CN115983572A - Method and device for ordering fund parties, computer equipment and storage medium - Google Patents
Method and device for ordering fund parties, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115983572A CN115983572A CN202211659173.5A CN202211659173A CN115983572A CN 115983572 A CN115983572 A CN 115983572A CN 202211659173 A CN202211659173 A CN 202211659173A CN 115983572 A CN115983572 A CN 115983572A
- Authority
- CN
- China
- Prior art keywords
- candidate
- primary
- target
- party
- candidate fund
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000012163 sequencing technique Methods 0.000 claims abstract description 60
- 230000006870 function Effects 0.000 claims description 24
- 238000005457 optimization Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012797 qualification Methods 0.000 description 4
- 238000005461 lubrication Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the application discloses a fund party sorting method, a fund party sorting device, computer equipment and a storage medium. The method comprises the following steps: acquiring target order information of a target applicant sent by a user terminal; determining a primary characteristic and a secondary characteristic respectively corresponding to each preset candidate fund party and target applicant party according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing; dividing the candidate fund side into a plurality of groups according to the primary characteristics and a preset group division rule, and sequencing the groups to obtain primary sequencing; respectively sorting the candidate fund parties in each group according to the secondary characteristics to obtain the secondary sorting of the candidate fund parties in each group; determining a target rank of the candidate fund party according to the primary rank and the secondary rank; and sending the target sequence to the user terminal. By implementing the method of the embodiment of the application, the sorting precision of the candidate fund party can be improved.
Description
Technical Field
The present application relates to the field of financial technologies, and in particular, to a method and an apparatus for ordering funders, a computer device, and a storage medium.
Background
With the continuous progress of science and technology, the internet financial industry is developed vigorously, and with the change of the consumption concept of people, services such as loan and loan through the network also become a common fund turnover mode for people. After the applicant proposes a fund application (order), the fund lending platform ranks a plurality of candidate fund parties capable of providing funds to obtain the matching degree of each candidate fund party and the current order.
The existing specific sorting process is as follows: firstly, after a user places an order, the user and an order are subjected to pre-matching screening, and fund parties which do not meet hard rules are removed, so that a candidate fund party list capable of receiving the order is obtained. Then, manually sorting each candidate fund party in the candidate fund party list based on the historical performance of the candidate fund parties, setting manual priority for the current fund party, and sorting each fund party according to the set priority.
However, the candidate fund party list is manually set with priority in advance, the fund party priority is the same for different orders, the fund parties are not flexibly adapted according to the characteristics of the current orders, the orders are only sorted based on the analysis experience of human beings on historical data, and the sorting precision is not high.
Disclosure of Invention
The embodiment of the application provides a fund side sorting method, a fund side sorting device, computer equipment and a storage medium, and the fund side sorting precision can be improved.
In a first aspect, an embodiment of the present application provides a method for ranking funders, including:
acquiring target order information of a target application party sent by a user terminal;
determining a primary characteristic and a secondary characteristic which correspond to each preset candidate fund party and the target applicant respectively according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing;
dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing;
sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group;
determining a target rank of the candidate funder according to the primary rank and the secondary rank;
and sending the target sequence to the user terminal, so that the user obtains the target sequence through the user terminal, and determining the matching degree of the target order information and each candidate fund party.
In a second aspect, an embodiment of the present application further provides a funder sorting apparatus, which includes:
the receiving and sending unit is used for acquiring target order information of a target application party sent by the user terminal;
the processing unit is used for determining a primary characteristic and a secondary characteristic which are respectively corresponding to each preset candidate fund party and the target applicant according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing; dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing; sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group; determining a target rank of the candidate funder according to the primary rank and the secondary rank;
the receiving and sending unit is further configured to send the target rank to the user terminal, so that a user obtains the target rank through the user terminal, and determines a matching degree between the target order information and each candidate fund party.
In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the foregoing method when executing the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium, in which a computer program is stored, the computer program including program instructions, which when executed by a processor, implement the above method.
The embodiment of the application provides a funding party sorting method and device, computer equipment and a storage medium. Wherein the method comprises the following steps: acquiring target order information of a target applicant sent by a user terminal; determining a primary characteristic and a secondary characteristic which are respectively corresponding to each preset candidate fund party and the target applicant according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing; dividing the candidate fund party into a plurality of groups according to the primary characteristics and a preset group division rule, and sequencing the groups to obtain primary sequencing; sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group; determining a target rank of the candidate funder according to the primary rank and the secondary rank; and sending the target sequence to the user terminal, so that the user obtains the target sequence through the user terminal, and determining the matching degree of the target order information and each candidate fund party. On one hand, in the embodiment, a plurality of business targets (including primary features and secondary features) can be determined according to the target order information of the current target applicant, and the candidate fund parties are sorted according to the plurality of business targets corresponding to the current target order information without manually setting priorities for the candidate fund parties in advance, so that the scheme can flexibly sort the candidate fund parties according to the characteristics of the current target order and improve the sorting precision when matching the fund parties; on the other hand, the method designs double-layer sequencing, firstly utilizes the primary characteristics to carry out first-layer sequencing, utilizes a group division rule to divide candidate fund parties with similar scores into the same group in the first-layer sequencing, thereby reducing errors caused by sequencing according to absolute values, and then ranks the candidate fund parties in each group according to the secondary characteristics, thereby realizing the function of optimizing the primary target firstly and then optimizing the secondary target, and further improving the sequencing precision.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a block diagram of an intelligent matching model according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a funding party ranking method according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of a funder ranking method according to another embodiment of the present application;
FIG. 4 is a schematic block diagram of a funder's sequencing device provided by an embodiment of the present application;
fig. 5 is a schematic block diagram of a computer device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a funding party sorting method and device, computer equipment and a storage medium.
