Employment management system based on user behavior information

Abstract

The invention discloses a guarantee deposit deduction management system based on user behavior information, relates to the technical field of credit calculation, and solves the problem that historical behaviors are neglected and cannot accurately represent current credit of a user in analysis of guarantee deposit deduction by using the historical behaviors, so that the credit of the user cannot be accurately represented. And the influence of the age of the user and the change of the resident area on the credit behavior of the user is neglected. According to the method, behavior factors are obtained by analyzing conventional information; analyzing the age to obtain an age influence factor, and analyzing the geographic position of the user to obtain a position influence factor; adjusting the behavior factor based on the age influence factor and the position influence factor to obtain a use factor; based on the use factor and the commodity amount, obtaining a reduction coefficient of the lease, and based on the reduction coefficient, performing reduction on the guarantee deposit; according to the invention, timeliness and accuracy of user behavior credit analysis during renting can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of data processing and relates to a credit calculation technology, in particular to a deposit reduction management system based on user behavior information. Background Art

[0002] With the rapid development of the sharing economy model, deposits are widely used as a means of credit guarantee. The traditional deposit model requires users to pay a certain amount of money as a guarantee before using a service. The fixed amount of deposit increases the user's financial burden and reduces the user experience. Financial institutions and enterprises hope to reduce the user's financial pressure through more flexible means, while effectively reducing the risk of deposit reduction based on user behavior information.

[0003] At present, most deposit reduction management systems based on user behavior information use historical behavior to analyze the deposit reduction amount, ignoring the fact that historical behavior cannot accurately represent the user's current credit, which reduces the accuracy of the analysis and increases the deposit reduction risk of the enterprise. At the same time, most deposit reduction management systems based on user behavior information ignore the impact of changes in user age and permanent residence area on user credit behavior, and cannot effectively adjust the credit behavior of users of different ages in different areas, which increases the limitations of the system.

[0004] Therefore, the present invention discloses a deposit reduction management system based on user behavior information to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a deposit reduction management system based on user behavior information, which is used to solve the technical problems that when analyzing deposit reduction using historical behavior, the historical behavior is ignored and cannot accurately represent the user's current credit, and the impact of changes in the user's age and permanent area of ​​residence on the user's credit behavior is ignored. The present invention obtains behavioral factors by analyzing conventional information; obtains age influence factors by analyzing age, and obtains location influence factors by analyzing the user's geographical location; obtains usage factors by adjusting the behavioral factors based on the age influence factors and the location influence factors; obtains the reduction coefficient of this lease based on the usage factor and the commodity amount, and reduces the deposit based on the reduction coefficient to solve the above problems.

[0006] To achieve the above-mentioned purpose, the first aspect of the present invention provides a deposit reduction management system based on user behavior information, including: a behavior analysis module, and an information collection module, a reduction calculation module and a database connected thereto;

[0007] The information collection module is used to obtain basic information of the user; wherein the basic information includes general information and special information; the general information includes the number of rentals, the number of breaches and the duration of breaches; the special information includes age, user geographic location, and the amount of the goods rented this time;

[0008] The behavior analysis module is used to analyze the general information to obtain the behavior factor; analyze the age to obtain the age influence factor, analyze the user's geographical location to obtain the location influence factor; adjust the behavior factor based on the age influence factor and the location influence factor to obtain the usage factor;

[0009] The reduction and exemption calculation module is used to obtain the reduction and exemption coefficient of this lease based on the usage factor and the commodity amount, and reduce the deposit based on the reduction and exemption coefficient.

[0010] Preferably, the obtaining of basic information of the user includes:

[0011] The user's age, number of rentals, number of defaults, and the duration of defaults corresponding to each number of defaults are extracted from the database; the amount of the goods rented by the user this time is retrieved from the database, as well as the storage location of the goods corresponding to the user's historical rentals, and the user's geographic location is obtained by analyzing the storage location of the goods.

[0012] It should be noted that the basic information of the user obtained by the present invention is all performed with the authorization of the user, and the storage and extraction of the basic information of the user by the database are all performed with the authorization of the user.

[0013] Preferably, analyzing the storage location of the goods to obtain the user's geographical location includes:

[0014] A1: extract the commodity storage locations corresponding to each historical rental of the current user, obtain the setting area where each commodity storage location is located, and mark the number of commodity storage locations in each setting area as the number of regional commodities in the corresponding setting area; wherein the range of the setting area is obtained by manual selection;

[0015] A2: extract the maximum value of the number of commodities in the area, and determine whether the ratio of the maximum value to the total number of commodity storage locations exceeds a preset ratio; if yes, mark the set area corresponding to the maximum value as the user geographic location of the current user; if no, jump to A3; wherein the preset ratio is obtained through experience;

[0016] A3: Mark the two setting areas with the largest number of regional commodities as target setting areas, mark the target setting area with a large number of regional commodities as user geographic location one, mark the target setting area with a small number of regional commodities as user geographic location two, and mark the setting areas corresponding to user geographic location one and user geographic location two as user geographic location of the current user.

[0017] Preferably, the analysis of conventional information to obtain behavioral factors includes:

[0018] B1: Extract the number of rentals ZN of the current user in the database record, and determine whether the number of rentals ZN is less than the standard number; if yes, set the deposit of the user's current rental to the standard deposit YJ; if no, jump to B2; wherein the standard number is obtained through experience;

[0019] B2: Extract the number of breaches WN and the number of leases ZN, and obtain the current user's compliance ratio SL based on the formula SL = (ZN-WN) / ZN;

[0020] B3: Extract the default duration corresponding to each default number WN, and summarize the default durations into a duration data group; obtain the variance of the duration data group, and determine whether the variance is less than the variance setting threshold; if yes, obtain the average value of the data in the duration data group; if no, remove the default duration with the largest difference from the mode of the current duration data group in the duration data group, and re-determine the variance until the variance of the current duration data group is less than the corresponding variance setting threshold, and then obtain the average value of the remaining data in the current duration data group; wherein the variance setting threshold is obtained through experience;

[0021] B4: Mark the average value of the duration data group as the characteristic default duration TZ, and obtain the current user's behavior factor BY based on the formula BY=SL×α / exp((TZ-BTZ) / BTZ); wherein BTZ is the standard default duration set manually; α is the amplitude adjustment coefficient, and the value range of α is (0,1).

[0022] It is worth noting that the present invention obtains a behavior factor that can express the current user's behavior credit by analyzing the current user's general information. This behavior factor can only express the current user's behavior credit in the historical general information, and human behavior will change with age or permanent area. If the user's behavior at this moment is analyzed only based on historical behavior, it will inevitably be out of time. Therefore, the present invention subsequently analyzes the current user's age and permanent area, and uses the results of the analysis to adjust the behavior factor to obtain a factor that can express the user's behavior credit at the current moment under the influence of the age and permanent area credit environment.

[0023] Preferably, the analysis of age to obtain age influencing factors includes:

[0024] Extract the user's age, extract the behavior factors BY corresponding to all users of the current age from the database, mark several of the behavior factors BY as target behavior factors, mark the maximum value of the target behavior factors as the maximum target behavior factor ZM, and obtain the scaling value SZ based on the formula SZ=ZM×β; where β is the proportional coefficient, and the value range of β is (0.5,0.9];

[0025] The target behavior factors greater than the scaling value SZ are summarized into the first group, and the remaining target behavior factors are summarized into the second group; the average values ​​of the first group and the second group are obtained, and the average value of the first group is marked as the first average value YPZ, and the average value of the second group is marked as the second average value RPZ;

[0026] Based on the formula TWZ1=δ1×YPZ+δ2×RPZ, the characteristic behavior factor TWZ1 of the behavior factor corresponding to the current user's age is obtained; wherein δ1 and δ2 are both proportional coefficients greater than 0;

[0027] The behavior factor BY of the current user is extracted, and the age influence factor NYZ is obtained based on the formula NYZ=(TWZ1-BY) / BY.

[0028] It should be noted that the age of the user's regular information record may be very different from the user's current age. People have different constraints on themselves at different ages, and their behaviors may also be different. Therefore, the present invention analyzes age as an influencing situation.

[0029] It should be noted that the characteristic behavior factor TWZ1 obtained by the present invention is equivalent to the ratio and sum of the average values ​​of the first group and the second group. The present invention does not directly obtain the average value of the current age user behavior factor, but uses the scaling value SZ to divide the current age user behavior factor into two groups, calculates the average value of the two groups, and then sums the average value calculation results proportionally. Compared with directly calculating the average value, this can reduce the impact of outliers on the overall average value to a certain extent and improve the stability of the data; and the grouping criteria can be dynamically adjusted according to the actual data, making the grouping more flexible and better adapting to the changes in user behavior of different age groups.

