A computer rental operation system based on Internet

Abstract

The present invention discloses an Internet-based computer rental operation system, which relates to the field of rental management technology and is used to solve the problem that new equipment demands of enterprises and individuals are not met as business expands, personnel increase or technology updates, thereby reducing user experience and rental coverage. Information on rented enterprises and information on unrented enterprises are collected and brought into a random forest prediction model to obtain the probability of new demand for each rented enterprise and the probability of rental demand for each unrented enterprise, and then average them and perform weighted calculation to obtain a regional rental demand assessment coefficient, which is compared with a preset demand threshold to obtain the enterprise with the most demand characteristics. The conversion rate of unrented enterprises to rented enterprises per unit time and the rate of increase of regional unrented enterprises per unit time are brought into fuzzy logic to determine the weight assignment result, thereby improving the accuracy of regional rental coverage and saving computing resources.

Description

Technical Field

[0001] The present invention relates to the technical field of leasing management, and more specifically, to an Internet-based computer leasing operation system. Background Art

[0002] With the rapid development of information technology, the demand for computer equipment by individuals and enterprises is increasing. The recommendation method for computer rental in the traditional computer rental operation system mainly relies on offline sales recommendations and online information delivery, which is based on simple equipment classification and fixed promotion strategies.

[0003] The prior art has the following deficiencies:

[0004] At present, different regional structures are prioritized for offline sales recommendations, and there is no in-depth exploration of whether individuals or companies that have already leased have the possibility of further leasing. Obviously, leasing does not mean that the user's needs are completely fixed, especially with the expansion of business, increase in personnel or technological updates, enterprises and individuals have new equipment needs that are not met, which in turn reduces user experience and leasing coverage. Therefore, an Internet-based computer leasing operation system is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an Internet-based computer rental operation system, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0007] To achieve the above object, the present invention provides the following technical solution: a computer rental operation system based on the Internet, including a data collection module, a data processing module, a demand analysis module and a weight assignment module; signal connections between the modules;

[0008] The data collection module is used to collect information about leased and unleased enterprises. Through data processing, the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of unleased industries in the region are obtained and sent to the data processing module;

[0009] The data processing module is used to obtain the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of regional unleased industries. The random forest prediction model is used to obtain the probability of new demand for each leased enterprise and the probability of lease demand for each unleased enterprise, and send them to the demand analysis module;

[0010] The demand analysis module is used to receive the new demand probability of each leased enterprise and the lease demand probability of each unleased enterprise, and perform weighted calculation after averaging to obtain the regional lease demand assessment coefficient, and compare it with the preset demand threshold to obtain the comparison result and obtain the enterprise information with the most demand characteristics based on the comparison result, and send it to the weight assignment module;

[0011] The weight assignment module is used to obtain the enterprise information with the most demand characteristics. By analyzing the corresponding regional leasing demand assessment coefficient, the conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time are obtained, and then normalized and fuzzy logic is used to determine the weight assignment results.

[0012] In a preferred embodiment, the data processing process is as follows:

[0013] By collecting the original number of employees in the leased enterprise information and the number of current employees after a unit of time and calculating the ratio, the proportion of new employees in the leased enterprise can be obtained. ; Where t is the t-th unit time; q=1, 2, 3, ..., p, p is the total number of leased enterprises;

[0014] The utilization rate of corporate rental computers is calculated by adding the daily utilization rate of corporate rental computers per unit time and calculating the ratio of the time per unit time. ;

[0015] The signing time of the lease contract can be obtained by checking the lease contract and the renewal and termination agreements submitted by the enterprise between the signing date of the lease contract and the end date of the contract. ;

[0016] The lease contract period is obtained by subtracting the current time from the leased computer's usage period. ;

[0017] The ratio of the total area of ​​the unrented enterprise to the total number of its current employees is calculated to obtain the ratio of the enterprise area to the number of employees. ; Where j is the jth unleased enterprise;

[0018] The market share data of unrented enterprises in the region and the region as a whole are collected in adjacent unit time periods and the difference is calculated by the Herfindahl-Hirschman index to obtain the regional unrented industry concentration index difference. .

[0019] In a preferred embodiment, the proportion of new employees in the leased enterprises, the utilization rate of leased computers in the enterprises, the signing time of the lease contract, the lease contract period, the ratio of enterprise area to employees, and the difference in the concentration index of the unleased industries in the region are normalized and brought into the feature matrix. , the feature matrix Each feature in is brought into the random forest model trained by verifying the model accuracy to calculate the probability of new demand for each leased enterprise and the probability of leasing demand for each unleased enterprise. The specific formula is expressed as:

[0020] as well as ;

[0021] In the formula, is the probability of new demand for leased enterprises, is the probability of leasing demand of unleased enterprises, The newly inputted characteristic data of the leased enterprise include the proportion of new employees in the leased enterprise, the utilization rate of the leased computers in the enterprise, the signing time of the lease contract, and the term of the lease contract; The newly input unrented enterprise characteristic data includes the enterprise area to number of employees ratio and the regional unrented industry concentration index difference. is the output result generated by the mth decision tree, m is the mth decision tree, and M is the total number of decision trees.

[0022] In a preferred embodiment, the new demand probability set of leased enterprises and the rental demand probability set of unleased enterprises are obtained, which are: as well as ; Perform average processing and then substitute it into the weighted calculation formula to obtain the regional rental demand assessment coefficient, which is:

[0023] ;

[0024] In the formula, is the regional rental demand assessment coefficient, is the average probability of new demand for leased enterprises, is the average probability of leasing demand of unleased enterprises; as well as are the preset proportional coefficients of the average probability of new demand of leased enterprises and the average probability of leasing demand of unleased enterprises, respectively, and as well as are greater than 0, is the total number of unleased enterprises.

[0025] In a preferred embodiment, if the regional rental demand assessment coefficient is greater than or equal to the demand threshold, the region is marked as a demand region and a recommendation signal is generated;

[0026] If the regional rental demand assessment coefficient is less than the demand threshold, the area is marked as a saturated area and a saturation signal is generated.

[0027] In a preferred embodiment, for the area where the recommendation signal is generated, the product of the maximum value of the probability of new demand of the rented enterprises in the area and the average value of the probability of new demand of the rented enterprises and the product of the maximum value of the probability of leasing demand of the unrented enterprises and the average value of the probability of leasing demand of the unrented enterprises are obtained, and the sizes are compared, and the maximum value after comparison is taken as the enterprise with the most demand characteristics.

[0028] In a preferred embodiment, the enterprise information with the most demand characteristics includes the conversion rate of unleased enterprises to leased enterprises per unit time and the increase rate of unleased enterprises in the region per unit time.

[0029] In a preferred embodiment, the conversion rate of unleased enterprises to leased enterprises per unit time is obtained by calculating the ratio of the number of unleased enterprises converted to leased enterprises after signing the lease contract to the total number of original unleased enterprises;

[0030] By calculating the ratio of the number of unrented enterprises in the region that increases per unit time to the total number of enterprises in the region, the rate of increase of unrented enterprises in the region per unit time can be obtained.

[0031] In a preferred embodiment, the conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in a region per unit time are defined as input variables and divided into different fuzzy sets respectively;

[0032] The weight assignment result is defined as the output variable and divided into fuzzy sets;

[0033] Formulate fuzzy rules to describe the conversion rate of unleased enterprises to leased enterprises per unit time and the impact of the increase rate of unleased enterprises in the region per unit time on the weight assignment results;

[0034] Perform fuzzy reasoning based on fuzzy rules and determine the weight assignment scheme.

[0035] Technical effects and advantages of the present invention:

[0036] 1. The present invention collects the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to number of employees, and the difference in concentration index of unleased industries in the region, and brings them into the random forest prediction model to obtain the probability of new demand for each leased enterprise and the probability of lease demand for each unleased enterprise, and then performs weighted calculation after averaging to obtain the regional lease demand assessment coefficient and compares it with the preset demand threshold to obtain the enterprise with the most demand characteristics, and dynamically predict the demand. At the same time, the lease probability of the leased enterprises is combined to improve the accuracy of the regional lease coverage, so as to achieve the purpose of quickly finding the enterprise with the most demand characteristics and save computing resources.

[0037] 2. The present invention uses the normalized conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time, and introduces fuzzy logic to determine the weight assignment result, thereby eliminating the differences between features and making the weights dynamically changeable. The calculation of the regional leasing demand assessment coefficient for the next unit time is more accurate, thereby improving the accuracy of the prediction and ensuring the efficiency of the system in mining the enterprises with the most demand characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a module schematic diagram of an Internet-based computer rental operation system. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example 1

[0041] The present invention discloses a computer rental operation system based on the Internet, such as Figure 1 As shown, it includes a data acquisition module, a data processing module, a demand analysis module and a weight assignment module; the signal connections between the modules;

[0042] The data collection module is used to collect information about leased and unleased enterprises. Through data processing, the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of unleased industries in the region are obtained and sent to the data processing module;

[0043] Specifically, the information of leased enterprises includes the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts and the term of lease contracts; the information of unleased enterprises includes the ratio of enterprise area to employees and the difference in concentration index of unleased industries in different regions;

[0044] For leased and unleased enterprises, the data collection module is connected to the Internet to query the corresponding leased and unleased enterprises;

[0045] It should be noted that the data analysis module prioritizes dividing the operating city or region into multiple regions. The number and rules of the specific division regions are not limited, but are divided by the experimenters based on the number of urban areas or regional enterprises, which will not be elaborated here;

[0046] There are multiple leased enterprises and multiple unleased enterprises in a certain area. This embodiment takes the area as the analysis object and connects to the Internet through the data acquisition module to query the corresponding leased enterprises and unleased enterprises in the area.

[0047] The ratio of new employees in rented companies refers to the ratio of the number of new employees in a company that has rented computer equipment to the total number of original employees in the company within a unit of time. The acquisition logic is to define the length of the unit time first, and obtain the ratio of new employees in the rented company by collecting the original number of employees in the rented company information and the number of current employees after a unit of time and calculating the ratio. ; Where t is the t-th unit time; q=1, 2, 3, ..., p, p is the total number of leased enterprises;

[0048] It should be noted that the definition of unit time length is usually based on the built-in clock of the rental operation system and is set by the experimenter in the system background. For example, "one month" or "one quarter" is not limited here.

[0049] Furthermore, the data collection module collects the original number of employees through the signed lease contract, and obtains the current number of employees by connecting to the Internet to query the company's public information after a unit of time;

[0050] The utilization rate of leased computers in an enterprise refers to the ratio of the number of computers actually used by the enterprise among the leased computers to the total number of leased computers combined with the usage time of the leased computers. The logic for obtaining it is to calculate the ratio of the number of computers actually used by the enterprise among the leased computers per day to the total number of leased computers in a unit of time and the ratio of the time the enterprise uses the leased computers every day to the total time of the day, and then get the formula:

[0051] ;

[0052] In the formula, Computer utilization for business rental, is the number of computers actually used on the first day, is the total number of leased computers, The duration of using the rental computer on the first day, is the length of a whole day, i.e. 24 hours, is the number of computers actually used on the next day, The rental computer time for the next day's use, is the number of computers actually used on day t, The duration of using the rental computer on day t, is the total number of days in the unit time;

[0053] The expressions of t and q have been described above and will not be described here. Specifically, the above formula describes that the utilization rate of the computer rental of the enterprise is obtained by adding the daily utilization rate of the computer rental of the enterprise per unit time and calculating the ratio of the time length per unit time (i.e. the total number of days). ;

[0054] The signing time of a lease contract refers to the period from the signing date of the lease contract to the end date of the contract. Specifically, the lease contract may change between units of time, such as when the company renews or terminates the lease. The specific acquisition logic is to obtain the signing time of the lease contract through the lease contract and the renewal and termination agreements submitted by the company between the signing date of the lease contract and the end date of the contract. ;

[0055] Specifically, according to the renewal and termination agreements submitted by the detected enterprises, the signing time of the lease contract is increased or decreased accordingly to obtain the change of the signing time of the lease contract between units of time;

[0056] The lease contract period refers to the period from the current time to the period of use of the leased computer specified in the lease contract. It is a clear time frame agreed upon by both parties in the contract. Specifically, the lease contract period will change over time. The logic for obtaining it is to subtract the current time from the period of use of the leased computer to get the lease contract period. ;

[0057] Among them, for unleased enterprises, the data collection module is used to collect the ratio of enterprise area to number of people and the difference in regional unleased industry concentration index;

[0058] The enterprise area to headcount ratio refers to the ratio of the enterprise area to the number of employees. Specifically, when the enterprise area to headcount ratio gradually decreases, it means that the enterprise is recruiting more employees and needs more office equipment. The logic for obtaining the enterprise area to headcount ratio is to calculate the ratio of the total area of ​​the unrented enterprise to the total number of its current employees. ; Where j is the jth unleased enterprise;

[0059] The regional unleased industry concentration index difference is the change difference between the Herfindahl-Hirschman index of the regional overall enterprises and the Herfindahl-Hirschman index of the unleased enterprises in adjacent unit time. The acquisition logic is to collect the market share data of the unleased enterprises and the region as a whole in adjacent unit time and bring them into the Herfindahl-Hirschman index to calculate the difference, and then obtain the regional unleased industry concentration index difference;

[0060] Specifically, at each unit time, the Herfindahl-Hirschman index of the region is calculated based on the market share of unrented enterprises. The formula is as follows:

[0061] ;

[0062] In the formula, is the Herfindahl-Hirschman index, g is the total number of unrented enterprises in the region, is the market share of the jth enterprise;

[0063] By calculating the difference between the unrented enterprises and the regional Herfindahl-Hirschman index between adjacent unit times, that is:

[0064] ;

[0065] In the formula, is the difference in concentration index of the unleased industries in the region; where g+p is the total number of enterprises in the region, j+q is the j+qth enterprise; then p is the total number of leased enterprises; g has been described above and will not be repeated here;

[0066] Among them, the Herfindahl-Hirschman Index is an economic indicator used to measure market concentration. It expresses the intensity of industry competition by calculating the sum of the squares of the market shares of all enterprises in the market. Since it can be used to reveal the concentration of regional enterprises, it can be used to predict regional leasing coverage.

[0067] It should be noted that when the difference in the regional unleased industry concentration index increases, it means that the number and scale of unleased enterprises in the region are gradually concentrated, and there is a greater potential for seeking leasing, and the growth trend of the leasing coverage rate of the unleased area is higher;

[0068] The data processing module is used to obtain the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of regional unleased industries. The random forest prediction model is used to obtain the probability of new demand for each leased enterprise and the probability of lease demand for each unleased enterprise, and send them to the demand analysis module;

[0069] The proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in regional non-leased industry concentration index are normalized to operate under the same dimension. The specific formula is expressed as follows:

[0070] ;

[0071] In the formula, is the normalized data, is the original data value, is the maximum value in the data set, is the minimum value in the data set; specifically, the raw data value refers to the proportion of new employees in rented enterprises, the utilization rate of rented computers in enterprises, the signing time of the lease contract, the term of the lease contract, the ratio of enterprise area to employees, and the difference in the concentration index of the unrented industries in the region;

[0072] Create a feature matrix , including the characteristics of leased and unleased enterprises, specifically:

[0073] ;

[0074] Set the output label to y. Specifically, predict the probability of new demand for leased enterprises and the probability of leasing demand for unleased enterprises, where T is the total number of unit time; y is a continuous value, and the specific value of y is between;

[0075] It should be noted that random forest is an ensemble learning algorithm based on multiple decision trees. It randomly selects features and generates multiple decision trees. The final output result is determined by majority voting or average.

[0076] Specifically, the random forest prediction formula is:

[0077] ;

[0078] In the formula, It is The output of a decision tree is is the total number of decision trees, To predict the results;

[0079] It should be noted that the technical personnel in this field set the parameters of random forests according to data information such as historical regional rental coverage. Usually, the number of generated trees M, the maximum depth D of each tree, and the minimum number of samples for node splitting of the control tree are set according to the scale of the data set;

[0080] The dataset Divide the training set and test set, use the training set to train the random forest model, and build multiple decision trees;

[0081] Use the test set to verify the model performance, calculate the predicted value, and evaluate the model accuracy. Specifically, the accuracy of the model is calculated by the ratio of the number of correctly classified samples to the total number of samples;

[0082] Among them, there is no limit on the specific value of the model accuracy, but it is set by the experimenters based on the historical regional rental demand and is not limited here;

[0083] Furthermore, the hyperparameters of the random forest (such as the number and depth of trees) are adjusted according to the accuracy of the model to improve the prediction performance of the model;

[0084] Specifically, the formulas for the probability of new demand of each leased enterprise and the probability of leasing demand of each unleased enterprise are:

[0085] as well as ;

[0086] In the formula, is the probability of new demand for leased enterprises, is the probability of leasing demand of unleased enterprises, The newly inputted characteristic data of the leased enterprise include the proportion of new employees in the leased enterprise, the utilization rate of the leased computers in the enterprise, the signing time of the lease contract, and the term of the lease contract; The characteristic data of newly input unleased enterprises include the ratio of enterprise area to number of employees and the difference in regional unleased industry concentration index; is the output result generated by the mth decision tree, m is the mth decision tree, and M is the total number of decision trees;

[0087] The demand analysis module is used to receive the new demand probability of each leased enterprise and the rental demand probability of each unleased enterprise, and average them and perform weighted calculation to obtain the regional rental demand assessment coefficient, and compare it with the preset demand threshold to obtain the comparison result and obtain the enterprise information with the most demand characteristics based on the comparison result, and send it to the weight assignment module;

[0088] Specifically, the new demand probability set of leased enterprises and the rental demand probability set of unleased enterprises are obtained, which are: as well as ; After averaging, the weighted calculation formula is used to obtain the regional rental demand assessment coefficient, which is:

[0089] ;

[0090] In the formula, is the regional rental demand assessment coefficient, is the average probability of new demand for leased enterprises, is the average probability of leasing demand of unleased enterprises; as well as are the preset proportional coefficients of the average probability of new demand of leased enterprises and the average probability of leasing demand of unleased enterprises, respectively, and as well as are greater than 0, is the total number of unrented enterprises;

[0091] It should be noted that the logic of obtaining the demand threshold is to collect historical leasing information, conduct exploratory data analysis on the collected information, identify the behavior patterns of leasing demand and renewal mode, and obtain the demand threshold through the probability distribution model. Therefore, the demand threshold is constantly changing;

[0092] The exploratory data analysis involved in this embodiment refers to statistical analysis and visualization of historical leasing information, aiming to identify the patterns of leasing demand and renewal behavior. The probability distribution model is a mathematical function type used to describe the possibility of random variable values ​​and their corresponding probabilities, which will not be described in detail here.

[0093] Compare and analyze the regional rental demand assessment coefficient with the demand threshold, specifically:

[0094] If the regional rental demand assessment coefficient is greater than or equal to the demand threshold, the region is marked as a demand region and a recommendation signal is generated;

[0095] If the regional rental demand assessment coefficient is less than the demand threshold, the region is marked as a saturated region and a saturation signal is generated;

[0096] It should be noted that when the regional rental demand assessment coefficient is less than the demand threshold, it means that the computer demand of the rented enterprises has been saturated, and the non-rented enterprises have no demand and conditions for leasing, so it is considered that the region is now saturated;

[0097] Furthermore, this embodiment only uses the regional rental demand evaluation coefficient obtained in one unit time detection. In fact, the change of regional rental demand in different unit time can be further calculated, and personalized demand recommendations can be generated according to the change frequency and comparison results;

[0098] For example, for areas with too fast frequency of change, there may be drawbacks such as short enterprise change cycle, or when encountering areas that continuously generate saturation signals, leasing work cannot be continued. The information is transmitted to the operation system, and the system can execute the signal of appropriately reducing the recommended resources in the area. Among them, the duration of the saturation signal generated by the regional leasing demand assessment coefficient and the speed of its change frequency can be set based on the historical leasing information of each area, and are not limited here;

[0099] For the area where the recommendation signal is generated, obtain the product of the maximum value of the probability of new demand of the leased enterprises in the area and the average value of the probability of new demand of the leased enterprises, as well as the product of the maximum value of the probability of leasing demand of the unleased enterprises and the average value of the probability of leasing demand of the unleased enterprises, and compare the sizes. The maximum value after comparison is taken as the enterprise with the most demand characteristics;

[0100] For example, for area A, there are two companies, a and b, which have the maximum probability of new demand of the leased companies among the leased companies, 0.68, and the maximum probability of leasing demand of the unleased companies among the unleased companies, 0.70. Specifically, the average probability of new demand of the leased companies is 0.54, and the average probability of leasing demand of the unleased companies is 0.46, so 0.68*0.54=0.3672, 0.70*0.46=0.322, so company a is the company with the most demand characteristics in A;

[0101] The present invention collects the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to number of employees, and the difference in concentration index of unleased industries in the region, and brings them into a random forest prediction model to obtain the probability of new demand for each leased enterprise and the probability of lease demand for each unleased enterprise, and then performs weighted calculation after averaging to obtain the regional lease demand assessment coefficient and compares it with the preset demand threshold to obtain the enterprise with the most demand characteristics, dynamically predict the demand, and at the same time combine the lease probability of the leased enterprises to improve the accuracy of the regional lease coverage, so as to achieve the purpose of quickly finding the enterprise with the most demand characteristics and save computing resources.

[0102] Example 2

[0103] In Example 1 of the present invention, an example is given to illustrate the collection of the proportion of new employees in rented enterprises, the utilization rate of rented computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to number of employees, and the difference in concentration index of unrented industries in the region, and the random forest prediction model is brought in to obtain the probability of new demand for each rented enterprise and the probability of renting demand for each unrented enterprise, and the regional rental demand evaluation coefficient is obtained by weighted calculation after averaging and compared with the preset demand threshold to obtain the operation strategy of the enterprise with the most demand characteristics; however, in Example 1, only the two aspects of rented enterprises and unrented enterprises are comprehensively considered, and the weight design for calculating the regional rental demand evaluation coefficient is not accurate enough. Obviously, since the enterprise rental status changes with the change of unit time, the attributes of rented enterprises and unrented enterprises in different unit times are also different. The specific weight assignment is fixed, which will lead to a decrease in the calculation accuracy of the regional rental demand evaluation coefficient, thereby affecting the efficiency of the system in mining the enterprises with the most demand characteristics; in view of the above problems, Example 2 of the present invention is further refined;

[0104] The weight assignment module is used to obtain the enterprise information with the most demand characteristics. By analyzing the corresponding regional leasing demand assessment coefficient, the conversion rate of unleased enterprises to leased enterprises per unit time and the increase rate of unleased enterprises in the region per unit time are obtained, and normalized, and fuzzy logic is used to determine the weight assignment result;

[0105] The enterprise information with the most demand characteristics includes the conversion rate of unleased enterprises to leased enterprises per unit time and the increase rate of unleased enterprises in the region per unit time;

[0106] It should be noted that the conversion rate of the unleased enterprises to the leased enterprises per unit time and the rate of increase of the unleased enterprises in the region per unit time are obtained based on the predicted probability described in the above embodiment 1, and will not be elaborated here;

[0107] The logic for obtaining the conversion rate of unleased enterprises to leased enterprises per unit time is to calculate the ratio of the number of unleased enterprises converted into leased enterprises after signing the lease contract to the total number of original unleased enterprises per unit time, and obtain the conversion rate of unleased enterprises to leased enterprises per unit time;

[0108] For example, within a unit time, the number of lease contracts signed by unleased enterprises is w, and the number of leased enterprises converted is w. The total number of original unleased enterprises is g. The conversion rate of unleased enterprises to leased enterprises within a unit time is obtained by ratio calculation, wherein the calibration of the total number of original unleased enterprises has been described in the above embodiment 1, and will not be repeated here;

[0109] Specifically, the unit time mentioned in this embodiment corresponds to the unit time length and position in the above-mentioned embodiment 1. For example, the position of the unit time in the above-mentioned embodiment 1 is at the position T-6 of the total number of unit times, that is, the position of the unit time in this embodiment is also at the position T-6, that is, the unit time in embodiment 1 corresponds to the unit time in embodiment 2;

[0110] It should be noted that when the conversion rate of unleased enterprises to leased enterprises per unit time is greater, it means that the leasing demand of unleased enterprises in the area is stronger, which means that in the next unit time, unleased enterprises should be given priority, and the weight assignment of the average probability of leasing demand of unleased enterprises should be increased;

[0111] The rate of increase of unleased enterprises in a region per unit time refers to the rate at which the number of unleased enterprises in a region increases per unit time to the total number of enterprises in the region, assuming that the number of enterprises in the region remains unchanged. Specifically, the acquisition logic is to calculate the ratio of the number of unleased enterprises in a region that increases per unit time to the total number of enterprises in the region, and obtain the rate of increase of unleased enterprises in a region per unit time.

[0112] It should be noted that the increase of unleased enterprises is divided into two types, namely, newly added external enterprises in the region and leased enterprises that have changed from leased enterprises in the previous unit time to unleased enterprises due to expiration or termination of leases. Since the increase of unleased enterprises is caused by the expiration or termination of leases of leased enterprises, the greater the increase rate of unleased enterprises in the region per unit time, the more priority is given to the increase in the number of unleased enterprises, and the weight of the average value of the probability of leasing demand of unleased enterprises is increased;

[0113] The conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time are normalized to satisfy the fuzzy logic to process and compare input data more effectively;

[0114] It should be noted that the normalization process has been described in Example 1 and will not be described in detail here.

[0115] Obtain the normalized conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time and use fuzzy logic to determine the weight assignment result;

[0116] Among them, the weight assignment result refers to the weight assignment of the average value of the rental demand probability of unleased enterprises;

[0117] It should be noted that the total weight value of the average value of the new demand probability of the leased enterprises and the average value of the rental demand probability of the unleased enterprises in the above-mentioned embodiment 1 is 1, so no matter whether the weight assignment result is referred to as the weight assignment of the average value of the rental demand probability of the unleased enterprises or the weight assignment of the average value of the new demand probability of the leased enterprises, the remaining weight assignment can be calculated, so this embodiment uses the weight assignment of the average value of the rental demand probability of the unleased enterprises as the weight assignment result;

[0118] For example, "High", "Low", and "Medium" are used to judge the conversion rate of unleased enterprises to leased enterprises per unit time, and "Many", "Less", and "Average" are used to judge the increase rate of unleased enterprises in a region per unit time.

[0119] Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0120] The conversion rate of unleased enterprises to leased enterprises per unit time is marked as X, the rate of increase of unleased enterprises in the region per unit time is marked as U, and the weight assignment result is marked as C_results;

[0121] Then we can define:

[0122] Rule 1: IF (X is High) AND (U is Many) THEN (C_results is High)

[0123] Rule 2: IF (U is Low) AND (U is Less) THEN (C_results is Low) ...

[0124] Perform fuzzy reasoning based on fuzzy rules and determine the weight assignment scheme;

[0125] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as an example, it can actually be divided into more than three sets to facilitate better accurate adjustment according to different similarities.

[0126] Specifically, when the weight assignment result is marked as "High", the weight of the average probability of leasing demand of unleased enterprises is increased by 20% based on the current unit time. Conversely, when the weight assignment result is marked as "Low", the weight of the average probability of leasing demand of unleased enterprises is decreased by 30% based on the current unit time.

[0127] Furthermore, for the judgment of the conversion rate of unleased enterprises to leased enterprises per unit time and the increase rate of unleased enterprises in the region per unit time, the threshold can be set according to the actual situation for judgment. For example, when the conversion rate of unleased enterprises to leased enterprises per unit time exceeds 55%, it is marked as "High", and when the increase rate of unleased enterprises in the region per unit time is higher than 47%, it is marked as "Many", etc., which will not be elaborated here;

[0128] The present invention uses the normalized conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time, and introduces fuzzy logic to determine the weight assignment result, thereby eliminating the differences between characteristics and making the weights dynamically changeable. The calculation of the regional leasing demand assessment coefficient in the next unit time is more accurate, thereby improving the accuracy of the prediction and ensuring the efficiency of the system in mining the enterprises with the most demand characteristics.

[0129] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0130] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0131] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0138] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An Internet-based computer rental operation system, characterized by: It includes data acquisition module, data processing module, demand analysis module and weight assignment module; signal connection between each module; The data collection module is used to collect information about leased and unleased enterprises. Through data processing, the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of unleased industries in the region are obtained and sent to the data processing module; The data processing module is used to obtain the proportion of new employees in leased enterprises, the utilization rate of leased computers in enterprises, the signing time of lease contracts, the term of lease contracts, the ratio of enterprise area to employees, and the difference in concentration index of regional unleased industries. The random forest prediction model is used to obtain the probability of new demand for each leased enterprise and the probability of lease demand for each unleased enterprise, and send them to the demand analysis module; The demand analysis module is used to receive the new demand probability of each leased enterprise and the lease demand probability of each unleased enterprise, and perform weighted calculation after averaging to obtain the regional lease demand assessment coefficient, and compare it with the preset demand threshold to obtain the comparison result and obtain the enterprise information with the most demand characteristics based on the comparison result, and send it to the weight assignment module; The weight assignment module is used to obtain the enterprise information with the most demand characteristics. By analyzing the corresponding regional leasing demand assessment coefficient, the conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in the region per unit time are obtained, and then normalized and fuzzy logic is used to determine the weight assignment results.

2. According to claim 1, the computer rental operation system based on the Internet is characterized in that: The data processing process is as follows: By collecting the original number of employees in the leased enterprise information and the number of current employees after a unit of time and calculating the ratio, the proportion of new employees in the leased enterprise can be obtained. ; Where t is the t-th unit time; q=1, 2, 3, ..., p, p is the total number of leased enterprises; The utilization rate of corporate rental computers is calculated by adding the daily utilization rate of corporate rental computers per unit time and calculating the ratio of the time per unit time. ; The signing time of the lease contract can be obtained by checking the lease contract and the renewal and termination agreements submitted by the enterprise between the signing date of the lease contract and the end date of the contract. ; The lease contract period is obtained by subtracting the current time from the leased computer's usage period. ; The ratio of the total area of ​​the unrented enterprise to the total number of its current employees is calculated to obtain the ratio of the enterprise area to the number of employees. ; Where j is the jth unleased enterprise; The market share data of unrented enterprises in the region and the region as a whole are collected in adjacent unit time periods and the difference is calculated by the Herfindahl-Hirschman index to obtain the regional unrented industry concentration index difference. .

3. The computer rental operation system based on the Internet according to claim 2 is characterized in that: The proportion of new employees in rented enterprises, the utilization rate of rented computers in enterprises, the signing time of the lease contract, the term of the lease contract, the ratio of enterprise area to employees, and the difference in the concentration index of the unrented industries in the region are normalized and brought into the feature matrix , the feature matrix Each feature in is brought into the random forest model trained by verifying the model accuracy to calculate the probability of new demand for each leased enterprise and the probability of leasing demand for each unleased enterprise. The specific formula is expressed as: as well as ; In the formula, is the probability of new demand for leased enterprises, is the probability of leasing demand of unleased enterprises, The newly inputted characteristic data of the leased enterprise include the proportion of new employees in the leased enterprise, the utilization rate of the leased computers in the enterprise, the signing time of the lease contract, and the term of the lease contract; The newly input unrented enterprise characteristic data includes the enterprise area to number of employees ratio and the regional unrented industry concentration index difference. is the output result generated by the mth decision tree, m is the mth decision tree, and M is the total number of decision trees.

4. The computer rental operation system based on the Internet according to claim 3 is characterized by: Get the new demand probability set of leased enterprises and the rental demand probability set of unleased enterprises, which are: as well as ; Perform average processing and then substitute it into the weighted calculation formula to obtain the regional rental demand assessment coefficient, which is: ； In the formula, is the regional rental demand assessment coefficient, is the average probability of new demand for leased enterprises, is the average probability of leasing demand of unleased enterprises; as well as are the preset proportional coefficients of the average probability of new demand of leased enterprises and the average probability of leasing demand of unleased enterprises, respectively, and as well as are greater than 0, is the total number of unleased enterprises.

5. The computer rental operation system based on the Internet according to claim 4 is characterized in that: If the regional rental demand assessment coefficient is greater than or equal to the demand threshold, the region is marked as a demand region and a recommendation signal is generated; If the regional rental demand assessment coefficient is less than the demand threshold, the area is marked as a saturated area and a saturation signal is generated.

6. The computer rental operation system based on the Internet according to claim 5 is characterized in that: For the area where the recommendation signal is generated, obtain the product of the maximum value of the probability of new demand of the leased enterprises in the area and the average value of the probability of new demand of the leased enterprises, as well as the product of the maximum value of the probability of leasing demand of the unleased enterprises and the average value of the probability of leasing demand of the unleased enterprises, and compare the sizes. Take the maximum value after comparison as the enterprise with the most demand characteristics.

7. The computer rental operation system based on the Internet according to claim 1 is characterized by: The enterprise information with the most demand characteristics includes the conversion rate of unleased enterprises to leased enterprises per unit time and the increase rate of unleased enterprises in the region per unit time.

8. The computer rental operation system based on the Internet according to claim 7 is characterized in that: By calculating the ratio of the number of non-leased enterprises converted into leased enterprises after signing the lease contract to the total number of original non-leased enterprises, the conversion rate of non-leased enterprises into leased enterprises per unit time is obtained; By calculating the ratio of the number of unrented enterprises in the region that increases per unit time to the total number of enterprises in the region, the rate of increase of unrented enterprises in the region per unit time can be obtained.

9. The computer rental operation system based on the Internet according to claim 8 is characterized in that: The conversion rate of unleased enterprises to leased enterprises per unit time and the rate of increase of unleased enterprises in a region per unit time are defined as input variables, and divided into different fuzzy sets respectively; The weight assignment result is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the conversion rate of unleased enterprises to leased enterprises per unit time and the impact of the increase rate of unleased enterprises in the region per unit time on the weight assignment results; Perform fuzzy reasoning based on fuzzy rules and determine the weight assignment scheme.

Images