CN114066478A

CN114066478A - Target classification evaluation method and device based on informed production information

Info

Publication number: CN114066478A
Application number: CN202111138287.0A
Authority: CN
Inventors: 李荣花; 钟威; 李问; 周晨晨; 宁梦星
Original assignee: Dongfang Weiyin Technology Co ltd
Current assignee: Dongfang Weiyin Technology Co ltd
Priority date: 2021-09-27
Filing date: 2021-09-27
Publication date: 2022-02-18

Abstract

One or more embodiments of the present specification provide a method and an apparatus for target classification evaluation based on known production information, including: acquiring comparison information, and performing admission verification according to a verification rule table; after the access, inquiring the intellectual property information and judging whether the intellectual property information meets the conditions or not; if yes, continuously extracting anti-fraud information items, carrying out anti-fraud scoring, and judging whether the sum of scores exceeds a threshold value; if not, determining an index score corresponding to each item of comparison information according to a preset score table, and calculating a final comprehensive score through a score card model in combination with the weight; and determining the target type of the target, constructing a resource allocation scheme according to the target type, and outputting the resource allocation scheme. One or more embodiments of the present disclosure perform multiple checks on the comparison information of the target, and perform comprehensive evaluation around the intellectual property information, so that the evaluation factors of the target are more comprehensive, the classification of the target after evaluation is more accurate, and the efficiency and accuracy of target classification are improved.

Description

Target classification evaluation method and device based on informed production information

Technical Field

One or more embodiments of the present disclosure relate to the technical field of data analysis, and in particular, to a method and an apparatus for classification and evaluation of targets based on known production information.

Background

With the development of internet information technology, various resource products based on big data in various fields are successively introduced by various organizations, such as: financing schemes for different customers, storage space allocation schemes, material allocation schemes, and so on. The client can log in the business system of each organization through channels such as websites, mobile phone clients, WeChat small programs and the like, fill in resource allocation requirements, finish application submission on the lines, then the system can realize automatic approval in a zero-manual intervention mode according to information input and authorized by the client, and then the system can determine the allocation scheme of resources according to the established evaluation scheme of the target client. In the prior art, the evaluation manner of the target client is mostly to evaluate and classify the target client according to the target client business data such as tax data and asset data of the target client, or according to the cooperation duration, default times and the like of the target client. With the development of society, people pay more and more attention to other assets, and the real situation of the target cannot be accurately determined only by evaluating the target from the existing aspect, so that a scheme capable of accurately and comprehensively evaluating the specific type of the target is urgently needed.

Disclosure of Invention

In view of the above, one or more embodiments of the present disclosure are directed to a method and an apparatus for target classification evaluation based on knowledge information.

In view of the above, one or more embodiments of the present specification provide a method for classification and evaluation of targets based on known production information, including:

acquiring comparison information of a target, and performing admission verification on the comparison information according to a preset verification rule table;

after the admission verification is passed, inquiring the intellectual property information of the target, and judging whether the intellectual property information meets the set conditions;

if the intellectual property information meets set conditions, extracting anti-fraud information items from the comparison information, carrying out anti-fraud scoring on the anti-fraud information items, and judging whether the sum of all the anti-fraud scoring exceeds a scoring threshold value;

if the sum of all the anti-fraud scores does not exceed the score threshold, determining an index score corresponding to each item of the comparison information according to a preset score table, and calculating a final comprehensive score through a score card model by combining the weight of each item of the comparison information;

and determining the target type of the target according to the final comprehensive score, constructing a resource allocation scheme according to the target type, and outputting the resource allocation scheme.

In some embodiments, before obtaining the alignment information of the target, the method further includes:

acquiring application information and identity information of a target, calling prestored information of the target according to the identity information, and performing cross check on the application information and the prestored information;

and after the verification is passed, acquiring comparison information of the target according to the identity information.

In some embodiments, the obtaining of the application information and the identity information of the target includes:

acquiring user identity information input by a user, calling reserved information corresponding to the user, and verifying the user identity information through the reserved information;

and after the verification is passed, acquiring the application information continuously input by the user, determining the target to be evaluated by the user according to the application information, and calling the identity information corresponding to the target.

In some embodiments, after the outputting the resource allocation scheme, the method further includes:

when the number of the targets of the target type is determined to exceed the number threshold, counting the identity information of all the targets, classifying the targets through the identity information, determining the average value of the final comprehensive scores corresponding to the targets in each class, determining the optimal class in all the classes according to the average value, and adjusting the weight corresponding to the optimal class.

In some embodiments, the weights include: the type weight and the index weight corresponding to each item of comparison information;

the method comprises the following steps of determining an index score corresponding to each item of comparison information according to a preset score table, and calculating a final comprehensive score through a score card model by combining the weight of each item of comparison information, wherein the index score comprises:

determining the information type and the corresponding type weight of each item of the comparison information, calculating a type score according to the index score corresponding to the comparison information and the corresponding index weight in each information type, and calculating the final comprehensive score according to the type scores of all types and the corresponding type weights.

Based on the same concept, one or more embodiments of the present specification further provide a target classification evaluation apparatus based on known production information, including:

the access module is used for acquiring comparison information of a target and carrying out access verification on the comparison information according to a preset verification rule table;

the judgment module is used for inquiring the intellectual property information of the target after the admission check is passed and judging whether the intellectual property information meets the set conditions;

the anti-fraud module is used for extracting anti-fraud information items from the comparison information if the intellectual property information meets set conditions, carrying out anti-fraud scoring on the anti-fraud information items and judging whether the sum of all the anti-fraud scoring exceeds a scoring threshold value or not;

the calculation module is used for determining the index score corresponding to each item of comparison information according to a preset score table if the sum of all the anti-fraud scores does not exceed a score threshold value, and calculating to obtain a final comprehensive score through a score card model by combining the weight of each item of comparison information;

and the output module is used for determining the target type of the target according to the final comprehensive score, constructing a resource allocation scheme according to the target type and outputting the resource allocation scheme.

In some embodiments, before the admission module obtains the alignment information of the target, the admission module further includes:

In some embodiments, the obtaining, by the admission module, the application information and the identity information of the target includes:

In some embodiments, after the outputting module outputs the resource allocation scheme, the method further includes:

the calculation module determines an index score corresponding to each item of the comparison information according to a preset score table, and obtains a final comprehensive score through a score card model calculation by combining the weight of each item of the comparison information, wherein the calculation module comprises:

As can be seen from the above description, one or more embodiments of the present specification provide a method and an apparatus for target classification evaluation based on known production information, including: acquiring comparison information, and performing admission verification according to a verification rule table; after the access, inquiring the intellectual property information and judging whether the intellectual property information meets the conditions or not; if yes, continuously extracting anti-fraud information items, carrying out anti-fraud scoring, and judging whether the sum of scores exceeds a threshold value; if not, determining an index score corresponding to each item of comparison information according to a preset score table, and calculating a final comprehensive score through a score card model in combination with the weight; and determining the target type of the target through the final comprehensive score, constructing a resource allocation scheme according to the target type, and outputting the resource allocation scheme. One or more embodiments of the present disclosure perform multiple checks on the comparison information of the target, and perform comprehensive evaluation around the intellectual property information, so that the evaluation factors of the target are more comprehensive, the classification of the target after evaluation is more accurate, and the efficiency and accuracy of target classification are improved.

Drawings

In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.

Fig. 1 is a schematic flow chart of a target classification evaluation method based on known production information according to one or more embodiments of the present disclosure;

fig. 2 is a schematic structural diagram of a target classification evaluation device based on known production information according to one or more embodiments of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the present specification more apparent, the present specification is further described in detail below with reference to specific embodiments and the accompanying drawings.

It should be noted that technical terms or scientific terms used in the embodiments of the present specification should have a general meaning as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that a element, article, or method step that precedes the word, and includes the element, article, or method step that follows the word, and equivalents thereof, does not exclude other elements, articles, or method steps. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.

As described in the background section, with the development of society, people pay more and more attention to other assets (e.g., intellectual property rights, etc.), in the existing solutions, the related intellectual property rights business is only operated as a single business, and at the same time, an offline mode is mainly adopted, that is, a target customer provides related intellectual property rights information such as patent rights, trademark rights, soft copyright rights, etc. that the target customer has legally, and then an approval mechanism performs offline investigation and approval and then classifies the target accordingly.

In combination with the above actual situations, one or more embodiments of the present specification provide a target classification evaluation scheme based on known product information, and through multiple checks on comparison information of a target and comprehensive evaluation around knowledge right-of-production information, the target evaluation factors are more comprehensive, classification of the target after evaluation is more accurate, and efficiency and accuracy of target classification are improved.

Referring to fig. 1, a schematic flow chart of a target classification evaluation method based on known production information according to an embodiment of the present specification specifically includes the following steps:

step 101, obtaining comparison information of a target, and performing admission check on the comparison information according to a preset check rule table.

This step aims at performing admission verification for the corresponding comparison information of the target. The target may be a natural person such as a user, or an enterprise company. The comparison information is information capable of reflecting the specific situation of the target object, the data collection and the data generation are carried out by a third party supplier, and the data at least comprises tax data, financial data, judicial data, credit investigation data, industry data, industrial and commercial data and the like of the target object. Aiming at various different comparison information, a check rule table aiming at each piece of comparison information is preset, and as long as any one of the check rule tables is hit, the target is considered to be unqualified. In a specific application scenario, the comparison information for the client target, whether the hit is currently overdue, whether it is in a regulatory list, etc., or whether the hit target asset does not meet a minimum threshold criteria, etc., is used. A client may be denied admission if it hits a rule.

The way to obtain the alignment information of the target can be many ways, for example: by receiving information manually input by a user, by querying and acquiring desired information through the internet, by directly transmitting information from a third party through a dedicated docking interface, and the like.

And step 102, after the admission check is passed, inquiring the intellectual property information of the target, and judging whether the intellectual property information meets the set conditions.

The step aims to inquire the related intellectual property information of the target after the access is passed, and check whether the condition of the target intellectual property meets the access condition. The intellectual property information is the proprietary right, trademark right, software copyright, etc. owned by the target object. And then, setting conditions which need to be met by the intellectual property information, wherein in a specific application scene, the setting conditions can be in the form of judging whether the client has the patent rights, judging whether the number of the patent rights of the client reaches a set threshold value, judging whether the average valid time of the patent rights is not lower than the set threshold value and the like.

The way to query the target for the related intellectual property information may be many ways, for example: inquiring related intellectual property information through a third-party platform according to the unique identification of the target, such as the personal identification code of the individual target, the uniform social credit code of the enterprise target and the like; or inquiring the relevant information of the target through the Internet; or by information manually entered by a worker, and so forth.

Step 103, if the intellectual property information meets the set condition, extracting anti-fraud information items from the comparison information, performing anti-fraud scoring on the anti-fraud information items, and judging whether the sum of all the anti-fraud scoring exceeds a scoring threshold value.

This step is intended to verify whether a fraud is present in the target for each anti-fraud information item in the comparison information. The information items are information items related to fraud in the comparison information, such as: fraud records, identity fraud terms, data fraud terms, and the like. The data of these information items are then scored according to preset rules, which may be a score for each information item, for example: for the number of times of identity authentication, no is 0, less (e.g., 1 to 3) is 1, more (e.g., 4 to 10) is 2, and more (e.g., 11 or more) is 3, etc. Similar information items may also be scored once in a category, such as: the tax data counterfeiting time items, the financial data counterfeiting time items, the insurance data counterfeiting time items and the like can be divided into data counterfeiting time items, and the data counterfeiting time items are directly scored. And finally, adding the scores of all the information items of the target, and judging whether the scores exceed a set score threshold value. The score threshold is preset, for example, 8 or 10 points, or C-level risk, etc. If the risk exceeds the threshold value, the risk is considered to be too high, and the target fraud verification cannot be passed.

And 104, if the sum of all the anti-fraud scores does not exceed the score threshold, determining an index score corresponding to each item of the comparison information according to a preset score table, and calculating a final comprehensive score through a score card model by combining the weight of each item of the comparison information.

The step aims to score indexes of each item of comparison information and obtain a final comprehensive score by utilizing a scoring card model in combination with the weight. Wherein, the preset score table is provided with grades corresponding to each item and scores corresponding to each grade, for example: target assets are on a scale of zero to one hundred thousand, corresponding to 1 point, one hundred thousand to one million, 2 points, one million to one million, 3 points, and so on. So that each item of comparison information can obtain a score. Then, combining the weights, which is generally the product of the score and the weight value. The combination of the scores and the weights may be a final weight for each score; or each score may correspond to multiple weights, such as: the score of one piece of comparison information is X, which corresponds to a self-weight firstly, then a type weight is set according to the type of the comparison information (for example, the data type is tax data), after the product of all the scores under the type and the self-weight is calculated, the sum is added, then the combination of the type weights is carried out, and the like. And finally, obtaining a final comprehensive score by using a score card model, wherein the final comprehensive score is obtained by adding the index score and the weight after being combined. The presentation of the final composite score may be numeric or hierarchical.

The scoring card model is a common modeling method in the field of credit risk assessment. The credit scoring card models mainly comprise three types (A scoring card, B scoring card and C scoring card): a scoring card: applying for a scoring card, before emphasizing on the loan, establishing a credit risk score in a client acquisition period, and predicting the probability of default risk brought by the client; b, scoring card: in the action scoring card and the emphasis loan, in the client application processing period, an application risk scoring model is established, the risk probability of default delinquent within a certain period after the client opens an account is predicted, and the applications of clients with poor credit and non-target clients are effectively eliminated; c, grading card: and (4) after the credit card is urged to be collected and the credit card is emphatically credited, establishing an urging collection grading model in the client management period, and predicting the probability of the urging collection strategy reaction for overdue clients so as to take corresponding urging collection measures.

After the final composite score is obtained, the final composite score can be evaluated again by setting a threshold, for example, a numerical final composite score, setting a threshold level of 60 points, and if the final composite score does not reach the level, the target is considered to be unqualified, and finally, output and resource allocation are rejected.

In a specific application scenario, the intelligent rating model is a rating card model, and the specific comparison data to be utilized by the rating card model is determined, then the comparison data are classified according to the preset classification standard, then the weight distribution is performed according to the specific weight proportion of each category set by the rating card model, so that the weight value of each category in the rating card model and the specific weight value of each item in each category can be determined, then each item is scored according to a preset scoring table, the specific scoring mode is that the specific index value is compared with the rating threshold interval, and the score corresponding to the rating threshold interval is obtained in which rating threshold interval the index value is. Then combining the score with the weight of the item to obtain a score, summing the scores of all items in a large class, combining the sum with the weight of the class to obtain the score of the class, and finally summing the scores of all classes to obtain the final comprehensive score. And (4) obtaining a final comprehensive score of 100 by the scoring card model, and determining the grade of the target customer according to the comprehensive score, wherein the final score of the target customer is 90-100, that customer is 1 and the like.

And 105, determining the target type of the target according to the final comprehensive score, constructing a resource allocation scheme according to the target type, and outputting the resource allocation scheme.

This step is intended to determine the type of the target by its final composite score, and to establish a resource allocation plan according to this type and output the resource allocation plan. The target type is a plurality of classification grades of the target, for example, the final comprehensive score is in a score form, each 10 grades is divided into one grade, and each grade corresponds to one target type; or the final integrated score is in the form of grades, each grade corresponding to a target type. And then outputting the target type and establishing a resource allocation scheme according to the target type, wherein the resource of the resource allocation scheme can be money, an item (such as a company inventory item allocation scheme and the like), a virtual storage space (such as a database allocation scheme and the like) and the like. In a specific application scenario, the operation of the subsequent step may be continued without the previous step passing, which may not affect the final structure, but may calculate a corresponding final composite score for the target, for example, even if the admission check or the intellectual property information judgment of the target fails, the operation of the subsequent step may be performed and the final composite score may be calculated, but when the target type is finally determined, the target types of all the targets may be finally unqualified due to the previous target having an item that does not pass, and the like.

This resource allocation plan is then output for storage, display or reprocessing of the resource allocation plan. According to different application scenarios and implementation requirements, the specific output mode of the resource allocation scheme can be flexibly selected.

For example, for an application scenario in which the method of the present embodiment is executed on a single device, the resource allocation scheme may be directly output in a display manner on a display part (display, projector, etc.) of the current device, so that an operator of the current device can directly see the content of the resource allocation scheme from the display part.

For another example, for an application scenario executed on a system composed of multiple devices by the method of this embodiment, the resource allocation scheme may be sent to other preset devices serving as receivers in the system through any data communication manner (e.g., wired connection, NFC, bluetooth, wifi, cellular mobile network, etc.), so that the preset devices receiving the resource allocation scheme may perform subsequent processing on the preset devices. Optionally, the preset device may be a preset server, the server is generally arranged at a cloud end, and serves as a data processing and storage center, which can store and distribute the resource allocation scheme; the receiver of the distribution is a terminal device, and the holders or operators of the terminal devices may be current users, target users, staff related to target enterprises or companies, staff related to the resource allocation scheme, individuals and the like.

For another example, for an application scenario executed on a system composed of multiple devices, the method of this embodiment may directly send the resource allocation scheme to a preset terminal device through any data communication manner, where the terminal device may be one or more of the foregoing paragraphs.

In a specific application scenario, after the system obtains comparison information, namely intellectual property data, industry and business data, tax data, personal credit data, enterprise credit data, judicial data, financial institution customer data and the like, comprehensive checking of an admission strategy is performed, hundreds of strong checking rules (indexes) are provided for admission decision checking, investigation is performed from dimensions of industry and business, tax involvement, credit investigation, judicial expertise and the like, and the strong rules mean that a client is rejected when hitting an index, such as hitting a current overdue, hitting a supervision blacklist and the like. Meanwhile, whether the client has legal and effective patent rights, trademark rights, soft copyright rights and whether the intellectual property conditions meet the admission conditions is judged, and the admission conditions are also realized in an index form, for example, the client is required to have patents or reach a certain number of patents, or the average validity period of the patents is not less than years, and the admission conditions are directly rejected if the client does not meet the admission conditions.

And then, carrying out comprehensive verification on a fraud behavior strategy, wherein the fraud behavior verification also refers to a standard system, and is different from access, whether the fraud behavior passes the verification is a final score according to all indexes, the fraud behavior firstly inspects whether an application subject cheats loan in modes of identity counterfeiting, data counterfeiting and the like, or whether a fraud loan record exists, if the score does not reach the standard of directly identifying fraud, then the fraud behavior is identified through a series of normal operation behaviors and operation sign indexes from the perspective of fraud cost, if the customer meets the condition, the fraud behavior can be finally identified as non-fraud, namely, whether the customer fraud behavior verification passes is judged according to score grades, for example, the score is less than 8, the fraud behavior verification passes, and the customer identifies as a non-fraud customer.

Then, carrying out comprehensive verification on an intelligent rating model, judging multiple dimensions of related information of intellectual property rights of the customers (such as comprehensive value of patents, the scale of core patent property rights, the scale of appearance design patents, the condition of patent composition, the condition of trademarks, the condition of soft writings and the like), credit level, liability level, profit level, operation capacity, tax performance and the like through the intelligent rating model, carrying out comprehensive grade evaluation on the customers, wherein the intelligent rating can be understood as a rating card model, the examined default probability of the customers is the default probability of the customers, the structure of the rating card model is divided into model indexes and model modules, each index corresponds to a score, the indexes and the modules correspond to weights, the module weights are obtained by combining the index scores under the modules and the index weights, and then the module scores and the module weights are combined to be added to finally obtain comprehensive scores of the customers, and grading according to the scores, wherein the final comprehensive score obtained by the grading card model is a percentage, for example, customers possibly lower than 60 points are rejected.

And finally, the credit approval (resource allocation) results of the client such as the amount, interest rate and term are output by combining the access strategy verification, the fraud behavior strategy verification and the intelligent rating model evaluation utilization factor model. And obtaining a comprehensive result, namely all models in the process are required to pass through, and then obtaining the limit, interest rate and time limit of the client according to a preset configuration table.

The method for evaluating the classification of the targets based on the known production information, which is provided by applying one or more embodiments of the specification, comprises the following steps: acquiring comparison information, and performing admission verification according to a verification rule table; after the access, inquiring the intellectual property information and judging whether the intellectual property information meets the conditions or not; if yes, continuously extracting anti-fraud information items, carrying out anti-fraud scoring, and judging whether the sum of scores exceeds a threshold value; if not, determining an index score corresponding to each item of comparison information according to a preset score table, and calculating a final comprehensive score through a score card model in combination with the weight; and determining the target type of the target through the final comprehensive score, constructing a resource allocation scheme according to the target type, and outputting the resource allocation scheme. One or more embodiments of the present disclosure perform multiple corrections on the comparison information of the target, and perform comprehensive evaluation around the intellectual property information, so that the evaluation factors of the target are more comprehensive, the classification of the target after evaluation is more accurate, and the efficiency and accuracy of target classification are improved.

It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the multiple devices may interact with each other to complete the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In an alternative embodiment of the present specification, whether the information of the target object is accurate is determined for more accuracy. Before the obtaining of the comparison information of the target, the method further comprises:

The application information and the identity information are obtained by inputting or calling according to related information by a user. The pre-stored information is the relevant information of the target object stored by the system itself or a third party. The cross-checking is to perform the same information cross-validation between two or more parties according to the application information and the pre-stored information, for example: the personal assets are 100 thousands in the application information, 100 thousands are stored in the system database, and 100 thousands are stored in the third-party database, so that after the three-party cross validation is carried out on the personal assets, the accuracy of the personal assets is determined to be 100 thousands. Then, the identity information is the relevant information of the calibration target, for example: when the target is an individual, the identity information can be a name, an identity identification code and the like; when the target is an enterprise, the identity information can be enterprise full names, organization codes, legal person related information and the like.

In an alternative embodiment of the present specification, in order to confirm whether a user who performs target classification evaluation based on known production information is a legitimate user, that is, whether the user can apply for classification evaluation of a target. The acquiring of the application information and the identity information of the target comprises the following steps:

The user identity information is information representing the identity of the user, and may be text information, image and picture information, sound information, and the like, for example: corresponding user name, password information, user name information, etc., face recognition image information of the user, identification document photo information, etc., voice information of the user, etc. It may be user input or the system may be invoked as required. The reserved information is the user identity information reserved by the user in the system or the third party.

And then, after the user identity is verified and confirmed, the target input by the user and needing classification evaluation is obtained, and the related information is obtained or called.

In an optional embodiment of the present description, in order to flexibly adjust the weight value corresponding to each piece of information, the obtained final score can more accurately represent the target. After the outputting the resource allocation scheme, the method further includes:

In a specific application scenario, after target data reaches a certain amount, the system integrates customer data performance through data analysis, and continuously optimizes and adjusts the weight value. Such as: in the initial setting, regarding the individual target, the target quality of 40 years is considered to be the best, so that the weight of the age item is set to be the highest, but the final comprehensive score of the whole 35-year-old target is the highest, the default probability is the lowest, and the like through the evaluation of thousands of targets, the weight of the 35-year-old target is correspondingly set to be the highest, and the weight of the 40-year-old target is correspondingly adjusted. The classification is to classify the targets according to corresponding indexes, for example, classifying according to age periods, etc., and then determine an average value of the final comprehensive scores of all targets in each classification, and then determine an optimal classification according to the average value, and finally adjust the weight of the optimal classification.

In an alternative embodiment of the present description, the calculation of the final composite score is performed more intuitively and quickly. The weights include: the type weight and the index weight corresponding to each item of comparison information;

The scoring card model is mainly divided into three types of scoring cards: a scoring card model: applying for a scoring card model, before emphasizing on credit, establishing credit risk scoring in a client acquisition period, and predicting the probability of default risk brought by the client; b, grading card model: in the behavior scoring card model and the emphasis loan, in the client application processing period, an application risk scoring model is established, the risk probability of default delinquent within a certain period after the client opens an account is predicted, and the applications of clients with poor credit and non-target clients are effectively eliminated; c, grading card model: and (4) an acceptance urging scoring model is established in the client management period after the credit card model is paid with emphasis, and the probability of response of an acceptance urging strategy is predicted for overdue clients, so that corresponding acceptance urging measures are taken.

Based on the same concept, one or more embodiments of the present specification further provide a target classification evaluation apparatus based on known production information, as shown in fig. 2, including:

the admission module 201 acquires comparison information of a target, and performs admission verification on the comparison information according to a preset verification rule table;

the judging module 202 is used for inquiring the intellectual property information of the target after the admission check is passed, and judging whether the intellectual property information meets the set conditions;

an anti-fraud module 203, which extracts anti-fraud information items from the comparison information if the intellectual property information meets a set condition, performs anti-fraud scoring on the anti-fraud information items, and determines whether the sum of all the anti-fraud scoring exceeds a scoring threshold;

the calculation module 204 is used for determining an index score corresponding to each item of comparison information according to a preset score table if the sum of all the anti-fraud scores does not exceed a score threshold, and calculating a final comprehensive score through a score card model by combining the weight of each item of comparison information;

and the output module 205 determines the target type of the target according to the final composite score, constructs a resource allocation scheme according to the target type, and outputs the resource allocation scheme.

As an optional embodiment, before the admission module 201 obtains the comparison information of the target, the method further includes:

As an optional embodiment, the admission module 201 obtains the application information and the identity information of the target, including:

As an optional embodiment, after the outputting module 205 outputs the resource allocation scheme, the method further includes:

As an alternative embodiment, the weight includes: type weight and index weight corresponding to each item of comparison information;

the calculating module 204 determines an index score corresponding to each item of the comparison information according to a preset score table, and obtains a final comprehensive score through a score card model calculation by combining the weight of each item of the comparison information, including:

For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware components in implementing one or more embodiments of the present description.

The device of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the present disclosure, features in the above embodiments or in different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.

In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the disclosure. Further, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.

While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the embodiments discussed.

It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A target classification evaluation method based on known production information is characterized by comprising the following steps:

if the sum of all the anti-fraud scores does not exceed the score threshold, determining an index score corresponding to each item of the comparison information according to a preset score table, and calculating through a score card model by combining the weight of each item of the comparison information to obtain a final comprehensive score;

2. The method of claim 1, wherein before obtaining the comparison information of the target, the method further comprises:

3. The method of claim 2, wherein the obtaining of the application information and the identity information of the target comprises:

4. The method of claim 1, wherein after outputting the resource allocation scheme, further comprising:

5. The method of claim 1, wherein the weighting comprises: the type weight and the index weight corresponding to each item of comparison information;

6. An object classification evaluation device based on commodity knowledge information, comprising:

the access module acquires comparison information of a target and performs access verification on the comparison information according to a preset verification rule table;

the calculation module is used for determining an index score corresponding to each item of comparison information according to a preset score table if the sum of all the anti-fraud scores does not exceed a score threshold value, and calculating a final comprehensive score through a score card model by combining the weight of each item of comparison information;

7. The apparatus of claim 6, wherein before the admission module obtains the comparison information of the target, the admission module further comprises:

8. The apparatus of claim 7, wherein the admission module obtains application information and identity information of the target, and comprises:

9. The apparatus of claim 6, wherein after the outputting module outputs the resource allocation scheme, the apparatus further comprises:

10. The apparatus of claim 6, wherein the weights comprise: the type weight and the index weight corresponding to each item of comparison information;