[0030] Preferably, the analyzing the user's geographical location to obtain the location influence factor includes:

[0031] C1: Extract the setting area corresponding to the user's geographic location of the current user, and determine whether the number of setting areas corresponding to the current user is 1; if yes, jump to C2; if no, jump to C3;

[0032] C2: extracting the mode of the behavior factor BY of the user in the setting area, and marking the mode as the characteristic behavior factor 2 TWZ2 corresponding to the user geographic location of the current user;

[0033] C3: Extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location one, and mark the mode as the first mode DZ1; extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location two, and mark the mode as the second mode DZ2; obtain the characteristic behavior factor two TWZ2 of the behavior factor corresponding to the user's geographic location of the current user based on the formula TWZ2=γ1×DZ1+γ2×DZ2; wherein γ1 and γ2 are proportional coefficients greater than 0, and γ1+γ2=1;

[0034] C4: extract the current user's behavior factor BY, and obtain the position influence factor WYZ based on the formula WYZ=(TWZ2-BY) / BY.

[0035] Preferably, the step of adjusting the behavior factor based on the age influence factor and the location influence factor to obtain the usage factor includes:

[0036] The age influencing factor NYZ, location influencing factor WYZ and behavior factor BY of the current user are extracted, and the usage factor SYZ of the current user is obtained based on the formula SYZ = (1 + ρ × (exp (θ1 × NYZ + θ2 × WYZ) - 1)) × BY; wherein ρ is the amplitude adjustment coefficient of the exp() function, and the value range of ρ is (0, 1); θ1 and θ2 are both proportional coefficients greater than 0, and θ1 + θ2 = 1.

[0037] It should be noted that the usage factor SYZ is obtained by adjusting the behavior factor BY by the age influence factor NYZ and the location influence factor WYZ. This usage factor SYZ can be expressed as the current user's behavioral credit at the current moment after being influenced by the age and the credit environment of the resident area.

[0038] Preferably, the reduction coefficient of the current lease based on the usage factor and the commodity amount is obtained, including:

[0039] The usage factor SYZ of the current user is used to determine whether the usage factor SYZ is greater than the usage factor threshold SYT; if yes, the reduction coefficient JS of this lease is assigned a value of 1; if no, the amount Q of the goods leased this time is extracted, and the reduction coefficient JS of this lease is obtained based on the formula JS=SYZ / SYT×μ / exp((Q-PQ) / PQ); wherein the usage factor threshold is obtained through experience, PQ is the average amount of all goods in the database, and μ is an amplitude adjustment coefficient greater than 0.

[0040] Preferably, the reduction of the deposit based on the reduction coefficient includes:

[0041] Extract the exemption coefficient JS of this lease and the standard deposit YJ of this leased product, and obtain the exemption amount JM based on the formula JM=JS×YJ. Reduce the deposit of this lease based on the exemption amount JM.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention obtains behavior factors by analyzing conventional information; obtains age influence factors by analyzing age, obtains location influence factors by analyzing user geographic locations; obtains usage factors by adjusting behavior factors based on age influence factors and location influence factors; obtains exemption coefficients for this rental based on usage factors and commodity amounts, and reduces deposits based on exemption coefficients, thereby solving the technical problems of analyzing deposit exemptions based on historical behaviors, ignoring that historical behaviors cannot accurately represent the user's current credit, and ignoring the impact of changes in user age and resident areas on user credit behaviors; the present invention can improve the timeliness and accuracy of user behavior credit analysis during leasing.

[0044] 2. The present invention obtains a behavior factor that can express the current user's behavior credit by analyzing the current user's general information. This behavior factor can only express the current user's behavior credit in the historical general information, and human behavior will change with age or permanent area. If the user's behavior at this moment is analyzed only based on historical behavior, it will inevitably be out of time. Therefore, the present invention also analyzes the current user's age and permanent area in the follow-up, and uses the results of the analysis to adjust the behavior factor to obtain a factor that can express the user's behavior credit at the current moment under the influence of the age and permanent area credit environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a schematic diagram of the operation steps of the present invention;

[0047] Figure 2 It is a schematic diagram of the system module of the present invention;