The execution subject of the funding party sorting method may be the funding party sorting device provided in this embodiment, or an intelligent matching model integrated with the funding party sorting device, or a computer device integrated with the funding party sorting device or the intelligent matching model, where the funding party sorting device may be implemented in a hardware or software manner, and the computer device is a server.
In some embodiments, the intelligent matching model in this embodiment comprises a ranking module, and in other embodiments, referring to fig. 1, the intelligent matching model comprises at least one of a planning module, a wind control module, and a bottom module in addition to the ranking module, wherein the planning module is used for globally optimal rough allocation, determining recommended and non-recommended candidate fund parties; the sorting module is a core module of the application and is used for sorting the candidate fund parties; the wind control module is used for controlling the risk of the divided funding party; the bottom layer module is used for realizing the functions of the planning module, the sequencing module and the wind control module, the whole process is run through to support the bottom layer, and the method mainly comprises the steps of processing and reading in the real-time characteristic field of the model, developing and deploying the model (comprising a machine learning prediction model, an operation and research optimization model, a matching sequencing model and the like), external interaction and the like.
Referring to fig. 2, fig. 2 is a flowchart illustrating a funding party sorting method according to an embodiment of the present disclosure. As shown in fig. 2, the method includes the following steps S110-S160.
And S110, acquiring target order information of the target application party sent by the user terminal.
In this embodiment, the target applicant is a user who currently applies for funds from the platform, the target order information includes user information and fund application information, the user information includes gender, age, area and occupation of the user, and the fund application information includes fund application amount and term.
Specifically, in this embodiment, after the user terminal receives the target order information of the target applicant input by the user, the user terminal sends the target order information to the server.
And S120, determining the primary characteristics and the secondary characteristics corresponding to each preset candidate fund party and the target applicant respectively according to the target order information.
Wherein the degree of influence of the secondary features on the candidate funder ordering is less than the degree of influence of the primary features on the candidate funder ordering.
In some embodiments, the primary features include profit margin, pass rate, and degree of match, and the secondary features include a dividend ratio (based on business considerations, the dividend ratio need not be as large as possible, so the present application downgrades the dividend ratio to put it into the secondary features).
The calculation process of each primary feature is described as follows:
profit margin:
specifically, the embodiment may predict by establishing a profit margin calculation model, and specifically, the model determines the profit margins respectively corresponding to each candidate fund party and the target applicant party according to the target application amount in the target order information and the profit margins corresponding to the target application amount for each candidate fund party.
In some embodiments, the profit margin corresponding to each candidate fund party can be obtained only by inputting the target application amount into the corresponding profit margin calculation model, wherein, for the candidate fund party i, the formula for calculating the profit margin in the model is as follows:
f 1 i ＝L i /gmv i ；
wherein f is 1 i Is the profit margin, L, of the candidate fund party i corresponding to the target applicant i For the profit amount corresponding to the target application amount of the candidate fund party i, gmv i And applying for the quota as a target.
The passing rate is as follows:
in some embodiments, the prediction may be performed by establishing a passing rate calculation model, and specifically, the passing rate corresponding to each candidate fund party and the target applicant is determined according to the historical passing amount of orders and the historical total number of orders of each candidate fund party.
In some embodiments, the passage rate calculation model determines the passage rate of the candidate funder by the following formula:
Matching degree:
in some embodiments, the degree of matching utility function is based on the degree of matching considerations in terms of region, number of sessions, and pricing. Specifically, because the matching degree is not well quantified, the matching degree corresponding to each candidate fund party and the target applicant can be determined according to the target order information based on a preset matching degree utility function in the embodiment; wherein, the utility function of the matching degree is as follows:
wherein, rate _ diff represents the price difference of the qualification limit (price maximum value-price minimum value of the qualification limit), and term _ diff represents the price difference of the qualification limit. Wherein the pricing is the interest rate of the sponsor.
The calculation process of the secondary features is described as follows:
the dividend can pay for the risk by oneself and return the commission according to the proportion or the fixed income. The candidate fund party needs the platform to bear the risk, and in order to control the risk, a certain proportion (such as 5%) of the deposit is charged to the platform to deal with the bad account loss when receiving the assets. In order to relieve the pressure of the deposit and obtain higher operation profit, the platform has a certain requirement on the allocation ratio, in this embodiment, a service function of the allocation ratio is set, and in the service function, the smaller the absolute value of the difference between the real-time allocation ratio of the candidate fund party and the target value (i.e., the preset allocation ratio) is, the higher the corresponding allocation ratio score is.
S130, dividing the candidate fund side into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing.
Specifically, the candidate fund parties are ranked through a ranking module, and in some embodiments, the ranking module in the intelligent matching model comprises an optimization layer and a constraint layer, wherein the optimization layer uses primary features for ranking, and the constraint layer uses secondary features for ranking.
With respect to the optimization layer:
respectively executing the steps a and b:
step a, determining a primary matching score corresponding to each candidate fund party according to the primary features and the preset feature weight corresponding to each primary feature.
Specifically, the candidate fund parties respectively determine primary matching scores of the target applicant and each candidate fund party in the optimization layer according to the following formula:
wherein, Y i 1 Corresponding primary matching scores, f, in the optimization layer for candidate funder i 1 i Profit margin, w, for candidate funder i corresponding to target applicant 1 Is the weight corresponding to the profit margin,
the corresponding passing rate of the candidate fund party i is obtained; w is a 2 As a weight corresponding to the pass rate, f 3 i Is the matching degree, w, of the target applicant corresponding to the candidate fund party i 3 The weight corresponding to the matching degree.
Wherein the characteristic weight is obtained according to a subjective and objective fusion weighting method (fusion subjective weighting method and objective weighting method), w 1 、w 2 Or w 3 The process of assigning weights is as follows:
w＝λ*w z +(1-λ)*w k ；
wherein λ ∈ (0,1) is a predetermined constant, w z For the weights determined by subjective weighting, w k Are weights determined by objective weighting.
The objective of determining the characteristic weight through the subjective and objective fusion weighting method is mainly to take the advantages of each characteristic, and the subjective weighting method is artificially and subjectively set and reflects the intention of a decision maker, but is static and unchangeable once set. The objective weighting result, the data itself reflects the weight information, and is more objective and dynamically variable, so the two are combined.
Subjective weighting method:
by adopting an Analytic Hierarchy Process (AHP for short), the problem that a business party cannot visually draft and rate the weight can be solved, only the relative importance between every two targets needs to be determined through the method, consistency check is also carried out, and whether the weight setting is reasonable or not is judged. The method comprises the following steps:
(1) establishing a hierarchical model; (2) constructing a judgment matrix (3) and checking the consistency CI; (4) computing feature vectors
Objective weighting method:
the entropy weight method is adopted and is based on the principle that: the smaller the variation degree of the index is, the less the amount of information is reflected, and the lower the corresponding weight value should be. An extreme example is: if the index is the same value for all the sponsor samples, we can consider the weight of the index to be 0, i.e. the index does not help our comprehensive evaluation.
The calculation steps of the entropy weight method are divided into the following steps:
1) Determining an index system;
2) Data preprocessing: redundant data processing, outlier processing, etc.;
3) Normalization processing: the indices of different dimensions are isometrically normalized (linear normalization or z-score method);
wherein, linear normalization:
the z-score method:
wherein x is ij The value of the jth index of the ith sponsor in the sponsor sample; max (x) j ) Is the maximum value of the jth index in the sponsor sample, min (x) j ) Is the minimum value of the jth index in the sponsor sample,
is the average value of the jth sample in the sponsor sample, and S is the standard deviation of the jth sample in the sponsor sample.
4) Calculating the entropy and weight of the index:
(1) the specific gravity of the jth index of the ith party is calculated:
(2) calculating the information entropy of the j index:
(3) calculating the weight of the jth index:
wherein, according to the different indexes, w j May be w 1 、w 2 Or w 3 。
Although the entropy weight method can objectively reflect index differentiation forces from data to a certain degree, the dependency on sample data is large, and the weight may be distorted if no business experience guides, so that the final attribute weight combines subjective expert scoring and objective data entropy weight, and the two are fused to each other to better exert the advantages of the entropy weight method.
And b, dividing the candidate fund party into a plurality of groups according to the primary matching scores and the group division rule, and sorting the groups according to the score interval size corresponding to each group in the group division rule to obtain the primary sorting.
In this embodiment, after the primary matching score is determined, the candidate fund is divided into a plurality of groups according to a group division rule, and each group is sorted according to a score interval corresponding to each group in the group division rule, so as to obtain the primary sort.
In the following examples, the group division rules are shown in table 1:
TABLE 1
| Fractional interval | [0，2) | [2，4) | [4，6) | [6，8) | [8，10] |
| Group of | 1 | 2 | 3 | 4 | 5 |
For example, if the primary matching score corresponding to a candidate principal is 3, the candidate principal is divided into group 2.
S140, respectively sorting the candidate fund parties in each group according to the secondary characteristics to obtain a secondary sorting of the candidate fund parties in each group.
Wherein, the implementation step of determining the secondary ranking of the candidate fund parties in the group is implemented in a constraint layer, which is specifically as follows:
with respect to the constraining layer:
secondary optimization objectives for constrained tier degradation, such as fractional-run-length, similar to the optimization layer, are also weighted and summed to calculate a constrained tier score Y i 2 (which is a secondary matching score corresponding to the candidate fund party i in the constraint layer) if the constraint layer only has a division ratio, the value corresponding to the division ratio is multiplied by the corresponding characteristic weight, namely the corresponding secondary matching score.
S150, determining the target rank of the candidate fund party according to the primary rank and the secondary rank.
In this embodiment, the comprehensive ranking of the candidate fund parties is determined according to the primary ranking and the secondary ranking of the candidate fund parties, and when the ranking is finally comprehensively evaluated, the ranking is performed according to the ranking of the scores of the optimization layer, and then the scores of the constraint layer are ranked.
Therefore, the double-layer sequencing is designed, on one hand, the primary target can be optimized firstly, and then the secondary target can be optimized, on the other hand, the characteristic value of target quantization is derived from the result of a utility function or a prediction model, and is not completely accurate, so that similar scores are divided into the same level, and the error influence brought by sequencing according to absolute values can be reduced.
S160, sending the target sequence to the user terminal.
In this embodiment, after the server calculates the target rank of each candidate fund party, the server sends the target rank to the user terminal, so that the user obtains the target rank through the user terminal, and determines the matching degree between the target order information and each candidate fund party, wherein in the target rank, the higher the matching degree between the candidate fund party and the target order information is, the higher the matching degree is.
In this embodiment, the intelligent matching model is further provided with a risk layer, and specifically, in this layer, a risk score of each candidate fund party can be obtained; a risk label containing the corresponding risk score is then added for each of the candidate funding parties. In this embodiment, a risk score threshold may also be set, and then candidate fund parties with risk scores greater than the risk score threshold are filtered out, so as to reduce the recommendation risk.
In summary, on one hand, in the present embodiment, a plurality of business targets (including primary features and secondary features) may be determined according to the target order information of the current target applicant, and the candidate fund parties are sorted according to the plurality of business targets corresponding to the current target order information, without manually setting priorities in advance for the candidate fund parties, and thus, according to the characteristics of the current target order, the candidate fund parties may be flexibly sorted, and the sorting accuracy is high; on the other hand, the method designs double-layer sequencing, firstly utilizes the primary characteristics to carry out first-layer sequencing, utilizes a group division rule to divide candidate fund parties with similar scores into the same group in the first-layer sequencing, thereby reducing errors caused by sequencing according to absolute values, and then ranks the candidate fund parties in each group according to the secondary characteristics, thereby realizing the function of optimizing the primary target firstly and then optimizing the secondary target, and further improving the sequencing precision.
Fig. 3 is a flowchart illustrating a funding party ranking method according to another embodiment of the present disclosure. As shown in fig. 3, the funder ordering method of the present embodiment includes steps S210-S2100.
Compared with the embodiment corresponding to fig. 2, the embodiment adds the function of the planning module, wherein the function of the planning module is global optimal coarse distribution, and the addition of the planning module mainly considers that the decision of a single order is optimal, but not the optimal decision under the global situation. Although the action is decided by a pen order, the eye is aimed globally. Therefore, an optimized coarse distribution is firstly made on the basis of the whole situation, and the sequencing accuracy is further improved.
S210, acquiring target order information of a target application party sent by the user terminal.
In this embodiment, the target applicant is a user who currently applies for funds from the platform, the target order information includes user information and fund application information, the user information includes gender, age, area and occupation of the user, and the fund application information includes fund application amount and term.
And S220, respectively adding pre-distribution labels to the candidate fund parties according to the target order information based on a preset global optimization model, wherein the pre-distribution labels comprise recommended labels and non-recommended labels.
In this embodiment, the global optimization model is constructed by the following 3 steps:
step 1, defining service problems:
defining the current scene business problem: based on data such as position of the sponsor, budget of the asset, etc., how to allocate can achieve global optimum.
Step 2, modeling solution:
based on the business problem, converting the business problem into a mathematical language, establishing an optimization model through a linear programming algorithm, and respectively determining three important factors: decision variables, objective functions and constraints.
(1) Defining variables:
decision variables: magnitude x of assignment of asset group i to sponsor j ij
The known constants are: such as the total position of the borrowed money in the month with C (n) as the sponsor n, the budget level of the z _ i asset group i, and so on
(2) Defining an objective function: the optimization formula is as follows, where t is profit margin, g is contribution gmv, d1 and d2 are preset weights, and the objective function is as follows:
(3) setting a constraint condition: the formula is shown in the following set and mainly comprises: the position of the sponsor, the hard rules of the sponsor, the capital budget, the constraint of the large disc lubrication ratio and the like.
φ(y)≤G
(4) Solving a model: carrying out optimization solution on the established model to obtain the optimal solution of the model
Step 3, model application
And finally, applying the result of the global optimization model to intelligent matching, and acquiring the current order and a recommended sponsor list under global optimal coarse distribution in real time.
