CN116245542A - Method, apparatus, device and computer readable medium for processing data - Google Patents
Method, apparatus, device and computer readable medium for processing data Download PDFInfo
- Publication number
- CN116245542A CN116245542A CN202310250088.1A CN202310250088A CN116245542A CN 116245542 A CN116245542 A CN 116245542A CN 202310250088 A CN202310250088 A CN 202310250088A CN 116245542 A CN116245542 A CN 116245542A
- Authority
- CN
- China
- Prior art keywords
- category
- data
- historical data
- same
- same kind
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012545 processing Methods 0.000 title claims abstract description 45
- 238000004088 simulation Methods 0.000 claims abstract description 120
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000013210 evaluation model Methods 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 10
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marine Sciences & Fisheries (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Finance (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, equipment and a computer readable medium for processing data, relating to the technical field of artificial intelligence. One embodiment of the method comprises the following steps: classifying merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories of merchant historical data, financial historical data, management historical data and guarantee historical data; generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category; the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data; and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data. The embodiment can increase the amount of credit evaluation data and trust the credit to the merchant through the training model.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a method, apparatus, device, and computer readable medium for processing data.
Background
The agricultural product wholesale market is a main carrier for agricultural product circulation, and plays an important role in linking production and marketing, and is used for bearing more than 70% of the total quantity of agricultural product circulation. As key links and main channels of fresh agricultural product circulation, the characteristics of huge total quantity, numerous associated subjects and dense fund transaction are reflected. The wholesale market of agricultural products is located in the industrial chain center and is a bridge, logistics, information flow and fund flow gathering place for connecting hundreds of millions of producers and consumers.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art: credit rating data of small micro enterprises such as agricultural product suppliers and individual industrial merchants are insufficient, so that credit cannot be granted to the merchants.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, apparatus, device, and computer readable medium for processing data, which can increase the amount of credit evaluation data and trust merchants through training models.
To achieve the above object, according to one aspect of an embodiment of the present invention, there is provided a method of processing data, including:
classifying merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories of merchant historical data, financial historical data, management historical data and guarantee historical data;
Generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category;
the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data;
and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data.
The classifying the merchant historical data into category historical data includes:
converting an image in merchant input information into an image text, and taking the image text and the input text in the merchant input information as merchant historical data;
and analyzing semantics in the merchant historical data, and dividing the merchant historical data into category historical data.
The converting the image in the merchant input information into the image text comprises the following steps:
screening out the image from the merchant input information;
and converting the image in the merchant input information into an original image text, and deleting invalid text in the original image text to obtain the image text.
The noise adding weight based on the category history data of the same category generates random noise of the same category, and the noise adding weight comprises the following steps:
the noise adding weight is obtained on the basis of the same category of historical data;
and generating random noise of the same category based on the noise adding weight of the category history data of the same category.
The noise adding weight obtained on the basis of the same category of historical data comprises:
acquiring two types of historical data from the same type of historical data;
training to obtain a data characteristic model by adopting one type of historical data in the two types of historical data and the difference value of the two types of historical data;
and inputting category history data in the category history data of the same category into the data characteristic model to obtain the noise adding weight.
The noise adding weight obtained on the basis of the same category of historical data comprises:
and taking the standard deviation of the historical data of the same category as the weighted noise.
The noise adding weight based on the category history data of the same category generates random noise of the same category, and the noise adding weight comprises the following steps:
Randomly selecting an adjustment parameter in a random noise range of the category history data of the same category;
and generating the random noise of the same category based on the noise adding weight of the category history data of the same category and the adjustment parameter.
The same kind of category history data is combined with the same kind of random noise to construct the same kind of simulation history data, and the method comprises the following steps:
the same kind of category history data is combined with the same kind of random noise to establish new history data of the same kind;
and if the same type of history data is consistent with the same type of new history data in characteristics, taking the same type of new history data as the same type of simulation history data.
The same kind of category history data is combined with the same kind of random noise to establish the same kind of new history data, which comprises the following steps:
and combining one category of historical data of the same category with the random noise of the same category to establish new historical data of the same category.
And if the same type of history data is consistent with the same type of new history data in characteristics, taking the same type of new history data as the same type of simulation history data, wherein the method comprises the following steps:
The new historical data of the same kind belong to the statistical range of the historical data of the same kind, and the historical data of the same kind is determined to be consistent with the new historical data of the same kind in characteristic;
and taking the newly-built historical data of the same kind as the simulation historical data of the same kind.
After the simulation history data of the same kind are constructed, the method further comprises the following steps:
adding the simulation historical data of the same kind to the simulation historical data of the same kind;
and generating random noise of the same kind based on the noise adding weight of the category history data of the same kind so as to reconstruct simulation history data of the same kind.
And generating random noise of the same kind based on the noise adding weight of the category history data of the same kind to reconstruct simulation history data of the same kind, wherein the method comprises the following steps:
generating random noise of the same kind based on the noise adding weight of the category history data of the same kind so as to reconstruct simulation history data of the same kind;
and if the simulation historical data of the same kind meet the preset construction conditions, stopping constructing the simulation historical data.
The training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data comprises the following steps:
labeling the plurality of category simulation historical data and the plurality of category historical data;
determining credit parameters of the marked multiple kinds of simulation historical data and multiple kinds of class historical data through preset rating conditions;
to determine the credit parameters of the data, training and building a credit evaluation model.
According to a second aspect of an embodiment of the present invention, there is provided an apparatus for processing data, including:
the classification module is used for classifying the merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories including merchant historical data, financial historical data, management historical data and guarantee historical data;
the generation module is used for generating random noise of the same category based on the noise adding weight of the category history data of the same category, and the noise adding weight is obtained on the basis of the category history data of the same category;
the construction module is used for constructing the same kind of simulation historical data by combining the same kind of random noise;
The establishment module is used for training and establishing a credit evaluation model by adopting the plurality of kinds of simulation historical data and the plurality of kinds of category historical data.
According to a third aspect of an embodiment of the present invention, there is provided an electronic device that processes data, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the methods as described above.
According to a fourth aspect of embodiments of the present invention, there is provided a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described above.
According to a fifth aspect of embodiments of the present invention, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as provided by embodiments of the present invention.
One embodiment of the above invention has the following advantages or benefits: classifying merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories of merchant historical data, financial historical data, management historical data and guarantee historical data; generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category; the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data; and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data. Aiming at merchant historical data, simulation historical data is constructed, the number of credit evaluation data is increased, and credit is given to merchants through a training model.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic flow diagram of a method of processing data according to an embodiment of the present invention;
FIG. 2 is a flow chart of classifying merchant historical data into category historical data according to an embodiment of the invention;
FIG. 3 is a flow diagram of converting an image in merchant entry information into image text in accordance with an embodiment of the invention;
FIG. 4 is a flow chart of generating random noise of the same kind according to an embodiment of the present invention;
FIG. 5 is a flow chart of obtaining a noise added weight according to an embodiment of the invention;
FIG. 6 is a flow chart of generating random noise of the same kind according to an embodiment of the invention;
FIG. 7 is a flow chart of constructing simulation history data of the same kind according to an embodiment of the present invention;
FIG. 8 is a flow chart of a method for identifying one category of history data consistent with the characteristics of a new category of history data according to an embodiment of the invention;
FIG. 9 is a flow chart of reconstructing the same kind of simulation history data according to an embodiment of the present invention;
FIG. 10 is a flow diagram of stopping building simulation history data in accordance with an embodiment of the invention;
FIG. 11 is a flow chart of training and building a credit rating model according to an embodiment of the invention;
FIG. 12 is a main structural diagram of an apparatus for processing data according to an embodiment of the present invention;
FIG. 13 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 14 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness. The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations.
The agricultural product wholesale market is a bridge connecting hundreds of millions of producers and consumers, and a distribution site for logistics, information flow and fund flow. From the aspect of financial services, the agricultural product wholesale market has the advantage of prizing all participants of an industrial chain in the financial field, and has comprehensive requirements on services such as payment, settlement, credit and the like.
Credit rating data is typically based on the credit rating data to assist in the development of the business. However, the credit rating data of small micro-enterprises or individual industrial merchants such as the main body of the agricultural product wholesale market, the agricultural product suppliers, and the like are insufficient. The credit evaluation data is insufficient, and the repayment capability of the merchant cannot be known, so that credit cannot be granted to the merchant.
In summary, credit evaluation data of small micro enterprises such as agricultural product suppliers or individual industrial merchants is insufficient, so that credit cannot be granted to the merchants.
In order to solve the problem that credit evaluation data are insufficient and cannot be trusted to the merchant, the following technical scheme in the embodiment of the invention can be adopted.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for processing data according to an embodiment of the present invention, and the simulation history data is constructed for the merchant history data, so as to increase the amount of credit evaluation data. As shown in fig. 1, the method specifically comprises the following steps:
s101, classifying merchant historical data into category historical data, wherein the category historical data comprises the following categories of merchant historical data, financial historical data, management historical data and guarantee historical data.
In an embodiment of the present invention, the processing object is merchant history data. Merchant historical data is data of small micro enterprises or individual industrial merchants in the agricultural product business transaction process. The trade process of the small micro enterprises and the individual industrial and commercial enterprises has the characteristics of more trade times and small trade amount. For merchant credit, the existing credit way is difficult to be adopted, and the small micro enterprises and the individual industrial merchants are credit.
In the embodiment of the invention, the merchant historical data is divided into a plurality of dimensions starting from the merchant historical data, so that the merchant is comprehensively evaluated.
Referring to fig. 2, fig. 2 is a flowchart illustrating a process of classifying merchant history data into category history data according to an embodiment of the invention. The method specifically comprises the following steps:
s201, converting the image in the merchant input information into an image text, and taking the image text and the input text in the merchant input information as the merchant historical data.
In the embodiment of the invention, the merchant mostly adopts photographing or scanning and other modes to input information. The merchant input information comprises an image and input text, and the image comprises merchant data. In order to improve the operation efficiency, the images in the merchant input information can be converted into image texts, and the image texts and the input texts in the merchant input information are used as merchant historical data.
Referring to fig. 3, fig. 3 is a flow chart illustrating a process of converting an image in merchant entry information into image text according to an embodiment of the present invention. The method specifically comprises the following steps:
s301, screening out images in merchant input information.
The merchant entry information includes images and text. In order to improve the efficiency of processing the merchant input information, images are screened out from the merchant input information in a file format mode. As one example, the file format includes one or more of bmp, jpg, png, tif, gif, pcx, tga, exif, fpx, svg, psd, cdr, pcd, dxf, ufo, eps, ai, raw, WMF, webp, avif, and apng.
S302, converting the image in the merchant input information into an original image text, and deleting invalid text in the original image text to obtain the image text.
By adopting an image processing mode, the image in the merchant input information can be converted into an original image text. The original image text is the text corresponding to the image in the merchant entry information. In order to increase the speed of processing data and avoid the influence caused by invalid texts, the invalid texts in the original image texts can be deleted to obtain the image texts. As one example, a keyword is preset, and text that does not include the preset keyword is taken as invalid text. Such as: presetting keywords: and (5) identifying the merchant.
In the embodiment of fig. 3, the validity of the image text is improved by eliminating invalid text.
S202, analyzing semantics in the merchant historical data and dividing the merchant historical data into category historical data.
In an embodiment of the present invention, in order to accurately identify the merchant, the merchant history data may be divided into category history data according to semantics in the merchant history data. As one example, natural language processing (NLP, natural Language Processing) is employed to analyze semantics in merchant historical data.
Category history data is a collection of history data belonging to the same category. Category history data includes a plurality of categories, merchant history data, financial history data, management history data, and vouching history data.
Merchant historical data is historical data characterizing a merchant feature. As one example, merchant history data includes: merchant identification, merchant address, and merchant business hours, etc.
Financial history data is historical data characterizing the financial state of a merchant. As one example, the financial history data includes: invoice information, tax payment records and financial statements.
The management history data is history data representing daily business conditions of the merchant. As one example, the management history data includes order information, sales information, and social security payment records.
The vouching history data is history data characterizing the performance of the merchant. As one example, the vouching history data includes vouching amount, vouching date, and vouching person.
In an embodiment of the present invention, the category history data includes a plurality of categories, merchant history data, financial history data, management history data, and vouch-for history data. It is understood that category history data includes at least two categories. For the same kind of history data, simulation history data of that kind is constructed.
In addition, the category history data belongs to the structured data, so that the simulation history data can be constructed by the structured data, and the speed of constructing the simulation history data is improved.
S102, generating random noise of the same kind based on the noise adding weight of the historical data of the same kind, wherein the noise adding weight is obtained on the basis of the historical data of the same kind.
In an embodiment of the invention, the simulation history data is constructed on the basis of the same category of history data. It will be appreciated that for the same category, two types of data are involved, category history data and simulation history data.
As one example, category technology data includes merchant historical data and financial historical data. Specifically, the simulation history data of the merchant history data can be constructed by adopting the merchant history data; the simulation history data of the financial history data may be constructed using the financial history data.
For each class, there is a corresponding noise-adding weight. Based on the noise adding weight, random noise of this kind is generated.
Referring to fig. 4, fig. 4 is a schematic flow chart of generating random noise of the same kind according to an embodiment of the present invention. The method specifically comprises the following steps:
S401, noise adding weight obtained on the basis of the same category historical data.
For each class, a noise-adding weight may be obtained. The noise adding weight is obtained on the basis of the same category of historical data. As one example, the standard deviation of the same kind of category history data is taken as the weighted noise. The standard deviation is used as the weighted noise, so that the difference between the historical data of the same category can be identified.
Referring to fig. 5, fig. 5 is a schematic flow chart of obtaining a noise adding weight according to an embodiment of the present invention. The method specifically comprises the following steps:
s501, acquiring two types of historical data from the same type of historical data.
In one embodiment of the invention, the same kind of category history data may be used to obtain the noise adding weight by training a model.
Specifically, two category history data are acquired from the same category history data. As one example, in the same category history data, two category history data are randomly acquired. As another example, to improve the authenticity of the data, one category history data smaller than the average value and one category history data larger than the average value may be selected.
S502, training to obtain a data characteristic model by adopting one type of historical data in the two types of historical data and the difference value of the two types of historical data.
And training to obtain a data characteristic model by using the difference value of the two types of historical data and one type of historical data in the two types of historical data. As an example, one of the two types of history data is used as an input parameter of the data feature model, and the data feature model is obtained by training with the difference value of the two types of history data.
S503, inputting category history data in the category history data of the same category into a data characteristic model to obtain a noise adding weight.
After the data feature model is trained, one category of historical data in the same category of historical data can be input into the data feature model to obtain the noise adding weight.
In one embodiment of the present invention, category history data in a preset number of category history data of the same category may be respectively input to the data feature model to obtain a preset number of noise adding weights. And then taking the average value of the preset data plus noise weights as the final plus noise weight.
In the embodiment of fig. 5, the data feature model is used to obtain the noise adding weight to improve the realism of the noise adding weight.
S402, generating random noise of the same kind based on the noise adding weight of the historical data of the same kind.
According to the noise adding weight of the historical data of the same category, random noise of the same category can be generated.
Referring to fig. 6, fig. 6 is a schematic flow chart of generating random noise of the same kind according to an embodiment of the present invention. The method specifically comprises the following steps:
s601, randomly selecting an adjustment parameter in a random noise range of the same type of historical data.
The adjustment parameters may be randomly selected in a random noise range of the same kind of category history data in consideration of randomness of noise. The random noise range is different for different categories of historical data. The random noise range may be preset based on the category. Then, the adjustment parameters are randomly selected within the random noise range.
S602, generating random noise of the same kind based on the noise adding weight and the adjustment parameter of the historical data of the same kind.
After the adjustment parameters are determined, the random noise of the same kind can be generated based on the noise adding weight and the adjustment parameters of the historical data of the same kind. As an example, the product of the noise adding weight and the adjustment parameter may be regarded as random noise for the same kind.
In the embodiment of fig. 6, the same kind of random noise is generated in consideration of randomness on the basis of the noise adding weight.
S103, combining the same kind of historical data with the same kind of random noise to construct the same kind of simulation historical data.
The same kind of simulation history data is constructed based on the same kind of category history data and the same kind of random noise. As one example, the sum or difference of the same kind of category history data and the same kind of random noise is taken as the same kind of simulation history data.
Referring to fig. 7, fig. 7 is a schematic flow chart of constructing simulation history data of the same kind according to an embodiment of the present invention. The method specifically comprises the following steps:
s701, combining the same kind of historical data with the same kind of random noise to establish new historical data of the same kind.
The same kind of new historical data can be established by combining the same kind of historical data with the same kind of random noise. As one example, an average of a plurality of same-kind category technical data is combined with same-kind random noise to create same-kind newly created history data.
In one embodiment of the invention, a piece of historical data of the same category can be combined with random noise of the same category to establish new historical data of the same category in consideration of randomness of the data.
As an example, a sum or a difference of a piece of randomly acquired category history data of the same category and random noise of the same category is taken as newly created history data of the same category.
S702, setting the new history data of the same type as the simulation history data of the same type if the characteristics of the new history data of the same type are consistent with those of the new history data of the same type.
In order to ensure that the characteristics of the simulation historical data are the same as those of the category historical data, the same category historical data are required to be confirmed to be consistent with the characteristics of the same category newly-built historical data, and then the same category newly-built historical data are required to be used as the same category of simulation historical data.
Referring to fig. 8, fig. 8 is a schematic flow chart for confirming that one category of history data is consistent with the characteristics of the newly created history data of the same category according to an embodiment of the present invention. The method specifically comprises the following steps:
s801, newly-built historical data of the same type belong to the statistical range of the historical data of the same type, and the historical data of the same type is determined to be consistent with the newly-built historical data of the same type in characteristics.
In the embodiment of the invention, whether the newly built historical data characteristics belong to the statistical range of the category historical data is taken as a judging basis for determining whether the category historical data is consistent with the newly built historical data characteristics. The statistical range of the category history data may be preset for the category. I.e. the statistical range of different categories of history data is different. As one example, the statistical range of the preset category history data includes between an upper quartile and a lower quartile of the category history data.
And determining that the new historical data of the same type belongs to the statistical range of the historical data of the same type, and determining that the historical data of the same type is consistent with the new historical data of the same type in characteristic. Correspondingly, the newly built historical data of the same kind do not belong to the statistical range of the historical data of the same kind, and the historical data of the same kind is determined to be different from the newly built historical data of the same kind in characteristic.
S802, taking newly built historical data of the same kind as simulation historical data of the same kind.
After the same type of history data is determined to be consistent with the characteristics of the same type of new history data, the same type of new history data can be used as the same type of simulation history data.
In the embodiment of fig. 8, the statistical range of category history data is used to verify the newly created history data to ensure the practicality of the newly created data.
To this end, a simulation history is constructed. In the process of processing data, the number of one simulation history can not meet the actual use requirement. Thus, it is necessary to construct again simulation history data using the embodiment of fig. 9.
Referring to fig. 9, fig. 9 is a schematic flow chart of reconstructing the same kind of simulation history data according to an embodiment of the present invention. The method specifically comprises the following steps:
S901, adding the same kind of simulation history data to the same kind of category history data.
The same kind of simulation history data may be added to the same kind of category history data. It will be appreciated that the current category history data includes not only real category history data but also simulation history data.
S902, generating random noise of the same kind based on the noise adding weight of the historical data of the same kind, so as to reconstruct the simulation historical data of the same kind.
The simulation history data needs to be constructed based on the noise adding weight, and then the same kind of random noise is generated according to S102 and S103, that is, based on the noise adding weight of the same kind of category history data, so as to construct the same kind of simulation history data again.
Referring to fig. 10, fig. 10 is a schematic flow chart of stopping building simulation history data according to an embodiment of the present invention. The method specifically comprises the following steps:
s1001, generating random noise of the same kind based on the noise adding weight of the historical data of the same kind, so as to reconstruct the simulation historical data of the same kind.
And generating random noise of the same kind based on the noise adding weight of the historical data of the same kind so as to reconstruct the simulation historical data of the same kind. And executing construction for multiple times to obtain multiple simulation historical data of the same kind.
S1002, if the simulation historical data of the same kind meet preset construction conditions, stopping constructing the simulation historical data.
If the simulation historical data of the same kind meets the preset construction conditions, stopping constructing the simulation historical data; similarly, if the simulation history data of the same kind does not satisfy the preset construction condition, the construction of the simulation history data is stopped.
As one example, the preset build condition includes a threshold of the number of simulation history data of the same kind. That is, the number of the simulation history data of the same kind is greater than or equal to the number of the simulation history data of the same kind, and the construction of the simulation history data is stopped; and if the number of the simulation historical data of the same kind is smaller than the number threshold of the simulation historical data of the same kind, continuing to construct the simulation historical data.
In the embodiment of fig. 9, the simulation history data is constructed a plurality of times to satisfy the construction condition.
S104, training and establishing a credit evaluation model by adopting the plurality of kinds of simulation historical data and the plurality of kinds of category historical data.
A plurality of kinds of simulation history data are constructed using S102 and S103. The simulation historical data can make up for the characteristic of smaller category historical data quantity. And training and establishing a credit evaluation model by adopting the multiple kinds of simulation historical data and the multiple kinds of class historical data, and further evaluating the credit limit of the merchant by using the credit evaluation model.
Referring to fig. 11, fig. 11 is a schematic flow chart of training and establishing a credit rating model according to an embodiment of the present invention. The method specifically comprises the following steps:
s1101, labeling a plurality of kinds of simulation historical data and a plurality of kinds of historical data.
Data annotation is the process of processing raw voice, picture, text, video, etc. data to convert it into machine-identifiable information.
In the embodiment of the invention, a preset label condition can be adopted to label a plurality of kinds of simulation historical data and a plurality of kinds of category historical data. As an example, no default record exists in the data, and merchants increase 1 score according to preset label conditions; tax records in the data are good, and merchants increase 2 points.
S1102, determining credit parameters of the marked multiple kinds of simulation historical data and multiple kinds of class historical data through preset rating conditions.
The credit parameters of the rating conditions can be preset for the marked multiple kinds of simulation historical data and multiple kinds of class historical data. As one example, the preset primary rating condition includes: the total score of the commercial tenant is more than 90 minutes, and the information parameter is determined to be high; the preset secondary rating condition comprises the following steps: the total score of the commercial tenant is less than or equal to 90 minutes and more than or equal to 60 minutes, and the information parameter is determined as the middle score; the preset three-level rating condition comprises the following steps: the total score of the merchant is less than 60 minutes, and the information parameter is determined to be low.
S1103, training and establishing a credit evaluation model by determining the credit parameters of the data.
And training and establishing a credit evaluation model by using the plurality of types of simulation historical data, the plurality of types of category historical data and credit parameters of the data.
As one example, the credit rating model is trained with the credit parameters of the data using the plurality of category simulation history data and the plurality of category history data as input parameters of the credit rating model. Finally, a credit evaluation model which completes training is obtained.
The credit evaluation model may employ a recurrent neural network (Recurrent Neural Network, RNN). The credit evaluation data are often time-series correlated, and the RNN is a preferred choice for time series analysis, in which the output of the network at a certain time is correlated with the output at a certain time or several times before, in addition to the input at the current time.
In the embodiment of FIG. 11, the credit rating model is trained and built using simulation history data and category history data.
In the above embodiment, the merchant history data is divided into category history data including a plurality of categories of merchant history data, financial history data, management history data and vouch-for history data; generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category; the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data; and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data. Aiming at merchant historical data, simulation historical data is constructed, the number of credit evaluation data is increased, and credit is given to merchants through a training model.
Referring to fig. 12, fig. 12 is a schematic main structure diagram of an apparatus for processing data according to an embodiment of the present invention, where the apparatus for processing data may implement a method for processing data, and as shown in fig. 12, the apparatus for processing data specifically includes:
a dividing module 1201, configured to divide merchant historical data into category historical data, where the category historical data includes the following categories, merchant historical data, financial historical data, management historical data and guarantee historical data;
a generating module 1202, configured to generate random noise of the same category based on a noise adding weight of the category history data of the same category, where the noise adding weight is obtained based on the category history data of the same category;
the construction module 1203 is configured to combine the same kind of random noise with the same kind of historical data to construct the same kind of simulation historical data;
the establishing module 1204 is configured to train and establish a credit evaluation model using the plurality of kinds of simulation history data and the plurality of kinds of category history data.
In one embodiment of the present invention, the dividing module 1201 is specifically configured to convert an image in the merchant input information into an image text, and take the image text and the input text in the merchant input information as the merchant history data;
And analyzing semantics in the merchant historical data, and dividing the merchant historical data into category historical data.
In one embodiment of the present invention, the dividing module 1201 is specifically configured to screen the image from the merchant input information;
and converting the image in the merchant input information into an original image text, and deleting invalid text in the original image text to obtain the image text.
In one embodiment of the present invention, the generating module 1202 is specifically configured to obtain the noise adding weight based on the same category of historical data;
and generating random noise of the same category based on the noise adding weight of the category history data of the same category.
In one embodiment of the present invention, the generating module 1202 is specifically configured to obtain two types of historical data from the same type of historical data;
training to obtain a data characteristic model by adopting one type of historical data in the two types of historical data and the difference value of the two types of historical data;
and inputting category history data in the category history data of the same category into the data characteristic model to obtain the noise adding weight.
In one embodiment of the present invention, the generating module 1202 is specifically configured to use the standard deviation of the historical data of the same category as the weighted noise.
In one embodiment of the present invention, the generating module 1202 is specifically configured to randomly select an adjustment parameter in a random noise range of the category history data of the same category;
and generating the random noise of the same category based on the noise adding weight of the category history data of the same category and the adjustment parameter.
In one embodiment of the present invention, the construction module 1203 is specifically configured to combine the same type of random noise with the same type of history data to build new history data of the same type;
and if the same type of history data is consistent with the same type of new history data in characteristics, taking the same type of new history data as the same type of simulation history data.
In one embodiment of the present invention, the construction module 1203 is specifically configured to combine a piece of category history data of the same category with the random noise of the same category to build new history data of the same category.
In one embodiment of the present invention, the construction module 1203 is specifically configured to determine that the same type of history data is consistent with the same type of newly created history data if the same type of newly created history data belongs to the statistical range of the same type of history data;
And taking the newly-built historical data of the same kind as the simulation historical data of the same kind.
In one embodiment of the present invention, the construction module 1203 is specifically configured to add the same kind of simulation history data to the same kind of category history data;
and generating random noise of the same kind based on the noise adding weight of the category history data of the same kind so as to reconstruct simulation history data of the same kind.
In one embodiment of the present invention, the construction module 1203 is specifically configured to generate the random noise of the same type based on the noise adding weight of the category history data of the same type, so as to reconstruct the simulation history data of the same type;
and if the simulation historical data of the same kind meet the preset construction conditions, stopping constructing the simulation historical data.
In one embodiment of the present invention, the establishing module 1204 is specifically configured to annotate the plurality of category simulation historical data and the plurality of category historical data;
determining credit parameters of the marked multiple kinds of simulation historical data and multiple kinds of class historical data through preset rating conditions;
To determine the credit parameters of the data, training and building a credit evaluation model.
Fig. 13 illustrates an exemplary system architecture 1300 to which a method of processing data or an apparatus of processing data of an embodiment of the present invention may be applied.
As shown in fig. 13, system architecture 1300 may include terminal devices 1301, 1302, 1303, a network 1304, and a server 1305. The network 1304 is used as a medium to provide communication links between the terminal devices 1301, 1302, 1303 and the server 1305. The network 1304 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 1305 through the network 1304 using the terminal devices 1301, 1302, 1303 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 1301, 1302, 1303, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 1301, 1302, 1303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 1305 may be a server providing various services, such as a background management server (by way of example only) that provides support for shopping-type websites browsed by users using the terminal devices 1301, 1302, 1303. The background management server may analyze and process the received data such as the product information query request, and feedback the processing result (e.g., the target push information, the product information—only an example) to the terminal device.
It should be noted that, the method for processing data provided by the embodiment of the present invention is generally performed by the server 1305, and accordingly, the device for processing data is generally disposed in the server 1305.
It should be understood that the number of terminal devices, networks and servers in fig. 13 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
A computer program product according to an embodiment of the present invention includes a computer program that, when executed by a processor, implements a method for processing data according to an embodiment of the present invention.
Referring now to FIG. 14, there is illustrated a schematic diagram of a computer system 1400 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 14 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 14, the computer system 1400 includes a Central Processing Unit (CPU) 1401, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1402 or a program loaded from a storage section 1408 into a Random Access Memory (RAM) 1403. In the RAM 1403, various programs and data required for the operation of the system 1400 are also stored. The CPU 1401, ROM 1402, and RAM 1403 are connected to each other through a bus 1404. An input/output (I/O) interface 1405 is also connected to the bus 1404.
The following components are connected to the I/O interface 1405: an input section 1406 including a keyboard, a mouse, and the like; an output portion 1407 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 1408 including a hard disk or the like; and a communication section 1409 including a network interface card such as a LAN card, a modem, and the like. The communication section 1409 performs communication processing via a network such as the internet. The drive 1410 is also connected to the I/O interface 1405 as needed. Removable media 1411, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memory, and the like, is installed as needed on drive 1410 so that a computer program read therefrom is installed as needed into storage portion 1408.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 1409 and/or installed from the removable medium 1411. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 1401.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a partitioning module, a generating module, a building module, and a building module. The names of these modules do not constitute a limitation on the module itself in some cases, and for example, the dividing module may also be described as "for dividing merchant history data into category history data including the following categories, merchant history data, financial history data, management history data, and warranty history data".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include:
classifying merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories of merchant historical data, financial historical data, management historical data and guarantee historical data;
generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category;
the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data;
and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data.
According to the technical scheme of the embodiment of the invention, the merchant historical data is divided into category historical data, wherein the category historical data comprises the following categories of merchant historical data, financial historical data, management historical data and guarantee historical data; generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category; the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data; and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data. Aiming at merchant historical data, simulation historical data is constructed, the number of credit evaluation data is increased, and credit is given to merchants through a training model.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
In the technical scheme of the invention, the aspects of acquisition, analysis, use, transmission, storage and the like of the related user personal information all meet the requirements of related laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside the aspects of legal use and the like, and are subjected to supervision and management of a supervision department. Necessary measures should be taken for the personal information of the user to prevent illegal access to such personal information data, ensure that personnel having access to the personal information data comply with the regulations of the relevant laws and regulations, and ensure the personal information of the user. Once these user personal information data are no longer needed, the risk should be minimized by limiting or even prohibiting the data collection and/or deletion.
User privacy is protected, when applicable, by de-identifying the data, including in some related applications, such as by removing a particular identifier (e.g., date of birth, etc.), controlling the amount or specificity of stored data (e.g., collecting location data at a city level rather than at a specific address level), controlling how the data is stored, and/or other methods.
Claims (17)
1. A method of processing data, comprising:
classifying merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories of merchant historical data, financial historical data, management historical data and guarantee historical data;
generating random noise of the same category based on a noise adding weight of the category history data of the same category, wherein the noise adding weight is obtained on the basis of the category history data of the same category;
the same kind of category historical data is combined with the same kind of random noise to construct the same kind of simulation historical data;
and training and establishing a credit evaluation model by adopting a plurality of kinds of simulation historical data and a plurality of kinds of category historical data.
2. The method of processing data according to claim 1, wherein the classifying merchant history data into category history data comprises:
converting an image in merchant input information into an image text, and taking the image text and the input text in the merchant input information as merchant historical data;
and analyzing semantics in the merchant historical data, and dividing the merchant historical data into category historical data.
3. The method of processing data according to claim 2, wherein converting the image in the merchant entry information into image text comprises:
screening out the image from the merchant input information;
and converting the image in the merchant input information into an original image text, and deleting invalid text in the original image text to obtain the image text.
4. The method of processing data according to claim 1, wherein the generating the same kind of random noise based on the noise adding weight of the same kind of the category history data includes:
the noise adding weight is obtained on the basis of the same category of historical data;
and generating random noise of the same category based on the noise adding weight of the category history data of the same category.
5. The method of processing data according to claim 4, wherein the noise-adding weight obtained on the basis of the same kind of category history data includes:
acquiring two types of historical data from the same type of historical data;
training to obtain a data characteristic model by adopting one type of historical data in the two types of historical data and the difference value of the two types of historical data;
and inputting category history data in the category history data of the same category into the data characteristic model to obtain the noise adding weight.
6. The method of processing data according to claim 4, wherein the noise-adding weight obtained on the basis of the same kind of category history data includes:
and taking the standard deviation of the historical data of the same category as the weighted noise.
7. The method of processing data according to claim 4, wherein generating the same kind of random noise based on the noise adding weight of the same kind of the category history data includes:
randomly selecting an adjustment parameter in a random noise range of the category history data of the same category;
And generating the random noise of the same category based on the noise adding weight of the category history data of the same category and the adjustment parameter.
8. The method of processing data according to claim 1, wherein the same category of historical data, in combination with the same category of random noise, constructs the same category of simulated historical data, comprising:
the same kind of category history data is combined with the same kind of random noise to establish new history data of the same kind;
and if the same type of history data is consistent with the same type of new history data in characteristics, taking the same type of new history data as the same type of simulation history data.
9. The method of processing data according to claim 8, wherein the same category of history data, in combination with the same category of random noise, creates the same category of newly created history data, comprising:
and combining one category of historical data of the same category with the random noise of the same category to establish new historical data of the same category.
10. The method of processing data according to claim 8, wherein the same category of history data is characterized by being identical to the same category of new history data, and wherein regarding the same category of new history data as the same category of simulation history data comprises:
The new historical data of the same kind belong to the statistical range of the historical data of the same kind, and the historical data of the same kind is determined to be consistent with the new historical data of the same kind in characteristic;
and taking the newly-built historical data of the same kind as the simulation historical data of the same kind.
11. The method of processing data according to claim 1, further comprising, after said constructing said same kind of simulation history data:
adding the simulation historical data of the same kind to the simulation historical data of the same kind;
and generating random noise of the same kind based on the noise adding weight of the category history data of the same kind so as to reconstruct simulation history data of the same kind.
12. The method of processing data according to claim 11, wherein the generating the same kind of random noise based on the noise adding weight of the same kind of the category history data to reconstruct the same kind of simulation history data includes:
generating random noise of the same kind based on the noise adding weight of the category history data of the same kind so as to reconstruct simulation history data of the same kind;
And if the simulation historical data of the same kind meet the preset construction conditions, stopping constructing the simulation historical data.
13. The method of processing data according to claim 1, wherein training and building a credit rating model using the plurality of categories of simulation history data and the plurality of categories of category history data comprises:
labeling the plurality of category simulation historical data and the plurality of category historical data;
determining credit parameters of the marked multiple kinds of simulation historical data and multiple kinds of class historical data through preset rating conditions;
to determine the credit parameters of the data, training and building a credit evaluation model.
14. An apparatus for processing data, comprising:
the classification module is used for classifying the merchant historical data into category historical data, wherein the category historical data comprises a plurality of categories including merchant historical data, financial historical data, management historical data and guarantee historical data;
the generation module is used for generating random noise of the same category based on the noise adding weight of the category history data of the same category, and the noise adding weight is obtained on the basis of the category history data of the same category;
The construction module is used for constructing the same kind of simulation historical data by combining the same kind of random noise;
the establishment module is used for training and establishing a credit evaluation model by adopting the plurality of kinds of simulation historical data and the plurality of kinds of category historical data.
15. An electronic device for processing data, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-13.
16. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-13.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310250088.1A CN116245542A (en) | 2023-03-13 | 2023-03-13 | Method, apparatus, device and computer readable medium for processing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310250088.1A CN116245542A (en) | 2023-03-13 | 2023-03-13 | Method, apparatus, device and computer readable medium for processing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116245542A true CN116245542A (en) | 2023-06-09 |
Family
ID=86633117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310250088.1A Pending CN116245542A (en) | 2023-03-13 | 2023-03-13 | Method, apparatus, device and computer readable medium for processing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116245542A (en) |
-
2023
- 2023-03-13 CN CN202310250088.1A patent/CN116245542A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11050690B2 (en) | Method for providing recording and verification service for data received and transmitted by messenger service, and server using method | |
| Chang | A cybernetics social cloud | |
| Andryani et al. | Social media analytics: data utilization of social media for research | |
| CA3138730C (en) | Public-opinion analysis method and system for providing early warning of enterprise risks | |
| CN111401700B (en) | Data analysis method, device, computer system and readable storage medium | |
| US11500929B2 (en) | Hierarchical federated learning using access permissions | |
| US9471665B2 (en) | Unified system for real-time coordination of content-object action items across devices | |
| US20230023630A1 (en) | Creating predictor variables for prediction models from unstructured data using natural language processing | |
| US20220114603A1 (en) | Systems and methods for tracking data shared with third parties using artificial intelligence-machine learning | |
| US20230195759A1 (en) | Data processing systems and methods for automatically detecting and documenting privacy-related aspects of computer software | |
| Chohan et al. | Electronic government services value creation from artificial intelligence: AI-based e-government services for Pakistan | |
| CN114692007A (en) | Method, device, equipment and storage medium for determining representation information | |
| US20200311625A1 (en) | Determining a nexus score of digital assets | |
| CN111177653B (en) | Credit evaluation method and device | |
| CN111191050B (en) | Knowledge graph ontology model construction method and device | |
| Alkouz et al. | EPPR: blockchain for educational record sharing and recommendation using the Ethereum platform | |
| CN116245542A (en) | Method, apparatus, device and computer readable medium for processing data | |
| US11526572B2 (en) | System and method for ethical collection of data | |
| CN114817346A (en) | Service processing method and device, electronic equipment and computer readable medium | |
| WO2020251866A1 (en) | Risk management of processes utilizing personal data | |
| KR102523014B1 (en) | Online transaction document management method and device, system using artificial intelligence and blockchain | |
| KR102022412B1 (en) | System for automatic generating of legal documents and a method thereof | |
| Abid et al. | A Dynamic and Automated Access Control Management System for Social Networks | |
| CN116703555A (en) | Early warning method, early warning device, electronic equipment and computer readable medium | |
| Ria Andryani et al. | Social Media Analytics: Data Utilization of Social Media for Research. |
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 |