[0048] Figure 3 The figure is a schematic diagram of the operation steps for obtaining the age influencing factor of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0050] See also Figure 1-Figure 2 , the first aspect of the present invention provides a deposit reduction management system based on user behavior information, including: a behavior analysis module, and an information collection module, a reduction calculation module and a database connected thereto;

[0051] Information collection module: used to obtain basic information of users; basic information includes general information and special information; general information includes number of rentals, number of defaults and duration of defaults; special information includes age, user geographic location and amount of goods rented this time;

[0052] Behavior analysis module: used to analyze general information to obtain behavior factors; analyze age to obtain age influence factors, and analyze user geographic location to obtain location influence factors; adjust behavior factors based on age influence factors and location influence factors to obtain usage factors;

[0053] Reduction and exemption calculation module: used to obtain the reduction and exemption coefficient of this lease based on the usage factor and the commodity amount, and reduce the deposit based on the reduction and exemption coefficient.

[0054] For example, in this embodiment, the information obtained after the current rental user's authorization is: the number of rentals is 50, the number of breaches is 5, the age is 21 years old, the user's geographic location is set area 6, and the amount of the goods rented this time is 260 yuan;

[0055] In this embodiment, the standard number of times is set to 5 times; because the number of rentals ZN=50 of the current user in the database record is not less than 5 times; therefore, the number of breaches WN=5 and the number of rentals ZN=50 are extracted, and based on the formula SL=(ZN-WN) / ZN=(50-5) / 50=, the current user's compliance ratio SL=0.9 is obtained;

[0056] Extract the default duration corresponding to each default number WN, and summarize several default durations into a duration data group; obtain the variance of the duration data group, and determine whether the variance is less than the variance setting threshold; if yes, obtain the average value of the data in the duration data group; if no, remove the default duration with the largest difference from the mode of the current duration data group in the duration data group, and re-determine the variance until the variance of the current duration data group is less than the corresponding variance setting threshold, and then obtain the average value of the remaining data in the current duration data group;

[0057] In this embodiment, the average value of the duration data group is marked as the characteristic default duration TZ=0.6h, and based on the formula BY=SL×α / exp((TZ-BTZ) / BTZ)=0.9×0.9 / exp((0.6h-0.5h) / 0.5h)=0.66, the behavior factor BY=0.66 of the current user is obtained; wherein, the standard default duration BTZ=0.5h set in this embodiment, the amplitude adjustment coefficient α is set to 0.9;

[0058] Extract the behavior factors BY corresponding to all users aged 21 from the database, mark several behavior factors BY as target behavior factors, mark the maximum value among the target behavior factors as the maximum target behavior factor ZM=1, and obtain the scaling value SZ=0.6 based on the formula SZ=ZM×β=1×0.6=0.6; wherein, in this embodiment, the proportional coefficient β is 0.6;

[0059] The target behavior factors greater than the scaling value SZ=0.6 are summarized as the first group, and the remaining target behavior factors are summarized as the second group; the average values ​​of the first group and the second group are obtained, and the average value of the first group is marked as the first average value YPZ=0.9, and the average value of the second group is marked as the second average value RPZ=0.56;

[0060] Based on the formula TWZ1=δ1×YPZ+δ2×RPZ=0.6×0.9+0.4×0.56=0.76, the characteristic behavior factor of the behavior factor corresponding to the current user age is obtained as TWZ1=0.76; wherein, in this embodiment, the proportional coefficient δ1 is taken as 0.6, and the proportional coefficient δ2 is taken as 0.4;

[0061] Extract the current user's behavior factor BY=0.66, and based on the formula NYZ=(TWZ1-BY) / BY=(0.76-0.66) / 0.66=0.15, get the age influence factor NYZ=0.15;

[0062] Since the number of setting areas corresponding to the user geographic location of the current user is 1, the mode of the behavior factor BY of the user in setting area 6 is extracted, and the mode is marked as the characteristic behavior factor 2 corresponding to the user geographic location of the current user TWZ2=0.9;

[0063] Extract the current user's behavior factor BY=0.66, and based on the formula WYZ=(TWZ2-BY) / BY=(0.9-0.66) / 0.66=0.36, get the position influence factor WYZ=0.36;

[0064] The age influence factor NYZ=0.15, the location influence factor WYZ=0.36 and the behavior factor BY=0.66 of the current user are extracted, and based on the formula SYZ=(1+ρ×(exp(θ1×NYZ+θ2×WYZ)-1))×BY=(1+0.8×(exp(0.4×0.15+0.6×0.36)-1))×0.66=0.83, the usage factor SYZ=0.83 of the current user is obtained; wherein, in this embodiment, the proportional coefficient θ1 is taken as 0.4, the proportional coefficient θ2 is taken as 0.6, and the amplitude adjustment coefficient ρ is taken as 0.8;

[0065] Because the usage factor SYZ=0.83 is not greater than the usage factor threshold SYT=1, the amount of the goods rented this time Q=260 is extracted, and based on the formula JS=SYZ / SYT×μ / exp((Q-PQ) / PQ)=0.83 / 1×0.2 / exp((260-200) / 200)=0.12, the exemption coefficient JS=0.12 for this lease is obtained; wherein, in the database of this embodiment, the average amount PQ of all goods is 200, and the amplitude adjustment coefficient μ is 0.2;

[0066] Extract the exemption coefficient JS = 0.12 of this lease and the standard deposit YJ = 20 of this leased product, and based on the formula JM = JS × YJ = 0.12 × 20 = 2.4, get the exemption amount JM = 2.4;

[0067] The deposit for this lease is reduced based on the reduction amount JM=2.4.

[0068] The basic information of the user obtained in this application includes:

[0069] The user's age, number of rentals, number of defaults, and the duration of defaults corresponding to each number of defaults are extracted from the database; the amount of the goods rented by the user this time is retrieved from the database, as well as the storage location of the goods corresponding to the user's historical rentals, and the user's geographic location is obtained by analyzing the storage location of the goods.

[0070] In this application, the location of the goods is analyzed to obtain the user's geographic location, including:

[0071] A1: Extract the commodity storage locations corresponding to each historical rental of the current user, obtain the setting area where each commodity storage location is located, and mark the number of commodity storage locations in each setting area as the number of regional commodities in the corresponding setting area; wherein the range of the setting area is obtained by manual selection;

[0072] A2: Extract the maximum value of the number of regional commodities, and determine whether the ratio of the maximum value to the total number of commodity storage locations exceeds the preset ratio; if yes, mark the set area corresponding to the maximum value as the user geographic location of the current user; if no, jump to A3; wherein the preset ratio is obtained through experience;

[0073] A3: Mark the two setting areas with the largest number of regional products as target setting areas, mark the target setting area with a large number of regional products as user geographic location 1, mark the target setting area with a small number of regional products as user geographic location 2, and mark the setting areas corresponding to user geographic location 1 and user geographic location 2 as the user geographic location of the current user.

[0074] It should be noted that a single setting area may be marked as the user's geographic location, or two setting areas may be marked as the user's geographic location.

[0075] In this application, conventional information is analyzed to obtain behavioral factors, including:

[0076] B1: Extract the number of rentals ZN of the current user in the database record, and determine whether the number of rentals ZN is less than the standard number; if yes, set the deposit of the user's current rental to the standard deposit YJ; if no, jump to B2; the standard number is obtained through experience;

[0077] B2: Extract the number of breaches WN and the number of leases ZN, and obtain the current user's compliance ratio SL based on the formula SL = (ZN-WN) / ZN;

[0078] B3: Extract the default duration corresponding to each default number WN, and summarize several default durations into a duration data group; obtain the variance of the duration data group, and determine whether the variance is less than the variance setting threshold; if yes, obtain the average value of the data in the duration data group; if no, remove the default duration with the largest difference from the mode of the current duration data group in the duration data group, and re-determine the variance until the variance of the current duration data group is less than the corresponding variance setting threshold, and then obtain the average value of the remaining data in the current duration data group; wherein the variance setting threshold is obtained through experience;

[0079] B4: Mark the average value of the duration data group as the characteristic default duration TZ, and obtain the current user's behavior factor BY based on the formula BY=SL×α / exp((TZ-BTZ) / BTZ); wherein BTZ is the standard default duration set manually; α is the amplitude adjustment coefficient, and the value range of α is (0,1).

[0080] It should be noted that in this application, the abnormal values ​​of the current user's default duration are removed through variance judgment to obtain a set of stable data, and then the average value of this set of stable data is calculated to obtain a characteristic value that can represent the current user's default duration, which provides data support for the subsequent analysis of user behavior factors.

[0081] See also Figure 3 In this application, age is analyzed to obtain age influencing factors, including:

[0082] Extract the user's age, extract the behavior factors BY corresponding to all users of the current age from the database, mark several behavior factors BY as target behavior factors, mark the maximum value of the target behavior factors as the maximum target behavior factor ZM, and obtain the scaling value SZ based on the formula SZ = ZM × β; where β is the proportional coefficient, and the value range of β is (0.5, 0.9];

[0083] The target behavior factors greater than the scaling value SZ are summarized into the first group, and the remaining target behavior factors are summarized into the second group; the average values ​​of the first group and the second group are obtained, and the average value of the first group is marked as the first average value YPZ, and the average value of the second group is marked as the second average value RPZ;

[0084] Based on the formula TWZ1=δ1×YPZ+δ2×RPZ, the characteristic behavior factor TWZ1 of the behavior factor corresponding to the current user's age is obtained; wherein δ1 and δ2 are both proportional coefficients greater than 0;

[0085] The behavior factor BY of the current user is extracted, and the age influence factor NYZ is obtained based on the formula NYZ=(TWZ1-BY) / BY.

[0086] It should be noted that the current age user behavior factor is divided into two groups using the scaling value SZ, and the average values ​​of the two groups are calculated and then proportionally summed. Since the number of data in the two groups is different, the final calculation result is different from the value of the current age user behavior factor calculated directly.

[0087] It should be noted that the present invention obtains a characteristic behavior factor 1 that can express the current age by analyzing all users in the age stage of the current user in the database. This characteristic behavior factor can be understood as a characteristic behavior credit that can express the current age group.

[0088] In this application, the user's geographical location is analyzed to obtain location influencing factors, including:

[0089] C1: Extract the setting area corresponding to the user's geographic location of the current user, and determine whether the number of setting areas corresponding to the current user is 1; if yes, jump to C2; if no, jump to C3;

[0090] C2: extract the mode of the behavior factor BY of the user in the setting area, and mark the mode as the characteristic behavior factor 2 TWZ2 corresponding to the user's geographic location of the current user;

[0091] C3: Extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location one, and mark the mode as the first mode DZ1; extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location two, and mark the mode as the second mode DZ2; obtain the characteristic behavior factor two TWZ2 of the behavior factor corresponding to the user's geographic location of the current user based on the formula TWZ2=γ1×DZ1+γ2×DZ2; wherein γ1 and γ2 are proportional coefficients greater than 0, and γ1+γ2=1;

[0092] C4: extract the current user's behavior factor BY, and obtain the position influence factor WYZ based on the formula WYZ=(TWZ2-BY) / BY.

[0093] It should be noted that the user's permanent residence area has a great influence on user behavior. When users in a region generally exhibit good credit behavior, these behaviors will gradually evolve into regional norms, affecting new and existing users, making the entire region tend to be trustworthy. People living in a good credit environment are more likely to imitate the positive behavior patterns of people around them, thus forming their own good credit behavior; conversely, when users in a region generally exhibit bad credit behavior, then such behavior may be regarded as "normal", causing more people to follow suit, thus forming their own bad credit behavior.

[0094] In this application, the behavior factor is adjusted based on the age influence factor and the location influence factor to obtain the usage factor, including:

[0095] The age influencing factor NYZ, location influencing factor WYZ and behavior factor BY of the current user are extracted, and the usage factor SYZ of the current user is obtained based on the formula SYZ = (1 + ρ × (exp (θ1 × NYZ + θ2 × WYZ) - 1)) × BY; wherein ρ is the amplitude adjustment coefficient of the exp() function, and the value range of ρ is (0, 1); θ1 and θ2 are both proportional coefficients greater than 0, and θ1 + θ2 = 1.

[0096] In this application, the reduction coefficient for this lease is obtained based on the usage factor and the commodity amount, including:

[0097] The current user's usage factor SYZ is used to determine whether the usage factor SYZ is greater than the usage factor threshold SYT; if yes, the reduction coefficient JS for this lease is assigned a value of 1; if no, the amount Q of the goods leased this time is extracted, and the reduction coefficient JS for this lease is obtained based on the formula JS=SYZ / SYT×μ / exp((Q-PQ) / PQ); wherein the usage factor threshold is obtained through experience, PQ is the average amount of all goods in the database, and μ is an amplitude adjustment coefficient greater than 0.

[0098] In this application, the deposit is reduced based on the reduction coefficient, including:

[0099] Extract the exemption coefficient JS of this lease and the standard deposit YJ of this leased product, and obtain the exemption amount JM based on the formula JM=JS×YJ. Reduce the deposit of this lease based on the exemption amount JM.

[0100] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0101] Working principle of the present invention:

[0102] The present invention first obtains the number of leases, number of defaults, duration of defaults, age, geographic location of the user and the amount of goods leased this time; analyzes the number of leases, number of defaults and duration of defaults to obtain a behavior factor, and obtains a factor that can express the historical credit of the current user; analyzes the age to obtain an age influence factor, and analyzes the geographic location of the user to obtain a location influence factor; adjusts the behavior factor based on the age influence factor and the location influence factor to obtain a usage factor, and obtains a factor that can express the current credit of the user after being affected by changes in the user's age and geographic location; obtains a reduction coefficient for this lease based on the usage factor and the amount of goods, and reduces the deposit based on the reduction coefficient.

[0103] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A deposit reduction management system based on user behavior information, characterized in that: include: Behavior analysis module, and the information collection module, exemption calculation module and database connected thereto; The information collection module is used to obtain basic information of the user; wherein the basic information includes general information and special information; the general information includes the number of rentals, the number of breaches and the duration of breaches; the special information includes age, user geographic location, and the amount of the goods rented this time; The behavior analysis module is used to analyze the general information to obtain the behavior factor; analyze the age to obtain the age influence factor, analyze the user's geographical location to obtain the location influence factor; adjust the behavior factor based on the age influence factor and the location influence factor to obtain the usage factor; The reduction and exemption calculation module is used to obtain the reduction and exemption coefficient of this lease based on the usage factor and the commodity amount, and reduce the deposit based on the reduction and exemption coefficient.

2. The deposit reduction and exemption management system based on user behavior information according to claim 1 is characterized in that: The behavior analysis module communicates and / or is electrically connected to the information collection module, the exemption calculation module and the database respectively; the database communicates and / or is electrically connected to the information collection module, the behavior analysis module and the exemption calculation module respectively.

3. The deposit reduction and exemption management system based on user behavior information according to claim 1 is characterized in that: The obtaining of basic information of the user includes: The user's age, number of rentals, number of defaults, and the duration of defaults corresponding to each number of defaults are extracted from the database; the amount of the goods rented by the user this time is retrieved from the database, as well as the storage location of the goods corresponding to the user's historical rentals, and the user's geographic location is obtained by analyzing the storage location of the goods.

4. The deposit reduction and exemption management system based on user behavior information according to claim 3 is characterized in that: The analyzing the commodity storage location to obtain the user's geographic location includes: A1: extract the commodity storage locations corresponding to each historical rental of the current user, obtain the setting area where each commodity storage location is located, and mark the number of commodity storage locations in each setting area as the number of regional commodities in the corresponding setting area; A2: extract the maximum value of the number of commodities in the area, and determine whether the ratio of the maximum value to the total number of commodity storage locations exceeds a preset ratio; if yes, mark the set area corresponding to the maximum value as the user geographic location of the current user; if no, jump to A3; A3: Mark the two setting areas with the largest number of regional commodities as target setting areas, mark the target setting area with a large number of regional commodities as user geographic location one, mark the target setting area with a small number of regional commodities as user geographic location two, and mark the setting areas corresponding to user geographic location one and user geographic location two as user geographic location of the current user.

5. The deposit reduction and exemption management system based on user behavior information according to claim 4 is characterized in that: The behavior factors obtained by analyzing the conventional information include: B1: Extract the number of rentals ZN of the current user in the database record, and determine whether the number of rentals ZN is less than the standard number; if yes, set the deposit of the user's current rental to the standard deposit YJ; if no, jump to B2; B2: Extract the number of breaches WN and the number of leases ZN, and obtain the current user's compliance ratio SL based on the formula SL = (ZN-WN) / ZN; B3: Extract the default duration corresponding to each default number WN, and summarize the default durations into a duration data group; obtain the variance of the duration data group, and determine whether the variance is less than the variance setting threshold; if yes, obtain the average value of the data in the duration data group; if no, remove the default duration with the largest difference from the mode of the current duration data group in the duration data group, and re-determine the variance until the variance of the current duration data group is less than the corresponding variance setting threshold, and then obtain the average value of the remaining data in the current duration data group; B4: Mark the average value of the duration data group as the characteristic default duration TZ, and obtain the current user's behavior factor BY based on the formula BY=SL×α / exp((TZ-BTZ) / BTZ); where BTZ is the standard default duration; α is the amplitude adjustment coefficient, and the value range of α is (0,1).

6. The deposit reduction and exemption management system based on user behavior information according to claim 5 is characterized in that: The age influencing factors obtained by analyzing age include: Extract the user's age, extract the behavior factors BY corresponding to all users of the current age from the database, mark several of the behavior factors BY as target behavior factors, mark the maximum value of the target behavior factors as the maximum target behavior factor ZM, and obtain the scaling value SZ based on the formula SZ=ZM×β; where β is the proportional coefficient, and the value range of β is (0.5,0.9]; The target behavior factors greater than the scaling value SZ are summarized into the first group, and the remaining target behavior factors are summarized into the second group; the average values ​​of the first group and the second group are obtained, and the average value of the first group is marked as the first average value YPZ, and the average value of the second group is marked as the second average value RPZ; Based on the formula TWZ1=δ1×YPZ+δ2×RPZ, the characteristic behavior factor TWZ1 of the behavior factor corresponding to the current user's age is obtained; wherein δ1 and δ2 are both proportional coefficients greater than 0; The behavior factor BY of the current user is extracted, and the age influence factor NYZ is obtained based on the formula NYZ=(TWZ1-BY) / BY.

7. The deposit reduction and exemption management system based on user behavior information according to claim 6 is characterized in that: The analyzing of the user's geographical location to obtain the location influencing factor includes: C1: Extract the setting area corresponding to the user's geographic location of the current user, and determine whether the number of setting areas corresponding to the current user is 1; if yes, jump to C2; if no, jump to C3; C2: extracting the mode of the behavior factor BY of the user in the setting area, and marking the mode as the characteristic behavior factor 2 TWZ2 corresponding to the user geographic location of the current user; C3: Extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location one, and mark the mode as the first mode DZ1; extract the mode of the behavior factor BY of the user in the setting area corresponding to the user's geographic location two, and mark the mode as the second mode DZ2; obtain the characteristic behavior factor two TWZ2 of the behavior factor corresponding to the user's geographic location of the current user based on the formula TWZ2=γ1×DZ1+γ2×DZ2; wherein γ1 and γ2 are proportional coefficients greater than 0, and γ1+γ2=1; C4: extract the current user's behavior factor BY, and obtain the position influence factor WYZ based on the formula WYZ=(TWZ2-BY) / BY.

8. The deposit reduction and exemption management system based on user behavior information according to claim 7 is characterized in that: The use factor is obtained by adjusting the behavior factor based on the age influence factor and the location influence factor, including: The age influencing factor NYZ, location influencing factor WYZ and behavior factor BY of the current user are extracted, and the usage factor SYZ of the current user is obtained based on the formula SYZ = (1 + ρ × (exp (θ1 × NYZ + θ2 × WYZ) - 1)) × BY; wherein ρ is the amplitude adjustment coefficient of the exp() function, and the value range of ρ is (0, 1); θ1 and θ2 are both proportional coefficients greater than 0, and θ1 + θ2 = 1.

9. The deposit reduction and exemption management system based on user behavior information according to claim 8 is characterized in that: The reduction coefficient for this lease based on the usage factor and the commodity amount includes: The usage factor SYZ of the current user is used to determine whether the usage factor SYZ is greater than the usage factor threshold SYT; if yes, the reduction coefficient JS of this lease is assigned a value of 1; if no, the amount Q of the goods leased this time is extracted, and the reduction coefficient JS of this lease is obtained based on the formula JS=SYZ / SYT×μ / exp((Q-PQ) / PQ); wherein PQ is the average amount of all goods in the database, and μ is an amplitude adjustment coefficient greater than 0.

10. The deposit reduction and exemption management system based on user behavior information according to claim 9 is characterized in that: The reduction of the deposit based on the reduction coefficient includes: Extract the exemption coefficient JS of this lease and the standard deposit YJ of this leased product, and obtain the exemption amount JM based on the formula JM=JS×YJ. Based on the exemption amount JM, the deposit of this lease is exempted.

Images