At this point, by the first planning module, the fund candidates are divided into 2 large queues, and pre-allocation labels are respectively added to each candidate fund party, where the pre-allocation labels include recommended labels and non-recommended labels, that is, whether the fund candidates are recommended fund parties under global optimal rough allocation.
S230, determining the candidate fund party corresponding to the recommended label as a first candidate fund party, and determining the candidate fund party corresponding to the unrenominated label as a second candidate fund party.
In this embodiment, the candidate fund party corresponding to the recommended tag is determined as a first candidate fund party (grouped in one column), the candidate fund party corresponding to the unreported tag is determined as a second candidate fund party (grouped in another column), finally, two columns of candidate fund parties are obtained, and the subsequent sorting module sorts each column of candidate fund parties respectively.
S240, determining a primary characteristic and a secondary characteristic which correspond to each preset candidate fund party and the target applicant respectively according to the target order information.
Wherein the degree of influence of the secondary features on the candidate funder ordering is less than the degree of influence of the primary features on the candidate funder ordering.
In this embodiment, step S240 is similar to step S120 in the corresponding embodiment of fig. 2, and details thereof are not repeated here.
S250, dividing the first candidate fund party into a plurality of first groups according to the primary features and the group division rules, and sequencing the first groups to obtain a first primary sequence.
In this embodiment, after the candidate fund party in step S130 is replaced by the first candidate fund party, this step is similar to step S130, and the detailed sorting process is not described herein.
S260, dividing the second candidate fund party into a plurality of second groups according to the primary features and the group division rules, and sequencing the second groups to obtain a second primary sequence.
In this embodiment, after the candidate fund party in step S130 is replaced by the second candidate fund party, this step is similar to step S130, and the detailed description of the sorting process is omitted here.
S270, the candidate fund parties in each first group are respectively ranked according to the secondary features, and a first secondary ranking of the candidate fund parties in each first group is obtained.
In this embodiment, after the group in step S140 is replaced by the first group, this step is similar to step S140, and the detailed secondary sorting process is not described herein.
S280, respectively sorting the candidate fund parties in each second group according to the secondary features to obtain a second secondary sorting of the candidate fund parties in each second group.
In this embodiment, after the group in step S140 is replaced with the second group, this step is similar to step S140, and the detailed secondary sorting process is not described herein.
S290, determining the target sequence according to the first primary sequence, the first secondary sequence, the second primary sequence and the second secondary sequence.
The present embodiment combines a first primary ranking and a first secondary ranking of a first candidate funder (recommended funder), and a second primary ranking and a second secondary ranking of a second candidate funder (non-recommended funder).
Specifically, the first candidate fund party is ranked according to the first primary ranking and the first secondary feature to obtain a first ranking; namely, a first rank is determined according to the rank between the first small groups and the rank of the first fund candidate in the first small groups, and the obtained first rank is the rank between the first fund candidate.
Meanwhile, sorting the second candidate fund parties according to the second primary sorting and the second secondary sorting to obtain a second sorting; that is, a second rank is determined for the ranks between the second groups and the ranks of the second candidate funders within the second groups, and the resulting second rank is the rank between the second candidate funders.
Finally, determining the target sequence according to the first sequence and the second sequence; in this embodiment, the first rank is ahead of the second rank, i.e., the first candidate funder is ahead and the second candidate funder is behind.
S2100, sending the target sequence to the user terminal.
In this embodiment, after the server calculates the target rank of each candidate fund party, the server sends the target rank to the user terminal, so that the user obtains the target rank through the user terminal, and determines the matching degree between the target order information and each candidate fund party, wherein in the target rank, the higher the matching degree between the candidate fund party and the target order information is, the higher the matching degree is.
In summary, the present embodiment includes the following beneficial effects:
1. compared with the prior art that the priority is set manually, the optimization of a plurality of business targets (profit margin, passing rate, matching degree, proportion and qualification risk) is realized simultaneously by building an intelligent matching model containing a plurality of modules, and the optimization is more time-saving, labor-saving, efficient and intelligent.
2. During sorting, a planning module is introduced, global optimal coarse distribution is firstly carried out, and then sorting decision is carried out on a single order. And organically combining offline global optimization and a real-time greedy algorithm.
3. The multi-attribute utility function method of the multi-objective optimization algorithm is innovated and improved based on the service scene, the target design is innovated, and meanwhile, double-layer sequencing is designed, the hierarchical level of an optimization layer is arranged first, and then a constraint layer is arranged, so that the error caused by sequencing according to absolute values is reduced, and meanwhile, the function of optimizing a primary target first and then optimizing a secondary target can be realized.
4. For the business targets (matching degree and proportion) which are difficult to predict directly and are difficult to describe manually, the method converts the business targets into model language, designs a series of utility functions based on business functions, and skillfully incorporates the business targets into an optimization target for matching and sequencing according to local conditions.
Fig. 4 is a schematic block diagram of a sorting apparatus of a funding party according to an embodiment of the present disclosure. As shown in fig. 4, the present application also provides a ranking device of the funder corresponding to the above method of ranking funder. The funder's ranking device, which may be configured in a server, includes means for performing the funder's ranking method described above. Specifically, referring to fig. 4, the funder sorting device 400 includes a transceiver unit 401 and a processing unit 402.
