CN105894089A - Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof - Google Patents
Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof Download PDFInfo
- Publication number
- CN105894089A CN105894089A CN201610251602.3A CN201610251602A CN105894089A CN 105894089 A CN105894089 A CN 105894089A CN 201610251602 A CN201610251602 A CN 201610251602A CN 105894089 A CN105894089 A CN 105894089A
- Authority
- CN
- China
- Prior art keywords
- user
- poi
- determining
- credit
- frequency
- 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.)
- Pending
Links
- 238000011835 investigation Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 238000009826 distribution Methods 0.000 claims description 34
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000010411 cooking Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000009193 crawling Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000000470 constituent Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004883 computer application Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method of establishing a credit investigation model, a credit investigation determination method and the corresponding apparatus thereof. The method of establishing a credit reporting model comprises the steps: collecting the visiting characteristics of a user with the known credit status as a training sample; utilizing the training sample to train a machine learning model, and obtaining a credit investigation model; collecting the user visiting characteristics of a user to be evaluated; and inputting the user visiting characteristics into the credit investigation model, and obtaining the credit status of the user to be evaluated. For the method of establishing a credit investigation model, as the user visiting information is utilized as the characteristics to establish the credit investigation model and the characteristics can be reported and collected through a positioning device of the user, the labor cost is reduced; and as the characteristics can more objectively describe the credit level of the user, falsification cooking is difficult for the credit level of the user so that the accuracy for credit investigation is improved.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of computer application, in particular to a credit investigation model establishing method, a credit investigation determining method and a corresponding device.
[ background of the invention ]
Credit investigation refers to the activities of collecting, sorting, storing and processing credit information of natural people, legal people and other organizations according to law, providing services such as credit reports, credit assessment, credit information consultation and the like for the outside, helping clients judge and control credit risks and performing credit management. Credit investigation is of great importance to financial institutions, for example, before a loan is issued to a user, it is necessary to evaluate credit assessment of the user so as to reduce bad-account rate as much as possible.
For an individual user, the traditional credit investigation model adopts characteristics such as income, age, occupation and the like, which mainly depend on manual collection and input, on one hand, the acquisition of information is time-consuming and labor-consuming, and on the other hand, the provided information has the possibility of counterfeiting and is difficult to verify.
[ summary of the invention ]
In view of the above, the present invention provides a method for establishing a credit investigation model, a method for determining credit investigation, and a corresponding device, so as to improve the accuracy of credit investigation and reduce the labor cost.
The specific technical scheme is as follows:
the invention provides a method for establishing a credit investigation model, which comprises the following steps:
collecting user visit characteristics of known credit conditions as training samples;
and training a machine learning model by using the training samples to obtain a credit investigation model.
According to a preferred embodiment of the invention, the user visit feature comprises at least one of the following features:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
According to a preferred embodiment of the present invention, when the location of the user is determined to be within the range of a POI by the user's location device, it is determined that the user has visited the POI; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
According to a preferred embodiment of the present invention, the consumer POI comprises:
a restaurant, hotel, educational institution, entertainment venue, or mall.
According to a preferred embodiment of the present invention, the collecting of the distribution of the user position movement tracks includes:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
According to a preferred embodiment of the present invention, the machine learning model includes:
logistic regression models, support vector machine models, artificial neural networks, or gradient decision trees.
The invention also provides a credit investigation determination method, which comprises the following steps:
collecting user visiting characteristics of a user to be evaluated;
inputting the user visiting characteristics into a credit investigation model to obtain the credit condition of the user to be evaluated;
the credit investigation model is established by the establishment method of the credit investigation model.
According to a preferred embodiment of the invention, the user visit feature comprises at least one of the following features:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
According to a preferred embodiment of the present invention, when the location of the user is determined to be within the range of a POI by the user's location device, it is determined that the user has visited the POI; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
According to a preferred embodiment of the present invention, the collecting of the distribution of the user position movement tracks includes:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
The invention also provides a device for establishing the credit investigation model, which comprises the following components:
the first collecting unit is used for collecting the user visit characteristics of the known credit conditions as training samples;
and the training unit is used for training the machine learning model by using the training samples to obtain a credit investigation model.
According to a preferred embodiment of the invention, the user visit feature comprises at least one of the following features:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
According to a preferred embodiment of the present invention, when determining that the user accesses a POI, the first collecting unit specifically performs:
determining that the user accesses a certain POI by determining that the position of the user is within the range of the POI through a positioning device of the user; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
According to a preferred embodiment of the present invention, the consumer POI comprises:
a restaurant, hotel, educational institution, entertainment venue, or mall.
According to a preferred embodiment of the present invention, when the first collecting unit collects the distribution status of the movement tracks of the user position, the first collecting unit specifically performs:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
According to a preferred embodiment of the present invention, the machine learning model adopted by the training unit comprises:
logistic regression models, support vector machine models, artificial neural networks, or gradient decision trees.
The invention also provides a credit investigation determination device, which comprises:
the second collecting unit is used for collecting the user visiting characteristics of the user to be evaluated;
the credit evaluation unit is used for inputting the user visiting characteristics collected by the second collection unit into a credit investigation model to obtain the credit condition of the user to be evaluated;
wherein the credit investigation model is established by the credit investigation model establishing device.
According to a preferred embodiment of the invention, the user visit feature comprises at least one of the following features:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
According to a preferred embodiment of the present invention, when determining that the user accesses a POI, the second collecting unit specifically performs:
determining that the user accesses a certain POI by determining that the position of the user is within the range of the POI through a positioning device of the user; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
According to a preferred embodiment of the present invention, when the second collecting unit collects the distribution status of the movement tracks of the user position, the second collecting unit specifically performs:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
According to the technical scheme, the credit investigation model is established by using the user visit information as the characteristic, the characteristic can be reported and collected through the positioning device of the user, the labor cost is reduced, the credit level of the user can be objectively described through the characteristic, the counterfeiting is difficult to make, and the credit investigation accuracy is improved.
[ description of the drawings ]
FIG. 1 is a flow chart of a main method provided by an embodiment of the present invention;
fig. 2 is a schematic diagram of an apparatus for establishing a credit investigation model according to an embodiment of the present invention;
fig. 3 is a structural diagram of a credit investigation apparatus according to an embodiment of the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
When the credit investigation model is established, a new characteristic, namely a user visiting characteristic, is adopted to establish the credit investigation model. The user visit characteristics refer to characteristics which are extracted by tracking the offline activities of the user and are related to the credit characteristics of the user, and the characteristics are not pure geographic position characteristics, but are more abundant semantic characteristics through deep characteristic processing and fusion with other data sources. The method provided by the present invention will be described in detail with reference to examples.
Fig. 1 is a flowchart of a main method provided in an embodiment of the present invention, which mainly includes two stages: the method comprises a credit investigation model establishing stage and a credit investigation determining stage utilizing a credit investigation model, wherein the credit investigation model establishing stage can be executed in advance in the credit investigation determining stage, or can be executed periodically and timely updated independently of the credit investigation determining stage, the credit investigation determining stage is realized by utilizing an established or continuously updated credit investigation model, the two processes are independent of each other, and the sequence of the front and back execution is taken as an example in the embodiment. As shown in fig. 1, the method may include the steps of:
in 101, user visit characteristics of known credit conditions are collected as training samples.
In constructing the training sample, the collection of visiting characteristics needs to be carried out for some users with known credit conditions. Wherein the known credit status refers to that the credit scores or credit ratings of the users have been determined, and the training sample is composed of the user visit characteristics and the user credit status. In the simplest example, a user with excellent credit is assumed to have a credit score of 1, and a user with poor credit is assumed to have a credit score of 0, which can also be understood as a positive sample and a negative sample, and then the users are subjected to visit characteristic collection, so as to construct a training sample used for training the credit investigation model. In the case of credit rating, users with known credit status may be classified into several grades in advance, such as good, medium, and poor grades, and then the visited features of the users are collected to construct training samples.
The collected user visit features may include, but are not limited to, the following:
1) the number Of times or frequency that the user visits the POI (Point Of Interest) Of each category. By POI is meant information of an element in a geographic information system that may contain descriptive information and location information of the element, and a POI (i.e., an element in a geographic information system) may be a shop, a house, a bus stop, a mailbox, a tourist attraction, a restaurant, a hotel, an educational institution, etc. When a user arrives at a certain POI, the POI is indicated to be interested by the user to a certain degree. In addition, the POI includes not only location information but also rich semantic information including the name, category, feature, and the like of the location in the description information of the POI. By combining the position information and the semantic information, the preference of the user can be embodied.
When collecting the visiting information of the user to the POI, the method can be realized through a positioning device of the user, and the positioning device can be equipment with a positioning function, such as a mobile phone of the user, a tablet personal computer and the like. The method can be realized in the following specific ways:
in one implementation, if the user's location is determined by the user's positioning device to be within range of a POI (e.g., within 1 kilometer of the POI location), it may be determined that the POI is visited by the user.
Another implementation manner is that, if it is determined that the location of the user is within the range of a certain POI through the positioning apparatus of the user and an Access Point (AP) that the user accesses the POI is obtained, it is determined that the user accesses the POI, and this implementation manner needs to be combined with the acquisition of user information of other data sources, that is, APs accessing the POIs. The AP of each POI has an SSID (Service set identifier), and when a user accesses the AP of a POI through a mobile phone, a tablet computer, an intelligent wearable device, or the like, a record containing the user identifier, the SSID, and access time may exist in the database, and the AP to which the user has accessed the POI may be known through the record.
In another implementation, if it is obtained that the user searches for a certain POI on the electronic map, and it is determined that the position of the user is within the range of the POI through the positioning device of the user within a set time period, it is determined that the user has visited the POI. The implementation mode also needs to be combined with other data sources, namely, a retrieval record of the user on the electronic map is obtained, after the user retrieves the electronic map, a record containing the user identification, the retrieval key word, the retrieval time and the like exists in the database, and the user can be known to retrieve a certain POI on the electronic map through the record.
In addition, the number of times or frequency of the user accessing the POI can be recorded according to the category, wherein the granularity of the category can be flexibly set according to actual requirements. Categories of POIs may be such as business circles, educational institutions, restaurants, hotels, tourist attractions, and so on.
2) The number of times or frequency that the stay time of the user in each category of POI exceeds the preset time length. This feature is similar to the feature of type 1) for accessing a POI, but adds a restriction that further requires the user to stay at the POI for a sufficient amount of time, for example, a preset length of time of 15 minutes. The dwell characteristic can better reflect the preference of the user. Other features are basically the same as those of the feature 1), and are not described in detail herein.
3) The number of times or frequency that the user visits the respective level of consumer POI.
For some special POIs, i.e. consumer POIs, such as restaurants, hotels, educational institutions, entertainment venues, shopping malls, etc., the level of the POIs can better depict the consumption level of the user, so that the POIs can be further associated with the credit level of the user, and the feature of credit preference cannot be reflected by the simple geographic location.
Each consumption POI can be divided into a plurality of levels according to the consumption level in advance, taking a restaurant as an example, the consumption can be divided into the levels of <50 Yuan, 50-100 Yuan, 100-; taking a hotel as an example, the hotel can be divided into a quick hotel, three stars, four stars, five stars and the like according to different star grades; and then respectively counting the number or frequency of the access of the user to the POI of the consumption class at each level.
The consumption level of each consumption POI can be obtained by crawling the online information or manually marking.
4) The number of times or frequency that the stay time of the user at each level of the consumption type POI exceeds the preset time length. This feature is similar to the feature of type 3) for accessing POIs, but adds a restriction that further requires the user to stay at the POI for a sufficient period of time, for example, 30 minutes for a preset period of time for a restaurant POI and 2 hours for a hotel POI. The dwell characteristic can better reflect the preference of the user. The rest is basically the same as the feature of the type 3), and the description is omitted.
5) The number of times or frequency that the user visits each tourist location. The tourism characteristics of the user can be counted through the positioning equipment of the user, and the tourism characteristics reflect the consumption level and the risk preference of the user to a great extent, so that the credit level of the user is reflected. If the user's location is determined to be within the range of a country by the user's location device, the user may be deemed to have traveled to that country. For example, if the user has gone twice in the United states, the signature may be expressed as:
travel $ us: 2
In this way, the countries, provinces, cities, etc. that the user has gone to for some time in the past can be counted. This feature also includes the number of countries, provinces and cities that the user has gone to for some time in the past.
6) And (4) the distribution condition of the user position movement track. The movement track of the position of the user to be detected can be obtained by the user positioning device, and the features obtained by the movement track can include, but are not limited to, the following two types:
the first method comprises the following steps: and counting the moving distance of the user in a set time period. For example, the daily moving distance of the user is counted, and the user can be further divided according to different types of time, such as classification according to working days, holidays and weekends, classification according to lunch time and dinner time, classification according to day and night, and the like. The maximum moving distance of a user on all working days can be counted to be 25 km, and the sum, the average, the median and the like of the moving distances of each day can be calculated besides the maximum moving distance.
And the second method comprises the following steps: and counting the distribution information of the moving distance of the user on different gears in a set time period. The feature is actually a refinement of the first feature, for example, the maximum moving distance of a user per day may be graded according to less than 100 kilometers, 100 and 200 kilometers, and 200 and 500 kilometers, so as to count the frequency of the user appearing in different gears.
The statistics of the distribution condition of the moving track is actually the statistics of the moving distance, and the statistics has no correlation with the geographical position information. The distribution condition of the movement track can implicitly reflect behaviors such as whether the user is out of business, moved, changed in work, needs to frequently go on business and the like, and the credit level of the user is reflected to a certain extent.
At 102, the machine learning model is trained by using the training samples to obtain a credit investigation model.
The training samples collected in step 101 are put into a Machine learning model for training, and the Machine learning model that can be selected may include, but is not limited to, an LR (Logistic Regression) model, an SVM (Support Vector Machine) model, an ANN (Artificial neural network) or a GBDT (Gradient Boosting Decision Tree).
It should be noted that, in training the credit investigation model, besides the user visit features collected in step 101, features used in the prior art, such as user occupation, age, income, and other features extracted from e.g. e-commerce transaction data and social data of the user, may be further combined.
The above is a process of establishing a credit investigation model, and the following step is a process of determining credit investigation using the credit investigation model.
In 103, user visit characteristics of the user to be evaluated are collected.
The collection of the user visit characteristics of the user to be evaluated in this step is the same as the type and manner of the characteristics collected in step 101, and is not described herein again.
And in 104, inputting the collected user visiting characteristics of the user to be evaluated into a credit investigation model to obtain the credit condition of the user to be evaluated.
The result obtained by the credit investigation model output can be the credit score of the user to be evaluated, the credit rating of the user to be evaluated, and other credit condition embodying modes.
The method provided by the invention is described above, and the device provided by the invention is described in detail below with reference to the embodiment.
Fig. 2 is a schematic diagram of an apparatus for establishing a credit investigation model according to an embodiment of the present invention, and as shown in fig. 2, the apparatus may include: a first collection unit 01 and a training unit 02, wherein the main functions of each constituent unit are as follows:
the first collecting unit 01 is responsible for collecting the user visit characteristics of the known credit status as training samples.
Wherein the user visit feature may comprise at least one of the following features:
1) the number of times or frequency that the user visits each category of POI; categories of POIs may be such as business circles, educational institutions, restaurants, hotels, tourist attractions, and so on.
2) The number of times or frequency that the stay time of the user in each category of POI exceeds the preset time length.
3) The number of times or frequency that the user visits the respective level of consumer POI. Consumer POIs may include such things as: a restaurant, hotel, educational institution, entertainment venue or mall, and the like. The consumption level of each consumption POI can be obtained by crawling the online information or manually marking.
4) The number of times or frequency that the stay time of the user at each level of the consumption type POI exceeds the preset time length.
5) The number of times or frequency that the user visits each tourist location.
6) And (4) the distribution condition of the user position movement track. When collecting the distribution situation of the movement track of the user position, the first collection unit 01 may obtain the movement track of the user through a positioning device of the user; and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
The first collecting unit 01 may adopt, but is not limited to, the following ways when determining that the user accesses the POI:
in the first mode, if the position of the user is determined to be within the range of a certain POI by the positioning device of the user, the user is determined to visit the POI.
And secondly, determining that the position of the user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if the access point AP of the user accessing the POI is obtained.
And thirdly, acquiring that the user searches a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and determining that the user accesses the POI.
The training unit 02 is responsible for training the machine learning model by using the training samples to obtain a credit investigation model.
The machine learning model adopted by the training unit 02 may include, but is not limited to: an LR (logistic regression) model, an SVM (Support Vector Machine) model, an ANN (Artificial Neural Network) or a GBDT (gradient boosting Decision Tree).
Fig. 3 is a structural diagram of a credit investigation apparatus according to an embodiment of the present invention, and as shown in fig. 3, the apparatus may include: a second collecting unit 11 and a credit evaluation unit 12, wherein the main functions of each constituent unit are as follows:
the second collecting unit 11 is responsible for collecting the user visit characteristics of the user to be evaluated. The second collection unit 11 collects the user visit features of the user to be evaluated in the same type and manner as the features collected by the first collection unit 01.
Wherein the user visit feature may comprise at least one of the following features:
1) the number of times or frequency that the user visits each category of POI; categories of POIs may be such as business circles, educational institutions, restaurants, hotels, tourist attractions, and so on.
2) The number of times or frequency that the stay time of the user in each category of POI exceeds the preset time length.
3) The number of times or frequency that the user visits the respective level of consumer POI. Consumer POIs may include such things as: a restaurant, hotel, educational institution, entertainment venue or mall, and the like. The consumption level of each consumption POI can be obtained by crawling the online information or manually marking.
4) The number of times or frequency that the stay time of the user at each level of the consumption type POI exceeds the preset time length.
5) The number of times or frequency that the user visits each tourist location.
6) And (4) the distribution condition of the user position movement track. When collecting the distribution situation of the movement track of the user position, the second collecting unit 11 may obtain the movement track of the user through a positioning device of the user; and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
The second collecting unit 11 may adopt, but is not limited to, the following ways when determining that the user visits the POI:
in the first mode, if the position of the user is determined to be within the range of a certain POI by the positioning device of the user, the user is determined to visit the POI.
And secondly, determining that the position of the user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if the access point AP of the user accessing the POI is obtained.
And thirdly, acquiring that the user searches a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and determining that the user accesses the POI.
The credit evaluation unit 12 is responsible for inputting the user visiting characteristics collected by the second collection unit 11 into a credit investigation model to obtain the credit status of the user to be evaluated. The obtained credit condition can be the credit score of the user to be evaluated, the credit rating of the user to be evaluated, and other credit condition embodying modes can be adopted.
The execution main body of the method provided in the embodiment of the present invention, that is, the apparatus may be an application located in the local terminal, or may also be a functional unit such as a plug-in or Software Development Kit (SDK) located in the application located in the local terminal, or may also be located at the server side, which is not particularly limited in this embodiment of the present invention.
The method and the device provided by the invention can be suitable for a credit evaluation system for natural people, and can be well applied to the field of finance. For example, a financial institution as a consumer credit provider may perform credit evaluation on a consumer by the method and apparatus provided by the present invention before the consumer is offered a loan, and determine whether or how much credit the consumer is offered a loan to the consumer based on the credit status of the consumer. The method and apparatus provided by the present invention are not limited to this application, and may also be applied to other scenes or fields, which are not exhaustive here.
As can be seen from the above description, the method and apparatus provided by the present invention can have the following advantages:
1) the invention adopts the user visit information as the characteristic to establish the credit investigation model, the characteristic can be reported and collected by the positioning device of the user, the labor cost is reduced, the characteristic can more objectively depict the credit level of the user, the counterfeiting is difficult, and the credit investigation accuracy is improved.
2) The user visit information is not a pure geographic position characteristic, but contains rich semantic characteristics to reflect the risk preference of the user. The diversity of user behaviors can be embodied through stay expressions of the user at different POIs, and the consumption preference and the economic capability of the user, which cannot be embodied by a single geographical position, can be further embodied by combining unstructured information such as POI description and structured information such as consumption level of consumption POIs. The credit preference of the user can be embodied through semantic features contained in the mobile features of the user, so that various behaviors such as whether the user loses business, moves home, changes work, frequently goes on business and the like are implicitly embodied.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (20)
1. A method for establishing a credit investigation model is characterized by comprising the following steps:
collecting user visit characteristics of known credit conditions as training samples;
and training a machine learning model by using the training samples to obtain a credit investigation model.
2. The method of claim 1, wherein the user visited feature comprises at least one of:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
3. The method of claim 2, wherein the user is determined to have visited a POI by determining that the user's location is within range of the POI by the user's location device; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
4. The method of claim 2, wherein the consumer POI comprises:
a restaurant, hotel, educational institution, entertainment venue, or mall.
5. The method according to claim 2, wherein the collecting of the distribution of the user position movement tracks comprises:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
6. The method of claim 1, wherein the machine learning model comprises:
logistic regression models, support vector machine models, artificial neural networks, or gradient decision trees.
7. A method for credit determination, the method comprising:
collecting user visiting characteristics of a user to be evaluated;
inputting the user visiting characteristics into a credit investigation model to obtain the credit condition of the user to be evaluated;
wherein the credit model is established using the method of any one of claims 1 to 6.
8. The method of claim 7, wherein the user visited feature comprises at least one of:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
9. The method of claim 8, wherein the user is determined to have visited a POI by determining that the user's location is within range of the POI by the user's location device; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
10. The method according to claim 8, wherein the collecting of the distribution of the user position movement tracks comprises:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
11. An apparatus for establishing a credit investigation model, the apparatus comprising:
the first collecting unit is used for collecting the user visit characteristics of the known credit conditions as training samples;
and the training unit is used for training the machine learning model by using the training samples to obtain a credit investigation model.
12. The apparatus of claim 11, wherein the user visited feature comprises at least one of:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
13. The apparatus according to claim 12, wherein the first collecting unit, when determining that the user accesses the POI, specifically performs:
determining that the user accesses a certain POI by determining that the position of the user is within the range of the POI through a positioning device of the user; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
14. The apparatus of claim 12, wherein the consumer POI comprises:
a restaurant, hotel, educational institution, entertainment venue, or mall.
15. The apparatus according to claim 12, wherein the first collecting unit specifically performs, when collecting the distribution status of the user position movement trajectory:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
16. The apparatus of claim 11, wherein the machine learning model employed by the training unit comprises:
logistic regression models, support vector machine models, artificial neural networks, or gradient decision trees.
17. A credit determination apparatus, characterized in that the apparatus comprises:
the second collecting unit is used for collecting the user visiting characteristics of the user to be evaluated;
the credit evaluation unit is used for inputting the user visiting characteristics collected by the second collection unit into a credit investigation model to obtain the credit condition of the user to be evaluated;
wherein the credit model is established using an apparatus according to any of claims 11 to 16.
18. The apparatus of claim 17, wherein the user visited feature comprises at least one of:
the number of times or frequency that the user visits each category of POI;
the number of times or frequency that the stay time of the user in each category of POI exceeds the preset time;
the number of times or frequency that the user accesses the consumption type POI at each level;
the number of times or frequency that the stay time of the user at each level of consumption type POI exceeds the preset time;
the number of times or frequency that the user visits each tourist location;
and (4) the distribution condition of the user position movement track.
19. The apparatus according to claim 18, wherein the second collecting unit, when determining that the user accesses the POI, specifically performs:
determining that the user accesses a certain POI by determining that the position of the user is within the range of the POI through a positioning device of the user; or,
determining that the position of a user is within the range of a certain POI through a positioning device of the user, and determining that the user accesses the POI if an access point AP of the user accessing the POI is obtained; or,
and acquiring that the user searches for a certain POI on the electronic map, and determining that the position of the user is within the range of the POI through the positioning device of the user within a set time length, and then determining that the user accesses the POI.
20. The apparatus according to claim 18, wherein the second collecting unit specifically performs, when collecting the distribution status of the user position movement trajectory:
acquiring a moving track of a user through positioning equipment of the user;
and counting the moving distance of the user in a set time period, or counting the distribution information of the moving distance of the user in different gears in the set time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610251602.3A CN105894089A (en) | 2016-04-21 | 2016-04-21 | Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610251602.3A CN105894089A (en) | 2016-04-21 | 2016-04-21 | Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105894089A true CN105894089A (en) | 2016-08-24 |
Family
ID=56704228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610251602.3A Pending CN105894089A (en) | 2016-04-21 | 2016-04-21 | Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105894089A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779116A (en) * | 2016-11-29 | 2017-05-31 | 清华大学 | A kind of net based on spatiotemporal data structure about car client reference method |
| CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
| CN107767262A (en) * | 2017-10-24 | 2018-03-06 | 上海点融信息科技有限责任公司 | Information processing method, device and computer-readable recording medium |
| CN107766418A (en) * | 2017-09-08 | 2018-03-06 | 广州汪汪信息技术有限公司 | A kind of credit estimation method based on Fusion Model, electronic equipment and storage medium |
| CN107818506A (en) * | 2017-09-30 | 2018-03-20 | 上海壹账通金融科技有限公司 | Electronic installation, credit risk control method and storage medium |
| CN108133619A (en) * | 2018-02-06 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | Method, apparatus, storage medium and the terminal device of Parking prediction |
| WO2018120427A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Risk assessment method, apparatus, and device based on location service, and storage medium |
| WO2018120425A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Personal property status assessing method, apparatus, device, and storage medium |
| WO2018145586A1 (en) * | 2017-02-08 | 2018-08-16 | 腾讯科技（深圳）有限公司 | Credit scoring method and server |
| CN108460674A (en) * | 2018-02-01 | 2018-08-28 | 平安科技（深圳）有限公司 | Information processing method, device, computer equipment and storage medium |
| WO2018176179A1 (en) * | 2017-03-27 | 2018-10-04 | 杭州呯嘭智能技术有限公司 | Rapid settlement method for cross-border payment based on big credit data |
| CN108632228A (en) * | 2017-03-24 | 2018-10-09 | 优估（上海）信息科技有限公司 | A kind of decision engine dispatching method and system |
| CN108876076A (en) * | 2017-05-09 | 2018-11-23 | 中国移动通信集团广东有限公司 | The personal credit methods of marking and device of data based on instruction |
| CN111400663A (en) * | 2020-03-17 | 2020-07-10 | 深圳前海微众银行股份有限公司 | Risk identification method, device, equipment and computer readable storage medium |
| CN112802231A (en) * | 2021-03-19 | 2021-05-14 | 四川万网鑫成信息科技有限公司 | Vehicle risk assessment method, device, equipment and medium based on GPS data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593349A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement position analysis method in sense network environment |
| CN103617239A (en) * | 2013-11-26 | 2014-03-05 | 百度在线网络技术（北京）有限公司 | Method and device for identifying named entity and method and device for establishing classification model |
| CN104572937A (en) * | 2014-12-30 | 2015-04-29 | 杭州云象网络技术有限公司 | Offline friend recommendation method based on indoor living circle |
| CN104866969A (en) * | 2015-05-25 | 2015-08-26 | 百度在线网络技术（北京）有限公司 | Personal credit data processing method and device |
-
2016
- 2016-04-21 CN CN201610251602.3A patent/CN105894089A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593349A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement position analysis method in sense network environment |
| CN103617239A (en) * | 2013-11-26 | 2014-03-05 | 百度在线网络技术（北京）有限公司 | Method and device for identifying named entity and method and device for establishing classification model |
| CN104572937A (en) * | 2014-12-30 | 2015-04-29 | 杭州云象网络技术有限公司 | Offline friend recommendation method based on indoor living circle |
| CN104866969A (en) * | 2015-05-25 | 2015-08-26 | 百度在线网络技术（北京）有限公司 | Personal credit data processing method and device |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779116A (en) * | 2016-11-29 | 2017-05-31 | 清华大学 | A kind of net based on spatiotemporal data structure about car client reference method |
| CN106779116B (en) * | 2016-11-29 | 2020-11-10 | 清华大学 | Online taxi appointment customer credit investigation method based on time-space data mining |
| WO2018120425A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Personal property status assessing method, apparatus, device, and storage medium |
| WO2018120427A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Risk assessment method, apparatus, and device based on location service, and storage medium |
| US11816727B2 (en) | 2017-02-08 | 2023-11-14 | Tencent Technology (Shenzhen) Company Limited | Credit scoring method and server |
| US11170436B2 (en) | 2017-02-08 | 2021-11-09 | Tencent Technology (Shenzhen) Company Limited | Credit scoring method and server |
| WO2018145586A1 (en) * | 2017-02-08 | 2018-08-16 | 腾讯科技（深圳）有限公司 | Credit scoring method and server |
| CN108632228B (en) * | 2017-03-24 | 2021-02-09 | 优估（上海）信息科技有限公司 | Decision engine scheduling method and system |
| CN108632228A (en) * | 2017-03-24 | 2018-10-09 | 优估（上海）信息科技有限公司 | A kind of decision engine dispatching method and system |
| WO2018176179A1 (en) * | 2017-03-27 | 2018-10-04 | 杭州呯嘭智能技术有限公司 | Rapid settlement method for cross-border payment based on big credit data |
| CN108876076A (en) * | 2017-05-09 | 2018-11-23 | 中国移动通信集团广东有限公司 | The personal credit methods of marking and device of data based on instruction |
| CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
| CN107766418A (en) * | 2017-09-08 | 2018-03-06 | 广州汪汪信息技术有限公司 | A kind of credit estimation method based on Fusion Model, electronic equipment and storage medium |
| CN107818506A (en) * | 2017-09-30 | 2018-03-20 | 上海壹账通金融科技有限公司 | Electronic installation, credit risk control method and storage medium |
| WO2019062009A1 (en) * | 2017-09-30 | 2019-04-04 | 深圳壹账通智能科技有限公司 | Electronic device, credit risk control method, and storage medium |
| CN107767262B (en) * | 2017-10-24 | 2020-07-28 | 上海点融信息科技有限责任公司 | Information processing method, apparatus and computer readable storage medium |
| CN107767262A (en) * | 2017-10-24 | 2018-03-06 | 上海点融信息科技有限责任公司 | Information processing method, device and computer-readable recording medium |
| CN108460674A (en) * | 2018-02-01 | 2018-08-28 | 平安科技（深圳）有限公司 | Information processing method, device, computer equipment and storage medium |
| CN108133619A (en) * | 2018-02-06 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | Method, apparatus, storage medium and the terminal device of Parking prediction |
| CN108133619B (en) * | 2018-02-06 | 2020-05-29 | 百度在线网络技术（北京）有限公司 | Parking lot parking prediction method and device, storage medium and terminal equipment |
| CN111400663A (en) * | 2020-03-17 | 2020-07-10 | 深圳前海微众银行股份有限公司 | Risk identification method, device, equipment and computer readable storage medium |
| CN111400663B (en) * | 2020-03-17 | 2022-06-14 | 深圳前海微众银行股份有限公司 | Model training method, device, equipment and computer readable storage medium |
| CN112802231A (en) * | 2021-03-19 | 2021-05-14 | 四川万网鑫成信息科技有限公司 | Vehicle risk assessment method, device, equipment and medium based on GPS data |
| CN112802231B (en) * | 2021-03-19 | 2021-07-06 | 四川万网鑫成信息科技有限公司 | Vehicle risk assessment method, device, equipment and medium based on GPS data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894089A (en) | Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof | |
| Wang et al. | Understanding travellers’ preferences for different types of trip destination based on mobile internet usage data | |
| Krumm et al. | Placer: semantic place labels from diary data | |
| CN102594905B (en) | Method for recommending social network position interest points based on scene | |
| Zheng et al. | Mining interesting locations and travel sequences from GPS trajectories | |
| WO2018076695A1 (en) | Smart recommendation system and smart recommendation method | |
| KR102189065B1 (en) | Interest profile of a user of a mobile application | |
| CN109614556B (en) | Access path prediction and information push method and device | |
| Furletti et al. | Identifying users profiles from mobile calls habits | |
| CN106651603A (en) | Risk evaluation method and apparatus based on position service | |
| CN105718576B (en) | Personalized location recommender system relevant to geographical feature | |
| CN103914536A (en) | Interest point recommending method and system for electronic maps | |
| CN111737605A (en) | Travel purpose identification method and device based on mobile phone signaling data | |
| CN102194006B (en) | Search system and method capable of gathering personalized features of group | |
| CN103577509A (en) | Route recommendation system and method thereof | |
| WO2017157184A1 (en) | Method and device for determining attribute information of geographical location | |
| CN107666649A (en) | Personal property state evaluating method and device | |
| Steenbruggen | Tourism geography: Emerging trends and initiatives to support tourism in Morocco | |
| Liang et al. | Assessing the validity of SafeGraph data for visitor monitoring in Yellowstone National Park | |
| Yu et al. | Analyzing the structure of tourism destination network based on digital footprints: Taking Guilin, China as a case | |
| Honarparvar et al. | Improvement of a location-aware recommender system using volunteered geographic information | |
| CN115408618A (en) | Interest point recommendation method based on social relationship fusion position dynamic popularity and geographic features | |
| Birkin et al. | An examination of personal mobility patterns in space and time using twitter | |
| Shende et al. | Analyzing changes in travel patterns due to Covid-19 using Twitter data in India | |
| Yang et al. | Optimization of tourism information analysis system based on big data algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160824 |
|
| RJ01 | Rejection of invention patent application after publication |