resource profile information from object resource information.
[0104] Specifically, the object resource information of the target object is analyzed to obtain object resource profile information. Evaluating a company's intangible assets (such as software copyrights, qualifications, patents, etc.) presents certain difficulties, such as the difficulty in determining the transaction price and economic benefits of intangible assets. Therefore, expert review is used to evaluate intangible assets.
[0105] The specific steps are as follows:
[0106] ① The system sends the company's intangible assets to 5 random experts in the corresponding field. The experts score the assets based on factors such as technology, economic benefits, practicality, competitiveness, application prospects, development difficulty, and legal status. ② The average score from the 5 experts is used as the company's object resource profile information (IA).
[0107] By executing the above method on any target object, you can obtain the object resource profile information corresponding to each target object.
[0108] Step 306: Input the object network information into the object network information analysis submodule to obtain the object network profile information corresponding to each target object.
[0109] The object network information analysis submodule can be an algorithm that generates object network profile information from object network information.
[0110] Specifically, this involves analyzing public opinion information about the company. This analysis includes not only examining the company itself, but also analyzing its legal representative and key leaders. For example... Figure 10 As shown, the specific steps are as follows:
[0111] ① Check the credit history of the company's legal representative and key leaders; calculate their credit scores based on the credit history: For each legal representative and key leader, first set an initial credit score. If their credit history includes instances of being a loan user, having no credit history, having accumulated three or six consecutive loan applications, bad debts, being a defaulter, or having frequent loan inquiries, a certain number of points will be deducted. Then, calculate the average credit score as the descriptive data R for the company leaders' target personnel.
[0112] ② Collect news related to the company, its legal representative, and key leaders from the internet over the past three years; process the collected news: categorize news into positive and negative news, and determine the impact coefficient of each news item. For positive news, the impact coefficient is +1, and for negative news, it is -1. Calculate the news's popularity based on comments, reposts, and other data, and track the duration the news maintains a certain level of popularity; calculate the score for each news item = impact coefficient * popularity * duration. Use the average score of all news items as the target audience status news description information U for the company.
[0113] ③ Calculate the public opinion information score PS of the reporting enterprise: Add the target personnel description data R of the enterprise leader and the target status news description information U to obtain the target network situation profile information of the enterprise PS = R + U.
[0114] By executing the above method on any target object, you can obtain object network profile information corresponding to each target object.
[0115] In this embodiment, by subdividing the object digital portrait generation module, different information in the target object is processed accordingly, and corresponding portrait information is generated for each. This achieves targeted processing methods for different information and improves the accuracy of portrait information generation.
[0116] In one embodiment, such as Figure 4 As shown, the basic information of the object is input into the object basic information analysis submodule to obtain the basic profile information of each target object, including:
[0117] Step 402: Based on the object basic information analysis submodule, the object basic information is standardized to obtain the object correlation coefficient matrix corresponding to each target object.
[0118] The object correlation coefficient matrix can be composed of the correlation coefficients between objects in each column of the matrix. That is, the element in the i-th row and j-th column of the correlation matrix is the correlation coefficient between the i-th and j-th columns of the original matrix.
[0119] Specifically, the collected sample data undergoes preprocessing. Missing, redundant, and outlier data are deleted and corrected to obtain data for each technology target, with each target having a specific indicator, thus generating an initial data matrix.
[0120]
[0121] The initial data matrix B is standardized using the following method:
[0122]
[0123] in:
[0124]
[0125] The object correlation coefficient matrix of the standardized data is then:
[0126]
[0127] in:
[0128]
[0129] Step 404: Calculate the object correlation coefficient matrix using principal component analysis to obtain the basic profile information of each target object.
[0130] Principal component analysis can be a statistical method. It transforms a set of potentially correlated variables into a set of linearly uncorrelated variables through orthogonal transformation; this transformed set of variables is called the principal components.
[0131] Specifically, using principal component analysis, the object eigenvalues (λ1, λ2, ... λ) of the object correlation coefficient matrix G are calculated. m ) and the corresponding object feature vector α i =(α i1 ,α i2 ,...α im), i = 1, 2, ..., m. Select the top k principal components whose cumulative contribution rate reaches 85% or higher. The formula for calculating the contribution t of each principal component is:
[0132]
[0133] Calculate the principal component description information F of the target entity, assuming the indicators of the applicant company are:
[0134]
[0135] Then the descriptive information F of each principal component is:
[0136]
[0137] Calculate the Basic Profile Information (BI) of the target object: Add the components of each principal component description information to obtain the Basic Profile Information (BI) of the target object: BI = F1 + F2 + ... + F k By executing the above method on any target object, we can obtain basic profile information of each target object.
[0138] In this embodiment, principal component analysis is used to calculate the correlation coefficient matrix of the object. Because of the introduction of principal component analysis, the sum of squared deviations or variances are used to measure the basic information of the object when drawing the basic information profile of the object, which can improve the accuracy of the basic information profile of the object.
[0139] In one embodiment, such as Figure 5 As shown, the basic information of the objects is standardized to obtain the object correlation coefficient matrix corresponding to each target object, including:
[0140] Step 502: Based on the number of target objects in the basic information of the object and the data indicators of each target object, obtain the initial data matrix corresponding to each target object.
[0141] Among them, the target data indicators can be at least one piece of information in the basic information of the enterprise, such as: basic information of the legal person and main leaders of the enterprise, business license, real estate certificate, net profit, income tax, financial expenses, fixed assets, main business revenue, etc.
[0142] The initial data matrix can be a matrix composed of the numbers of the target objects and the data indicators of each object.
[0143] Specifically, the collected sample data undergoes preprocessing. Missing, redundant, and outlier data are deleted and corrected to obtain data for each technology target, with each target having a specific indicator, thus generating an initial data matrix.
[0144]
[0145] The initial data matrix B is standardized using the following method:
[0146]
[0147] in:
[0148]
[0149] Step 504: Standardize the initial data matrix to obtain the object correlation coefficient matrix corresponding to each target object.
[0150] Specifically, the object correlation coefficient matrix of the data after standardizing the initial data matrix is as follows:
[0151]
[0152] in:
[0153]
[0154] In this embodiment, by establishing an initial data matrix based on the number of target objects and object data indicators and then performing standardization processing, a corresponding object correlation coefficient matrix can be established for business needs. Furthermore, by utilizing the characteristics of the object correlation coefficient matrix, the accuracy of subsequent calculations can be improved.
[0155] In one embodiment, such as Figure 6 As shown, principal component analysis was used to calculate the correlation coefficient matrix of the objects, obtaining the basic profile information of each target object, including:
[0156] Step 602: Take any target object as the first object to be described, and extract features from the object correlation coefficient matrix according to the principal component analysis method to obtain the object feature values and object feature vectors corresponding to each target object.
[0157] The first object to be described can be the target object corresponding to the basic information of the object being drawn.
[0158] Among them, the object feature values can be feature values obtained by feature extraction from the object correlation coefficient matrix.
[0159] Among them, the object feature vector can be a vector composed of each feature value in the object correlation coefficient matrix.
[0160] Specifically, taking any target object as the first object to be described, principal component analysis is used to calculate the object eigenvalues (λ1, λ2, ... λ) of the object correlation coefficient matrix G. m ) and the corresponding object feature vector α i =(α i1 ,α i2 ,...α im ), i = 1, 2, ... m.
[0161] Step 604: Based on the object feature values and the cumulative contribution rate of the principal components, filter the object feature vectors to obtain the filtered object feature vectors.
[0162] The cumulative contribution rate of principal components can be the proportion of the variance of the principal components in the total variance of the random variable under investigation.
[0163] Among them, the filtered object feature vector can be the feature vector remaining after filtering the object feature vectors according to certain conditions.
[0164] Specifically, the top k principal components with a cumulative contribution rate of 85% or higher are selected, and the formula for calculating the contribution t of each principal component is as follows:
[0165]
[0166] Based on the above conditions, the object eigenvectors α of the object correlation coefficient matrix G are... i =(α i1 ,α i2 ,...α im After filtering by i = 1, 2, ... m, the feature vector of the filtered objects is obtained.
[0167] Step 606: Multiply the filtered object feature vectors with the initial data matrix to obtain the principal component description information corresponding to each object data index in each target object.
[0168] The principal component description information can be the score corresponding to one of the indicators obtained by principal component analysis for the target object.
[0169] Specifically, the principal component description information F of the target entity is calculated, and the indicators of the applicant enterprise are set as follows:
[0170]
[0171] Then the descriptive information F of each principal component is:
[0172]
[0173] Step 608: Superimpose the principal component description information corresponding to the first object to be described to obtain the basic profile information of the object corresponding to the first object to be described.
[0174] Specifically, the basic information profile (BI) of the target object is calculated by summing the components of each principal component description information to obtain the basic information profile (BI) of the target object: BI = F1 + F2 + ... + F k .
[0175] Step 610: Integrate the basic profile information of each first object to be described to obtain the basic profile information of each target object.
[0176] Specifically, by executing the methods corresponding to steps 602 to 608 for any target object, the basic profile information of each target object can be obtained.
[0177] In this embodiment, by extracting features from the object correlation coefficient matrix and multiplying the extracted feature vectors with the initial data matrix, the influence of various factors in the target object on the basic profile information of the object can be fully considered, thereby reducing the error in the basic profile of the object in depicting the target object.
[0178] In one embodiment, such as Figure 7 As shown, the object network information is input into the object network information analysis submodule to obtain object network profile information corresponding to each target object, including:
[0179] Step 702: Take any target object as the second object to be described, and describe each object according to the personal information of each object person in the second object to be described, so as to obtain the object person description data corresponding to each object person.
[0180] The second object to be described can be one of the target objects for which the personal information of each object is described separately.
[0181] The personal information of the target personnel can be the personal credit information of any employee in the target group.
[0182] The target personnel can be any employee of the target group, such as: legal representative, chairman, president, etc.
[0183] Among them, the descriptive data of the target personnel can be the credit score data of the corporate legal person and the main leader.
[0184] Specifically, this involves analyzing public opinion information about the company. This analysis includes not only the company itself but also its legal representative and key leaders. This involves checking the credit records of the company's legal representative and key leaders; calculating their credit scores based on these records: for each legal representative and key leader, an initial credit score is set, and points are deducted for each instance of being a loan applicant, having no credit history, having accumulated three or six consecutive loan applications, bad debts, being a defaulter, or frequently applying for loans. The average credit score is then calculated as the descriptive data R for the company leaders' target audience.
[0185] Step 704: Describe the second object to be described based on the public information of each object and the public information of each target object to obtain the target object news description information corresponding to the second object to be described.
[0186] Among them, the publicly disclosed information about the target personnel can be news information related to the corporate legal person and key leaders.
[0187] Among them, publicly available information about the target object can be news information related to the target object.
[0188] Specifically, news related to the company, its legal representative, and key leaders from the internet over the past three years is collected. The collected news is then processed: it is categorized as positive or negative, and an impact coefficient is determined. Positive news has an impact coefficient of +1, while negative news has an impact coefficient of -1. The news's popularity is calculated based on data such as comments and reposts, and the duration for which the news maintains a certain level of popularity is recorded. Each news item is scored as follows: Score = Impact Coefficient * Popularity * Duration. The average score of all news items is used as the target audience status news description information U for the company.
[0189] Step 706: Add the personnel description data of each object corresponding to the second object to be described and the news description information of the target object to obtain the network situation profile information of the object corresponding to the second object to be described.
[0190] Specifically, the public opinion information score PS of the reporting enterprise is calculated by adding the target personnel description data R of the enterprise leader and the target status news description information U to obtain the target network situation profile information PS = R + U.
[0191] Step 708: Integrate the object network profile information corresponding to each second object to be described to obtain the object network profile information corresponding to each target object.
[0192] Specifically, by executing the methods corresponding to steps 702 to 706 for any target object, object network profile information corresponding to each target object can be obtained.
[0193] In this embodiment, by using object personnel description data to describe the object personnel in the target object, and using target object news description information to describe the target object, it is possible to subdivide the object personnel and the specific number of appearances of the target object in online news, and express them in a targeted manner using mathematical language, thereby improving the accuracy of the object's online situation profile information.
[0194] In one embodiment, such as Figure 8 As shown, based on the publicly available information of each individual and each target, the second object to be described is described, resulting in the target object news description information corresponding to the second object to be described, including:
[0195] Step 802: Add up the influence coefficient, information popularity and duration corresponding to the public information of each object in the second object to be described to obtain the news description information of each object corresponding to the public information of each object.
[0196] Among them, the impact coefficient, information popularity, and duration can be the influence of news information, its popularity in society, and the duration of its influence, respectively.
[0197] Among them, the news description information of the target personnel can be a rating of the target personnel based on the information in the news.
[0198] Specifically, news related to corporate legal representatives and key leaders from the past three years is collected from the internet. The collected news is then processed: it is categorized as positive or negative, and an impact coefficient is determined. For positive news, the impact coefficient is +1, and for negative news, it is -1. The news's popularity is calculated based on comments, reposts, and other data, and the duration of that popularity is recorded. Each news item is scored as follows: Score = Impact Coefficient * Popularity * Duration, yielding news descriptions for each individual's publicly available information.
[0199] Step 804: Add up the influence coefficient, information popularity and duration corresponding to the public information of each target object in the second object to be described to obtain the object status news description information corresponding to the public information of each target object.
[0200] Among them, the news description information of the object status can be a rating of the target object based on the information in the news.
[0201] Specifically, news related to the company from the internet over the past three years is collected. The collected news is then processed: it is categorized into positive and negative news, and an impact coefficient is determined. For positive news, the impact coefficient is +1, and for negative news, it is -1. The news's popularity is calculated based on data such as comments and reposts, and the duration for which the news maintains a certain level of popularity is recorded. The score for each news item is calculated as: Impact Coefficient * Popularity * Duration, yielding news descriptions corresponding to the publicly available information of each target entity.
[0202] Step 806: Average the news description information of each object and the news description information of each object's status to obtain the news description information of the target object corresponding to the second object to be described.
[0203] Specifically, the average of the news description information of each person and the news description information of each situation is calculated to obtain the average of all news scores, thus obtaining the target news description information corresponding to the second object to be described.
[0204] In this embodiment, by specifying the calculation methods for public information of the target personnel and public information of the target object, the news description information of the target object can be described from a quantitative perspective, which improves the accuracy of subsequent calculation of the network situation profile information of the target object, thus qualitatively improving the overall profile information drawing.
[0205] In one embodiment, the training steps for the resource scheduling description module are as follows: Figure 11 As shown:
[0206] The collected data is preprocessed, and missing, redundant, or abnormal data is deleted or corrected.
[0207] Calculate the principal component description information F of the target object, the object resource profile information IA, the object personnel description data R of the target object's leader, and the target object status news description information U in the sample.
[0208] Each sample's principal component description information F, object resource profile information IA, target leader's personnel description data R, and target object status news description information U are combined into a k+3 dimensional vector, and this vector is used to represent the sample attribute set x = (F1, F5, ..., F k ,IA,R,U);
[0209] Let y represent the loan details of the sample, i.e., y = (y 1 ,y 2 ,y 3 ,y 4 ), where y 1 This represents the amount of resources allocated by the enterprise; y 2Indicates the resource allocation rate; y 3 Indicates the resource scheduling period; y 4 This indicates the reverse resource scheduling method, when y 4 =1 indicates interest followed by principal, y 4 =2 indicates interest-only payments followed by principal payments, y 4 =3 indicates equal principal payments, y 4 =4 indicates equal principal and interest payments, y 4 =5 indicates equal monthly installments and equal interest, y 4 =6 indicates equal principal and interest.
[0210] Construct a dataset D = {(x1,y1),(x2,y2),...,(x p ,y p )},x j ∈R k+3 ,y j ∈R 4 x j =(F j1 ,F j2 ,...F jk IA j ,R j U j () represents the attribute set of the j-th sample. The label represents the j-th sample, i.e., the enterprise's resource scheduling details, and the dataset is divided into a training set and a validation set.
[0211] Resource scheduling description module training: The resource scheduling description module is trained using a feedforward neural network. Assume the neural network has q hidden neurons, and the threshold of the l-th neuron in the output layer is θ. l The threshold of the h-th neuron in the hidden layer is γ. h The connection weight between the j-th neuron in the input layer and the h-th neuron in the hidden layer is v. jh The connection weight between the h-th neuron in the hidden layer and the l-th neuron in the output layer is w. hl The input received by the h-th neuron in the hidden layer is... The input received by the l-th neuron in the output layer is Where c h The output of the h-th neuron in the hidden layer is given by f(x), which is the output of the sigmoid function used by both hidden and output layer neurons, i.e., f(x) = 1 / (1+e). -x So for sample (x) r ,y r Assuming the output of the neural network is Right now Then the neural network in (x r ,y r The mean square error on ) is First, all connection weights and thresholds in the neural network are randomly initialized within the range (0,1). For each sample in the training set, the connection weights and thresholds are adjusted using the backpropagation algorithm (BP algorithm). This iterative process is repeated. After each iteration, the error is estimated using the validation set. If the validation set error increases, training is stopped, and the connection weights and thresholds with the minimum validation set error are returned, thus forming a resource scheduling description module.
[0212] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0213] Based on the same inventive concept, this application also provides a resource scheduling apparatus for implementing the resource scheduling method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more resource scheduling apparatus embodiments provided below can be found in the limitations of a resource scheduling method described above, and will not be repeated here.
[0214] In one embodiment, such as Figure 12 As shown, a resource scheduling device is provided, including: a target object information acquisition module 1202, an object status profile information acquisition module 1204, a target object description information acquisition module 1206, a filtered target object acquisition module 1208, and a target resource scheduling module 1210, wherein:
[0215] The target object information acquisition module 1202 is used to acquire the basic information, resource information and network information of each target object, and to judge the authenticity of the basic information and resource information; the target object has a resource scheduling relationship with the resource scheduling platform;
[0216] The object profile information acquisition module 1204 is used to input the object basic information, object resource information and object network information into the object digital profile generation module corresponding to the resource scheduling platform when the object basic information and object resource information are both true, so as to obtain the object basic profile information, object resource profile information and object network profile information corresponding to each target object respectively.
[0217] The target object description information acquisition module 1206 is used to overlay the basic information profile information, resource information profile information, and network information profile information of each object to obtain the target object description information corresponding to each target object on the resource scheduling platform; the target object description information respectively represents the classification of each target object on the resource scheduling platform.
[0218] The filtered target object module 1208 is used to input the description information of each target object into the resource scheduling description module corresponding to the resource scheduling platform, and obtain each filtered target object whose description information meets the preset conditions;
[0219] The target resource scheduling module 1210 is used to send the resource scheduling details, target object description information and object information data corresponding to each selected target object to the resource scheduling platform. The resource scheduling platform is used to schedule each target resource to each selected target object.
[0220] In one embodiment, the object profile information obtaining module 1204 is further configured to input object basic information to the object basic information analysis submodule to obtain object basic profile information corresponding to each target object; input object resource information to the object resource information analysis submodule to obtain object resource profile information corresponding to each target object; and input object network information to the object network information analysis submodule to obtain object network profile information corresponding to each target object.
[0221] In one embodiment, the object profile information obtaining module 1204 is further used to standardize the object basic information based on the object basic information analysis submodule to obtain the object correlation coefficient matrix corresponding to each target object; and to calculate the object correlation coefficient matrix using principal component analysis to obtain the object basic profile information corresponding to each target object.
[0222] In one embodiment, the object profile information obtaining module 1204 is further configured to obtain an initial data matrix corresponding to each target object based on the number of target objects in the object basic information and the object data indicators corresponding to each target object; and to perform standardization processing on the initial data matrix to obtain the object correlation coefficient matrix corresponding to each target object.
[0223] In one embodiment, the object profile information obtaining module 1204 is further configured to: take any target object as the first object to be described; extract features from the object correlation coefficient matrix using principal component analysis to obtain object feature values and object feature vectors corresponding to each target object; filter the object feature vectors based on the object feature values and the cumulative contribution rate of the principal components to obtain filtered object feature vectors; multiply the filtered object feature vectors by the initial data matrix to obtain the principal component description information corresponding to each object data indicator in each target object; superimpose the principal component description information corresponding to the first object to be described to obtain the basic profile information of the object corresponding to the first object to be described; and integrate the basic profile information of the objects corresponding to each first object to be described to obtain the basic profile information of the object corresponding to each target object.
[0224] In one embodiment, the object profile information obtaining module 1204 is further configured to: take any target object as the second object to be described; describe each object person according to the personal information of each object person of the second object to be described, and obtain object person description data corresponding to each object person; describe the second object to be described according to the public information of each object person and the public information of each target object, and obtain target object news description information corresponding to the second object to be described; add the object person description data corresponding to the second object to be described and the target object news description information to obtain object network profile information corresponding to the second object to be described; and integrate the object network profile information corresponding to each second object to be described to obtain object network profile information corresponding to each target object.
[0225] In one embodiment, the object profile information obtaining module 1204 is further configured to add the influence coefficient, information popularity, and duration corresponding to the public information of each object in the second object to be described, respectively, to obtain the object personnel news description information corresponding to the public information of each object; add the influence coefficient, information popularity, and duration corresponding to the public information of each target object in the second object to be described, respectively, to obtain the object status news description information corresponding to the public information of each target object; and average the object personnel news description information and the object status news description information to obtain the target object news description information corresponding to the second object to be described.
[0226] Each module in the aforementioned resource scheduling device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.
[0227] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 13 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores server data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a resource scheduling method.
[0228] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0229] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.
[0230] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0231] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.
[0232] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0233] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0234] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0235] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A resource scheduling method, characterized in that, The method includes: The system acquires basic object information, object resource information, and object network information corresponding to each target object, and verifies the authenticity of the basic object information and object resource information; the target object has a resource scheduling relationship with the resource scheduling platform. If the object basic information and the object resource information are both true, the object basic information, the object resource information and the object network information are input into the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information and object network profile information corresponding to each target object. The basic profile information, resource profile information, and network profile information of each object are superimposed to obtain the target object description information corresponding to each target object on the resource scheduling platform; the target object description information respectively represents the classification of each target object on the resource scheduling platform; The description information of each target object is input into the resource scheduling description module corresponding to the resource scheduling platform to obtain each filtered target object whose description information meets the preset conditions; The resource scheduling details, target object descriptions, and object information data corresponding to each of the selected target objects are sent to the resource scheduling platform, which is used to schedule each target resource to each of the selected target objects. The object digital profile generation module includes an object basic information analysis submodule, an object resource information analysis submodule, and an object network information analysis submodule. The step of inputting the object basic information, object resource information, and object network information into the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information for each target object includes: inputting the object basic information into the object basic information analysis submodule to obtain object basic profile information for each target object; inputting the object resource information into the object resource information analysis submodule to obtain object resource profile information for each target object; and inputting the object network information into the object network information analysis submodule to obtain object network profile information for each target object. The object network information includes personal information of the target personnel, publicly available information of the target personnel, and publicly available information of the target objects. The step of inputting the object network information into the object network information analysis submodule to obtain object network profile information corresponding to each target object includes: taking any one of the target objects as a second object to be described; describing each target personnel according to their personal information to obtain object personnel description data corresponding to each target personnel; adding the influence coefficient, information popularity, and duration corresponding to the publicly available information of each target personnel in the second object to be described to obtain object personnel news description information corresponding to the publicly available information of each target personnel; and then... The influence coefficient, information popularity, and duration corresponding to the public information of each target object in the second object to be described are added together to obtain the object status news description information corresponding to the public information of each target object. The news description information of each object personnel and the news description information of each object status are averaged to obtain the target object news description information corresponding to the second object to be described. The object personnel description data and the target object news description information corresponding to the second object to be described are added together to obtain the object network situation profile information corresponding to the second object to be described. The object network situation profile information corresponding to each of the second objects to be described is integrated to obtain the object network situation profile information corresponding to each target object.
2. The method according to claim 1, characterized in that, The step of inputting the basic information of the object into the basic information analysis submodule to obtain the basic profile information of the object corresponding to each target object includes: Based on the object basic information analysis submodule, the object basic information is standardized to obtain the object correlation coefficient matrix corresponding to each target object; Principal component analysis is used to calculate the correlation coefficient matrix of the objects to obtain the basic profile information of each target object.
3. The method according to claim 2, characterized in that, The standardization process for the basic information of the objects to obtain the object correlation coefficient matrix corresponding to each target object includes: Based on the number of target objects in the basic information of the object and the data indicators of each target object, an initial data matrix corresponding to each target object is obtained; The initial data matrix is subjected to the standardization process to obtain the object correlation coefficient matrix corresponding to each target object.
4. The method according to claim 3, characterized in that, The process of calculating the correlation coefficient matrix of the objects using principal component analysis yields basic profile information for each target object, including: Taking any one of the target objects as the first object to be described, the principal component analysis method is used to extract features from the object correlation coefficient matrix to obtain the object feature values and object feature vectors corresponding to each target object. Based on the object feature values and the cumulative contribution rate of the principal components, the object feature vector is filtered to obtain the filtered object feature vector; Multiply the filtered object feature vectors by the initial data matrix to obtain the principal component description information corresponding to each object data index in each target object; The principal component description information corresponding to the first object to be described is superimposed to obtain the basic profile information of the object corresponding to the first object to be described. The basic profile information of each of the first objects to be described is integrated to obtain the basic profile information of each of the target objects.
5. A resource scheduling device, characterized in that, The device includes: The target object information acquisition module is used to acquire basic object information, object resource information, and object network information corresponding to each target object, and to determine the authenticity of the basic object information and the object resource information; the target object has a resource scheduling relationship with the resource scheduling platform; The object profile information acquisition module is used to input the object basic information, the object resource information and the object network information into the object digital profile generation module corresponding to the resource scheduling platform when the object basic information and the object resource information are both true, so as to obtain the object basic profile information, object resource profile information and object network profile information corresponding to each target object respectively. The target object description information obtaining module is used to superimpose the basic information profile information, resource information profile information, and network information profile information of each object to obtain the target object description information corresponding to each target object on the resource scheduling platform; the target object description information respectively represents the classification of each target object on the resource scheduling platform; The module for obtaining filtered target objects is used to input the description information of each target object into the resource scheduling description module corresponding to the resource scheduling platform, and obtain each filtered target object whose description information meets the preset conditions; The target resource scheduling module is used to send the resource scheduling details, target object description information and object information data corresponding to each of the selected target objects to the resource scheduling platform. The resource scheduling platform is used to schedule each target resource to each of the selected target objects. The object digital profile generation module includes an object basic information analysis submodule, an object resource information analysis submodule, and an object network information analysis submodule. When the object basic information, object resource information, and object network information are input into the object digital profile generation module corresponding to the resource scheduling platform to obtain object basic profile information, object resource profile information, and object network profile information for each target object, the object profile information obtaining module is specifically used to: input the object basic information into the object basic information analysis submodule to obtain object basic profile information for each target object; input the object resource information into the object resource information analysis submodule to obtain object resource profile information for each target object; and input the object network information into the object network information analysis submodule to obtain object network profile information for each target object. The object network information includes personal information of the target personnel, publicly available information of the target personnel, and publicly available information of the target objects. When the object network information is input into the object network information analysis submodule to obtain object network profile information corresponding to each target object, the object profile information obtaining module is specifically used to take any one of the target objects as the second object to be described, describe each target personnel according to the personal information of each target personnel in the second object to be described, and obtain object personnel description data corresponding to each target personnel; and add the influence coefficient, information popularity, and duration corresponding to the publicly available information of each target personnel in the second object to be described to obtain the target personnel news corresponding to the publicly available information of each target personnel. The description information is as follows: The influence coefficient, information popularity, and duration corresponding to the public information of each target object in the second object to be described are summed to obtain the object status news description information corresponding to the public information of each target object; the news description information of each object personnel and the news description information of each object status are averaged to obtain the target object news description information corresponding to the second object to be described; the object personnel description data and the target object news description information corresponding to the second object to be described are summed to obtain the object network situation profile information corresponding to the second object to be described; the object network situation profile information corresponding to each of the second objects to be described is integrated to obtain the object network situation profile information corresponding to each target object.
6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.
8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.
Citation Information
Patent Citations
Multi-influence-factor small and micro enterprise credit line decision-making method and device
CN112766734A
Customer information processing method and device based on customer portrait
CN114066620A
Accurate enterprise analysis method and system based on enterprise portrait
CN114240266A
Credit risk early warning scoring method based on network big data
CN114529404A
