Rental-purchase management system and method with assorted relationship established

Abstract

The invention discloses a lease and purchase management system and method with a determined matching relation, and relates to the field of mechanical equipment software lease management systems.The system provided by the invention can construct and optimize a two-dimensional mechanical equipment combination matrix and generate a user feature matrix and an article feature matrix through matrix decomposition, so that equipment feature vectors are dynamically extracted. The system also calculates the similarity between the devices through the implicit matching coefficient, so as to generate a recommendation list with high matching device combination, thereby realizing the intelligent recommendation of the matching lease.

Description

Technical Field

[0001] The present invention relates to the field of mechanical equipment software leasing management system, and in particular to a leasing and purchasing management system and method for establishing a matching relationship. Background Art

[0002] In the machinery and equipment leasing industry, traditional leasing management systems usually rely on manual or simple online systems to complete the recommendation and supporting management of equipment leasing. These systems usually rely on static equipment information and leasing demand data, and it is difficult to dynamically capture the specific needs of users, historical leasing data, and the real-time leasing status of equipment. Traditional leasing management systems generally include a client and a backend, which are connected through an API interface to achieve basic data transmission between the client and the backend. Users can view the availability of equipment on the client and submit leasing requests to the backend. The backend processes the user's leasing request based on the equipment data in the system. However, this system focuses more on the leasing process of a single device and does not have an intelligent supporting recommendation function, making it difficult to effectively solve the combination needs of mechanical equipment. Since mechanical equipment often needs to be used in conjunction with other equipment in some scenarios, a single leasing recommendation is difficult to meet the multi-equipment leasing needs in complex application scenarios. For example, construction sites, engineering construction, mineral mining and other occasions often involve the coordinated use of multiple equipment, including excavators, cranes, transport vehicles and other equipment, and combined recommendations are required to meet actual needs.

[0003] At present, some advanced rental management systems have begun to try to introduce collaborative filtering recommendation algorithms, hoping to provide users with personalized equipment recommendations based on user historical data and equipment usage records. However, the recommendation process of these systems often stays at the recommendation between users and a single device, and it is difficult to handle scenarios involving the use of multiple devices. In actual operation, the defect of traditional systems is that they lack the ability to integrate and analyze multi-dimensional data. Since the rental demand of equipment is closely related to multiple factors such as equipment characteristics, rental frequency, and customer historical rental behavior, traditional systems are usually unable to make full use of these data to achieve accurate recommendations. First, traditional systems lack data-driven analysis and intelligent recommendation capabilities in equipment combination recommendations, which makes it difficult to provide effective equipment matching combination recommendations, affecting user experience. For example, in engineering projects, the rental demand for different equipment often changes according to project progress or construction period requirements, and a single equipment recommendation is difficult to meet these changing needs. Secondly, the calculation of equipment matching coefficients by traditional systems relies on fixed rules or static parameters and lacks dynamic adjustment capabilities. Since equipment may have matching requirements in different application scenarios, traditional systems are usually unable to flexibly adjust recommendation strategies according to actual usage, resulting in insufficient accuracy of recommendation results. In addition, the real-time data transmission efficiency in traditional systems is limited, making it difficult to efficiently process a large number of access requests and synchronously return real-time equipment rental data and recommendation results. Especially during the peak rental period, the data processing speed of traditional systems can easily become a bottleneck, affecting the user's rental experience. Summary of the invention

[0004] The present invention proposes a rental and purchase management system and method for establishing matching relationships, which realizes intelligent and dynamic equipment combination recommendation by introducing multiple technical means.

[0005] Among them, a rental and purchase management system with established matching relationship includes a client and a backend, the client and the backend are connected through an API interface communication, the client is used to send an access request to the backend, the backend is used to receive the access request and send real-time rental data to the client, the client sends a user rental request to the backend according to the real-time rental data, and the access request includes the user rental data;

[0006] Further:

[0007] The system also includes a server, which is connected to the database of the client and the backend respectively, and extracts the user rental data of the client and the mechanical equipment rental data in the database of the backend respectively, and the server is used to perform supporting rental analysis based on the extracted user rental data and mechanical equipment rental data;

[0008] The server specifically includes:

[0009] A data extraction unit is used to extract user rental data from the client and mechanical equipment rental data from the database of the backend, and to construct a two-dimensional mechanical equipment combination matrix based on the extracted data;

[0010] A feature extraction unit, used to decompose the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extract feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix;

[0011] An implicit matching coefficient calculation unit is used to calculate the similarity between mechanical devices according to the characteristic vectors of the mechanical devices and generate a mechanical device matching coefficient matrix;

[0012] A mechanical equipment combination recommendation unit is used to recommend a mechanical equipment combination that meets user needs based on an implicit matching coefficient and send mechanical equipment combination recommendation data;

[0013] After the client sends an access request to the backend, the backend and the server receive the access request at the same time, and the server and the backend send mechanical equipment combination recommendation data and real-time rental data to the client respectively.

[0014] Furthermore, in the data extraction unit, a two-dimensional mechanical equipment combination matrix is ​​used to represent the mechanical equipment E i and E j The mechanical equipment combination matrix is ​​represented by R(i,j), where R represents a two-dimensional matrix and W i and E j They respectively represent two different mechanical equipment IDs, and i and j respectively represent indexes of two different mechanical equipment.

[0015] Furthermore, the two-dimensional matrix R is specifically expressed as:

[0016]

[0017] Wherein, n represents the total number of mechanical equipment.

[0018] Furthermore, in the feature extraction unit, decomposing the mechanical equipment combination matrix into the user feature matrix and the item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely:

[0019] R≈P·Q T ;

[0020] Among them, R represents a two-dimensional matrix, P is the user feature matrix of mechanical equipment, that is, the potential features of mechanical equipment in user evaluation or rental behavior, Q is the item feature matrix of mechanical equipment, which represents the feature vector of mechanical equipment in the combination of mechanical equipment, and T represents transpose.

[0021] Furthermore, the implicit matching coefficient calculation unit specifically includes:

[0022] The implicit matching coefficient calculation subunit is used to calculate the matching coefficient by the similarity of the extracted mechanical equipment feature vectors;

[0023] An initialization matrix subunit is used to create an n×n initial matrix, wherein the initial matrix is ​​used to store matching coefficients between each pair of mechanical devices;

[0024] The matching coefficient subunit is used to fill the calculated matching coefficient value into the corresponding position in the matrix;

[0025] The matrix post-processing subunit is used to normalize the matrix by maximum and minimum scaling.

[0026] Furthermore, in the calculation of the implicit matching coefficient subunit, the calculation of the matching coefficient is specifically expressed as:

[0027]

[0028] Wherein, S(i,j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) represent the mechanical equipment E i and E j The characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

[0029] Furthermore, a rental purchase management method for establishing a matching relationship is provided, which is implemented based on any of the rental purchase management systems for establishing a matching relationship described above, and the method is applied to a server, and includes the following steps:

[0030] S1. Receive an access request sent by a client, wherein the access request includes user rental data;

[0031] S2. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend;

[0032] S3. Conduct supporting leasing analysis based on the extracted user leasing data and machinery and equipment leasing data;

[0033] Wherein, the step S3 specifically includes the following sub-steps:

[0034] S301. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend, and construct a two-dimensional mechanical equipment combination matrix based on the extracted data;

[0035] S302. Decomposing the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extracting the feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix;

[0036] S303. Calculate the similarity between mechanical equipment according to the characteristic vector of the mechanical equipment and generate a mechanical equipment matching coefficient matrix;

[0037] S304. Recommend a mechanical equipment combination that meets the user's needs based on the implicit matching coefficient, and send the mechanical equipment combination recommendation data to the client.

[0038] Furthermore, in step S302, decomposing the mechanical equipment combination matrix into a user feature matrix and an item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely:

[0039] R≈P·Q T ;

[0040] Among them, R represents a two-dimensional matrix, P is the user feature matrix of mechanical equipment, that is, the potential features of mechanical equipment in user evaluation or rental behavior, Q is the item feature matrix of mechanical equipment, which represents the feature vector of mechanical equipment in the combination of mechanical equipment, and T represents transpose.

[0041] Furthermore, the step S303 specifically includes the following sub-steps:

[0042] S3031. Calculate the matching coefficient by extracting the similarity of the mechanical equipment feature vector;

[0043] S3032. Create an n×n initial matrix, the initial matrix is ​​used to store the matching coefficients between each pair of mechanical equipment;

[0044] S3033. Fill the calculated matching coefficient value into the corresponding position in the matrix;

[0045] S3034. Normalize the matrix by maximum and minimum scaling.

[0046] Furthermore, in step S3031, the calculation of the matching coefficient is specifically expressed as:

[0047]

[0048] Wherein, S(i,j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) represent the mechanical equipment E i and E jThe characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

[0049] The beneficial effects of the invention are:

[0050] The system provided by the present invention can construct and optimize a two-dimensional mechanical equipment combination matrix, and generate a user feature matrix and an item feature matrix through matrix decomposition, thereby dynamically extracting equipment feature vectors. The system also calculates the similarity between devices through implicit matching coefficients, thereby generating a recommendation list of equipment combinations with high matching, thereby realizing intelligent recommendation of matching rental. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A system data flow diagram of a rental-purchase management system for establishing a matching relationship provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0053] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0054] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work are within the scope of protection of the present invention. It should be noted that relational terms such as the terms "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0055] Moreover, the terms "comprises," "comprising," or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or machine that includes a list of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article, or machine. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or machine that includes the element.

[0056] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0057] Among them, Figure 1 , a rental and purchase management system with established matching relationship, including a client and a backend, the client and the backend are connected through an API interface communication, the client is used to send an access request to the backend, the backend is used to receive the access request and send real-time rental data to the client, the client sends a user rental request to the backend according to the real-time rental data, the access request includes the user rental data;

[0058] Furthermore, the system also includes a server, which is connected to the database of the client and the backend respectively, and extracts the user rental data of the client and the mechanical equipment rental data in the database of the backend respectively, and the server is used to perform supporting rental analysis according to the extracted user rental data and mechanical equipment rental data;

[0059] The server specifically includes:

[0060] A data extraction unit is used to extract user rental data from the client and mechanical equipment rental data from the database of the backend, and to construct a two-dimensional mechanical equipment combination matrix based on the extracted data;

[0061] A feature extraction unit, used to decompose the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extract feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix;

[0062] An implicit matching coefficient calculation unit is used to calculate the similarity between mechanical devices according to the characteristic vectors of the mechanical devices and generate a mechanical device matching coefficient matrix;

[0063] A mechanical equipment combination recommendation unit is used to recommend a mechanical equipment combination that meets user needs based on an implicit matching coefficient and send mechanical equipment combination recommendation data;

[0064] After the client sends an access request to the backend, the backend and the server receive the access request at the same time, and the server and the backend send mechanical equipment combination recommendation data and real-time rental data to the client respectively.

[0065] Specifically, the user rental data in the client reflects the user's rental needs, preferences and other characteristics; the back-end database contains the rental data of all mechanical equipment, recording the type, purpose, rental status and other information of each equipment. The data extraction unit obtains the above two types of data through the API interface and integrates them into a two-dimensional mechanical equipment combination matrix. The elements in the matrix represent the user's preference for a specific mechanical equipment or the actual rental status.

[0066] Furthermore, in the data extraction unit, a two-dimensional mechanical equipment combination matrix is ​​used to represent the mechanical equipment E i and E j The mechanical equipment combination matrix is ​​represented by R(i,j), where R represents a two-dimensional matrix and W i and E j They respectively represent two different mechanical equipment IDs, and i and j respectively represent indexes of two different mechanical equipment.

[0067] Furthermore, the two-dimensional matrix R is specifically expressed as:

[0068]

[0069] Wherein, n represents the total number of mechanical equipment.

[0070] Furthermore, in the feature extraction unit, decomposing the mechanical equipment combination matrix into the user feature matrix and the item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely:

[0071] R≈P·Q T ;

[0072] Wherein, R represents a two-dimensional matrix, P is a user feature matrix of mechanical equipment, i.e., the potential features of mechanical equipment in user evaluation or rental behavior, Q is an item feature matrix of mechanical equipment, representing the feature vector of mechanical equipment in mechanical equipment combination, and T represents transposition. Specifically, the above matrix decomposition may preferably adopt singular value decomposition (SVD) or non-negative matrix decomposition (NMF), and matrix decomposition is used to convert sparse matrices into low-rank matrices to extract potential matching relationships between equipment. For example, non-negative matrix decomposition is selected:

[0073]

[0074] Among them, the P ikrepresents the value of the i-th device on the k-th implicit feature, the Q jk represents the value of the i-th device on the k-th implicit feature, where k represents the number of the implicit feature, ranging from 1 to d, where d is the feature dimension selected during decomposition (ie, the number of implicit features).

[0075] For P: According to the current Q value, gradually update each row so that R ≈ P·Q T ; For Q, under the condition that P is fixed, gradually update each column to optimize the overall reconstruction error.

[0076] The above process is iterated until convergence, that is, the loss function changes to zero or meets the accuracy requirements.

[0077] Furthermore, as a preferred implementation of the above embodiment, in order to find the optimal p and Q values, it is necessary to define and minimize the loss function, specifically:

[0078] L=∑ (i,j)∈R (R(i,j)-(P·Q T )(i,j)) 2 +λ(||P|| 2 +||Q|| 2 );

[0079] Wherein, the R(i,j)-(P·Q T )(o,j)) 2 Represents the reconstruction error, which is used to measure the matrix R and P·Q T similarity, the λ is the regularization coefficient, the ||P|| 2 +||Q|| 2 It is a regularization term that avoids overfitting by constraining the P and Q values.

[0080] Furthermore, the implicit matching coefficient calculation unit specifically includes:

[0081] The implicit matching coefficient calculation subunit is used to calculate the matching coefficient by the similarity of the extracted mechanical equipment feature vectors; specifically, the main task of the implicit matching coefficient calculation subunit is to use the feature vectors of the mechanical equipment to calculate the similarity between each pair of equipment to generate the matching coefficient. After the implicit matching coefficient calculation subunit extracts the feature vectors of the mechanical equipment, it uses methods such as cosine similarity and Pearson correlation coefficient to evaluate the similarity of each pair of equipment, thereby calculating the matching coefficient between them. These matching coefficients are used to characterize the degree of fit or adaptability between the equipment, thereby providing a basis for the recommendation unit.

[0082] The matrix initialization subunit is used to create an n×n initial matrix, which is used to store the matching coefficients between each pair of mechanical devices; specifically, the matrix initialization subunit is used to create an initial matrix for storing matching coefficients. In the system initialization phase, the subunit generates an empty matrix structure, the rows and columns of which represent the various devices in the system, and the element values ​​in the matrix are empty or default values ​​at the beginning. The initialized matrix provides storage space for subsequent steps to fill in the matching coefficients of each pair of devices calculated.

[0083] The matching coefficient subunit is used to fill the calculated matching coefficient value into the corresponding position in the matrix; the matrix post-processing subunit is used to normalize the matrix through maximum and minimum scaling; specifically, the matching coefficient subunit is responsible for filling the calculated matching coefficient value into the corresponding position in the matrix. For each pair of matching relationships of devices, once the matching coefficient is calculated, the subunit will store the matching coefficient in the corresponding position of the matching coefficient matrix. After filling the matrix one by one, the matching coefficient matrix will completely record the matching relationships between all devices.

[0084] Furthermore, in the calculation of the implicit matching coefficient subunit, the calculation of the matching coefficient is specifically expressed as:

[0085]

[0086] Wherein, S(i,j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) represent the mechanical equipment E i and E j The characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

[0087] Specifically, there are two implementation methods for implementing device recommendation through implicit matching coefficients, including:

[0088] Based on the recommendation of matching coefficient, for each device, according to the set of matching coefficients between the device and other devices, find the device with the highest matching coefficient and recommend the device combination.

[0089] Set a recommendation threshold, set a threshold for the matching coefficient, and illustratively, only recommend equipment combinations with S(i,j)>0.5.

[0090] Furthermore, P(i,:) is the device E i The feature vector in the latent feature space represents the performance of the device on the “user demand”. Q(j,:) is the device E jThe feature vector in the implicit feature space represents the performance of the device as a "supporting item", and the dot product P(i,:)·Q(j,:) measures the directional similarity of the two feature vectors. The modulus normalization of the denominator ensures that the similarity is in the range of [0,1]. In addition, through the above calculation, S(i,j) is the device E i and E j The matching coefficient.

[0091] The above implementation utilizes the user-item based matrix decomposition technology in collaborative filtering to represent the implicit requirements and features of the device as vectorized features, thereby measuring the similarity of the devices in the implicit feature space. For example, the performance of some devices in the implicit feature space may be more similar to that of another type of device, so that matching recommendations can be made based on feature similarity.

[0092] Furthermore, a rental purchase management method for establishing a matching relationship is provided, which is implemented based on any of the rental purchase management systems for establishing a matching relationship described above, and the method is applied to a server, and includes the following steps:

[0093] S1. Receive an access request sent by a client, wherein the access request includes user rental data;

[0094] S2. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend;

[0095] S3. Conduct supporting leasing analysis based on the extracted user leasing data and machinery and equipment leasing data;

[0096] Wherein, the step S3 specifically includes the following sub-steps:

[0097] S301. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend, and construct a two-dimensional mechanical equipment combination matrix based on the extracted data;

[0098] S302. Decomposing the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extracting the feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix;

[0099] S303. Calculate the similarity between mechanical equipment according to the characteristic vector of the mechanical equipment and generate a mechanical equipment matching coefficient matrix;

[0100] S304. Recommend a mechanical equipment combination that meets the user's needs based on the implicit matching coefficient, and send the mechanical equipment combination recommendation data to the client.

[0101] Furthermore, in step S302, decomposing the mechanical equipment combination matrix into a user feature matrix and an item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely:

[0102] R≈P·Q T ;

[0103] Among them, R represents a two-dimensional matrix, P is the user feature matrix of mechanical equipment, that is, the potential features of mechanical equipment in user evaluation or rental behavior, Q is the item feature matrix of mechanical equipment, which represents the feature vector of mechanical equipment in the combination of mechanical equipment, and T represents transpose.

[0104] Furthermore, the step S303 specifically includes the following sub-steps:

[0105] S3031. Calculate the matching coefficient by extracting the similarity of the mechanical equipment feature vector;

[0106] S3032. Create an n×n initial matrix, the initial matrix is ​​used to store the matching coefficients between each pair of mechanical equipment;

[0107] S3033. Fill the calculated matching coefficient value into the corresponding position in the matrix;

[0108] S3034. Normalize the matrix by maximum and minimum scaling.

[0109] Furthermore, in step S3031, the calculation of the matching coefficient is specifically expressed as:

[0110]

[0111] Wherein, S(i,j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) represent the mechanical equipment E i and E j The characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

[0112] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.

Claims

1. A rental and purchase management system with established matching relationships, comprising a client and a backend, wherein the client and the backend are connected through an API interface, wherein the client is used to send an access request to the backend, and the backend is used to receive the access request and send real-time rental data to the client, and the client sends a user rental request to the backend according to the real-time rental data, wherein the access request includes the user rental data; Features: The system also includes a server, which is connected to the database of the client and the backend respectively, and extracts the user rental data of the client and the mechanical equipment rental data in the database of the backend respectively, and the server is used to perform supporting rental analysis based on the extracted user rental data and mechanical equipment rental data; The server specifically includes: A data extraction unit is used to extract user rental data from the client and mechanical equipment rental data from the database of the backend, and to construct a two-dimensional mechanical equipment combination matrix based on the extracted data; A feature extraction unit, used to decompose the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extract feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix; An implicit matching coefficient calculation unit is used to calculate the similarity between mechanical devices according to the characteristic vectors of the mechanical devices and generate a mechanical device matching coefficient matrix; A mechanical equipment combination recommendation unit is used to recommend a mechanical equipment combination that meets user needs based on an implicit matching coefficient and send mechanical equipment combination recommendation data; After the client sends an access request to the backend, the backend and the server receive the access request at the same time, and the server and the backend send mechanical equipment combination recommendation data and real-time rental data to the client respectively.

2. A rental and purchase management system for establishing a matching relationship as claimed in claim 1, characterized in that: In the data extraction unit, the two-dimensional mechanical equipment combination matrix is ​​used to represent the mechanical equipment E i and E j The mechanical equipment combination matrix is ​​represented by R(i,j), where R represents a two-dimensional matrix and E i and E j They respectively represent two different mechanical equipment IDs, and i and j respectively represent indexes of two different mechanical equipment.

3. A rental and purchase management system for establishing matching relationships as claimed in claim 2, characterized in that: The two-dimensional matrix R is specifically expressed as: Wherein, n represents the total number of mechanical equipment.

4. A rental and purchase management system for establishing matching relationships as claimed in claim 1, characterized in that: In the feature extraction unit, decomposing the mechanical equipment combination matrix into the user feature matrix and the item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely: R≈P·Q T ; Among them, R represents a two-dimensional matrix, P is the user feature matrix of mechanical equipment, that is, the potential features of mechanical equipment in user evaluation or rental behavior, Q is the item feature matrix of mechanical equipment, which represents the feature vector of mechanical equipment in the combination of mechanical equipment, and T represents transpose.

5. A rental and purchase management system for establishing matching relationships as claimed in claim 1, characterized in that: The implicit matching coefficient calculation unit specifically includes: The implicit matching coefficient calculation subunit is used to calculate the matching coefficient by the similarity of the extracted mechanical equipment feature vectors; An initialization matrix subunit is used to create an n×n initial matrix, wherein the initial matrix is ​​used to store matching coefficients between each pair of mechanical devices; The matching coefficient subunit is used to fill the calculated matching coefficient value into the corresponding position in the matrix; Matrix post-processing is used to normalize the matrix by maximum and minimum scaling.

6. A rental and purchase management system for establishing matching relationships as claimed in claim 5, characterized in that: In the calculation of implicit matching coefficient subunit, the calculation of matching coefficient is specifically expressed as: Wherein, S(i,j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) represent the mechanical equipment E i and E j The characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

7. A rental and purchase management method for establishing a matching relationship, the method is implemented based on a rental and purchase management system for establishing a matching relationship as described in any one of claims 1 to 6, characterized in that: Applied to the server, it includes the following steps: S1. Receive an access request sent by a client, wherein the access request includes user rental data; S2. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend; S3. Conduct supporting leasing analysis based on the extracted user leasing data and machinery and equipment leasing data; Wherein, the step S3 specifically includes the following sub-steps: S301. Extract the user rental data of the client and the mechanical equipment rental data in the database of the backend, and construct a two-dimensional mechanical equipment combination matrix based on the extracted data; S302. Decomposing the mechanical equipment combination matrix into a user feature matrix and an item feature matrix, and extracting the feature vectors of the mechanical equipment in the matrix according to the user feature matrix and the item feature matrix; S303. Calculate the similarity between mechanical equipment according to the characteristic vector of the mechanical equipment and generate a mechanical equipment matching coefficient matrix; S304. Recommend a mechanical equipment combination that meets the user's needs based on the implicit matching coefficient, and send the mechanical equipment combination recommendation data to the client.

8. A rental purchase management method for establishing a matching relationship as claimed in claim 7, characterized in that: In step S302, decomposing the mechanical equipment combination matrix into the user feature matrix and the item feature matrix is ​​specifically as follows: decomposing the mechanical equipment combination matrix into the product of two low-rank matrices, namely: R≈P·Q T ; Among them, R represents a two-dimensional matrix, P is the user feature matrix of mechanical equipment, that is, the potential features of mechanical equipment in user evaluation or rental behavior, Q is the item feature matrix of mechanical equipment, which represents the feature vector of mechanical equipment in the combination of mechanical equipment, and T represents transpose.

9. A rental purchase management method for establishing a matching relationship as claimed in claim 7, characterized in that: The step S303 specifically includes the following sub-steps: S3031. Calculate the matching coefficient by extracting the similarity of the mechanical equipment feature vector; S3032. Create an n×n initial matrix, the initial matrix is ​​used to store the matching coefficients between each pair of mechanical equipment; S3033. Fill the calculated matching coefficient value into the corresponding position in the matrix; S3034. Normalize the matrix by maximum and minimum scaling.

10. A rental purchase management method for establishing a matching relationship as claimed in claim 9, characterized in that: In step S3031, the calculation of the matching coefficient is specifically expressed as: Wherein, S(i, j) represents the mechanical equipment E i and E j The matching coefficients of P(i,:) and Q(j,:) respectively represent the mechanical equipment E i and E j The characteristic vectors of ||P(i,:)|| and ||Q(j,:)|| represent the mechanical equipment E i and E j The length of the eigenvector of .

Images