Is an operation target factor. The achievement proportion of the Bayue bottom-keeping payment amount of different funding parties is calculated to be 12%, 38% and 60% according to the formula.

In another embodiment, if the operation target is lightning ticket customer aging, then the operation target factor of the lightning ticket and the customer aging is calculated based on the corresponding aging operation standard, specifically:

wherein N is standard paying time, t_iPaying time for each sponsor, wherein the flag is 1 to represent the factor with the lightning ticket operation target, the flag is 0 to represent the factor without the lightning ticket operation target,

and carrying out time-efficient operation on the target factors for the customers.

In other embodiments, the operation target may also be approval passing rate and/or asset quality management of an asset side, the server calculates the approval passing rate by using an eXtreme Gradient boost (XGBoost) algorithm, so as to obtain an operation target factor of the approval passing rate, and the calculation of the approval passing rate factor may relate to information such as requested object amount, usage, customer rating, application place, credit, age, occupation, academic calendar and the like. The asset side quality management factor is calculated by asset risk of the asset side.

203. Respectively reading a plurality of initial operation right groups based on a plurality of operation target groups;

the server reads the corresponding initial operation right group from the operation strategy of each available service object to obtain a plurality of initial operation right groups, wherein each fund party corresponds to one initial operation right group. Each operating weight in the set of operating weights represents a proportion of each target factor, e.g., the initial set of operating weights read from the a1 bank is [ 15%, 35%, 50% ].

204. Adjusting a plurality of initial operation right groups to generate a plurality of target operation right groups;

after reading the initial operation right groups, adjusting the initial operation right groups to generate a plurality of target operation right groups.

It should be noted that the initial operation right set may be adjusted or may not be adjusted.

Specifically, the server acquires an adjustment instruction sent from the outside, and analyzes the adjustment instruction to obtain a plurality of target value groups; then the server respectively adjusts a plurality of initial operation right groups according to a plurality of target value groups to obtain a plurality of target operation right groups; or the server generates a pre-trained weight model based on the historical adjustment record training model, and respectively adjusts a plurality of initial operation weight groups based on the trained weight model to obtain a plurality of target operation weight groups.

For example, an initial operation group is [ 15%, 35%, 50% ], and the server analyzes the adjustment instruction to obtain a corresponding target value group [ 20%, 30%, 50% ]; the server adjusts [ 15%, 35%, 50% ] according to [ 20%, 30%, 50% ] to obtain the target operation right group [ 20%, 30%, 50% ]. Or the server carries out model training based on the historical adjustment records to obtain a trained weight model, and then adjusts the initial operation weight set [ 15%, 35% and 50% ] based on the trained weight model respectively to obtain a target operation weight set [ 20%, 30% and 50% ].

The history adjustment record is an adjustment record that is retained when the adjustment is performed according to the adjustment instruction.

The server generates a pre-trained weight model based on a historical adjustment record training model, and respectively adjusts a plurality of initial operation weight groups based on the trained weight model to obtain a plurality of target operation weight groups, which specifically comprises:

acquiring a historical adjustment record, and reading first environmental data, second environmental data, target basic data, weight data and standard condition data from the historical adjustment record; performing model training based on the first environment data, the second environment data, the target basic data, the weight data and the standard reaching condition data to obtain a weight model; and the operation condition is monitored in real time by adopting a preset monitoring function to obtain a plurality of real-time operation indexes respectively corresponding to the plurality of available service objects, and the plurality of initial operation weight groups are respectively adjusted on the basis of the weight model and the plurality of real-time operation indexes to obtain a plurality of target operation weight groups.

It should be noted that, in this embodiment, the first environment data may be understood as asset environment data of the funding party, the second environment data may be understood as funding environment data of the funding party, the data of the standard reaching condition may be understood as the data of the money release amount achievement condition of the funding party, and the operation index is the total money release amount of all the funding parties.

For example, one operation target is that the loan time is 2 days, the corresponding operation target factor is 5, and the corresponding initial operation weight is 20%, but after the server operates for one day, the real-time operation index monitored by the monitoring function shows a decrease result, and at this time, the initial operation weight corresponding to the total loan time is input into the weight model to be adjusted, and the initial operation weight is adjusted from 20% to 19%.

205. A preset weighted sampling model is adopted to combine each operation target factor group and the corresponding target operation weight group to carry out score calculation on the corresponding available service object, and a service comprehensive score corresponding to each available service object is generated to obtain a plurality of service comprehensive scores;

the preset weighted sampling model relates to the following formula:

f(x_i)＝ω_i1x_i1+ω_i2x_i2+ω_i3x_i3+…

Specifically, the server multiplies each operation target factor in each operation target factor group by each corresponding target operation weight by using a preset weighting sampling model to generate a corresponding target operation factor evaluation group, and obtains a plurality of target operation factor evaluation groups; and the server calculates the score sum of each target operation factor scoring group, generates a service comprehensive score corresponding to each target operation factor scoring group and obtains a plurality of service comprehensive scores.

For example, the operation target group of the a1 bank is average loan aging of 2 days, the capital cost is 7.6%, and the customer rating requirement B, the corresponding operation target factor groups are [5,3,10], the corresponding target operation weight groups are [ 20%, 30%, 50% ], the server calculates that the target factor rating group corresponding to the a1 bank is [1,0.9,5], and therefore the comprehensive business rating corresponding to the a1 bank is calculated to be 6.9 based on [1,0.9,5 ]. The operation target group of A2 is average loan time effectiveness of 0.5 day, capital cost of 9 percent and customer rating requirement A, the corresponding operation target factor group is [10,1,1], the corresponding target operation weight group is [ 20%, 30%, 50% ], the target factor rating group corresponding to the A1 bank calculated by the server is [2,0.3,0.5], and the comprehensive A2 banking score calculated by the server based on [2,0.3,0.5] is 2.8.

206. And sequencing the plurality of service comprehensive scores from high to low to obtain a plurality of sequenced service comprehensive scores, and pushing a plurality of available service objects to the request object according to the corresponding sequence based on the plurality of sequenced service comprehensive scores.

In the present embodiment, assuming that the a1 bank has a business integration score of 6.9 and the a2 bank has a business integration score of 2.8, the a1 bank is pushed to the request object first, and then the a2 bank is pushed to the request object. In other embodiments, only the available business object with the highest business composite score, namely bank a1, may be pushed.

With reference to fig. 3, the method for pushing a business object in the embodiment of the present invention is described above, and a pushing device for a business object in the embodiment of the present invention is described below, where an embodiment of the pushing device for a business object in the embodiment of the present invention includes:

an availableobject obtaining module 301, configured to obtain request data of a request object, and obtain a plurality of available service objects according to the request data;

a targetfactor calculating module 302, configured to read an operation target group of each available service object, obtain multiple operation target groups, and calculate multiple operation target factor groups according to the multiple operation target groups, where the multiple operation target groups correspond to the multiple operation target factor groups one to one;

a targetweight obtaining module 303, configured to obtain, through a pre-trained weight model, a plurality of target operation weight sets based on the plurality of operation target groups, respectively, where the plurality of target operation weight sets correspond to the plurality of operation target factor groups one to one;

a comprehensivescore calculating module 304, configured to calculate scores of corresponding available service objects by using a preset weighted sampling model in combination with each operation target factor group and the corresponding target operation weight group, generate a service comprehensive score corresponding to each available service object, and obtain multiple service comprehensive scores;

an availableobject pushing module 305, configured to rank the multiple service composite scores in an order from high to low to obtain multiple ranked service composite scores, and based on the multiple ranked service composite scores, push the multiple available service objects to the request object in a corresponding order.

Referring to fig. 4, another embodiment of the pushing apparatus for business objects in the embodiment of the present invention includes:

Optionally, the availableobject obtaining module 301 may be further specifically configured to:

acquiring request data of a request object;

analyzing the request data of the request object, generating a request field, and determining a request attribute through the request field;

acquiring preset service standard data and preset service rules from each preset service object to obtain a plurality of service standard data and a plurality of service rules;

and screening the plurality of service standard data according to the request attribute, and screening the plurality of service rules according to the request attribute to obtain a plurality of available service objects, wherein the service standard data corresponding to the available service objects and the corresponding service rules are respectively matched with the request attribute.

Optionally, the targetfactor calculating module 302 may be further specifically configured to:

an operationstandard reading unit 3021, configured to read an operation standard corresponding to each operation target in each operation target group, to obtain an operation standard group corresponding to each operation target group;

a calculatingunit 3022, configured to calculate an operation target corresponding to each operation standard in each operation standard group, generate a corresponding operation target factor, and obtain a plurality of operation target factor groups, where the plurality of operation target groups correspond to the plurality of operation target factor groups one to one.

Optionally, the targetweight obtaining module 303 includes:

an initialweight reading unit 3031 configured to read a plurality of initial operation weight groups based on the plurality of operation target groups, respectively;

anadjusting unit 3032, configured to adjust the plurality of initial sets of operation right to generate a plurality of target sets of operation right.

Optionally, theadjusting unit 3032 includes:

aninstruction analyzing subunit 30321, configured to obtain an adjustment instruction sent from the outside, and analyze the adjustment instruction to obtain a plurality of target value groups;

afirst adjusting subunit 30322, configured to adjust the multiple initial operation right groups according to the multiple target value groups, respectively, to obtain multiple target operation right groups;

or,

asecond adjusting subunit 30323, configured to perform model training based on the historical adjustment records to obtain a pre-trained weight model, and adjust the multiple initial operation weight groups respectively based on the pre-trained weight model to obtain multiple target operation weight groups.

Optionally, thesecond adjusting subunit 30323 may be further specifically configured to:

acquiring a historical adjustment record, and reading first environmental data, second environmental data, target basic data, weight data and standard condition data from the historical adjustment record;

performing model training based on the first environment data, the second environment data, the target basic data, the weight data and the standard reaching condition data to obtain a pre-trained weight model;

and monitoring the operation condition in real time by adopting a preset monitoring function to obtain a plurality of real-time operation indexes respectively corresponding to a plurality of available service objects, and respectively adjusting the plurality of initial operation weight groups based on the pre-trained weight model and the plurality of real-time operation indexes to obtain a plurality of target operation weight groups.

Optionally, the comprehensivescore calculating module 304 may be further specifically configured to:

multiplying each operation target factor in each operation target factor group by each corresponding target operation weight by adopting a preset weighting sampling model to generate a corresponding target operation factor evaluation group and obtain a plurality of target operation factor evaluation groups;

and calculating the score sum of each target operation factor scoring group, generating a service comprehensive score corresponding to each target operation factor scoring group, and obtaining a plurality of service comprehensive scores.

Fig. 3 and fig. 4 describe the pushing apparatus of the business object in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the pushing device of the business object in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 5 is a schematic structural diagram of a pushing device for a business object according to an embodiment of the present invention, where the pushingdevice 500 for a business object may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and amemory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storingapplications 533 ordata 532.Memory 520 andstorage media 530 may be, among other things, transient or persistent storage. The program stored on thestorage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations in the pushingdevice 500 for a business object. Further, theprocessor 510 may be configured to communicate with thestorage medium 530, and execute a series of instruction operations in thestorage medium 530 on the pushingdevice 500 of the service object.

The pushingdevice 500 for business objects may also include one ormore power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one ormore operating systems 531, such as Windows server, Mac OS X, Unix, Linux, FreeBSD, and so on. Those skilled in the art will appreciate that the pushing device structure of the business object shown in fig. 5 does not constitute a limitation of the pushing device of the business object, and may include more or less components than those shown, or combine some components, or arrange different components.

The present invention further provides a pushing device for a business object, where the computer device includes a memory and a processor, where the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the pushing method for a business object in the foregoing embodiments.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and may also be a volatile computer-readable storage medium, where instructions are stored, and when the instructions are executed on a computer, the instructions cause the computer to execute the steps of the pushing method for the business object.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

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 computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for pushing a business object is characterized in that the method for pushing the business object comprises the following steps:

acquiring request data of a request object, and acquiring a plurality of available service objects according to the request data;

reading an operation target group of each available service object to obtain a plurality of operation target groups, and respectively calculating a plurality of operation target factor groups according to the operation target groups, wherein the operation target groups correspond to the operation target factor groups one by one;

acquiring a plurality of target operation weight groups respectively based on the plurality of operation target groups through a pre-trained weight model, wherein the plurality of target operation weight groups correspond to the plurality of operation target factor groups one by one;

a preset weighted sampling model is adopted to combine each operation target factor group and the corresponding target operation weight group to carry out score calculation on the corresponding available service object, and a service comprehensive score corresponding to each available service object is generated to obtain a plurality of service comprehensive scores;

and sequencing the plurality of service comprehensive scores from high to low to obtain a plurality of sequenced service comprehensive scores, and pushing the plurality of available service objects to the request object according to the corresponding sequence based on the plurality of sequenced service comprehensive scores.

2. The method for pushing a service object according to claim 1, wherein the obtaining request data of a request object and obtaining a plurality of available service objects according to the request data comprises:

acquiring request data of a request object;

3. The method according to claim 1, wherein the reading the operation target group of each available service object to obtain a plurality of operation target groups, and calculating a plurality of operation target factor groups according to the plurality of operation target groups, respectively, and the one-to-one correspondence between the plurality of operation target groups and the plurality of operation target factor groups comprises:

reading the operation standard corresponding to each operation target in each operation target group to obtain an operation standard group corresponding to each operation target group;

calculating the operation target corresponding to each operation standard in each operation standard group, generating corresponding operation target factors, and obtaining a plurality of operation target factor groups, wherein the operation target groups correspond to the operation target factor groups one by one.

4. The method of claim 1, wherein the obtaining, by a pre-trained weight model, a plurality of target operation weight sets based on the plurality of operation target sets respectively comprises:

respectively reading a plurality of initial operation right groups based on the plurality of operation target groups;

and adjusting the plurality of initial operation right groups to generate a plurality of target operation right groups.

5. The method for pushing business objects according to claim 4, wherein said adjusting the plurality of initial sets of operation rights to generate a plurality of target sets of operation rights comprises:

acquiring an adjusting instruction sent from the outside, and analyzing the adjusting instruction to obtain a plurality of target value groups;

respectively adjusting the plurality of initial operation right groups according to the plurality of target value groups to obtain a plurality of target operation right groups;

or,

and performing model training based on the historical adjustment records to obtain a pre-trained weight model, and respectively adjusting the plurality of initial operation weight groups based on the pre-trained weight model to obtain a plurality of target operation weight groups.

6. The method of claim 5, wherein the performing model training based on the historical adjustment records to obtain a pre-trained weight model, and adjusting the plurality of initial sets of operation weights based on the pre-trained weight model to obtain a plurality of target sets of operation weights comprises:

7. The method for pushing a service object according to claim 1, wherein the step of using a preset weighted sampling model to calculate the score of each available service object by combining each operation target factor group and the corresponding target operation weight group, and generating a service composite score corresponding to each available service object, and obtaining a plurality of service composite scores comprises:

8. A pushing device of a business object, wherein the pushing device of the business object comprises:

the system comprises an available object acquisition module, a service object acquisition module and a service object acquisition module, wherein the available object acquisition module is used for acquiring request data of a request object and acquiring a plurality of available service objects according to the request data;

the target factor calculation module is used for reading an operation target group of each available service object to obtain a plurality of operation target groups, and respectively calculating a plurality of operation target factor groups according to the operation target groups, wherein the operation target groups correspond to the operation target factor groups one by one;

a target weight obtaining module, configured to obtain, through a pre-trained weight model, a plurality of target operation weight sets based on the plurality of operation target groups, respectively, where the plurality of target operation weight sets correspond to the plurality of operation target factor groups one to one;

the comprehensive score calculation module is used for calculating scores of the corresponding available service objects by adopting a preset weighted sampling model and combining each operation target factor group and the corresponding target operation weight group, generating service comprehensive scores corresponding to each available service object and obtaining a plurality of service comprehensive scores;

and the available object pushing module is used for sequencing the plurality of service comprehensive scores from high to low to obtain a plurality of sequenced service comprehensive scores and pushing the plurality of available service objects to the request object according to the corresponding sequence based on the plurality of sequenced service comprehensive scores.

9. A pushing device of a business object, characterized in that the pushing device of the business object comprises: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invokes the instructions in the memory to cause a pushing device of the business object to perform the pushing method of the business object according to any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a pushing method for a business object according to any one of claims 1 to 7.