A transceiver unit 401, configured to acquire target order information of a target applicant sent by a user terminal;
a processing unit 402, configured to determine, according to the target order information, a primary feature and a secondary feature that correspond to each preset candidate fund party and the target applicant, respectively, where an influence of the secondary feature on a candidate fund party ranking is smaller than an influence of the primary feature on the candidate fund party ranking; dividing the candidate fund party into a plurality of groups according to the primary characteristics and a preset group division rule, and sequencing the groups to obtain primary sequencing; sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group; determining a target rank of the candidate funder according to the primary rank and the secondary rank;
the transceiver unit 401 is further configured to send the target rank to the user terminal, so that a user obtains the target rank through the user terminal, and determines a matching degree between the target order information and each candidate fund party.
In some real-time, after the transceiver unit 401 executes the step of acquiring the target order information of the target applicant sent by the user terminal, the processing unit 402 is further configured to:
respectively adding pre-distribution labels to the candidate fund parties according to the target order information based on a preset global optimization model, wherein the pre-distribution labels comprise recommended labels and non-recommended labels;
and determining the candidate fund party corresponding to the recommended label as a first candidate fund party, and determining the candidate fund party corresponding to the unrecommended label as a second candidate fund party.
In some real-time, when the processing unit 402 executes the step of dividing the candidate fund into a plurality of small groups according to the primary feature and a preset small group division rule, and ranking each of the small groups to obtain a primary ranking step, the processing unit is specifically configured to:
dividing the first candidate fund party into a plurality of first groups according to the primary features and the group division rules, and sequencing the first groups to obtain a first primary sequence;
dividing the second candidate fund party into a plurality of second groups according to the primary features and the group division rules, and sorting the second groups to obtain a second primary sort;
in some real-time, when the processing unit 402 performs the secondary ranking step of respectively ranking the candidate funders in each of the subgroups according to the secondary features to obtain the candidate funders in each of the subgroups, specifically:
sorting the candidate fund parties in each first subgroup according to the secondary features to obtain a first secondary sorting of the candidate fund parties in each first subgroup;
sorting the candidate fund parties in each second group according to the secondary features to obtain a second secondary sorting of the candidate fund parties in each second group;
in some real-time, the processing unit 402, when executing the step of determining the target ranking of the candidate funder according to the primary ranking and the secondary ranking, is specifically configured to:
sorting the first candidate fund party according to the first primary sorting and the first secondary feature to obtain a first sorting;
sorting the second candidate fund parties according to the second primary sort and the second secondary sort to obtain a second sort;
determining the target rank according to the first rank and the second rank.
In some real-time, the primary features include profit margin, pass rate, and degree of match, and the secondary features include dividend.
In some real-time, when the step of determining the primary features and the secondary features respectively corresponding to each preset candidate fund party and the target applicant according to the target order information is executed, the processing unit 402 is specifically configured to:
determining profit margins respectively corresponding to each candidate fund party and the target application party according to a target application amount in the target order information and profit margins corresponding to each candidate fund party and the target application amount;
determining the passing rate respectively corresponding to each candidate fund party and the target applicant party according to the historical passing order number and the historical order total number of each candidate fund party;
determining the matching degrees respectively corresponding to the candidate fund parties and the target applicant party according to the target order information based on a preset matching degree utility function;
and determining the lubrication division ratio respectively corresponding to each candidate fund party and the target applicant party according to the target order information based on a preset lubrication division ratio utility function.
In some real-time, when the processing unit 402 executes the step of dividing the candidate fund into a plurality of small groups according to the primary feature and a preset small group division rule, and ranking each of the small groups to obtain a primary ranking step, the processing unit is specifically configured to:
determining a primary matching score corresponding to each candidate fund party according to the primary characteristics and a preset characteristic weight corresponding to each primary characteristic, wherein the characteristic weight is obtained according to a subjective and objective fusion weighting method;
and dividing the candidate fund party into a plurality of groups according to the primary matching scores and the group division rule, and sorting the groups according to the score interval size corresponding to each group in the group division rule to obtain the primary sorting.
In some real-time, the processing unit 402 is further configured to:
acquiring a risk score of each candidate fund party through the transceiver unit 401;
adding a risk label for each of the candidate funders that includes a corresponding risk score.
It should be noted that, as can be clearly understood by those skilled in the art, the foregoing sequencing device for the fund side and the specific implementation process of each unit may refer to the corresponding description in the foregoing method embodiment, and for convenience and conciseness of description, no further description is provided herein.
The above-described funder's sequencing means may be embodied in the form of a computer program that may be run on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, which may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 5, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer programs 5032 include program instructions that, when executed, cause the processor 502 to perform a funding method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when executed by the processor 502, the computer program 5032 causes the processor 502 to perform a funding method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:
acquiring target order information of a target application party sent by a user terminal;
determining a primary characteristic and a secondary characteristic which are respectively corresponding to each preset candidate fund party and the target applicant according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing;
dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing;
sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group;
determining a target rank of the candidate funder according to the primary rank and the secondary rank;
and sending the target sequence to the user terminal, so that the user obtains the target sequence through the user terminal, and determining the matching degree of the target order information and each candidate fund party.
It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present application also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions. The program instructions, when executed by the processor, cause the processor to perform the steps of:
acquiring target order information of a target application party sent by a user terminal;
determining a primary characteristic and a secondary characteristic which correspond to each preset candidate fund party and the target applicant respectively according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing;
dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing;
sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group;
determining a target rank of the candidate funder according to the primary rank and the secondary rank;
and sending the target sequence to the user terminal, so that a user obtains the target sequence through the user terminal, and determining the matching degree of the target order information and each candidate fund party.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated in another system or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the application can be combined, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present application may be substantially or partially implemented in the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for ordering funders, the method being applied to a server, the method comprising:
acquiring target order information of a target application party sent by a user terminal;
determining a primary characteristic and a secondary characteristic respectively corresponding to each preset candidate fund party and the target applicant party according to the target order information;
dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing;
sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group;
determining a target rank of the candidate funder according to the primary rank and the secondary rank;
and sending the target sequence to the user terminal, so that the user obtains the target sequence through the user terminal, and determining the matching degree of the target order information and each candidate fund party.
2. The method according to claim 1, wherein after obtaining the target order information of the target applicant sent by the user terminal, the method further comprises:
respectively adding pre-distribution labels to the candidate fund parties according to the target order information based on a preset global optimization model, wherein the pre-distribution labels comprise recommended labels and non-recommended labels;
and determining the candidate fund party corresponding to the recommended label as a first candidate fund party, and determining the candidate fund party corresponding to the unrecommended label as a second candidate fund party.
3. The method of claim 2, wherein the dividing the candidate fund into a plurality of subgroups according to the primary characteristics and a preset subgroup division rule, and ranking each subgroup to obtain a primary ranking comprises:
dividing the first candidate fund party into a plurality of first groups according to the primary features and the group division rules, and sorting the first groups to obtain a first primary sorting;
dividing the second candidate fund party into a plurality of second groups according to the primary features and the group division rules, and sequencing the second groups to obtain a second primary sequence;
the sorting the candidate fund parties in each of the subgroups according to the secondary features to obtain a secondary sorting of the candidate fund parties in each of the subgroups comprises:
sorting the candidate fund parties in each first subgroup according to the secondary features to obtain a first secondary sorting of the candidate fund parties in each first subgroup;
sorting the candidate fund parties in each second group according to the secondary features to obtain a second secondary sorting of the candidate fund parties in each second group;
the determining a target rank of the candidate funder as a function of the primary rank and the secondary rank comprises:
sorting the first candidate fund party according to the first primary sorting and the first secondary feature to obtain a first sorting;
sorting the second candidate fund parties according to the second primary sort and the second secondary sort to obtain a second sort;
determining the target rank according to the first rank and the second rank.
4. The method of claim 1, wherein the primary characteristics comprise profit margin, pass rate, and degree of match, and the secondary characteristics comprise percentage.
5. The method according to claim 4, wherein the determining of the primary and secondary characteristics corresponding to each of the preset candidate funding parties and the target applicant according to the target order information comprises:
determining profit margins respectively corresponding to the candidate fund parties and the target applicant party according to a target application amount in the target order information and profit margins corresponding to the candidate fund parties and the target application amount;
determining the passing rate respectively corresponding to each candidate fund party and the target applicant party according to the historical passing order number and the historical order total number of each candidate fund party;
determining the matching degrees respectively corresponding to the candidate fund parties and the target applicant party according to the target order information based on a preset matching degree utility function;
and determining the partial proportion corresponding to each candidate fund party and the target applicant respectively according to the target order information based on a preset partial proportion utility function.
6. The method according to any one of claims 1 to 5, wherein the dividing the candidate fund into a plurality of subgroups according to the primary characteristics and a preset subgroup division rule, and sorting the subgroups to obtain a primary ranking comprises:
determining a primary matching score corresponding to each candidate fund party according to the primary characteristics and a preset characteristic weight corresponding to each primary characteristic, wherein the characteristic weight is obtained according to a subjective-objective fusion weighting method;
and dividing the candidate fund party into a plurality of groups according to the primary matching scores and the group division rules, and sorting the groups according to the score intervals corresponding to the groups in the group division rules to obtain the primary sorting.
7. The method according to any one of claims 1 to 5, further comprising:
obtaining a risk score for each of the candidate funders;
adding a risk label for each of the candidate funders that includes a corresponding risk score.
