CN114757724B - Precise information pushing system and method based on genetic algorithm - Google Patents
Precise information pushing system and method based on genetic algorithm Download PDFInfo
- Publication number
- CN114757724B CN114757724B CN202210666299.9A CN202210666299A CN114757724B CN 114757724 B CN114757724 B CN 114757724B CN 202210666299 A CN202210666299 A CN 202210666299A CN 114757724 B CN114757724 B CN 114757724B
- Authority
- CN
- China
- Prior art keywords
- user information
- user
- characteristic value
- level
- information characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an accurate information pushing system and method based on a genetic algorithm, in particular to the field of marketing methods, and the accurate information pushing system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a user information characteristic value, and the user information characteristic value comprises user age, user online time, user transfer transaction running water, user recent consumption amount, user family member conditions and the like; the analysis module is used for analyzing the user characteristics according to the user information characteristic values; the adjusting module is used for adjusting and screening the quadratic fitness function; and the pushing module is used for pushing information to the user according to the screened user feature set meeting the termination condition, and when the information is pushed, the pushing module is also used for matching the corresponding product according to the user feature set to push the information. The accurate information pushing system and method based on the genetic algorithm provided by the invention screen the user data by relying on the genetic algorithm, locate the user characteristics and effectively improve the information pushing efficiency.
Description
Technical Field
The invention relates to the technical field of information pushing, in particular to a precise information pushing system and method based on a genetic algorithm.
Background
A genetic algorithm is a search algorithm for solving the optimization in computational mathematics, and is one of evolutionary algorithms. Genetic algorithms are typically implemented as a computer simulation. The accurate marketing is to establish a personalized customer communication service system based on accurate positioning by means of modern information technology, realize a measurable low-cost expansion way of enterprises, and is one of core viewpoints in an attitude network marketing concept.
Chinese patent publication No. CN108805199A discloses an entity business marketing method based on genetic algorithm, comprising the following steps: collecting merchant data and user data; setting labels for different consumption types aiming at merchants; establishing a user preference model according to user data; carrying out initial clustering on merchant data and user data by using a k-means algorithm; and calculating the recommendation rate of the recommended user by the merchants meeting the conditions by adopting a genetic algorithm, generating a new alternative merchant data set, and accurately recommending the recommended user according to the ranking of each merchant in the data set. In the scheme, only merchant recommendation is carried out on the user, and accurate commodity pushing cannot be carried out.
Disclosure of Invention
Therefore, the invention provides a precise information pushing system and a precise information pushing method based on a genetic algorithm, which are used for solving the problem of low information pushing efficiency caused by the fact that user information cannot be precisely analyzed to precisely push a product in the prior art.
In order to achieve the above objects, in one aspect, the present invention provides an accurate information push system based on genetic algorithm, including,
the acquisition module is used for acquiring a user information characteristic value;
an analysis module for analyzing the user characteristics according to the user information characteristic values, which is connected with the acquisition module, the analysis module is internally provided with a grading unit and a screening unit, the grading unit is used for grading the user information characteristic values according to the user characteristic value matching coefficients, the graded user information characteristic values comprise a first-level user information characteristic value, a second-level user information characteristic value and a third-level user information characteristic value, the screening unit is used for calculating a moderate function according to the first-level user information characteristic value, the screening unit is connected with the grading unit, sets a termination condition of the moderate function, and increases the characteristic value of the next-grade user information to the moderate function when the moderate function does not meet the termination condition, screening again, and taking a moderate function which does not meet the termination condition after the third-level user information characteristic value is added as a secondary moderate function;
an adjusting module for adjusting and screening a quadratic moderation function, which is connected with the analyzing module, wherein a supplementing unit, a crossing unit, a mutation unit and a quadratic screening unit are arranged in the adjusting module, when the quadratic moderation function is adjusted, the supplementing unit is used for supplementing and acquiring a group of relative user information and a group of dynamically-changed user information, the crossing unit is used for crossing two mutually-corresponding user information characteristic values in the supplemented user information characteristic values through coefficient product to obtain crossed user information characteristic values, which are connected with the supplementing unit, the mutation unit is used for mutating a plurality of dynamically-changed user information characteristic values in the supplemented user information characteristic values to obtain mutated user information characteristic values, which are connected with the supplementing unit, the quadratic screening unit is used for carrying out mutation according to the existing user information characteristic values, The crossed user information characteristic values and the mutated user information characteristic values are subjected to secondary screening to select a user characteristic set meeting termination conditions, the user characteristic set is respectively connected with the crossing unit and the mutation unit, and when a secondary moderate function does not meet the termination conditions of the secondary screening, the secondary screening unit stops screening the user information characteristic values;
and the pushing module is used for pushing information to the user according to the screened user feature set meeting the termination condition, and when the information is pushed, the pushing module is also used for matching the corresponding product according to the user feature set to push the information.
Further, the classifying unit calculates a matching coefficient M of each user information feature value when classifying the acquired user information feature values, sets M = C/C0, C as the user information feature value, and C0 as a preset user information feature value, compares the matching coefficient M corresponding to each user information feature value with each preset matching coefficient, and classifies the acquired user information feature values according to the comparison result, wherein,
when M is larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a first-level user information characteristic value, which is marked as C11, C12.. C1x, and x is the number of the first-level user information characteristic value;
when M01 is larger than M and is not larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a second-level user information characteristic value, and marks the second-level user information characteristic value as C21 and C22.. C2y, wherein y is the number of the second-level user information characteristic value;
when M is not more than M01, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a third-level user information characteristic value, which is marked as C31, C32.. C3z, and z is the number of the third-level user information characteristic value;
the MO1 is a first preset matching coefficient, the MO2 is a second preset matching coefficient, and M01 is less than M02.
Further, when calculating the fitness function, the filtering unit calculates a first-level fitness function F1 according to the first-level user information characteristic value, sets F1= V11 × C11/C011+ V12 × C12/C012+. + -. + V1x × C1x/C01x, where V1i = (M-M02)/M02, sets i =1,2.. x, V1i is a first-level user characteristic coefficient, and C01i is a preset first-level user information characteristic value, compares the first-level fitness function F1 with a preset termination condition F0, and performs filtering according to the comparison result, where,
when F1 is larger than or equal to F0, the unit judges that the first-level fitness function F1 meets the termination condition, screens out the user feature set U1 in the first-level fitness function F1, and sets U1= { C11.. C1x };
when F1 < F0, the screening unit determines that the first-level fitness function F1 does not satisfy the termination condition, and performs screening again by calculating the second-level fitness function F2.
Further, the screening unit, when calculating the second-level fitness function F2, sets F2= F1+ V21 × C21/C021+ V22 × C22/C022+. + V2y × C2y/C02y, where V2j = (M-M01)/M01, sets j =1,2.. y, V2j as a second-level user characteristic coefficient, and C02j as a preset second-level user information characteristic value, compares the second-level fitness function F2 with a preset termination condition F0, and performs screening according to the comparison result, where,
when the F2 is larger than or equal to F0, the screening unit judges that the second-level user information feature value meets the moderate function termination condition, the screening unit screens out a user feature set U2 in a second-level moderate function F2, and U2= { C11.. C1x, C21.. C2y };
when F2 < F0, the filtering unit judges that the second-level user information characteristic value does not satisfy the moderate function termination condition, and performs filtering again by calculating a third-level moderate function F3.
Further, when calculating the third-level moderate function F3, the screening unit sets F3= F2+ V31 × C31/C031+ V32 × C32/C032+. + V3z × C3z/C03z, where V3k = M/M01, sets k =1,2.. z, V3k is a third-level user feature coefficient, z is the number of third-level user information feature values, and C03k is a preset third-level user information feature value, the screening unit compares the third-level moderate function F3 with a preset termination condition F0, and performs screening according to the comparison result, where,
when F3 is larger than or equal to F0, the screening unit judges that the third-level user information characteristic value meets the moderate function termination condition, and the screening unit screens out a user characteristic set U3 in a third-level moderate function F3 and sets U3= { C11.. C1x, C21.. C2y and C31.. C3z };
and when the F3 is less than the F0, the screening unit judges that the third-level user information characteristic value does not meet the moderate function termination condition, adjusts the secondary moderate function and screens the secondary moderate function.
Further, when the quadratic fitness function is adjusted and screened, the interleaving unit interleaves the user information feature values of a group of complementary relative user information through a coefficient product to generate an interleaved user information feature value C ', and sets C' =0.5 × Ca/COa +0.5 × Cb/COb, where Ca is a first relevant user information feature value, Cb is a second relevant user information feature value, COa is a preset first relevant user information feature value, and COb is a preset second relevant user information feature value.
Further, when carrying out mutation, the mutation unit carries out mutation according to a plurality of dynamically changing user information characteristic values in the supplemented user information characteristic values to generate a mutated user information characteristic value Ch, sets a mutation coefficient H, H =1/r, r is the number of dynamically changing user information to obtain the mutated user information characteristic value Ch, sets Ch = H × Vd × Cd/COd, Vd is a preset user information characteristic value mutation coefficient, sets Vd =1, Cd is the sum of the plurality of dynamically changing user information characteristic values, and COd is the sum of the preset user information characteristic values.
Further, the secondary screening unit calculates a secondary fitness function F 'and sets F' = F3+ C '+ Ch when performing secondary screening, compares the secondary fitness function F' with a preset termination condition F0, and performs screening according to the comparison result, wherein,
when F 'is more than or equal to F0, the secondary screening unit judges that the user information characteristic values subjected to secondary screening meet the moderate function termination condition, and the screening unit screens out user characteristic sets U4= { C11.. C1x, C21.. C2y, C31.. C3z, Ca, Cb, Cd } in the secondary screening moderate function F';
and when F' < F0, the secondary screening unit judges that the user information characteristic value subjected to secondary screening does not meet the moderate function termination condition, and stops screening.
Further, when information push is carried out, the push module selects different types of products to carry out information push according to the screened user feature set, wherein,
when the screened user feature set is U1, the pushing module selects A1 products to carry out information pushing;
when the screened user feature set is U2, the pushing module selects A2 products to carry out information pushing;
when the screened user feature set is U3, the pushing module selects A3 products to carry out information pushing;
when the screened user feature set is U4, the pushing module selects A4 products to carry out information pushing;
wherein A1 is a first predetermined product type, A2 is a second predetermined product type, A3 is a third predetermined product type, and A4 is a fourth predetermined product type.
In another aspect, the present invention further provides an accurate information pushing method based on a genetic algorithm, including,
step S1, obtaining a user information characteristic value through an obtaining module;
step S2, analyzing the user characteristic according to the user information characteristic value through the analysis module, grading the user information characteristic value according to the user characteristic value matching coefficient through the grading unit when analyzing, calculating the moderate function according to the graded user information characteristic value through the screening unit, and applying a quadratic moderate function to the moderate function which does not meet the termination condition;
step S3, adjusting and screening the quadratic fitness function through an adjusting module;
and step S4, pushing information to the user through the pushing module according to the screened user feature set meeting the termination condition.
Compared with the prior art, the method has the advantages that the user information is acquired through the acquisition module and is converted into specific numerical values to obtain the characteristic value of the user information, the user information is accurately acquired, the acquired user information is accurately analyzed through the analysis module, the acquired user information is classified and screened to screen out the user characteristics meeting the requirements, so that accurate product pushing is carried out according to the user characteristics to improve the efficiency of information pushing, information supplement is carried out on moderate functions which do not meet termination conditions after classification screening through the adjustment module, the supplement information is crossed and mutated, secondary screening is carried out, information pushing is carried out on users meeting the termination conditions according to the characteristic value of the user information through the pushing module, and the efficiency of information pushing is further improved.
Particularly, the grading unit compares the matching coefficient corresponding to each user information characteristic value with each preset matching coefficient through the matching coefficient of the user information characteristic value, grades the obtained user information characteristic value according to the comparison result, and grades the user information according to the matching degree, so that the user information with high matching degree is preferentially screened, the information pushing efficiency is improved, when the matching coefficient is larger than a second preset matching coefficient, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a first-stage user information characteristic value and marks the first-stage user information characteristic value, when the matching coefficient is larger than the first preset matching coefficient and smaller than or equal to the second preset matching coefficient, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a second-stage user information characteristic value and marks the second-stage user information characteristic value, and when the matching coefficient is smaller than the first preset matching coefficient, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a third-stage user information characteristic value and marks the third-stage user information characteristic value And marking, so as to grade the information, preferentially screening the user information with high matching degree, and improving the information pushing efficiency.
In particular, the filtering unit calculates a first level fitness function F1 based on the first level user information characteristic values, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, further improving the information pushing efficiency, the screening unit compares the first-level moderate function with a preset termination condition and screens according to the comparison result, wherein, when the first-level moderate function value is more than or equal to the preset termination condition, the unit judges that the first-level moderate function meets the termination condition and screens out the user feature set in the first-level moderate function, when the first-level moderate function value is smaller than the preset termination condition, the screening unit judges that the first-level moderate function does not meet the termination condition, and the second-level moderate function is calculated to perform screening again, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
In particular, the filtering unit calculates a second level moderation function F2 according to the second level user information characteristic value, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, thereby improving the information pushing efficiency, the screening unit compares the second-level moderate function with the preset termination condition and screens according to the comparison result, wherein, when the second level moderate function value is larger than or equal to the preset termination condition, the unit judges that the second level moderate function meets the termination condition and screens out the user characteristic set in the second level moderate function, when the second-level fitness function value is smaller than the preset termination condition, the screening unit judges that the second-level fitness function does not meet the termination condition, and the third-level moderate function is calculated to perform screening again, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
In particular, the screening unit calculates a third-level fitness function according to the third-level user information characteristic value, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, further improving the information pushing efficiency, the screening unit compares the third-level moderate function with the preset termination condition and screens according to the comparison result, wherein, when the third-level moderate function value is larger than or equal to the preset termination condition, the unit judges that the third-level moderate function meets the termination condition and screens out the user characteristic set in the third-level moderate function, when the third-level moderate function value is smaller than the preset termination condition, the screening unit judges that the third-level moderate function does not meet the termination condition, and adjusting and screening the quadratic fitness function, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
Particularly, the crossing unit crosses the user information characteristic values of a group of supplemented relative user information through a coefficient product to obtain crossed user information characteristic values, so that the user information is integrated and secondarily screened, the user characteristics are further accurately positioned, and the information pushing efficiency is improved.
Particularly, the mutation unit mutates a plurality of dynamically changing user information characteristic values in the supplemented user information characteristic values to obtain mutated user information characteristic values, so that user information is integrated and secondarily screened, user characteristics are further accurately positioned, and the information pushing efficiency is improved.
Particularly, the secondary screening unit performs screening again by calculating a secondary moderate function, thereby further screening user data, locating user characteristics, and effectively improving the efficiency of information pushing, compares the secondary moderate function with a preset termination condition, and performs screening according to the comparison result, wherein when the secondary moderate function is greater than or equal to the preset termination condition, the secondary screening unit determines that the user information characteristic value subjected to secondary screening satisfies the moderate function termination condition, the screening unit screens the user characteristic set in the secondary screening moderate function, and when the secondary moderate function is smaller than the preset termination condition, the secondary screening unit determines that the user information characteristic value subjected to secondary screening does not satisfy the moderate function termination condition, stops screening, and performs accurate analysis to improve the efficiency of product pushing.
Particularly, the pushing module selects different products to push information according to the screened user feature set, the information pushing efficiency is improved through accurate user analysis and product matching, when the pushing module pushes information, different products are selected to push information according to the screened user feature set, the user features are accurately positioned, and the information pushing efficiency is effectively improved.
Drawings
FIG. 1 is a schematic structural diagram of an accurate information push system based on a genetic algorithm according to an embodiment;
fig. 2 is a schematic flow chart of the precise information pushing method based on the genetic algorithm according to the embodiment.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Please refer to fig. 1, which is a diagram illustrating a precise information pushing system based on genetic algorithm according to an embodiment of the present invention, the system includes,
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring user information characteristic values, the user information comprises user age, user online time, user transfer transaction running water, user recent consumption amount, user family member condition and the like, the user information characteristic values correspond to specific numerical values, such as age 28, the user online time per day is 3 hours, the transfer transaction amount of a user in one year is 100 w, the user consumption amount in the near month is 2 w, the user family member number is 5 and the like, the embodiment does not specifically limit the user information, and other user information reflecting the user consumption capacity can be set by technicians in the field;
an analysis module for analyzing the user characteristics according to the user information characteristic values, which is connected with the acquisition module, the analysis module is internally provided with a grading unit and a screening unit, the grading unit is used for grading the user information characteristic values according to the user characteristic value matching coefficients, the graded user information characteristic values comprise a first-level user information characteristic value, a second-level user information characteristic value and a third-level user information characteristic value, the screening unit is used for calculating a moderate function according to the first-level user information characteristic value, the screening unit is connected with the grading unit, sets a termination condition of the moderate function, and increases the characteristic value of the next-grade user information to the moderate function when the moderate function does not meet the termination condition, screening again, and taking a moderate function which increases the characteristic value of the third-level user information and still does not meet the termination condition as a secondary moderate function;
an adjusting module for adjusting and screening a quadratic moderation function, which is connected with the analyzing module, wherein a supplementing unit, a crossing unit, a mutation unit and a quadratic screening unit are arranged in the adjusting module, when the quadratic moderation function is adjusted, the supplementing unit is used for supplementing and acquiring a group of relative user information and a group of dynamically-changed user information, the crossing unit is used for crossing two mutually-corresponding user information characteristic values in the supplemented user information characteristic values through coefficient product to obtain a crossed user information characteristic value C', which is connected with the supplementing unit, the mutation unit is used for mutating a plurality of dynamically-changed user information characteristic values in the supplemented user information characteristic values to obtain a mutated user information characteristic value Ch, which is connected with the supplementing unit, the quadratic screening unit is used for carrying out mutation according to the existing user information characteristic values, The crossed user information characteristic value C' and the mutated user information characteristic value Ch are subjected to secondary screening to select a user characteristic set meeting a termination condition, the user characteristic set is respectively connected with the crossing unit and the mutation unit, and when a secondary moderate function does not meet the termination condition of the secondary screening, the secondary screening unit stops screening the user information characteristic value;
and the pushing module is used for pushing information to the user according to the screened user feature set meeting the termination condition, and when the information is pushed, the pushing module is also used for matching the corresponding product according to the user feature set to push the information.
Specifically, in the system according to this embodiment, the acquisition module acquires user information, and converts the user information into a specific numerical value to obtain a user information characteristic value, so as to accurately acquire the user information, the analysis module performs accurate analysis on the acquired user information, the acquired user information is classified and screened, so as to screen out user characteristics that meet requirements, so as to perform accurate product pushing according to the user characteristics, so as to improve the efficiency of information pushing, the adjustment module performs information supplementation on a moderate function that does not meet a termination condition after the classification screening, and performs intersection and mutation on the supplemented information, so as to perform secondary screening, and the pushing module performs information pushing on a user that meets the termination condition according to the user information characteristic value, so as to further improve the efficiency of information pushing.
Specifically, the classifying unit calculates a matching coefficient M of each user information feature value when classifying the acquired user information feature values, sets M = C/C0, where C is the user information feature value, C0 is a preset user information feature value, compares the matching coefficient M corresponding to each user information feature value with each preset matching coefficient, and classifies the acquired user information feature values according to the comparison result, wherein,
when M is larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a first-level user information characteristic value, which is marked as C11, C12.. C1x, and x is the number of the first-level user information characteristic value;
when M01 is larger than M and is not larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a second-level user information characteristic value, and marks the second-level user information characteristic value as C21 and C22.. C2y, wherein y is the number of the second-level user information characteristic value;
when M is not more than M01, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a third-level user information characteristic value, which is marked as C31, C32.. C3z, and z is the number of the third-level user information characteristic value;
the MO1 is a first preset matching coefficient, the MO2 is a second preset matching coefficient, and M01 is less than M02.
Specifically, the grading unit compares matching coefficients corresponding to user information characteristic values with preset matching coefficients through matching coefficients of the user information characteristic values, grades the obtained user information characteristic values according to the comparison results, and grades the user information according to the matching degrees, so that user information with high matching degrees is preferentially screened, the information pushing efficiency is improved, when the matching coefficients are larger than a second preset matching coefficient, the grading unit takes the user information characteristic values corresponding to the matching coefficients as first-level user information characteristic values and marks the first-level user information characteristic values, when the matching coefficients are larger than the first preset matching coefficient and smaller than or equal to the second preset matching coefficient, the grading unit takes the user information characteristic values corresponding to the matching coefficients as second-level user information characteristic values and marks the second-level user information characteristic values, and when the matching coefficients are smaller than the first preset matching coefficient, the grading unit takes the user information characteristic values corresponding to the matching coefficients as third-level user information characteristic values And the values are marked, so that the information is classified, the user information with high matching degree is preferentially screened, and the information pushing efficiency is improved. It is to be understood that the present embodiment does not specifically limit the information level division, and those skilled in the art can freely set the information level division according to the information division requirement, for example, the information level division is five levels.
Specifically, when the filtering unit calculates the fitness function, the filtering unit calculates a first-level fitness function F1 according to a first-level user information characteristic value, sets F1= V11 × C11/C011+ V12 × C12/C012+. + V1x × C1x/C01x, where V1i = (M-M02)/M02, sets i =1,2.. x, V1i is a first-level user characteristic coefficient, and C01i is a preset first-level user information characteristic value, compares the first-level fitness function F1 with a preset termination condition F0, and performs filtering according to the comparison result, where,
when F1 is larger than or equal to F0, the unit judges that the first-level fitness function F1 meets the termination condition, screens out the user feature set U1 in the first-level fitness function F1, and sets U1= { C11.. C1x };
when F1 < F0, the filter unit determines that the first level fitness function F1 does not satisfy the termination condition, and performs the filtering again by calculating the second level fitness function F2.
Specifically, the screening unit calculates a first-level moderating function F1 based on the first-level user information characteristic value, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, further improving the information pushing efficiency, the screening unit compares the first-level moderate function with a preset termination condition and screens according to the comparison result, wherein, when the first-level moderate function value is more than or equal to the preset termination condition, the unit judges that the first-level moderate function meets the termination condition and screens out the user feature set in the first-level moderate function, when the first-level moderate function value is smaller than the preset termination condition, the screening unit judges that the first-level moderate function does not meet the termination condition, and the second-level moderate function is calculated to perform screening again, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
Specifically, when calculating the second-level fitness function F2, the filtering unit sets F2= F1+ V21 × C21/C021+ V22 × C22/C022+. + V2y × C2y/C02y, where V2j = (M-M01)/M01, sets j =1,2.. y, V2j as a second-level user characteristic coefficient, and C02j as a preset second-level user information characteristic value, compares the second-level fitness function F2 with a preset termination condition F0, and performs filtering according to the comparison result, where,
when the F2 is larger than or equal to F0, the screening unit judges that the characteristic value of the second-level user information meets the termination condition of the moderate function, and screens out the user characteristic set U2 in the second-level moderate function F2, and sets U2= { C11.. C1x, C21.. C2y };
when F2 < F0, the filtering unit judges that the second-level user information characteristic value does not satisfy the moderate function termination condition, and performs filtering again by calculating a third-level moderate function F3.
Specifically, the screening unit calculates a second level fitness function F2 according to the second level user information characteristic value, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, thereby improving the information pushing efficiency, the screening unit compares the second-level moderate function with the preset termination condition and screens according to the comparison result, wherein, when the second level moderate function value is more than or equal to the preset termination condition, the unit judges that the second level moderate function meets the termination condition and screens out the user characteristic set in the second level moderate function, when the second-level fitness function value is smaller than the preset termination condition, the screening unit judges that the second-level fitness function does not meet the termination condition, and a third-level moderate function is calculated to perform screening again, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
Specifically, when calculating the third-level moderate function F3, the screening unit sets F3= F2+ V31 × C31/C031+ V32 × C32/C032+. + V3z × C3z/C03z, where V3k = M/M01, sets k =1,2.. z, V3k is a third-level user feature coefficient, z is the number of third-level user information feature values, and C03k is a preset third-level user information feature value, compares the third-level moderate function F3 with a preset termination condition F0, and performs screening according to the comparison result, where,
when F3 is larger than or equal to F0, the screening unit judges that the third-level user information characteristic value meets the moderate function termination condition, and the screening unit screens out a user characteristic set U3 in a third-level moderate function F3 and sets U3= { C11.. C1x, C21.. C2y and C31.. C3z };
and when the F3 is less than the F0, the screening unit judges that the third-level user information characteristic value does not meet the moderate function termination condition, adjusts the secondary moderate function and screens the secondary moderate function.
Specifically, the screening unit calculates a third-level fitness function according to the third-level user information characteristic value, used for judging whether the moderate function meets the termination condition or not, thereby accurately screening out the user characteristic set, further improving the information pushing efficiency, the screening unit compares the third-level moderate function with the preset termination condition and screens according to the comparison result, wherein, when the third-level moderate function value is larger than or equal to the preset termination condition, the unit judges that the third-level moderate function meets the termination condition and screens out the user characteristic set in the third-level moderate function, when the third-level moderate function value is smaller than the preset termination condition, the screening unit judges that the third-level moderate function does not meet the termination condition, and adjusting and screening the quadratic fitness function, so that the user characteristic set is screened out more accurately, and the information pushing efficiency is improved.
Specifically, when the quadratic fitness function is adjusted and screened, the interleaving unit interleaves the user information characteristic values of a complementary set of relative user information by a coefficient product to generate an interleaved user information characteristic value C ', and sets C' =0.5 × Ca/COa +0.5 × Cb/COb, where Ca is a first related user information characteristic value, Cb is a second related user information characteristic value, COa is a preset first related user information characteristic value, and COb is a preset second related user information characteristic value.
Specifically, the intersecting unit in this embodiment intersects the user information characteristic values of a group of complementary relative user information through a coefficient product to obtain an intersecting user information characteristic value C', so as to integrate the user information, perform secondary screening, further accurately locate the user characteristics, and improve the information pushing efficiency. If the user income is 10K-grams per month, the user income information Ca =100, the user expenditure is 2K-grams per month, the user expenditure information Cb = -20, the preset user income information COa =10 is set, and the preset user expenditure information COb =5 is set, then the user balance difference, that is, the crossed user information characteristic value C ', C' =0.5 × Ca/COa +0.5 × Cb/COb =0.5 = 100/10+0.5 (-20)/5 = 3, can be obtained.
Specifically, when carrying out mutation, the mutation unit carries out mutation according to a plurality of dynamically changing user information characteristic values in the supplemented user information characteristic values to generate a mutated user information characteristic value Ch, sets a mutation coefficient H, H =1/r, r is the number of dynamically changing user information to obtain the mutated user information characteristic value Ch, sets Ch = H × Vd × Cd/COd, Vd is a preset user information characteristic value mutation coefficient, Vd =1, Cd is the sum of the plurality of dynamically changing user information characteristic values, and COd is the sum of the preset user information characteristic values.
Specifically, the mutation unit performs mutation on a plurality of dynamically changing user information characteristic values in the supplemented user information characteristic values to obtain a mutated user information characteristic value Ch, so that the user information is integrated and secondarily screened, the user characteristics are further accurately positioned, and the information pushing efficiency is improved. If the user balance difference value is dynamically changed, the today balance difference value is different from the yesterday balance difference value, a mutation coefficient is introduced at the moment, the meaning of the mutation coefficient in the case of the current situation represents the balance difference value within a period of time, the balance difference value Cy within a month is multiplied by the mutation coefficient h, and the user balance difference value characteristic value Ch is obtained. It can be understood that the embodiment does not specifically limit the dynamically changing user information, and those skilled in the art can freely set the user information according to the product target, for example, set the balance difference within one year.
Specifically, the secondary screening unit calculates a secondary fitness function F 'and sets F' = F3+ C '+ Ch when performing secondary screening, compares the secondary fitness function F' with a preset termination condition F0, and performs screening according to the comparison result, wherein,
when F 'is more than or equal to F0, the secondary screening unit judges that the user information characteristic values subjected to secondary screening meet the moderate function termination condition, and the screening unit screens out user characteristic sets U4= { C11.. C1x, C21.. C2y, C31.. C3z, Ca, Cb, Cd } in the secondary screening moderate function F';
and when F' < F0, the secondary screening unit judges that the user information characteristic value subjected to secondary screening does not meet the moderate function termination condition, and stops screening.
Specifically, the quadratic filtering unit of the present embodiment performs filtering again by calculating the quadratic fitness function F', thereby further screening user data, positioning user characteristics, effectively improving the efficiency of information push, by comparing the quadratic fitness function F' with the preset termination condition F0 and screening according to the comparison result, wherein, when the quadratic moderation function F 'is larger than or equal to the preset termination condition F0, the quadratic screening unit determines that the user information characteristic value after the quadratic screening satisfies the moderation function termination condition, the screening unit screens the user characteristic set in the quadratic screening moderation function F', when the secondary moderate function F' is smaller than the preset termination condition F0, the secondary screening unit judges that the user information characteristic value subjected to secondary screening does not meet the moderate function termination condition, and stops screening, so that the product pushing efficiency is improved through accurate analysis. It can be understood that, in this embodiment, the user information feature value of the secondary screening is not specifically limited, and those skilled in the art can freely set, for example, the user volume can be added for the secondary screening.
Specifically, when information push is performed, the push module selects different types of products to perform information push according to the screened user feature set, wherein,
when the screened user feature set is U1, the pushing module selects A1 products to carry out information pushing;
when the screened user feature set is U2, the pushing module selects A2 products to carry out information pushing;
when the screened user feature set is U3, the pushing module selects A3 products to carry out information pushing;
when the screened user feature set is U4, the pushing module selects A4 products to carry out information pushing;
wherein A1 is a first predetermined product type, A2 is a second predetermined product type, A3 is a third predetermined product type, and A4 is a fourth predetermined product type.
Specifically, in this embodiment, the pushing module selects different types of products according to the screened user feature set to perform information pushing, and improves the information pushing efficiency through accurate user analysis and product matching.
Please refer to fig. 2, which is a schematic flow chart illustrating a precise information pushing method based on a genetic algorithm according to the present embodiment, the method includes,
step S1, obtaining a user information characteristic value through an obtaining module;
step S2, analyzing the user characteristic according to the user information characteristic value through the analysis module, grading the user information characteristic value according to the user characteristic value matching coefficient through the grading unit when analyzing, calculating the moderate function according to the graded user information characteristic value through the screening unit, and applying a quadratic moderate function to the moderate function which does not meet the termination condition;
step S3, adjusting and screening the quadratic fitness function through an adjusting module;
and step S4, pushing information to the user through the pushing module according to the screened user feature set meeting the termination condition.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is apparent to those skilled in the art that the scope of the present invention is not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. An accurate information pushing system based on genetic algorithm is characterized by comprising,
the acquisition module is used for acquiring a user information characteristic value;
an analysis module for analyzing the user characteristics according to the user information characteristic values, which is connected with the acquisition module, the analysis module is internally provided with a grading unit and a screening unit, the grading unit is used for grading the user information characteristic values according to the user characteristic value matching coefficients, the graded user information characteristic values comprise a first-level user information characteristic value, a second-level user information characteristic value and a third-level user information characteristic value, the screening unit is used for calculating a moderate function according to the first-level user information characteristic value, the screening unit is connected with the grading unit, sets a termination condition of the moderate function, and increases the characteristic value of the next-grade user information to the moderate function when the moderate function does not meet the termination condition, screening again, and taking a moderate function which does not meet the termination condition after the third-level user information characteristic value is added as a secondary moderate function;
an adjusting module for adjusting and screening a quadratic moderation function, which is connected with the analyzing module, wherein a supplementing unit, a crossing unit, a mutation unit and a quadratic screening unit are arranged in the adjusting module, when the quadratic moderation function is adjusted, the supplementing unit is used for supplementing and acquiring a group of relative user information and a group of dynamically-changed user information, the crossing unit is used for crossing two mutually-corresponding user information characteristic values in the supplemented user information characteristic values through coefficient product to obtain crossed user information characteristic values, which are connected with the supplementing unit, the mutation unit is used for mutating a plurality of dynamically-changed user information characteristic values in the supplemented user information characteristic values to obtain mutated user information characteristic values, which are connected with the supplementing unit, the quadratic screening unit is used for carrying out mutation according to the existing user information characteristic values, The crossed user information characteristic values and the mutated user information characteristic values are secondarily screened to select a user characteristic set meeting termination conditions, the user characteristic set is respectively connected with the crossing unit and the mutation unit, and when a secondary moderate function does not meet the termination conditions of secondary screening, the secondary screening unit stops screening the user information characteristic values;
and the pushing module is used for pushing information to the user according to the screened user feature set meeting the termination condition, and when the information is pushed, the pushing module is also used for matching the corresponding product according to the user feature set to push the information.
2. The accurate information push system based on genetic algorithm as claimed in claim 1, wherein the ranking unit calculates a matching coefficient M for each user information characteristic value, sets M = C/C0, C is the user information characteristic value, C0 is the preset user information characteristic value, compares the matching coefficient M corresponding to each user information characteristic value with each preset matching coefficient, and ranks the obtained user information characteristic values according to the comparison result, when ranking the obtained user information characteristic values,
when M is larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a first-level user information characteristic value, which is marked as C11, C12.. C1x, and x is the number of the first-level user information characteristic value;
when M01 is larger than M and is not larger than M02, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a second-level user information characteristic value, and marks the second-level user information characteristic value as C21 and C22.. C2y, wherein y is the number of the second-level user information characteristic value;
when M is not more than M01, the grading unit takes the user information characteristic value corresponding to the matching coefficient as a third-level user information characteristic value, which is marked as C31, C32.. C3z, and z is the number of the third-level user information characteristic value;
the MO1 is a first predetermined matching coefficient, the MO2 is a second predetermined matching coefficient, and M01 is less than M02.
3. The accurate information push system based on genetic algorithm as claimed in claim 1, wherein the filtering unit calculates a first-level fitness function F1 according to the first-level user information characteristic value when calculating the fitness function, sets F1= V11 x C11/C011+ V12 x C12/C012+. to + V1x x C1x/C01x, wherein V1i = (M-M02)/M02, sets i =1,2.. x, V1i is the first-level user characteristic coefficient, C01i is the preset first-level user information characteristic value, the filtering unit compares the first-level fitness function F1 with the preset termination condition F0, and filters according to the comparison result, wherein,
when F1 is larger than or equal to F0, the unit judges that the first-level fitness function F1 meets the termination condition, screens out the user feature set U1 in the first-level fitness function F1, and sets U1= { C11.. C1x };
when F1 < F0, the filter unit determines that the first level fitness function F1 does not satisfy the termination condition, and performs the filtering again by calculating the second level fitness function F2.
4. The accurate information push system based on genetic algorithm according to claim 3, wherein the filtering unit sets F2= F1+ V21 xC 21/C021+ V22 xC 22/C022+. to + V2y xC 2y/C02y when calculating the second-level fitness function F2, wherein V2j = (M-M01)/M01, sets j =1,2.. y, V2j is a second-level user characteristic coefficient, C02j is a preset second-level user information characteristic value, the filtering unit compares the second-level fitness function F2 with a preset termination condition F0 and performs filtering according to the comparison result, wherein,
when the F2 is larger than or equal to F0, the screening unit judges that the characteristic value of the second-level user information meets the termination condition of the moderate function, and screens out the user characteristic set U2 in the second-level moderate function F2, and sets U2= { C11.. C1x, C21.. C2y };
when F2 < F0, the filtering unit judges that the second-level user information characteristic value does not satisfy the moderate function termination condition, and performs filtering again by calculating a third-level moderate function F3.
5. The accurate information push system based on genetic algorithm according to claim 4, wherein the filtering unit, when calculating the third-level fitness function F3, sets F3= F2+ V31 XC 31/C031+ V32 XC 32/C032+. to + V3z XC 3z/C03z, wherein V3k = M/M01, sets k =1,2.. z, V3k is a third-level user characteristic coefficient, z is a number of third-level user information characteristic values, and C03k is a preset third-level user information characteristic value, the filtering unit compares the third-level fitness function F3 with a preset termination condition F0, and performs filtering according to the comparison result, wherein,
when F3 is larger than or equal to F0, the screening unit judges that the third-level user information characteristic value meets the moderate function termination condition, and the screening unit screens out a user characteristic set U3 in a third-level moderate function F3 and sets U3= { C11.. C1x, C21.. C2y and C31.. C3z };
and when the F3 is less than the F0, the screening unit judges that the third-level user information characteristic value does not meet the moderate function termination condition, adjusts the secondary moderate function and screens the secondary moderate function.
6. The system of claim 1, wherein when the quadratic fitness function is adjusted and filtered, the interleaving unit interleaves a complementary set of relative user information characteristic values by a coefficient product to generate an interleaved user information characteristic value C ', where C' =0.5 xca/COa +0.5 xcb/COb is set, Ca is the first relevant user information characteristic value, Cb is the second relevant user information characteristic value, COa is the preset first relevant user information characteristic value, and COb is the preset second relevant user information characteristic value.
7. The precise information push system based on genetic algorithm as claimed in claim 6, wherein the mutation unit performs mutation according to a plurality of dynamically changing user information feature values in the supplemented user information feature values when performing mutation, to generate a mutated user information feature value Ch, sets a mutation coefficient H, H =1/r, r is a dynamically changing user information quantity, obtains a mutated user information feature value Ch, sets Ch = hxvd × Cd/COd, Vd is a preset user information feature value mutation coefficient, sets Vd =1, Cd is a sum of the plurality of dynamically changing user information feature values, and COd is a sum of the preset user information feature values.
8. The precise information push system according to claim 7, wherein the secondary filtering unit calculates a secondary fitness function F 'when performing the secondary filtering, sets F' = F3+ C '+ Ch, compares the secondary fitness function F' with a preset termination condition F0, and performs the filtering according to the comparison result,
when F 'is more than or equal to F0, the secondary screening unit judges that the user information characteristic values subjected to secondary screening meet the moderate function termination condition, and the screening unit screens out user characteristic sets U4= { C11.. C1x, C21.. C2y, C31.. C3z, Ca, Cb, Cd } in the secondary screening moderate function F';
and when F' < F0, the secondary screening unit judges that the user information characteristic value subjected to secondary screening does not meet the moderate function termination condition, and stops screening.
9. The accurate information pushing system based on genetic algorithm according to claim 1, wherein when pushing information, the pushing module selects different categories of products to push information according to the screened user feature set,
when the screened user feature set is U1, the pushing module selects A1 products to carry out information pushing;
when the screened user feature set is U2, the pushing module selects A2 products to carry out information pushing;
when the screened user feature set is U3, the pushing module selects A3 products to carry out information pushing;
when the screened user feature set is U4, the pushing module selects A4 products to carry out information pushing;
wherein A1 is a first predetermined product type, A2 is a second predetermined product type, A3 is a third predetermined product type, and A4 is a fourth predetermined product type.
10. A push method applied to the precise information push system based on genetic algorithm according to any one of claims 1-9, characterized by comprising,
step S1, obtaining a user information characteristic value through an obtaining module;
step S2, analyzing the user characteristic according to the user information characteristic value through the analysis module, grading the user information characteristic value according to the user characteristic value matching coefficient through the grading unit when analyzing, calculating the moderate function according to the graded user information characteristic value through the screening unit, and applying a quadratic moderate function to the moderate function which does not meet the termination condition;
step S3, adjusting and screening the quadratic fitness function through an adjusting module;
and step S4, pushing information to the user through the pushing module according to the screened user feature set meeting the termination condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210666299.9A CN114757724B (en) | 2022-06-14 | 2022-06-14 | Precise information pushing system and method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210666299.9A CN114757724B (en) | 2022-06-14 | 2022-06-14 | Precise information pushing system and method based on genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114757724A CN114757724A (en) | 2022-07-15 |
| CN114757724B true CN114757724B (en) | 2022-09-20 |
Family
ID=82336577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210666299.9A Active CN114757724B (en) | 2022-06-14 | 2022-06-14 | Precise information pushing system and method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114757724B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730286A (en) * | 2016-08-10 | 2018-02-23 | ***通信集团黑龙江有限公司 | A kind of target customer's screening technique and device |
| CN109816438A (en) * | 2019-01-11 | 2019-05-28 | 珠海天燕科技有限公司 | Information-pushing method and device |
| CN110210881A (en) * | 2018-02-28 | 2019-09-06 | 中兴通讯股份有限公司 | A kind of user interest prediction technique, apparatus and system |
| CN110390047A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Resource information recommended method, device, terminal and medium based on genetic algorithm |
| CN110751168A (en) * | 2019-09-03 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
| CN114549142A (en) * | 2022-03-17 | 2022-05-27 | 太平洋国际拍卖有限公司 | Online bidding auction information processing method and system |
| CN114547446A (en) * | 2022-02-15 | 2022-05-27 | 深圳闪回科技有限公司 | Order pushing method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160103469A (en) * | 2015-02-24 | 2016-09-01 | 삼성전자주식회사 | Apparatus and Method for operating the customized proposals service |
-
2022
- 2022-06-14 CN CN202210666299.9A patent/CN114757724B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730286A (en) * | 2016-08-10 | 2018-02-23 | ***通信集团黑龙江有限公司 | A kind of target customer's screening technique and device |
| CN110210881A (en) * | 2018-02-28 | 2019-09-06 | 中兴通讯股份有限公司 | A kind of user interest prediction technique, apparatus and system |
| CN109816438A (en) * | 2019-01-11 | 2019-05-28 | 珠海天燕科技有限公司 | Information-pushing method and device |
| CN110390047A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Resource information recommended method, device, terminal and medium based on genetic algorithm |
| CN110751168A (en) * | 2019-09-03 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
| CN114547446A (en) * | 2022-02-15 | 2022-05-27 | 深圳闪回科技有限公司 | Order pushing method and system |
| CN114549142A (en) * | 2022-03-17 | 2022-05-27 | 太平洋国际拍卖有限公司 | Online bidding auction information processing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于优化模糊遗传算法的地理信息个性化推送方法;邵改革;《测绘工程》;20150731;第24卷(第7期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114757724A (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103119582B (en) | Reduce the dissimilar degree between the first multivariate data group and the second multivariate data group | |
| CN111181939A (en) | Network intrusion detection method and device based on ensemble learning | |
| CN101496035B (en) | Method for classifying modes | |
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| JP5075009B2 (en) | Similarity analysis evaluation system | |
| CN110866819A (en) | Automatic credit scoring card generation method based on meta-learning | |
| CN109242135A (en) | A kind of model method for running, device and service server | |
| CN110807527A (en) | Line adjusting method and device based on guest group screening and electronic equipment | |
| CN110930198A (en) | Electric energy substitution potential prediction method and system based on random forest, storage medium and computer equipment | |
| Chicco et al. | Renyi entropy-based classification of daily electrical load patterns | |
| CN106874355A (en) | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously | |
| CN108921604A (en) | A kind of ad click rate prediction technique integrated based on Cost-Sensitive Classifiers | |
| CN107545360A (en) | A kind of air control intelligent rules deriving method and system based on decision tree | |
| CN111062806B (en) | Personal finance credit risk evaluation method, system and storage medium | |
| CN107194815B (en) | Client segmentation method and system | |
| CN109189876A (en) | A kind of data processing method and device | |
| CN112700324A (en) | User loan default prediction method based on combination of Catboost and restricted Boltzmann machine | |
| CN106886559A (en) | The collaborative filtering method of good friend's feature and similar users feature is incorporated simultaneously | |
| CN115577152A (en) | Online book borrowing management system based on data analysis | |
| CN116187808A (en) | Electric power package recommendation method based on virtual power plant user-package label portrait | |
| CN117391247A (en) | Enterprise risk level prediction method and system based on deep learning | |
| CN114819777A (en) | Enterprise sales business analysis and management system based on digital twin technology | |
| CN111324790A (en) | Load type identification method based on support vector machine classification | |
| CN114757724B (en) | Precise information pushing system and method based on genetic algorithm | |
| CN110309424A (en) | A kind of socialization recommended method based on Rough clustering |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |