Resource intelligent matching method and system based on multi-dimensional co-occurrence coefficient

Abstract

The invention discloses an intelligent resource matching method and system based on a multi-dimensional co-occurrence coefficient, and belongs to the technical field of intelligent resource allocation, the obtained resource matching result can better reflect the actual transportation cost and timeliness by obtaining a real-time geographic weight factor, and the resource allocation time attenuation coefficient is combined, so that the resource allocation efficiency is improved. It is ensured that the resources are matched when the value is the highest, a privilege reduction mechanism is introduced, privilege reduction processing is conducted on the resource matching priority of the head enterprise, monopoly influences can be effectively reduced, and resource matching reasonability is improved; and moreover, by adopting the user real-time co-occurrence coefficient, the attention of the customer to the real-time resource matching dynamic demand is improved, the resource configuration accuracy is improved, and the resource utilization efficiency is also remarkably improved by accurately matching and scheduling various types of resource configurations.

Description

Technical Field

[0001] This invention belongs to the field of intelligent resource allocation technology, specifically relating to an intelligent resource matching method and system based on multi-dimensional symbiotic coefficients. Background Technology

[0002] With the development of the industrial internet, the development of intelligent resource allocation technology has shown a trend of diversification, intelligence and cross-industry integration. However, with the use of intelligent resource allocation technology, some problems have inevitably emerged.

[0003] First, existing intelligent resource allocation technologies often focus more on conclusions derived from historical data. As shown in the invention patent document CN113742767A, existing recommendation algorithms often rely excessively on users' historical behavior data. For scenarios where resource demand is sudden, temporary, or geographically specific, the real-time matching is insufficient and the accuracy is inadequate. It fails to fully consider the impact of real-time geographical factors on resource availability and cost.

[0004] Secondly, the matching efficiency of existing resource allocation technologies is greatly affected by industry monopolies. This is because when traditional ERP scheduling systems handle resource matching, the matching efficiency drops significantly when the industry concentration is high (e.g., over 60%) (according to observational data, the efficiency may drop by as much as 40%). This makes it difficult for existing scheduling systems to effectively break resource monopolies, resulting in small and medium-sized enterprises or individual resource providers having difficulty obtaining fair matching opportunities.

[0005] Furthermore, existing technologies are unable to make reasonable and effective plans and schedules for idle resources, resulting in idle resources and low resource utilization.

[0006] As mentioned above, how to provide a resource intelligent matching method and system based on multi-dimensional symbiosis coefficients that can improve the accuracy of resource allocation, reduce the impact of monopolies, and improve resource utilization efficiency has become an urgent problem to be solved. Summary of the Invention

[0007] The purpose of this invention is to provide a resource intelligent matching method based on multi-dimensional symbiosis coefficients to solve the above-mentioned problems existing in the prior art.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] In a first aspect, the present invention provides a resource intelligent matching method based on multi-dimensional co-occurrence coefficients, including:

[0010] Acquire user profile data and real-time geographic weight factors, wherein the user profile data includes the frequency of real-time user interaction and the actual duration of user resource usage, and the real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations;

[0011] Based on the user profile data and the real-time geographic weight factor, the real-time co-occurrence coefficient of each user is calculated, wherein the real-time co-occurrence coefficient is used to characterize the association strength between the resource provider and the user.

[0012] The resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index are obtained. The resource matching priority of each user is calculated using the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor, and the user industry market concentration index. The resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time.

[0013] Based on the user industry market concentration index, leading companies are selected from each user, and the resource matching priority of the leading companies is downgraded to obtain the downgraded resource matching priority of the leading companies. The downgraded resource matching priority of the leading companies is used to replace the resource matching priority of the leading companies, and the results are integrated and sorted to form an executable resource matching priority sequence.

[0014] The resource configurations of each type are matched and scheduled according to the executable resource matching priority sequence to generate the optimal resource matching queue. The optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

[0015] In one possible design, user profile data and real-time geographic weighting factors are acquired, including:

[0016] The user profile data of each user is obtained from the enterprise database. The user profile data includes user productivity, user resource preference, user credit score, user social contribution rate, user real-time interaction frequency and user resource actual usage time.

[0017] Real-time geographic weighting factors are obtained from a third-party geographic information database. These factors include a resource transportation timeliness coefficient and a distance attenuation coefficient. The resource transportation timeliness coefficient is used to characterize the correlation between resource transportation distance and transportation time, and the distance attenuation coefficient is used to characterize the degree of influence of resource transportation distance on resource value.

[0018] In one possible design, based on the user profile data and the real-time geographic weighting factor, the real-time co-occurrence coefficient of each user is calculated, including:

[0019] The real-time co-occurrence coefficient K of basic users is calculated using the following formula. base :

[0020]

[0021] Among them, F int The real-time user interaction frequency is used to characterize the number of communication or transaction requests between the user and the resource provider within a preset time range.

[0022] F base This is the industry benchmark interaction value, which is used to characterize the average interaction frequency of the industry to which the user company belongs.

[0023] R reuse The resource reuse rate is used to characterize the proportion of the actual usage time of the user's resources in the total available resource duration;

[0024] G(t) is the geographic decay function, which is calculated through the real-time geographic weighting factor and is used to characterize the impact of resource transportation distance on resource matching value.

[0025] α, β, and γ are the interaction frequency weighting coefficient, resource reuse rate weighting coefficient, and geographical factor weighting coefficient, respectively, and the interaction frequency weighting coefficient, the resource reuse rate weighting coefficient, and the geographical factor weighting coefficient satisfy the following relationship:

[0026] α+β+γ=1 (2)

[0027] For each user, different interaction frequency weight coefficients, resource reuse rate weight coefficients, and geographical factor weight coefficients are preset, and calculations are performed separately based on the user profile data of each user to obtain the basic real-time user co-occurrence coefficient for each user.

[0028] In one possible design, after obtaining the basic real-time co-occurrence coefficients of each user, the following is also included:

[0029] The credit score of each user is quantified to obtain the credit weight ω of each user, and the social contribution rate of each user is quantified to obtain the social value score S of each user.

[0030] Using each user's credit weight ω and social value score S, the non-monetary gain coefficient K is calculated using the following formula. gain :

[0031] K gain =ω×S×0.2 (3)

[0032] The non-monetary gain coefficient K for each user gain The real-time co-occurrence coefficient K of the basic users mentioned above for each user base Add them together to obtain the final real-time user co-occurrence coefficient K. final :

[0033] K = K final =K base +K gain (4)

[0034] The final user real-time co-occurrence coefficient K final K represents the real-time co-occurrence coefficient of each user.

[0035] In one possible design, the resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index are obtained. Using these factors, the resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index are used to calculate the resource matching priority for each user, including:

[0036] Obtain the user's industry type, wherein the user's industry type includes technology-intensive industries and technology-intensive industries;

[0037] Obtain the resource allocation time decay coefficient λ, and according to the user industry type of each user, obtain the user industry adjustment factor η and user industry market concentration index of each user from the enterprise database, wherein the user industry market concentration index is represented by the Herfindahl-Hirschman Index (HHI).

[0038] The resource matching priority P is calculated using the following formula:

[0039]

[0040] Based on the user industry adjustment factor η and the user industry market concentration index for each user, the resource matching priority for each user is calculated separately.

[0041] In one possible design, based on the user industry market concentration index, leading companies are selected from among the users. The resource matching priority of these leading companies is then downgraded to obtain a downgraded resource matching priority. This downgraded resource matching priority replaces the original resource matching priority of the leading companies, and the sequences are integrated and sorted to form an executable resource matching priority sequence, including:

[0042] Obtain the user industry concentration threshold for each user;

[0043] Each user's industry market concentration index is compared with each user's industry market concentration threshold to determine whether each user's industry market concentration index exceeds the corresponding industry market concentration threshold.

[0044] If not, the user is considered a non-leading enterprise; if yes, the user is considered a leading enterprise.

[0045] Obtain the anti-monopoly weight penalty coefficient, assign resource matching priority to each user identified as a leading enterprise, and use the anti-monopoly weight penalty coefficient to perform forced weight reduction processing to obtain the resource matching priority of the leading enterprise with reduced weight, wherein the anti-monopoly weight penalty coefficient does not exceed 0.6;

[0046] The resource matching priority of the leading enterprise is replaced by the resource matching priority of the leading enterprise. The resource matching priority of each non-leading enterprise is integrated and sorted with the resource matching priority of the leading enterprise of each leading enterprise to form an executable resource matching priority sequence for each user.

[0047] In one possible design, resource configurations of various types are matched and scheduled according to the executable resource matching priority sequence to generate an optimal resource matching queue. This optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource matching suggestions and resource scheduling instructions, including:

[0048] Obtain resource configurations of various types, perform resource matching on each type of resource configuration according to the executable resource matching priority sequence, and generate the optimal resource matching queue;

[0049] Based on the optimal resource matching queue, resource matching suggestions are generated based on the resource configuration of each type. The resource matching suggestions include resource acquisition suggestions and resource scheduling suggestions. There are multiple resource acquisition suggestions, each corresponding to a different user.

[0050] The resource acquisition suggestions are sent to each user accordingly, and the resource scheduling suggestions are sent to the resource provider.

[0051] Based on the optimal resource matching queue, resource scheduling instructions are generated for each type of resource configuration, and these instructions are sent to the resource provider to complete the resource scheduling.

[0052] Secondly, the present invention provides a resource intelligent matching system based on multi-dimensional symbiosis coefficients, including:

[0053] The user data acquisition module is used to acquire user profile data and real-time geographic weight factors. The user profile data includes the user's real-time interaction frequency and the user's actual resource usage time. The real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations.

[0054] The symbiosis coefficient calculation module is used to calculate the real-time symbiosis coefficient of each user based on the user profile data and the real-time geographic weight factor, wherein the real-time symbiosis coefficient is used to characterize the association strength between the resource provider and the user;

[0055] The priority calculation module is used to obtain the resource allocation time decay coefficient, user industry adjustment factor and user industry market concentration index, and to calculate the resource matching priority of each user using the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor and the user industry market concentration index. The resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time.

[0056] The de-weighting processing module is used to select leading companies from various users based on the user industry market concentration index, de-weight the resource matching priority of the leading companies, obtain the de-weighted resource matching priority of the leading companies, replace the resource matching priority of the leading companies with the de-weighted resource matching priority of the leading companies, and integrate and sort them to form an executable resource matching priority sequence.

[0057] The resource scheduling module is used to match and schedule resource configurations of various types according to the executable resource matching priority sequence to generate an optimal resource matching queue, and to feed back the optimal resource matching queue to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

[0058] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the resource intelligent matching method based on multi-dimensional co-occurrence coefficients as described in the first aspect or any possible design of the first aspect.

[0059] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the resource intelligent matching method based on multi-dimensional symbiosis coefficients as described in the first aspect or any possible design of the first aspect.

[0060] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the resource intelligent matching method based on multi-dimensional symbiosis coefficients as described in the first aspect or any possible design of the first aspect.

[0061] Beneficial Effects: This invention provides a resource intelligent matching method based on multi-dimensional symbiosis coefficients, including: First, acquiring user profile data and real-time geographic weight factors, wherein the user profile data includes the user's real-time interaction frequency and the user's actual resource usage time, and the real-time geographic weight factors are used to characterize the correlation between resources and user geographic locations; Second, based on the user profile data and the real-time geographic weight factors, calculating the real-time symbiosis coefficient for each user, wherein the real-time symbiosis coefficient is used to characterize the correlation strength between the resource provider and the user; Then, acquiring resource allocation time decay coefficients, user industry adjustment factors, and user industry market concentration indicators, and utilizing the user real-time symbiosis coefficients, resource allocation time decay coefficients, user industry adjustment factors, and user behavior... The system uses an industry market concentration index to calculate the resource matching priority for each user, where the resource allocation time decay coefficient characterizes the rate at which the value of a resource decays over time. Then, based on the user's industry market concentration index, leading companies are selected from among the users, and their resource matching priorities are downweighted to obtain downweighted resource matching priorities. These downweighted priorities replace the original resource matching priorities of the leading companies and are integrated and sorted to form an executable resource matching priority sequence. Finally, resource configurations of various types are matched and scheduled according to the executable resource matching priority sequence to generate an optimal resource matching queue. This optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource scheduling suggestions and instructions. By acquiring real-time geographic weighting factors, the resource matching results better reflect actual transportation costs and timeliness. Combined with a resource allocation time decay coefficient, this ensures that resources are matched when their value is highest. Furthermore, a de-weighting mechanism is introduced to reduce the priority of resource matching for leading companies, effectively mitigating the impact of monopolies and improving the rationality of resource matching. Moreover, by adopting a real-time user symbiosis coefficient, customer attention to the dynamic needs of real-time resource matching is increased, improving the accuracy of resource allocation. Through precise matching and scheduling of various types of resource allocation, resource utilization efficiency is also significantly improved. Attached Figure Description

[0062] Figure 1 A flowchart illustrating the intelligent resource matching method based on multi-dimensional symbiosis coefficients provided in this embodiment of the invention;

[0063] Figure 2A functional structure diagram of a resource intelligent matching system based on multi-dimensional symbiosis coefficients provided in an embodiment of the present invention;

[0064] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0065] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0066] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0067] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0068] Example:

[0069] like Figure 1 As shown, this embodiment provides a resource intelligent matching method based on multi-dimensional co-occurrence coefficients, including:

[0070] S1. Obtain user profile data and real-time geographic weight factors, wherein the user profile data includes the user's real-time interaction frequency and the user's actual resource usage time, and the real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations;

[0071] In one possible implementation, step S1, acquiring user profile data and real-time geographic weight factors, can be broken down into, but is not limited to, the following steps S11-S12, including:

[0072] S11. Obtain user profile data for each user from the enterprise database, wherein the user profile data includes user productivity, user resource preference, user credit score, user social contribution rate, user real-time interaction frequency, and user resource actual usage time;

[0073] S12. Obtain real-time geographic weighting factors from a third-party geographic information database, wherein the real-time geographic weighting factors include a resource transportation timeliness coefficient and a distance attenuation coefficient, wherein the resource transportation timeliness coefficient is used to characterize the correlation between resource transportation distance and transportation time, and the distance attenuation coefficient is used to characterize the degree of influence of resource transportation distance on resource value.

[0074] It should be noted that the enterprise database here can optionally be a pre-set user industry information database, which includes user profile data for each user.

[0075] S2. Based on the user profile data and the real-time geographic weight factor, calculate the real-time co-occurrence coefficient of each user, wherein the real-time co-occurrence coefficient is used to characterize the association strength between the resource provider and the user;

[0076] In one possible implementation, step S2, based on the user profile data and the real-time geographic weight factor, calculates the real-time co-occurrence coefficient of each user, which can be decomposed, but is not limited to, the following steps S21-S22, including:

[0077] S21. Calculate the real-time co-occurrence coefficient K of basic users using the following formula. base :

[0078]

[0079] Among them, F int The real-time user interaction frequency is used to characterize the number of communication or transaction requests between the user and the resource provider within a preset time range.

[0080] F base This is the industry benchmark interaction value, which is used to characterize the average interaction frequency of the industry to which the user company belongs.

[0081] R reuse The resource reuse rate is used to characterize the proportion of the actual usage time of the user's resources in the total available resource duration;

[0082] G(t) is the geographic decay function, which is calculated through the real-time geographic weighting factor and is used to characterize the impact of resource transportation distance on resource matching value.

[0083] α, β, and γ are the interaction frequency weighting coefficient, resource reuse rate weighting coefficient, and geographical factor weighting coefficient, respectively, and the interaction frequency weighting coefficient, the resource reuse rate weighting coefficient, and the geographical factor weighting coefficient satisfy the following relationship:

[0084] α+β+γ=1 (2)

[0085] S22. For each user, different interaction frequency weight coefficients, resource reuse rate weight coefficients, and geographical factor weight coefficients are preset, and calculated separately based on the user profile data of each user to obtain the basic real-time co-occurrence coefficient of each user.

[0086] It should be noted that, in possible implementation scenarios, the user real-time interaction frequency F int Used to characterize the number of communication or transaction requests between a user and a resource provider within a preset time range (which can be preset to at least 24 hours), when the user's real-time interaction frequency F int The higher the value, the more urgent the user's need for resources; the industry benchmark interaction value F base Data can be obtained from authoritative databases as a benchmark for the user's industry. This benchmark is used to compare and evaluate the recent interaction frequency (real-time user interaction frequency) of various users to determine whether there are any urgent short-term resource needs that exceed the industry benchmark; resource reuse rate R reuse This is used to evaluate the efficiency of user resource utilization. A low resource reuse rate indicates that the resource is underutilized and often idle. The resource reuse rate is then incorporated into the basic user real-time symbiosis coefficient K. base The calculation effectively considers resource vacancy and waste, helping to prioritize the matching of idle resources during resource allocation and improve resource utilization. The geographical decay function G(t) characterizes the impact of resource transportation distance on resource matching value. The longer the resource transportation distance, the lower the resource matching value. Therefore, it is necessary to prioritize resource allocation for the nearest users, which makes the basic user real-time symbiosis coefficient K... base It can reduce logistics costs and shorten delivery cycles.

[0087] In one possible implementation, after obtaining the basic real-time co-occurrence coefficients of each user in step S2, it may also include, but is not limited to, the following steps S23-S26:

[0088] S23. Quantify the user credit value of each user to obtain the credit weight ω of each user, and quantify the user social contribution rate of each user to obtain the social value score S of each user;

[0089] S24. Using each user's credit weight ω and social value score S, calculate the non-monetary gain coefficient K using the following formula. gain :

[0090] K gain =ω×S×0.2 (3)

[0091] S25. Calculate the non-monetary gain coefficient K for each user. gain The real-time co-occurrence coefficient K of the basic users mentioned above for each user base Add them together to obtain the final real-time user co-occurrence coefficient K. final :

[0092] K = K final =K base +K gain (4)

[0093] S26. The final user real-time co-occurrence coefficient K final K represents the real-time co-occurrence coefficient of each user.

[0094] It should be noted that the introduction of the real-time user symbiosis coefficient K can dynamically quantify the multi-dimensional correlation strength between resource providers and users, solving the problems of lack of value anchoring and insufficient real-time performance in traditional matching technologies. Specifically, non-monetary resources such as equipment, labor, and agricultural products are difficult to value due to the lack of standardized pricing, making accurate matching and scheduling impossible. This results in a lack of value anchoring and matching results that do not meet actual needs. Therefore, it is necessary to transform non-monetary resources into calculable dimensionless coefficients through the real-time user symbiosis coefficient K, enabling a direct comparison of the value between different types of resource allocations. For example, by calculating the real-time user symbiosis coefficient K, the value of a machine tool idle for one hour can be compared. The matching value can be proportionally compared to the resource matching value of 10 tons of citrus, making resource matching more rational, more in line with actual resource value needs, and maintaining the principle of fairness in resource matching. In addition, because traditional resource matching schemes rely too much on historical data, they often cannot respond to emergencies (such as temporary labor needs due to project deadlines or emergency resource needs due to social emergencies), resulting in failed or inappropriate resource allocation. Therefore, it is necessary to update real-time user behavior to resource providers through the real-time user symbiosis coefficient K, thereby increasing the resource matching priority for users with urgent needs, and thus greatly improving the response speed of resource matching and scheduling when dealing with emergencies and sudden needs.

[0095] S3. Obtain the resource allocation time decay coefficient, user industry adjustment factor and user industry market concentration index, and use the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor and the user industry market concentration index to calculate the resource matching priority of each user, wherein the resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time.

[0096] In one possible implementation, step S3 involves obtaining the resource allocation time decay coefficient, the user industry adjustment factor, and the user industry market concentration index. Using these factors, the resource matching priority for each user is calculated. This step can be, but is not limited to, decomposed into the following steps S31-S34:

[0097] S31. Obtain the user's industry type, wherein the user's industry type includes technology-intensive industries and technology-intensive industries;

[0098] S32. Obtain the resource allocation time decay coefficient λ, and according to the user industry type of each user, obtain the user industry adjustment factor η and user industry market concentration index of each user from the enterprise database, wherein the user industry market concentration index is represented by the Herfindahl-HHI index.

[0099] S33. The resource matching priority P is calculated using the following formula. ：

[0100]

[0101] S34. Calculate the resource matching priority for each user based on the user industry adjustment factor η and the user industry market concentration index.

[0102] It should be noted that in practice, the user industry adjustment factor η and the user industry market concentration index (Herfindahl-Hirschman Index, HHI) for each user should be obtained from data published in authoritative databases. The user industry adjustment factor η is related to the user's industry type. For example, if the user's industry type is labor-intensive, then the user industry adjustment factor η can be obtained from published data in authoritative databases: η = 0.95; if the user's industry type is technology-intensive, then the user industry adjustment factor η can be obtained from published data in authoritative databases: η = 1.25. The Herfindahl-Hirschman Index (HHI) is a comprehensive indicator used to measure market concentration. It quantifies the degree of market monopoly or competition by calculating the sum of the squares of the market share of all firms in a specific market. The higher the HHI value, the higher the market concentration and the higher the degree of monopoly. When the market is in a state of perfect monopoly, the Herfindahl-Hirschman Index (HHI) value is 10,000, while when there are many firms in the market of the same size, the HHI value approaches 0. Therefore, introducing the HHI can better take into account the impact of large firms on small and medium-sized firms and improve the resistance of resource matching and scheduling to monopoly.

[0103] S4. Based on the user industry market concentration index, select leading companies from each user, reduce the resource matching priority of the leading companies to obtain the reduced resource matching priority of the leading companies, use the reduced resource matching priority of the leading companies to replace the resource matching priority of the leading companies, and integrate and sort them to form an executable resource matching priority sequence.

[0104] In one possible implementation, in step S4, based on the user industry market concentration index, leading companies are selected from each user, and the resource matching priority of these leading companies is downgraded to obtain a downgraded resource matching priority. This downgraded resource matching priority is then used to replace the original resource matching priority of the leading companies, and the results are integrated and sorted to form an executable resource matching priority sequence. This can be decomposed into, but is not limited to, the following steps S41-S45, including:

[0105] S41. Obtain the user industry concentration threshold for each user;

[0106] S42. Compare the user industry market concentration index of each user with the user industry concentration threshold of each user one by one to determine whether the user industry market concentration index of each user exceeds the corresponding user industry concentration threshold.

[0107] S43. If not, the user is considered a non-leading enterprise; if yes, the user is considered a leading enterprise.

[0108] S44. Obtain the anti-monopoly weight penalty coefficient, and apply the anti-monopoly weight penalty coefficient to the resource matching priority of each user identified as a leading enterprise, thereby obtaining the resource matching priority of the leading enterprise with reduced weight, wherein the anti-monopoly weight penalty coefficient does not exceed 0.6.

[0109] S45. The resource matching priority of the top enterprise is replaced by the resource matching priority of the top enterprise, and the resource matching priority of each non-top enterprise is integrated and sorted with the resource matching priority of the top enterprise of each top enterprise to form an executable resource matching priority sequence for each user.

[0110] It should be noted that, in one possible implementation, after the priority reduction of leading enterprises is completed, at least three alternative resource providers can be automatically recommended to SMEs affected by the resource allocation of leading enterprises, increasing their matching opportunities and ensuring that SMEs can obtain at least 15% of high-value resources. This priority reduction mechanism can fully protect the resource allocation of SMEs, help SMEs operate and develop normally, and at the same time, greatly curb the monopoly of leading enterprises on resource allocation.

[0111] S5. Match and schedule resource configurations of each type according to the executable resource matching priority sequence to generate an optimal resource matching queue. Feed back the optimal resource matching queue to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

[0112] In one possible implementation, step S5 involves matching and scheduling resource configurations of various types according to the executable resource matching priority sequence to generate an optimal resource matching queue. This optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource matching suggestions and resource scheduling instructions. This step can be broken down into, but is not limited to, the following steps S51-S54, including:

[0113] S51. Obtain resource configurations of various types, perform resource matching on each type of resource configuration according to the executable resource matching priority sequence, and generate the optimal resource matching queue;

[0114] S52. Based on the optimal resource matching queue, generate resource matching suggestions based on the resource configuration of each type, wherein the resource matching suggestions include resource acquisition suggestions and resource scheduling suggestions, and there are multiple resource acquisition suggestions, each corresponding to a user;

[0115] S53. The resource acquisition suggestion is sent to each user accordingly, and the resource scheduling suggestion is sent to the resource provider;

[0116] S54. Based on the optimal resource matching queue, generate resource scheduling instructions for each type of resource configuration, and send the resource scheduling instructions for each type of resource configuration to the resource provider to complete resource scheduling.

[0117] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the resource intelligent matching method based on multi-dimensional co-occurrence coefficients described in the first aspect of the embodiment, including:

[0118] The user data acquisition module is used to acquire user profile data and real-time geographic weight factors. The user profile data includes the user's real-time interaction frequency and the user's actual resource usage time. The real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations.

[0119] The symbiosis coefficient calculation module is used to calculate the real-time symbiosis coefficient of each user based on the user profile data and the real-time geographic weight factor, wherein the real-time symbiosis coefficient is used to characterize the association strength between the resource provider and the user;

[0120] The priority calculation module is used to obtain the resource allocation time decay coefficient, user industry adjustment factor and user industry market concentration index, and to calculate the resource matching priority of each user using the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor and the user industry market concentration index. The resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time.

[0121] The de-weighting processing module is used to select leading companies from various users based on the user industry market concentration index, de-weight the resource matching priority of the leading companies, obtain the de-weighted resource matching priority of the leading companies, replace the resource matching priority of the leading companies with the de-weighted resource matching priority of the leading companies, and integrate and sort them to form an executable resource matching priority sequence.

[0122] The resource scheduling module is used to match and schedule resource configurations of various types according to the executable resource matching priority sequence to generate an optimal resource matching queue, and to feed back the optimal resource matching queue to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

[0123] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0124] like Figure 3As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the resource intelligent matching method based on multi-dimensional co-occurrence coefficients as described in the first aspect of the embodiment.

[0125] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0126] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0127] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0128] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the resource intelligent matching method based on multi-dimensional co-occurrence coefficients as described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when executed on a computer, perform the resource intelligent matching method based on multi-dimensional co-occurrence coefficients as described in the first aspect of the embodiment.

[0129] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0130] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0131] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the resource intelligent matching method based on multi-dimensional symbiosis coefficients as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0132] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A resource intelligent matching method based on multi-dimensional symbiosis coefficients, characterized in that, include: Acquire user profile data and real-time geographic weight factors, wherein the user profile data includes the frequency of real-time user interaction and the actual duration of user resource usage, and the real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations; Based on the user profile data and the real-time geographic weight factor, the real-time co-occurrence coefficient of each user is calculated, wherein the real-time co-occurrence coefficient is used to characterize the association strength between the resource provider and the user. The resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index are obtained. The resource matching priority of each user is calculated using the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor, and the user industry market concentration index. The resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time. Based on the user industry market concentration index, leading companies are selected from each user, and the resource matching priority of the leading companies is downgraded to obtain the downgraded resource matching priority of the leading companies. The downgraded resource matching priority of the leading companies is used to replace the resource matching priority of the leading companies, and the results are integrated and sorted to form an executable resource matching priority sequence. The resource configurations of each type are matched and scheduled according to the executable resource matching priority sequence to generate the optimal resource matching queue. The optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

2. The resource intelligent matching method based on multi-dimensional symbiosis coefficients according to claim 1, characterized in that, Obtain user profile data and real-time geographic weighting factors, including: The user profile data of each user is obtained from the enterprise database. The user profile data includes user productivity, user resource preference, user credit score, user social contribution rate, user real-time interaction frequency and user resource actual usage time. Real-time geographic weighting factors are obtained from a third-party geographic information database. These factors include a resource transportation timeliness coefficient and a distance attenuation coefficient. The resource transportation timeliness coefficient is used to characterize the correlation between resource transportation distance and transportation time, and the distance attenuation coefficient is used to characterize the degree of influence of resource transportation distance on resource value.

3. The resource intelligent matching method based on multi-dimensional symbiosis coefficients according to claim 2, characterized in that, Based on the user profile data and the real-time geographic weighting factor, the real-time co-occurrence coefficient of each user is calculated, including: The real-time co-occurrence coefficient K of basic users is calculated using the following formula. base : Among them, F int The real-time user interaction frequency is used to characterize the number of communication or transaction requests between the user and the resource provider within a preset time range. F base This is the industry benchmark interaction value, which is used to characterize the average interaction frequency of the industry to which the user company belongs. R reuse The resource reuse rate is used to characterize the proportion of the actual usage time of the user's resources in the total available resource duration; G(t) is the geographic decay function, which is calculated through the real-time geographic weighting factor and is used to characterize the impact of resource transportation distance on resource matching value. α, β, and γ are the interaction frequency weighting coefficient, resource reuse rate weighting coefficient, and geographical factor weighting coefficient, respectively, and the interaction frequency weighting coefficient, the resource reuse rate weighting coefficient, and the geographical factor weighting coefficient satisfy the following relationship: α+β+γ=1 (2) For each user, different interaction frequency weight coefficients, resource reuse rate weight coefficients, and geographical factor weight coefficients are preset, and calculations are performed separately based on the user profile data of each user to obtain the basic real-time user co-occurrence coefficient for each user.

4. The resource intelligent matching method based on multi-dimensional symbiosis coefficients according to claim 3, characterized in that, After obtaining the basic real-time co-occurrence coefficients for each user, the following is also included: The credit score of each user is quantified to obtain the credit weight ω of each user, and the social contribution rate of each user is quantified to obtain the social value score S of each user. Using each user's credit weight ω and social value score S, the non-monetary gain coefficient K is calculated using the following formula. gain : K gain =ω×S×0.2 (3) The non-monetary gain coefficient K for each user gain The real-time co-occurrence coefficient K of the basic users mentioned above for each user base Add them together to obtain the final real-time user co-occurrence coefficient K. final : K=K final =K base +K gain (4) The final user real-time co-occurrence coefficient K final K represents the real-time co-occurrence coefficient of each user.

5. The resource intelligent matching method based on multi-dimensional co-occurrence coefficients according to claim 4, characterized in that, Obtain the resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index, and use the user real-time symbiosis coefficient, resource allocation time decay coefficient, user industry adjustment factor, and user industry market concentration index to calculate the resource matching priority of each user, including: Obtain the user's industry type, wherein the user's industry type includes technology-intensive industries and technology-intensive industries; Obtain the resource allocation time decay coefficient λ, and according to the user industry type of each user, obtain the user industry adjustment factor η and user industry market concentration index of each user from the enterprise database, wherein the user industry market concentration index is represented by the Herfindahl-Hirschman Index (HHI). The resource matching priority P is calculated using the following formula: Based on the user industry adjustment factor η and the user industry market concentration index for each user, the resource matching priority for each user is calculated separately.

6. The resource intelligent matching method based on multi-dimensional symbiosis coefficients according to claim 1, characterized in that, Based on the user industry market concentration index, leading companies are selected from each user group. The resource matching priority of these leading companies is then downgraded to obtain a downgraded resource matching priority. This downgraded resource matching priority is used to replace the original resource matching priority of the leading companies, and the results are integrated and sorted to form an executable resource matching priority sequence, including: Obtain the user industry concentration threshold for each user; Each user's industry market concentration index is compared with each user's industry market concentration threshold to determine whether each user's industry market concentration index exceeds the corresponding industry market concentration threshold. If not, the user is considered a non-leading enterprise; if yes, the user is considered a leading enterprise. Obtain the anti-monopoly weight penalty coefficient, assign resource matching priority to each user identified as a leading enterprise, and use the anti-monopoly weight penalty coefficient to perform forced weight reduction processing to obtain the resource matching priority of the leading enterprise with reduced weight, wherein the anti-monopoly weight penalty coefficient does not exceed 0.6; The resource matching priority of the leading enterprise is replaced by the resource matching priority of the leading enterprise. The resource matching priority of each non-leading enterprise is integrated and sorted with the resource matching priority of the leading enterprise of each leading enterprise to form an executable resource matching priority sequence for each user.

7. The resource intelligent matching method based on multi-dimensional symbiosis coefficients according to claim 1, characterized in that, Resource configurations of various types are matched and scheduled according to the executable resource matching priority sequence to generate an optimal resource matching queue. This optimal resource matching queue is then fed back to each user and resource provider to generate and issue corresponding resource matching suggestions and resource scheduling instructions, including: Obtain resource configurations of various types, perform resource matching on each type of resource configuration according to the executable resource matching priority sequence, and generate the optimal resource matching queue; Based on the optimal resource matching queue, resource matching suggestions are generated based on the resource configuration of each type. The resource matching suggestions include resource acquisition suggestions and resource scheduling suggestions. There are multiple resource acquisition suggestions, each corresponding to a different user. The resource acquisition suggestions are sent to each user accordingly, and the resource scheduling suggestions are sent to the resource provider. Based on the optimal resource matching queue, resource scheduling instructions are generated for each type of resource configuration, and these instructions are sent to the resource provider to complete the resource scheduling.

8. A resource intelligent matching system based on multi-dimensional symbiosis coefficients, characterized in that, include: The user data acquisition module is used to acquire user profile data and real-time geographic weight factors. The user profile data includes the user's real-time interaction frequency and the user's actual resource usage time. The real-time geographic weight factors are used to characterize the relationship between resources and user geographic locations. The symbiosis coefficient calculation module is used to calculate the real-time symbiosis coefficient of each user based on the user profile data and the real-time geographic weight factor, wherein the real-time symbiosis coefficient is used to characterize the association strength between the resource provider and the user; The priority calculation module is used to obtain the resource allocation time decay coefficient, user industry adjustment factor and user industry market concentration index, and to calculate the resource matching priority of each user using the user real-time symbiosis coefficient, the resource allocation time decay coefficient, the user industry adjustment factor and the user industry market concentration index. The resource allocation time decay coefficient is used to characterize the rate at which the value of resources decays over time. The de-weighting processing module is used to select leading companies from various users based on the user industry market concentration index, de-weight the resource matching priority of the leading companies, obtain the de-weighted resource matching priority of the leading companies, replace the resource matching priority of the leading companies with the de-weighted resource matching priority of the leading companies, and integrate and sort them to form an executable resource matching priority sequence. The resource scheduling module is used to match and schedule resource configurations of various types according to the executable resource matching priority sequence to generate an optimal resource matching queue, and to feed back the optimal resource matching queue to each user and resource provider to generate and issue corresponding resource scheduling suggestions and resource scheduling instructions.

9. An electronic device, characterized in that, The system includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the resource intelligent matching method based on multi-dimensional co-occurrence coefficients as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the resource intelligent matching method based on multi-dimensional symbiosis coefficients as described in any one of claims 1 to 7.

Images