8. A funder sequencing device, comprising:
the receiving and sending unit is used for acquiring target order information of a target application party sent by the user terminal;
the processing unit is used for determining a primary characteristic and a secondary characteristic which are respectively corresponding to each preset candidate fund party and the target applicant according to the target order information, wherein the influence degree of the secondary characteristic on the candidate fund party sequencing is smaller than the influence degree of the primary characteristic on the candidate fund party sequencing; dividing the candidate fund part into a plurality of groups according to the primary features and preset group division rules, and sequencing the groups to obtain primary sequencing; sorting the candidate fund parties in each group according to the secondary features to obtain a secondary sorting of the candidate fund parties in each group; determining a target rank of the candidate funder according to the primary rank and the secondary rank;
the receiving and sending unit is further configured to send the target rank to the user terminal, so that a user obtains the target rank through the user terminal, and determines a matching degree between the target order information and each candidate fund party.
9. A computer arrangement, characterized in that the computer arrangement comprises a memory, on which a computer program is stored, and a processor, which when executing the computer program, carries out the method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program comprising program instructions which, when executed by a processor, implement the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211659173.5A CN115983572B (en) | 2022-12-22 | 2022-12-22 | Method and device for ordering fund parties, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211659173.5A CN115983572B (en) | 2022-12-22 | 2022-12-22 | Method and device for ordering fund parties, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115983572A true CN115983572A (en) | 2023-04-18 |
| CN115983572B CN115983572B (en) | 2023-12-12 |
Family
ID=85975386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211659173.5A Active CN115983572B (en) | 2022-12-22 | 2022-12-22 | Method and device for ordering fund parties, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983572B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427171A (en) * | 2015-11-30 | 2016-03-23 | 北京口袋财富信息科技有限公司 | Data processing method of Internet lending platform rating |
| CN108475395A (en) * | 2016-11-02 | 2018-08-31 | 深圳投之家金融信息服务有限公司 | The sort method and device of network loan investment user |
| CN109583796A (en) * | 2019-01-08 | 2019-04-05 | 河南省灵山信息科技有限公司 | A kind of data digging system and method for Logistics Park OA operation analysis |
| CN111340584A (en) * | 2020-02-19 | 2020-06-26 | 深圳乐信软件技术有限公司 | Method, device, equipment and storage medium for determining fund side |
| CN115310851A (en) * | 2022-08-19 | 2022-11-08 | 国网河南省电力公司经济技术研究院 | Comprehensive evaluation method for power equipment overhaul investment scheme |
-
2022
- 2022-12-22 CN CN202211659173.5A patent/CN115983572B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427171A (en) * | 2015-11-30 | 2016-03-23 | 北京口袋财富信息科技有限公司 | Data processing method of Internet lending platform rating |
| CN108475395A (en) * | 2016-11-02 | 2018-08-31 | 深圳投之家金融信息服务有限公司 | The sort method and device of network loan investment user |
| CN109583796A (en) * | 2019-01-08 | 2019-04-05 | 河南省灵山信息科技有限公司 | A kind of data digging system and method for Logistics Park OA operation analysis |
| CN111340584A (en) * | 2020-02-19 | 2020-06-26 | 深圳乐信软件技术有限公司 | Method, device, equipment and storage medium for determining fund side |
| CN115310851A (en) * | 2022-08-19 | 2022-11-08 | 国网河南省电力公司经济技术研究院 | Comprehensive evaluation method for power equipment overhaul investment scheme |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115983572B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rezaie et al. | Evaluating performance of Iranian cement firms using an integrated fuzzy AHP–VIKOR method | |
| CN110415084B (en) | Intelligent product recommendation method and device | |
| Gajzler et al. | Evaluation of planned construction projects using fuzzy logic | |
| CN108921702A (en) | Garden trade and investment promotion method and device based on big data | |
| CN111340244A (en) | Prediction method, training method, device, server and medium | |
| US20210150548A1 (en) | System for automatic segmentation and ranking of leads and referrals | |
| Saputro et al. | Hybrid MCDM and simulation-optimization for strategic supplier selection | |
| CN111667307B (en) | Method and device for predicting financial product sales volume | |
| CN110634043A (en) | Supply and demand matching model obtaining method, supply and demand matching method, platform and storage medium | |
| CN110415123A (en) | Financial product recommended method, device and equipment and computer storage medium | |
| CN112561364A (en) | Power grid operation and maintenance cost level rationality evaluation technology based on combination weight | |
| US20130226665A1 (en) | Methods and systems for conducting surveys and processing survey data to generate a collective outcome | |
| CN113159213A (en) | Service distribution method, device and equipment | |
| CN113674040A (en) | Vehicle quotation method, computer device and computer-readable storage medium | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| Feng et al. | Deep learning for systemic risk measures | |
| CN114330837A (en) | Object processing method and device, computer equipment and storage medium | |
| Mohamed et al. | An information entropy weighting method combined to TOPSIS approach for ranking consulting firms | |
| Kurup et al. | Task personalization for inexpertise workers in incentive based crowdsourcing platforms | |
| US8473331B2 (en) | Computer-implemented systems and methods for determining future profitability | |
| CN115983572B (en) | Method and device for ordering fund parties, computer equipment and storage medium | |
| CN114282976B (en) | Vendor recommendation method and device, electronic equipment and medium | |
| CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
| US20230267542A1 (en) | System and method for analysing financial products | |
| CN113570114A (en) | Intelligent matching method and system for resource service and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |