CN108733696B - Credit investigation form generation method and device - Google Patents
Credit investigation form generation method and device Download PDFInfo
- Publication number
- CN108733696B CN108733696B CN201710256415.9A CN201710256415A CN108733696B CN 108733696 B CN108733696 B CN 108733696B CN 201710256415 A CN201710256415 A CN 201710256415A CN 108733696 B CN108733696 B CN 108733696B
- Authority
- CN
- China
- Prior art keywords
- user
- credit
- credit investigation
- assessed
- probability
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
Abstract
The embodiment of the application discloses a method and a device for generating a credit investigation form. In the embodiment of the application, when credit investigation is required for a user to be subjected to credit investigation, each behavior feature corresponding to the user is determined according to historical data corresponding to the user to be subjected to credit investigation, then the missing credit investigation category of the user is determined according to the probability of each behavior feature appearing under each credit investigation category which is determined in advance, and then a credit investigation form is generated according to the missing credit investigation category of the user, so that the user only needs to fill in credit investigation information on the missing credit investigation category, inconvenience caused to the user is reduced, and credit investigation efficiency is improved.
Description
Technical Field
The present application relates to the field of information technologies, and in particular, to a method and an apparatus for generating a credit investigation form.
Background
In the credit investigation field (credit investigation field), in order to evaluate the risk of a service request (such as loan, credit, etc.) made by a user, a credit investigation institution (credit investigation institution) usually collects credit investigation information of the user on each credit investigation category.
The credit investigation type refers to the type of credit investigation information, the credit investigation type is divided by credit investigation institutions according to a certain standard, and the division standards of different credit investigation institutions may be different. Credit information is information that may indicate the user's credit capabilities. For example, the credit investigation information corresponding to the user "with a college course" may indicate the credit ability of the user, and the credit investigation category of the credit investigation information may be "the school course" or "the educational experience".
In many cases, the credit investigation institution cannot collect the credit investigation information of the user in each credit investigation type, and the credit investigation institution does not collect the credit investigation type corresponding to the credit investigation information of the user, namely the credit investigation type missing by the user. At this time, the credit investigation institution will often require the user to provide credit investigation information on the credit investigation category that he or she lacks.
In practical applications, the credit investigation categories that are missing by different users are often different, but the credit investigation institution usually provides a standardized credit investigation form to the user who lacks the credit investigation categories, as shown in fig. 1, all the credit investigation categories are listed on the standardized credit investigation form, and the user is required to fill in corresponding credit investigation information for each credit investigation category one by one. However, the credit investigation institution usually collects the credit investigation information of the user on some credit investigation categories, and actually does not need the user to fill in the credit investigation information for the credit investigation categories again, which wastes a lot of time for the user and causes inconvenience for the user.
Disclosure of Invention
The embodiment of the application provides a credit investigation form generation method and device, and aims to solve the problem that the existing credit investigation form generation method causes inconvenience to users.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
the method for generating the credit investigation form provided by the embodiment of the application comprises the following steps:
acquiring historical data of a user to be assessed;
determining each behavior characteristic corresponding to the user to be assessed according to the historical data;
determining the credit investigation type missing by the user to be assessed according to the determined behavior characteristics and the predetermined probability of each behavior characteristic appearing under each credit investigation type;
and generating a credit investigation form according to the credit investigation type missing from the user to be subjected to credit investigation.
The device for generating the credit investigation form provided by the embodiment of the application comprises:
the acquisition module is used for acquiring historical data of a user to be credit-investigation;
the first determining module is used for determining each behavior characteristic corresponding to the user to be assessed according to the historical data;
the second determining module is used for determining the credit investigation type missing by the user to be assessed according to the determined behavior characteristics and the predetermined probability of the behavior characteristics appearing under each credit investigation type;
and the generation module is used for generating a credit investigation form according to the credit investigation type missing from the user to be subjected to credit investigation.
According to the technical scheme provided by the embodiment of the application, when the credit investigation needs to be performed on the user to be assessed, the behavior characteristics corresponding to the user are determined according to the historical data corresponding to the user to be assessed, then the missing credit investigation type of the user is determined by combining the probability of each behavior characteristic appearing under each credit investigation type, and then the credit investigation form is generated according to the missing credit investigation type of the user, so that the user only needs to fill in the credit investigation information on the missing credit investigation type, the inconvenience caused to the user is reduced, and the credit investigation efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a diagram of a conventional credit form;
fig. 2 is a flowchart of a method for generating a credit investigation form according to an embodiment of the present application;
figure 3a is a schematic illustration of an existing credit investigation provider used by a credit investigation institution to interact with a user;
fig. 3b is a schematic diagram of the credit investigation system provided by the embodiment of the present application interacting with the user;
fig. 4 is a schematic diagram of a credit investigation form generation apparatus according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a credit investigation form generation method and device.
In order to make those skilled in the art better understand the technical solutions in the present application, 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 only a part of the embodiments of the present application, and not all of the embodiments. 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.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a method for generating a credit investigation form according to an embodiment of the present application, including the following steps:
s201: and acquiring historical data of the user to be assessed.
The execution main body of the method can be a credit investigation system or a credit investigation device, and can also be a client used for executing credit investigation work, and the client can be installed on the existing credit investigation system used by a credit investigation institution. For convenience of description, the following description is made taking an example in which the main implementation body of the method is a credit investigation system.
In the embodiment of the present application, the history data may be data generated by a user to be assessed in life (on-line or off-line). The historical data can be obtained by workers from various ways, and can also be obtained by intelligent search engines, crawlers or other intelligent programs capable of obtaining the historical data from various ways. For example, the historical data generated in life by zhang san may be 5 ten thousand yuan deposited in a certain bank on 5 th 1 month in 2017, 10L filled in a gas station on 6 th 1 month in 2017, a student examination counseling shift entered in 2016 in 6 months, etc., the historical data of zhang san may be acquired by a worker visiting a certain bank, a gas station, and a counseling shift, or the historical data of zhang san may be acquired by an intelligent program from a database of a certain bank, a database of a gas station, and a website of a counseling shift.
S202: and determining each behavior characteristic corresponding to the user to be assessed according to the historical data.
In the embodiment of the application, the behavior characteristics of the user to be assessed can be some behaviors generated in life by the user to be assessed, such as automobile refueling behaviors, luxury goods purchasing behaviors, academic monograph borrowing behaviors and the like.
The behavior characteristics can be extracted from historical data of the user to be credit by the credit investigation system according to a preset extraction rule.
Wherein, the extraction rule can be to determine the behavior characteristics related to the historical data according to the keywords in the historical data. The corresponding relation between each keyword and each behavior feature is preset, so that the credit investigation system can extract the corresponding behavior feature as the behavior feature corresponding to the user to be credited according to the keywords with the frequency higher than a set value in the historical data (only the keywords with the higher frequency can indicate the behavior habit of the user).
The credit investigation system can also actively acquire historical data generated by the user by performing certain behaviors which may be related to credit ability, and further determine the habitual behavior of the user in the behaviors as the behavior characteristics of the user according to the acquired historical data.
For example, if historical data generated by zhang from 2016 to 2017 in 1 month is acquired from a highway management center, keywords such as refueling and toll stations with high frequency of occurrence can be analyzed and extracted from the historical data of zhang, then it can be determined that behavior characteristics corresponding to zhang can be a vehicle refueling behavior and a toll station payment behavior, and it is worth explaining that if the vehicle refueling behavior generated by zhang within a certain time is less (for example, 5 vehicle refueling behaviors are generated in one year), it is indicated that the behavior of refueling the vehicle is not a habitual behavior of zhang, and then the behavior characteristic corresponding to zhang cannot be determined as the vehicle refueling behavior; and the payment record and the refueling record of Zhang III can be obtained, and whether the Zhang III usually pays or refuels or not is judged, so that the behavior characteristic of Zhang III is determined.
The key point of analyzing and extracting the behavior characteristics from the historical data is that a series of division standards of the behavior characteristics preset by a worker are as accurate as possible and are independent of each other. Therefore, the credit investigation system can accurately reflect the credit investigation type of the user to be assessed according to the behavior characteristics extracted from the historical data of the user to be assessed according to the standard for dividing the behavior characteristics. Certainly, the staff can also adjust the standard for dividing the behavior characteristics at any time, and the accuracy of the credit investigation system is further improved.
S203: and determining the credit investigation type missing by the user to be assessed according to the determined various behavior characteristics and the predetermined probability of the behavior characteristics appearing under each credit investigation type.
According to the statistical rules, if the behavior characteristics corresponding to two users are the same or similar, the credit investigation categories of the two users should be the same or similar. Based on the statistical rule, in the embodiment of the application, the probability of each behavior feature appearing under each credit investigation type can be preset in the credit investigation system, so that the credit investigation system can inquire the probability of any behavior feature appearing under each credit investigation type.
In the embodiment of the present application, the probability of each behavior feature occurring under each credit category may be determined by:
the method comprises the steps of obtaining a data sample, wherein the data sample comprises behavior characteristics corresponding to a plurality of credit investigation users respectively and credit investigation categories of the credit investigation users respectively, and determining the probability of the behavior characteristics under each credit investigation category respectively according to the data sample and aiming at each behavior characteristic.
For example, the data sample includes 10000 credit assessed users, and each credit assessed user has a credit assessment category and corresponding individual behavior characteristics. Assuming that 3000 users with credit acquisition category y1 out of the 10000 users are counted, and then 300 users with behavior characteristics a1 out of the 3000 users with y1 are further counted, p (a1| y1) ═ 300/3000 ═ 1/10 can be finally obtained. Similarly, the conditional probability of each behavior feature with respect to each credit category can be counted and calculated. The conditional probability of a behavior feature with respect to an assessment category is the probability that the behavior feature occurs under the assessment category.
Various behavior feature sets x can be counted from the data samplesiProbability of occurrence P (x)i) For example, the corresponding behavior feature set x in 10000 credit-already-informed usersiIf there are 200 users (a1, a3, a4) who have already been informed, P (x) can be obtainedi) When the credit investigation category missing from a certain credit investigation user needs to be determined, 200/10000-2%, P (x) corresponding to the credit investigation user can be inquired from the statistical resulti). In addition, various credit categories y can be countediProbability of occurrence P (y)i) E.g. 10000 credit assessed users with credit category yiIf the credit-already-informed user (such as the automobile product) has 2000 people, P (y) can be obtainedi)＝2000/10000＝20％。
The more credit investigation users are contained in the data sample, the larger the data sample is, the closer the data sample is to the actual situation, and the more accurate the probability of each behavior characteristic obtained according to the data sample appearing under each credit investigation type is.
In the embodiment of the application, for each behavior feature corresponding to a user to be assessed, the probability of the behavior feature appearing under each assessment category is obtained by inquiring from the predetermined probability of the behavior feature appearing under each assessment category, and after the probability of the behavior feature corresponding to the user to be assessed appearing under each assessment category is obtained, the assessment category missing by the user to be assessed can be determined.
Specifically, for each credit investigation category, the probability that the user to be credit investigated has the credit investigation category may be calculated according to the probability that each behavior feature corresponding to the user to be credit investigated appears in the credit investigation category; and determining the credit investigation type of the user to be credit investigated according to the probability that the user to be credit investigated has each credit investigation type. And the other credit categories except the credit category of the user to be credit are the credit categories missing from the user to be credit.
According to the probability of each behavior feature corresponding to the user to be assessed for appearing under each assessment category, for each assessment category, substituting the probability of each behavior feature corresponding to the user to be assessed for appearing under each assessment category and the probability of the assessment category into the following formula:
wherein, P (y)i| x) is the probability that the user to be credit has the ith credit category, yiRepresenting the ith credit investigation type, x representing a set of various behavior characteristics corresponding to the user to be credit investigated, ajRepresents the jth behavior characteristic corresponding to the user to be assessed, m represents the number of the behavior characteristics corresponding to the user to be assessed, and P (y)i| x) represents the probability that the user to be credit has the ith credit category, P (y)i) Representing the probability of the occurrence of the ith credit category, the probability of the occurrence of each credit category also being determined or predetermined from the data sample, P (a)j|yi) And P (x) represents the probability of the occurrence of x. P (y)i)、P(aj|yi) And P (x) can be counted in advance from the statistical samples.
Obtaining the probability P (y) that the user to be assessed has the ith assessment categoryi| x), 1-P (y) may be substitutediAnd | x) is taken as the probability that the user to be credit lacks the ith credit category.
The above formula
Is derived according to Bayesian theorem. According to Bayes' theorem, the conditional probability of A relative to B is calculated as:
then, in order to determine the credit investigation category of the user to be assessed according to the conditional probability of each credit investigation category relative to the user to be assessed, then:
where x may be a set of behavior characteristics corresponding to the user to be assessed, and y may be a set of behavior characteristics corresponding to the user to be assessediIndicating the ith credit category. Actually, each behavior feature corresponding to the user to be assessed may be represented as x ═ a (a)1，a2，a3，……aj) Then, according to the probability formula:
therefore, according to the equations (1) and (2), it can be derived:
actually, the core idea of the technical solution claimed in the present application is to classify historical data of a user to be assessed based on a naive bayesian classification algorithm, determine an assessment category that the user to be assessed has, and further determine an assessment category that the user to be assessed lacks, so as to generate a corresponding assessment form.
Because the historical data of the users to be credit-assessed are redundant and disordered, the credit-assessment information is too specific, and the historical data and the credit-assessment information cannot be used as processing objects when the credit-assessment system executes a naive Bayesian classification algorithm, in the embodiment of the application, a series of irrelevant behavior characteristics can be extracted according to the historical data of the users to be credit-assessed, behavior habits of the users to be credit-assessed are abstracted into the irrelevant behavior characteristics, the conditional probability of each behavior characteristic relative to each credit-assessment category can be determined according to a data sample, and finally, the conditional probability of each credit-assessment category relative to the users to be credit-assessed is calculated, so that the degree of fit between each credit-assessment category and the users to be credit-assessed can be quantitatively compared.
In the embodiment of the application, after the probabilities that users to be assessed lose all credit categories are determined, the probabilities that the users to be assessed lose all credit categories are ranked from large to small, the credit categories corresponding to the first N probabilities are determined as the credit categories that the users to be assessed lose, wherein N is an integer greater than 0, and can be preset in a credit assessment system by a worker based on business experience. It should be noted that, when the above-mentioned method for comparing the rank of the probability that the user to be assessed lacks each credit category is adopted, the above-mentioned formula is not needed
Into the specific value of p (x), andit is sufficient to consider p (x) as a constant, and the specific value of p (x) has no influence on the final comparison result.
The credit investigation type corresponding to the probability greater than a specific value can be determined as the credit investigation type missing by the user to be assessed according to the probability that the user to be assessed loses each credit investigation type respectively, wherein the specific value can be preset in a credit investigation system by a worker based on business experience.
For example, the behavior characteristics corresponding to Zhang III are (refueling behavior, highway charging behavior, automobile consumption behavior, telephone fee recharging behavior, communication behavior, reporting examination and assistant class behavior, and purchasing advanced engineer training textbook behavior), and the types of the credit required to be collected by the credit investigation institution are automobile property, operator information, academic calendar, public deposit and house property. Then, the credit investigation system can inquire P (a) corresponding to each behavior feature corresponding to Zhang IIIjY), calculating the probabilities of the credit categories of the three-in-one loss and the three-in-one loss in sequence to be 40%, 35%, 32%, 82% and 97%, determining the credit categories (accumulation fund and house property) corresponding to the probabilities greater than 80% as the credit categories of the three-in-one loss, and sorting the 5 probabilities from large to small, and taking the credit categories (accumulation fund and house property) corresponding to the first two probabilities as the credit categories of the three-in-one loss.
S204: and generating a credit investigation form according to the credit investigation type missing from the user to be subjected to credit investigation.
After the credit investigation type missing from the user to be assessed is obtained, a credit investigation form which does not contain the credit investigation type of the user to be assessed can be generated.
It should be noted that, in the embodiment of the present application, the credit investigation form may be a paper form printed by a credit investigation system, or may also be an electronic form, a user interaction interface, and the like, in short, the credit investigation form may obtain credit investigation information provided by a user, and the specific form of the credit investigation form is not limited in the present application.
Figure 3a is a schematic diagram of the interaction with a user of a conventional credit investigation system used by a credit investigation institution. Fig. 3b is a schematic diagram of the credit investigation system provided by the present application interacting with the user.
As shown in fig. 3a, the user needs to fill in the credit investigation information on the standardized credit investigation form one by one for all credit investigation categories, which is low in convenience. As shown in fig. 3b, the credit investigation system first determines the missing credit investigation type of the user according to the behavior characteristics corresponding to the user, and then only requires the user to fill corresponding credit investigation information in the missing credit investigation type.
By the method shown in fig. 2, when a user to be assessed needs to assess credit, each behavior feature corresponding to the user is determined according to the historical data corresponding to the user to be assessed, then the user missing credit category is determined according to the probability that each behavior feature appears under each credit category determined in advance, and then the credit assessment form is generated according to the user missing credit assessment category, so that the user only needs to fill in the credit assessment information on the missing credit assessment category, thereby reducing inconvenience caused to the user and improving the credit assessment efficiency.
In the embodiment of the application, each credit investigation form to be filled by each credit investigation user is customized for the credit investigation user, and the credit investigation form to be filled by each credit investigation user may be different, which also realizes 'thousands of people and thousands of faces' of the credit investigation form.
According to the method for generating the credit investigation form, the staff is not required to update the standardized credit investigation form (adding the credit investigation type into the credit investigation form) when the credit investigation information on the new credit investigation type needs to be collected, and the customized credit investigation form can be provided for the user to be credited by the credit investigation system after the staff configures the credit investigation system once.
Furthermore, the credit investigation form generation method claimed by the application can be applied to the field of big data credit investigation, and the credit investigation system can calculate the credit investigation type and the missing credit investigation type of each social member according to massive historical data collected by a big data platform, so that big data credit investigation of each social member is realized.
In addition, in the existing credit investigation mode, a worker is required to screen credit investigation information of a user from numerous and complicated historical data of the user according to business experience, and then the missing credit investigation type of the user is analyzed. The credit investigation system provided by the embodiment of the application can perform credit investigation work mechanically on one hand, and can calculate the conditional probability of each credit investigation type relative to the user to be assessed on the other hand, so that the credit investigation work can be performed efficiently, and the credit investigation type missing by the user to be assessed can be determined accurately.
In addition, the acquired historical data of the user to be assessed may be historical data from one data source, for example, the historical data may be from a large data platform, as in the above-described embodiment, and each behavior feature corresponding to the user to be assessed may be determined according to the historical data from the large data platform.
As another implementation provided by the embodiment of the present application, the historical data may also be historical data from more than one data source. One data source represents one data acquisition path, and historical data acquired from different data sources often points to different credit categories.
For example, a bank is a data source, credit investigation types pointed by historical data corresponding to the bank are probably financial properties, and behavior characteristics such as collection behavior, loan behavior and deposit behavior of a user can be analyzed from the historical data corresponding to the bank. For another example, the learning telecommunication network database is a data source, the credit investigation type pointed by the historical data corresponding to the learning telecommunication network database is a academic calendar with a high probability, and the behavior characteristics of the user such as a learning behavior, a rest-study behavior, an incrassive behavior, a hanging behavior and the like can be analyzed from the historical data corresponding to the education department.
When there is more than one data source corresponding to the behavior feature corresponding to the user to be assessed, in the embodiment of the present application, for each data source, according to the behavior feature determined by the historical data from the data source and the predetermined probability of occurrence of each behavior feature in each assessment category, the assessment category missing from the user to be assessed with respect to the data source is determined, and then according to the assessment category missing from the user to be assessed with respect to each data source, the assessment category missing from the user to be assessed is determined.
Specifically, according to the probability of the user to be assessed missing each credit investigation type relative to the data source, the credit investigation type corresponding to the probability greater than a specific value is determined as the credit investigation type missing by the user to be assessed, and then the intersection is taken for the credit investigation type missing by the user to be assessed relative to each data source, which is the credit investigation type missing by the user to be assessed really.
The credit investigation category that the user to be credit has relative to each data source can be determined first, and the other credit investigation categories except all the credit investigation categories that the user to be credit has can be determined as the credit investigation category that the user to be credit lacks. That is, according to the probability that the user to be assessed has each assessment category relative to the data source, the assessment category corresponding to the probability not less than the specific value is determined as the assessment category that the user to be assessed has, and then the assessment categories that the user to be assessed has relative to each data source are merged, so that the other assessment categories except the merged set are the assessment categories that the user to be assessed really lacks.
For the credit investigation system, actually, each behavior feature set corresponding to a user to be assessed is divided into a plurality of behavior feature subsets corresponding to each data source according to different data sources. Determining the credit investigation type of the user to be credit which is missing relative to a certain data source, actually determining the credit investigation type of the user to be credit which is relative to the behavior feature subset according to the probability of each behavior feature appearing under each credit investigation type in the behavior feature subset corresponding to the data source, and then determining the credit investigation type of the user to be credit which is relative to each data source as the credit investigation type of the user to be credit. For specific embodiments, reference may be made to the above description, which is not repeated.
For example, Zhang three corresponding behavior feature subsets x1, x2 and x3 from three data sources are x1 (refueling behavior, highway charging behavior and automobile product consumption behavior), x2 (telephone fee recharging behavior and call behavior), x3 (registration and study guidance behavior and advanced engineer training textbook purchasing behavior), and the credit types required to be collected by the credit institution are automobile property, operator information, academic calendar, public accumulation fund and house property. Then, for x1, P (fueling behavior | vehicle property), P (fueling behavior | operator information), P (fueling behavior | academic calendar), P (fueling behavior | public accumulation), P (fueling behavior | house property) can be inquired, and similarly, conditional probabilities of highway toll collection behavior and automobile consumption behavior with respect to each credit investigation category can also be inquired.
In this way, the conditional probability P (y | x1) of each credit category with respect to x1 can be calculated. Assuming that the calculated P (y | x1) corresponding to the vehicle property, the operator information, the academic calendar, the public accumulation fund and the house property is 95%, 68%, 55%, 40% and 81% in this order, the credit category (vehicle property) corresponding to 95% may be taken as the credit category corresponding to x1 for the three-phase, or the credit category (vehicle property and house property) corresponding to a probability greater than 80% may be taken as the credit category corresponding to x1 for the three-phase. Similarly, the credit categories of three-phase signals with respect to x2 and x3 can be determined. Then, the credit category lacking zhang san is other credit categories except the credit categories which zhang san has for x1, x2, and x3, respectively.
In the existing credit investigation method, when a worker acquires historical data of a user from a plurality of data sources, the historical data acquired from a certain data source only can indicate that the user is likely to have a credit investigation type corresponding to the data source, but the worker cannot determine whether the user with the historical data of the data source has other credit investigation types which are not seemingly related to the data source. For example, if statistical rules indicate that people with high school calendars have car property at a high probability, in the existing credit investigation method, a worker often cannot subjectively and intuitively judge whether the historical data of a certain credit investigation user who learns a credit investigation network database can indicate whether the credit investigation user has the car property.
In the embodiment of the application, the credit investigation type which cannot be intuitively analyzed by some working personnel according to business experience can be determined as the credit investigation type of the user through the conditional probability of each behavior characteristic corresponding to the user to be assessed relative to each credit investigation type. Based on a naive Bayesian classification algorithm, quantifiable depth mining can be performed on historical data corresponding to the user by utilizing the probability of each behavior feature appearing under each credit investigation type obtained by counting data samples, so that the credit investigation type missing by the user can be determined more accurately. Therefore, the credit investigation types contained in the generated credit investigation form can be greatly reduced, and the excessive time of the user does not need to be wasted.
For example, the historical data of Zhang III is that oil is added 20 times in 1 month to 2017 in 1 month in 2016, the automobile seat cushion is purchased three times in 1 month to 8 months in 2016, and the fee is paid for 5 times at Kyowa high speed in 1 month to 2 months in 2017. Then, the staff can only judge that the credit investigation type of Zhang III is the vehicle property according to the historical data of Zhang III. However, the credit investigation system can determine the behavior characteristics corresponding to zhang san as (fuel filling behavior, highway toll collection behavior, vehicle consumption behavior) according to history data of zhang san, and can calculate P (vehicle yield | zhang) to be 95% and possibly P (academic calendar | zhang) to be 75%, which indicates that people with the three behavior characteristics are not only likely to be people with vehicle yield but also people with academic calendar with a high probability. Therefore, the credit investigation type of Zhang III can be the vehicle property and the academic calendar, and the credit investigation system does not need to list the academic calendar on the credit investigation form. In the conventional credit investigation method, the result of manual classification is that the academic calendar is not determined as the credit investigation category owned by zhang san.
Finally, it should be emphasized that those skilled in the art should understand that the determination of the probability of missing each credit category and the determination of the probability of having each credit category are equivalent technical means, and the determination of the credit category missing from the user to be assessed by any technical means should be within the scope of the protection claimed in the present application.
Based on the invoking method of the interactive control shown in fig. 2, an embodiment of the present application further provides a device for generating a credit investigation form, as shown in fig. 4, including:
the acquisition module 401 acquires historical data of a user to be assessed;
a first determining module 402, configured to determine, according to the historical data, various behavior characteristics corresponding to the user to be assessed;
a second determining module 403, configured to determine, according to the determined behavior features and the predetermined probability of occurrence of each behavior feature in each credit investigation category, a credit investigation category missing from the user to be assessed;
and the generating module 404 is used for generating a credit investigation form according to the credit investigation type missing from the user to be investigated.
The method for pre-determining the probability of each behavior feature appearing under each credit category specifically comprises the following steps: acquiring a data sample; the data sample comprises behavior characteristics corresponding to a plurality of credit investigation users respectively and credit investigation categories of the credit investigation users respectively; and according to the data sample, determining the probability of the behavior characteristic appearing under each credit investigation type aiming at each behavior characteristic.
The second determining module 403 is configured to query, from the predetermined probability of occurrence of each behavior feature in each credit investigation category, the probability of occurrence of each behavior feature in each credit investigation category corresponding to the user to be credit investigated; aiming at each credit investigation type, calculating the probability that the user to be assessed lacks the credit investigation type according to the probability that each behavior characteristic corresponding to the user to be assessed appears under the credit investigation type; and determining the credit investigation type missing by the user to be credit investigated according to the probability that the user to be credit investigated respectively misses each credit investigation type.
The second determining module 403 adopts a formula
Calculating the ith credit investigation type y of the user to be creditediProbability P (y)i| x); according to the P (y)i| x) determining the probability that the user to be assessed lacks the ith assessment category;
wherein x represents a set of various behavior characteristics corresponding to the user to be assessed, and ajRepresents the jth behavior characteristic corresponding to the user to be assessed, m represents the number of the behavior characteristics corresponding to the user to be assessed, and P (y)i| x) represents the treatmentProbability that credit investigation user has ith credit investigation type, P (y)i) Representing the probability of the occurrence of the ith credit category, the probability of the occurrence of each credit category being determined from the data samples, P (a)j|yi) And P (x) represents the probability of the occurrence of x.
The second determining module 403, according to the probabilities that the user to be assessed loses each assessment category respectively, determines the assessment category corresponding to the probability greater than the specific value as the assessment category that the user to be assessed lacks; or the probabilities of the users to be subjected to credit investigation missing all credit investigation categories are sorted from large to small, the credit investigation categories corresponding to the first N probabilities are determined as the credit investigation categories missing by the users to be subjected to credit investigation, and N is an integer larger than 0.
The obtaining module 401 obtains the historical data of the user to be credit from at least two data sources respectively;
the first determining module 402 is configured to determine, for each data source, a behavior feature corresponding to the user to be assessed according to historical data acquired from the data source;
the second determining module 403, for each data source, determines, according to the behavior features determined by the historical data from the data source and the predetermined probability of occurrence of each behavior feature in each credit investigation category, the credit investigation category that the user to be credit lacks relative to the data source; and determining the credit investigation type missing from the user to be assessed according to the credit investigation type missing from each data source of the user to be assessed.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (12)
1. A credit investigation form generation method is characterized by comprising the following steps:
acquiring historical data of a user to be assessed;
determining each behavior characteristic corresponding to the user to be assessed according to the historical data;
determining the credit investigation type missing by the user to be assessed according to the determined behavior characteristics and the predetermined probability of each behavior characteristic appearing under each credit investigation type;
and generating a credit investigation form according to the credit investigation type missing from the user to be subjected to credit investigation.
2. The method according to claim 1, wherein the pre-determining the probability of each behavior feature occurring under each credit category specifically comprises:
acquiring a data sample; the data sample comprises behavior characteristics corresponding to a plurality of credit investigation users respectively and credit investigation categories of the credit investigation users respectively;
and according to the data sample, determining the probability of the behavior characteristic appearing under each credit investigation type aiming at each behavior characteristic.
3. The method according to claim 2, wherein the step of determining the credit investigation category missing from the user to be assessed according to the determined behavior characteristics and the predetermined probability of occurrence of each behavior characteristic under each credit investigation category comprises:
inquiring the probability of each behavior characteristic corresponding to the user to be credit reported appearing under each credit reporting category from the predetermined probability of each behavior characteristic appearing under each credit reporting category;
aiming at each credit investigation type, calculating the probability that the user to be assessed lacks the credit investigation type according to the probability that each behavior characteristic corresponding to the user to be assessed appears under the credit investigation type;
and determining the credit investigation type missing by the user to be credit investigated according to the probability that the user to be credit investigated respectively misses each credit investigation type.
4. The method according to claim 3, wherein calculating the probability that the user to be assessed lacks the assessment category specifically comprises:
using a formula
Calculating the ith credit investigation type y of the user to be creditediProbability P (y)i|x)；
According to the P (y)i| x) determining the probability that the user to be assessed lacks the ith assessment category;
wherein x represents a set of various behavior characteristics corresponding to the user to be assessed, and ajRepresents the jth behavior characteristic corresponding to the user to be assessed, m represents the number of the behavior characteristics corresponding to the user to be assessed, and P (y)i| x) indicates that the user to be credit has the firstProbability of i credit categories, P (y)i) Representing the probability of the occurrence of the ith credit category, the probability of the occurrence of each credit category being determined from the data samples, P (a)j|yi) And P (x) represents the probability of the occurrence of x.
5. The method according to claim 3 or 4, wherein the determining the credit investigation type missing by the user to be assessed according to the probability that the user to be assessed respectively misses each credit investigation type specifically comprises:
determining the credit investigation type corresponding to the probability larger than a specific value as the credit investigation type missing by the user to be assessed according to the probability that the user to be assessed respectively misses each credit investigation type; or
And sequencing the probabilities of the users to be subjected to credit investigation missing all credit investigation categories respectively from large to small, and determining the credit investigation categories corresponding to the first N probabilities respectively as the credit investigation categories missing by the users to be subjected to credit investigation, wherein N is an integer larger than 0.
6. The method according to claim 1, wherein the obtaining of the historical data of the user to be assessed specifically comprises:
respectively acquiring historical data of the user to be assessed from at least two data sources;
determining each behavior characteristic corresponding to the user to be assessed according to the historical data, specifically comprising:
for each data source, determining behavior characteristics corresponding to the user to be assessed according to historical data acquired from the data source;
determining the credit category missing from the user to be credit according to the determined behavior features and the probability of each behavior feature appearing under each credit category, specifically comprising:
aiming at each data source, determining the credit investigation type of the user to be credit which is missing relative to the data source according to the behavior characteristics determined by the historical data from the data source and the predetermined probability of the occurrence of each behavior characteristic under each credit investigation type;
and determining the credit investigation type missing from the user to be assessed according to the credit investigation type missing from each data source of the user to be assessed.
7. An apparatus for generating a credit form, comprising:
the acquisition module is used for acquiring historical data of a user to be credit-investigation;
the first determining module is used for determining each behavior characteristic corresponding to the user to be assessed according to the historical data;
the second determining module is used for determining the credit investigation type missing by the user to be assessed according to the determined behavior characteristics and the predetermined probability of the behavior characteristics appearing under each credit investigation type;
and the generation module is used for generating a credit investigation form according to the credit investigation type missing from the user to be subjected to credit investigation.
8. The apparatus according to claim 7, wherein the predetermined probability of occurrence of each behavior feature under each credit category specifically comprises:
acquiring a data sample; the data sample comprises behavior characteristics corresponding to a plurality of credit investigation users respectively and credit investigation categories of the credit investigation users respectively;
and according to the data sample, determining the probability of the behavior characteristic appearing under each credit investigation type aiming at each behavior characteristic.
9. The apparatus according to claim 8, wherein the second determining module queries, from the predetermined probability of occurrence of each behavior feature in each credit investigation category, the probability of occurrence of each behavior feature in each credit investigation category corresponding to the user to be credit investigated; aiming at each credit investigation type, calculating the probability that the user to be assessed lacks the credit investigation type according to the probability that each behavior characteristic corresponding to the user to be assessed appears under the credit investigation type; and determining the credit investigation type missing by the user to be credit investigated according to the probability that the user to be credit investigated respectively misses each credit investigation type.
10. The apparatus of claim 9, wherein the second determining module employs a formula
Calculating the ith credit investigation type y of the user to be creditediProbability P (y)i| x); according to the P (y)i| x) determining the probability that the user to be assessed lacks the ith assessment category;
wherein x represents a set of various behavior characteristics corresponding to the user to be assessed, and ajRepresents the jth behavior characteristic corresponding to the user to be assessed, m represents the number of the behavior characteristics corresponding to the user to be assessed, and P (y)i| x) represents the probability that the user to be credit has the ith credit category, P (y)i) Representing the probability of the occurrence of the ith credit category, the probability of the occurrence of each credit category being determined from the data samples, P (a)j|yi) And P (x) represents the probability of the occurrence of x.
11. The apparatus according to claim 9 or 10, wherein the second determining module determines, according to the probabilities that the user to be assessed lacks each credit investigation category, the credit investigation category corresponding to the probability greater than a specific value as the credit investigation category that the user to be assessed lacks; or the probabilities of the users to be subjected to credit investigation missing all credit investigation categories are sorted from large to small, the credit investigation categories corresponding to the first N probabilities are determined as the credit investigation categories missing by the users to be subjected to credit investigation, and N is an integer larger than 0.
12. The apparatus of claim 7,
the acquisition module is used for respectively acquiring historical data of the user to be credit from at least two data sources;
the first determining module is used for determining the behavior characteristics corresponding to the user to be assessed according to the historical data acquired from each data source;
the second determining module is used for determining the credit investigation type of the user to be subjected to credit investigation which is missing relative to the data source according to the behavior characteristics determined by the historical data from the data source and the predetermined probability of the occurrence of each behavior characteristic under each credit investigation type aiming at each data source; and determining the credit investigation type missing from the user to be assessed according to the credit investigation type missing from each data source of the user to be assessed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256415.9A CN108733696B (en) | 2017-04-19 | 2017-04-19 | Credit investigation form generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256415.9A CN108733696B (en) | 2017-04-19 | 2017-04-19 | Credit investigation form generation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108733696A CN108733696A (en) | 2018-11-02 |
| CN108733696B true CN108733696B (en) | 2021-05-04 |
Family
ID=63924917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710256415.9A Active CN108733696B (en) | 2017-04-19 | 2017-04-19 | Credit investigation form generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108733696B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675251A (en) * | 2019-09-29 | 2020-01-10 | 支付宝(杭州)信息技术有限公司 | Credit-based service processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201628960U (en) * | 2010-03-25 | 2010-11-10 | 苏州韵语信息科技有限公司 | Electronic form intelligent input system based on network |
| CN102147727A (en) * | 2011-04-02 | 2011-08-10 | 中国科学院软件研究所 | Method for predicting software workload of newly-added software project |
| US8661027B2 (en) * | 2010-04-30 | 2014-02-25 | Alibaba Group Holding Limited | Vertical search-based query method, system and apparatus |
| CN103678672A (en) * | 2013-12-25 | 2014-03-26 | 北京中兴通软件科技股份有限公司 | Method for recommending information |
| CN105046559A (en) * | 2015-09-10 | 2015-11-11 | 河海大学 | Bayesian network and mutual information-based client credit scoring method |
| CN105320700A (en) * | 2014-08-05 | 2016-02-10 | 南京理工大学常熟研究院有限公司 | Database dynamic query form generation method |
| CN105528374A (en) * | 2014-10-21 | 2016-04-27 | 苏宁云商集团股份有限公司 | A commodity recommendation method in electronic commerce and a system using the same |
| CN106126221A (en) * | 2016-06-21 | 2016-11-16 | 浪潮电子信息产业股份有限公司 | A kind of list generates methods, devices and systems |
| CN106168976A (en) * | 2016-07-14 | 2016-11-30 | 武汉斗鱼网络科技有限公司 | A kind of specific user's method for digging based on NB Algorithm and system |
| CN106202168A (en) * | 2016-06-24 | 2016-12-07 | 武汉斗鱼网络科技有限公司 | A kind of web site contents methods of exhibiting and device |
-
2017
- 2017-04-19 CN CN201710256415.9A patent/CN108733696B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201628960U (en) * | 2010-03-25 | 2010-11-10 | 苏州韵语信息科技有限公司 | Electronic form intelligent input system based on network |
| US8661027B2 (en) * | 2010-04-30 | 2014-02-25 | Alibaba Group Holding Limited | Vertical search-based query method, system and apparatus |
| CN102147727A (en) * | 2011-04-02 | 2011-08-10 | 中国科学院软件研究所 | Method for predicting software workload of newly-added software project |
| CN103678672A (en) * | 2013-12-25 | 2014-03-26 | 北京中兴通软件科技股份有限公司 | Method for recommending information |
| CN105320700A (en) * | 2014-08-05 | 2016-02-10 | 南京理工大学常熟研究院有限公司 | Database dynamic query form generation method |
| CN105528374A (en) * | 2014-10-21 | 2016-04-27 | 苏宁云商集团股份有限公司 | A commodity recommendation method in electronic commerce and a system using the same |
| CN105046559A (en) * | 2015-09-10 | 2015-11-11 | 河海大学 | Bayesian network and mutual information-based client credit scoring method |
| CN106126221A (en) * | 2016-06-21 | 2016-11-16 | 浪潮电子信息产业股份有限公司 | A kind of list generates methods, devices and systems |
| CN106202168A (en) * | 2016-06-24 | 2016-12-07 | 武汉斗鱼网络科技有限公司 | A kind of web site contents methods of exhibiting and device |
| CN106168976A (en) * | 2016-07-14 | 2016-11-30 | 武汉斗鱼网络科技有限公司 | A kind of specific user's method for digging based on NB Algorithm and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108733696A (en) | 2018-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11797773B2 (en) | Navigating electronic documents using domain discourse trees | |
| Zhu et al. | Mining mobile user preferences for personalized context-aware recommendation | |
| CA3090497C (en) | Transaction classification based on transaction time predictions | |
| CN109636091B (en) | Method and device for identifying risk of required document | |
| CN110390182B (en) | Method, system and equipment for determining applet category | |
| CN110674188A (en) | Feature extraction method, device and equipment | |
| CN112182421A (en) | Potential customer mining method and device and electronic equipment | |
| CN105989066A (en) | Information processing method and device | |
| US20240060791A1 (en) | Identification of grouping criteria for bulk trip review in getting tax deductions | |
| US20170124085A1 (en) | Website navigation path analysis | |
| CN108733696B (en) | Credit investigation form generation method and device | |
| CN110008252B (en) | Data checking method and device | |
| CN115456801B (en) | Artificial intelligence big data wind control system, method and storage medium for personal credit | |
| CN108595498B (en) | Question feedback method and device | |
| US11379929B2 (en) | Advice engine | |
| CN114548963A (en) | Payment interaction processing method and device | |
| CN110738562B (en) | Method, device and equipment for generating risk reminding information | |
| US20160162814A1 (en) | Comparative peer analysis for business intelligence | |
| CN111523995A (en) | Method, device and equipment for determining characteristic value of model migration | |
| Miller | Acquisition program problem detection using text mining methods | |
| KR102635894B1 (en) | Smart power generation fuel price prediction system and method thereof | |
| Ali et al. | Honesty is the Best Policy: On the Accuracy of Apple Privacy Labels Compared to Apps' Privacy Policies | |
| CN117194514A (en) | Data summarization method, device and medium for business data | |
| CN114519631A (en) | Financing data processing method and device based on product matching | |
| CN114240496A (en) | Client mining method, device, equipment and storage medium applied to insurance recommendation |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201016 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201016 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |