CN108022150A - recommendation method and system based on O2O data - Google Patents
recommendation method and system based on O2O data Download PDFInfo
- Publication number
- CN108022150A CN108022150A CN201711236424.8A CN201711236424A CN108022150A CN 108022150 A CN108022150 A CN 108022150A CN 201711236424 A CN201711236424 A CN 201711236424A CN 108022150 A CN108022150 A CN 108022150A
- Authority
- CN
- China
- Prior art keywords
- mrow
- user
- consumption
- data information
- businessman
- 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.)
- Granted
Links
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the recommendation method and system based on O2O data, including:Capturing service data message, and service data information is updated in preset time;Consumption data information is counted, consumption data information includes the consumption number of times of the number of users of each businessman consumption, the number of users that same user consumes in different businessmans and each user in different businessmans;The number of users and same user of each businessman consumption are calculated in the number of users that different businessmans consume, obtain remaining profound similarity;According to each user in the consumption number of times of different businessmans, the interest-degree of user is obtained;According to the interest-degree of user and the weight model of distance, the preference of user is obtained, more accurately recommendation service can be provided, improves user experience.
Description
Technical field
The present invention relates to technical field of information processing, more particularly, to the recommendation method and system based on O2O data.
Background technology
At present, traditional commending system is generally based on the customer transaction data on line, according to the customer transaction number on line
According to the fancy grade for obtaining user, so as to be recommended according to the fancy grade of user, this way of recommendation usually only considers line
On customer transaction data, and without considering under factor under line, such as line service shop position and distance etc. information, for example, pushing away
The served distance user recommended is too remote, and user is likely to abandon consuming, so as to cause poor user experience.
The content of the invention
In view of this, it is an object of the invention to provide the recommendation method and system based on O2O data, can provide more smart
Accurate recommendation service, improves user experience.
In a first aspect, an embodiment of the present invention provides the recommendation method based on O2O data, the described method includes:
Capturing service data message, and the service data information is updated in preset time;
Consumption data information is counted, the consumption data information includes the number of users of each businessman consumption, same user exists
The consumption number of times of the number of users of different businessmans consumption and each user in different businessmans;
The number of users and the same user to each businessman's consumption is described in different businessman's consumption
Number of users is calculated, and obtains remaining profound similarity;
According to each user in the consumption number of times of the different businessmans, the interest-degree of the user is obtained;
According to the interest-degree of the user and the weight model of distance, the preference of the user is obtained.
With reference to first aspect, an embodiment of the present invention provides the first possible embodiment of first aspect, wherein, institute
State the number of users consumed to the number of users of each businessman's consumption and the same user in the different businessmans
Calculated, obtain remaining profound similarity, including:
The number of users and the same user to each businessman's consumption is described in different businessman's consumption
Number of users is calculated, and obtains the first matrix and the second matrix;
According to first matrix and second matrix, the remaining profound similarity is obtained.
The possible embodiment of with reference to first aspect the first, an embodiment of the present invention provides second of first aspect
Possible embodiment, wherein, it is described according to first matrix and second matrix, obtain the remaining profound similarity, bag
Include:
The remaining profound similarity is calculated according to the following formula:
Wherein, WuvFor the remaining profound similarity, N (u) ∩ N (v) are first matrix, | N (u) | × | N (v) | it is described
Second matrix.
With reference to first aspect, an embodiment of the present invention provides the third possible embodiment of first aspect, wherein, institute
The consumption number of times of each user of basis in the different businessmans are stated, obtaining the interest-degree of the user includes:
The interest-degree of the user is calculated according to the following formula:
Wherein, PujFor the interest-degree of the user, N (u) is the set for the article that the user likes, S (j, k) for be with
The set of k similar article j article, w are the similarities of article j and i, and r is interest of the user u to article i.
With reference to first aspect, an embodiment of the present invention provides the 4th kind of possible embodiment of first aspect, wherein, institute
Service data information is stated to further include including user data information, customer consumption data message and product data information, the method:
Judge whether the user data information or the product data information have renewal;
If the user data information or the product data information have renewal, to the user data information or institute
Product data information is stated to be updated or delete.
Second aspect, the embodiment of the present invention also provide the commending system based on O2O data, the system comprises:
First updating block, for capturing service data message, and to the service data information in preset time into
Row renewal;
Statistic unit, for counting consumption data information, the consumption data information includes the user of each businessman consumption
The consumption number of times of number of users that several, same user consumes in different businessmans and each user in different businessmans;
Computing unit, for the number of users to each businessman's consumption and the same user in the different business
The number of users of family's consumption is calculated, and obtains remaining profound similarity;
Interest-degree acquiring unit, in the consumption number of times of the different businessmans, being obtained according to each user
The interest-degree of the user;
Preference unit, for the interest-degree and the weight model of distance according to the user, obtains the inclined of the user
Good degree.
With reference to second aspect, an embodiment of the present invention provides the first possible embodiment of second aspect, wherein, institute
Stating computing unit includes:
Matrix acquisition module, for the number of users to each businessman's consumption and the same user it is described not
The number of users with businessman's consumption is calculated, and obtains the first matrix and the second matrix;
Remaining profound similarity acquisition module, for according to first matrix and second matrix, obtaining the remaining profound phase
Like degree.
With reference to the first possible embodiment of second aspect, an embodiment of the present invention provides second of second aspect
Possible embodiment, wherein, the remaining profound similarity acquisition module includes:
The remaining profound similarity is calculated according to the following formula:
Wherein, WuvFor the remaining profound similarity, N (u) ∩ N (v) are first matrix, | N (u) | × | N (v) | it is described
Second matrix.
With reference to second aspect, an embodiment of the present invention provides the third possible embodiment of second aspect, wherein, institute
Stating interest-degree acquiring unit includes:
The interest-degree of the user is calculated according to the following formula:
Wherein, PujFor the interest-degree of the user, N (u) is the set for the article that the user likes, S (j, k) for be with
The set of k similar article j article, w are the similarities of article j and i, and r is interest of the user u to article i.
With reference to second aspect, an embodiment of the present invention provides the 4th kind of possible embodiment of second aspect, wherein, institute
The system of stating further includes:
Judging unit, for judging whether the user data information or the product data information have renewal;
Second updating block, if having renewal for the user data information or the product data information, to institute
State user data information or the product data information is updated or deletes.
An embodiment of the present invention provides the recommendation method and system based on O2O data, including:Capturing service data message,
And service data information is updated in preset time;Consumption data information is counted, consumption data information includes each business
Consumption number of times of number of users, the number of users consumed in different businessmans of same user and each user of family's consumption in different businessmans;
The number of users and same user of each businessman consumption are calculated in the number of users that different businessmans consume, it is similar to obtain Yu Xuan
Degree;According to each user in the consumption number of times of different businessmans, the interest-degree of user is obtained;According to the interest-degree of user and away from
From weight model, obtain the preference of user, more accurately recommendation service can be provided, improve user experience.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution of the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, in describing below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
Put, other attached drawings can also be obtained according to these attached drawings.
Fig. 1 is the recommendation method flow diagram based on O2O data that the embodiment of the present invention one provides;
Fig. 2 is the flow chart of step S103 in the recommendation method based on O2O data that the embodiment of the present invention one provides;
Fig. 3 is API flow charts provided by Embodiment 2 of the present invention;
Fig. 4 is the commending system schematic diagram based on O2O data that the embodiment of the present invention three provides.
Icon:
The first updating blocks of 10-;20- statistic units;30- computing units;40- interest-degree acquiring units;50- preference lists
Member.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Lower all other embodiments obtained, belong to the scope of protection of the invention.
For ease of understanding the present embodiment, describe in detail below to the embodiment of the present invention.
Embodiment one:
Fig. 1 is the recommendation method flow diagram based on O2O data that the embodiment of the present invention one provides.
With reference to Fig. 1, this method comprises the following steps:
Step S101, capturing service data message, and the service data information is updated in preset time;
Here, service data information includes user data information, customer consumption data message and product data information;User
Data message, customer consumption data message and product data information specifically include following information.In the collection of service data information
During, it is necessary to judge service data information be first access also right and wrong access first.
If accessing first, disappeared using all information of ETL (or timed task JOB) batch capture C class users, C classes
Take all information, reward voucher and all information of affiliated businessman of data, being drawn into data warehouse (can be according to renewal time
Extract);
If right and wrong access first, daily zero point takes all information of C classes user's new registration yesterday, C classes consumption yesterday number
According to all information, reward voucher yesterday and all information of affiliated businessman, be drawn into data warehouse (can take out according to renewal time
Take);
If C classes user information has renewal in operation system, zero point it can take the data of renewal daily and update the data warehouse;
If operation system C classes reward voucher and affiliated Business Information have renewal and deletion, daily zero point renewal or deletion
Data warehouse, so as to ensure that the data of data warehouse are authentic and valid.
Step S102, counts consumption data information, and the consumption data information includes the number of users, same of each businessman consumption
The consumption number of times of number of users that one user consumes in different businessmans and each user in different businessmans;
Step S103, disappears the number of users and the same user of each businessman's consumption in the different businessmans
The number of users of expense is calculated, and obtains remaining profound similarity;
Step S104, according to each user in the consumption number of times of the different businessmans, obtains the user's
Interest-degree;
Step S105, according to the interest-degree of the user and the weight model of distance, obtains the preference of the user.
Here, user can be more reacted compared to traditional proposed algorithm RNN algorithms in the continuous of a certain stage hobby to become
Change process, accuracy rate higher.The proposed algorithm of the embodiment of the present invention is exactly to be calculated with reference to traditional coordination filter algorithm and RNN nerves
Method is combined, and more accurately recommendation service is provided for O2O application scenarios.
Wherein, O2O application scenarios are specially:With the popularization of mobile Internet, more and more users start to make at present
With mobile payment, mobile payment platform movement for trade company not only facilitates bank settlement, while can also provide more marketing
Service, for example reward voucher is provided to attract the client on periphery to go to get by trade company's wechat public platform, trade company's small routine, work as client
When using mobile payment can directly using the reward voucher got, while pay complete after payment platform according to user it
Preceding transaction record gives lead referral reward voucher.
Further, comprise the following steps with reference to Fig. 2, step S103:
Step S201, disappears the number of users and the same user of each businessman's consumption in the different businessmans
The number of users of expense is calculated, and obtains the first matrix and the second matrix;
Here, same user can be that different businessmans' statistics are disappeared by same user two-by-two in the number of users that different businessmans consume
The number of users taken.Specifically it can refer to Tables 1 and 2:
Table 1
Businessman 1 | Businessman 2 | Businessman 3 | Businessman 4 | Businessman 5 | |
C user | 5 | 4 | 4 | 2 | 0 |
Table 2
Businessman 1 | Businessman 2 | Businessman 3 | Businessman 4 | Businessman 5 | |
Businessman 1 | 0 | 3 | 3 | 1 | 0 |
Businessman 2 | 3 | 0 | 3 | 2 | 0 |
Businessman 3 | 2 | 3 | 0 | 4 | 0 |
Businessman 4 | 2 | 2 | 4 | 0 | 0 |
Businessman 5 | 0 | 0 | 1 | 1 | 0 |
In addition, consumption number of times of each user in different businessmans, the preference available for expression C user to different businessmans.
Referring in particular to table 3:
Table 3
C user | Businessman | Consumption number of times |
A | Businessman 1 | 2 |
A | Businessman 2 | 1 |
A | Businessman 3 | 1 |
A | Businessman 4 | 0 |
A | Businessman 5 | 0 |
B | Businessman 1 | 1 |
B | Businessman 2 | 1 |
B | Businessman 3 | 0 |
B | Businessman 4 | 0 |
B | Businessman 5 | 0 |
Step S202, according to the first matrix and the second matrix, obtains remaining profound similarity.
Further, step S202 includes:
According to formula (1) calculate more than profound similarity:
Wherein, WuvFor the remaining profound similarity, N (u) ∩ N (v) are first matrix, | N (u) | × | N (v) | it is described
Second matrix.Specifically it can refer to table 4:
Table 4
Businessman 1 | Businessman 2 | Businessman 3 | Businessman 4 | Businessman 5 | |
Businessman 1 | 0.47 | 0.63 | 0.71 | ||
Businessman 2 | 0.47 | 0.77 | 0.57 | ||
Businessman 3 | 0.63 | 0.77 | 0.89 | 0.45 | |
Businessman 4 | 0.71 | 0.57 | 0.89 | 0.5 | |
Businessman 5 | 0.45 | 0.5 |
Further, step S104 includes:
The interest-degree of user is calculated according to formula (2):
Wherein, PujFor the interest-degree of the user, N (u) is the set for the article that the user likes, S (j, k) for be with
The set of k similar article j article, w are the similarities of article j and i, and r is interest of the user u to article i.
Here, user u is a to k to the interest-degree=of article j and the similarity * user U of K most like article j article
The preference of article.
For example, the businessman that customer consumption is crossed is businessman 1 and businessman 2, the businessman not gone is businessman 3, businessman 4 and businessman 5.
So, the interest-degree of each businessman is respectively:
Interest-degree=1*0.47+1*0.63=1.1 of businessman 3;Interest-degree=1*0.57+1*0.89=1.46 of businessman 4;
Interest-degree=1*0+1*0.45=0.45 of businessman 5.Referring in particular to table 5:
Table 5
C user | Businessman | Interest-degree |
B | Businessman 3 | 1.1 |
B | Businessman 4 | 1.46 |
B | Businessman 5 | 0.45 |
In addition, considering the positional information of the businessman of user based on RNN, it is specially:Based on RNN model training sequence datas,
The interest-degree of user and the weight model S of distance are obtained, preference of the prediction user to new businessman is gone based on S, referring in particular to table
6:
Table 6
Further, service data information includes user data information, customer consumption data message and product data information,
The method further includes:
Judge whether user data information or the product data information have renewal;
If the user data information or the product data information have renewal, to the user data information or institute
Product data information is stated to be updated or delete.
Here, service data information is updated in preset time daily, preset time can be daily morning 1
Point, takes the successful C classes consumption data of payment (field that can be included, i.e. User ID and Merchant ID) of yesterday, so as to exclude business
The businessman that family closes, all reward voucher states all fail.Specifically table 7 is can refer to table 9:
Table 7
Using id | Wechat user id |
1 | A |
1 | B |
1 | C |
1 | D |
1 | E |
Table 8
Using id | Affiliated businessman | Longitude | Dimension |
1 | Businessman 1 | xxx | xxx |
1 | Businessman 2 | xxx | xxx |
1 | Businessman 3 | xxx | xxx |
1 | Businessman 4 | xxx | xxx |
1 | Businessman 5 | xxx | xxx |
Table 9
Using id | C user | Businessman | Date |
1 | A | Businessman 1 | |
1 | A | Businessman 1 | |
1 | A | Businessman 2 | |
1 | A | Businessman 3 | |
1 | B | Businessman 1 | |
1 | B | Businessman 2 | |
1 | C | Businessman 2 | |
1 | C | Businessman 3 | |
1 | C | Businessman 4 | |
1 | D | Businessman 4 | |
1 | D | Businessman 3 | |
1 | D | Businessman 1 | |
1 | E | Businessman 1 | |
1 | E | Businessman 2 | |
1 | E | Businessman 3 |
Embodiment two:
Fig. 3 is API flow charts provided by Embodiment 2 of the present invention.
With reference to Fig. 3, recommendation results Table A PI (Application Programming Interface, application programming
Interface) need to distinguish old and new users, if old user, and had consumer record under line before, then there can be recommendation results;
If new user, and there is no consumer record, then it can only do and recommend according to regular (being based on position).
This method comprises the following steps:
Step S201, API request entrance, input parameter is User ID, longitude where trade company, latitude, the quantity C recommended and
Province, city where businessman;
Step S202, inquires about the city where the user, all businesses lists to be recommended;
Step S203, judges whether the quantity of businessman in businesses lists is more than 0, if greater than 0, then n-th is taken from paging
Page data, verifies available reward voucher in all businessmans of nth page to be recommended;
Step S204, recommends available reward voucher list;
Whether step S205, judge list quantity not less than number C is recommended, if it is, carrying out final reward voucher row
Table;If it is not, then judging whether the current page number is equal to total page number;
Step S206, if it is, calculating based on the user apart from all businessmans apart from list;
Step S207, takes nth page data from paging, verifies available reward voucher in all businessmans of nth page to be recommended;
Step S208, recommends available reward voucher list and list quantity, so as to recommend final reward voucher list;
Step S209, if it is not, then taking the (n+1)th page data, and performs step S203;
Step S210, if the quantity of businessman is not more than 0 in businesses lists, judges whether longitude and latitude is empty;
Step S211, if sky, then takes the most hot coupons in city where C, and verify C to be recommended;
Step S212, judges whether list quantity is more than and is equal to number C, if it is, taking consequently recommended preferential of C bars
Certificate list;If it is not, then perform step S211;
Step S213, if longitude and latitude is not sky, calculates based on the user apart from all businessmans apart from list;
Step S214, takes nth page data in paging;
Step S215, verifies available reward voucher in all businessmans of nth page to be recommended;
Step S216, recommends available reward voucher list;
Step S217, judges whether list quantity is more than and equal to number C is recommended, if it is, C bars are as final before taking
The reward voucher list of recommendation;If it is not, then taking the (n+1)th page data, and perform step S214.
Embodiment three:
Fig. 4 is the commending system schematic diagram based on O2O data that the embodiment of the present invention three provides.
With reference to Fig. 4, which includes:
With reference to Fig. 4, which includes the first updating block 10, statistic unit 20, computing unit 30, interest-degree acquiring unit
40 and preference unit 50.
First updating block 10, for capturing service data message, and to the service data information in preset time
It is updated;
Statistic unit 20, for counting consumption data information, the consumption data information includes the use of each businessman consumption
The consumption number of times of number of users that amount, same user consume in different businessmans and each user in different businessmans;
Computing unit 30, for the number of users to each businessman's consumption and the same user in the difference
The number of users of businessman's consumption is calculated, and obtains remaining profound similarity;
Interest-degree acquiring unit 40, in the consumption number of times of the different businessmans, being obtained according to each user
To the interest-degree of the user;
Preference unit 50, for the interest-degree and the weight model of distance according to the user, obtains the user's
Preference.
Further, computing unit 30 includes:
Matrix acquisition module (not shown), for the number of users to each businessman's consumption and the same user
Calculated in the number of users of different businessman's consumption, obtain the first matrix and the second matrix;
Remaining profound similarity acquisition module (not shown), for according to first matrix and second matrix, obtaining institute
State remaining profound similarity.
Further, remaining profound similarity acquisition module (not shown) includes:
According to formula (1) calculate more than profound similarity.
Further, interest-degree acquiring unit 40 includes:
The interest-degree of the user is calculated according to formula (2):
Further, the system also includes:
Judging unit (not shown), for judging whether the user data information or the product data information have more
Newly;
Second updating block (not shown), if had more for the user data information or the product data information
Newly, then the user data information or the product data information are updated or deleted.
The embodiment of the present invention also provides a kind of electronic equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor, processor perform computer program when realize above-described embodiment provide based on O2O
The step of recommendation method of data.
The embodiment of the present invention also provides a kind of computer-readable recording medium, and meter is stored with computer-readable recording medium
Calculation machine program, the step of recommendation method based on O2O data of above-described embodiment is performed when computer program is run by processor.
The computer program product that the embodiment of the present invention is provided, including store the computer-readable storage of program code
Medium, the instruction that said program code includes can be used for performing the method described in previous methods embodiment, and specific implementation can be joined
See embodiment of the method, details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
With the specific work process of device, the corresponding process in preceding method embodiment is may be referred to, details are not described herein.
In addition, in the description of the embodiment of the present invention, unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected;Can
To be mechanical connection or be electrically connected;It can be directly connected, can also be indirectly connected by intermediary, Ke Yishi
Connection inside two elements.For the ordinary skill in the art, with concrete condition above-mentioned term can be understood at this
Concrete meaning in invention.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to contribute to the prior art or the part of the technical solution can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment the method for the present invention.
And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
In the description of the present invention, it is necessary to explanation, term " " center ", " on ", " under ", "left", "right", " vertical ",
The orientation or position relationship of the instruction such as " level ", " interior ", " outer " be based on orientation shown in the drawings or position relationship, merely to
Easy to describe the present invention and simplify description, rather than instruction or imply signified device or element must have specific orientation,
With specific azimuth configuration and operation, therefore it is not considered as limiting the invention.In addition, term " first ", " second ",
" the 3rd " is only used for description purpose, and it is not intended that instruction or hint relative importance.
Finally it should be noted that:Embodiment described above, is only the embodiment of the present invention, to illustrate the present invention
Technical solution, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those of ordinary skill in the art that:Any one skilled in the art
The invention discloses technical scope in, it can still modify the technical solution described in previous embodiment or can be light
It is readily conceivable that change, or equivalent substitution is carried out to which part technical characteristic;And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical solution of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention answers the scope of the claims of being subject to.
Claims (10)
- A kind of 1. recommendation method based on O2O data, it is characterised in that the described method includes:Capturing service data message, and the service data information is updated in preset time;Consumption data information is counted, the consumption data information includes the number of users of each businessman consumption, same user in difference Businessman consumption number of users and each user different businessmans consumption number of times;The user that the number of users and the same user to each businessman's consumption are consumed in the different businessmans Number is calculated, and obtains remaining profound similarity;According to each user in the consumption number of times of the different businessmans, the interest-degree of the user is obtained;According to the interest-degree of the user and the weight model of distance, the preference of the user is obtained.
- 2. the recommendation method according to claim 1 based on O2O data, it is characterised in that described to each businessman The number of users of consumption and the same user are calculated in the number of users of different businessman's consumption, obtain Yu Xuan Similarity, including:The user that the number of users and the same user to each businessman's consumption are consumed in the different businessmans Number is calculated, and obtains the first matrix and the second matrix;According to first matrix and second matrix, the remaining profound similarity is obtained.
- 3. the recommendation method according to claim 2 based on O2O data, it is characterised in that described according to first square Battle array and second matrix, obtain the remaining profound similarity, including:The remaining profound similarity is calculated according to the following formula:<mrow> <msub> <mi>W</mi> <mrow> <mi>u</mi> <mi>v</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>&cap;</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> <msqrt> <mrow> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>|</mo> <mo>&times;</mo> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> </msqrt> </mfrac> </mrow>Wherein, WuvFor the remaining profound similarity, N (u) ∩ N (v) are first matrix, | N (u) | × | N (v) | it is described second Matrix.
- 4. the recommendation method according to claim 1 based on O2O data, it is characterised in that each use of the basis In the consumption number of times of the different businessmans, obtaining the interest-degree of the user includes at family:The interest-degree of the user is calculated according to the following formula:<mrow> <msub> <mi>P</mi> <mrow> <mi>u</mi> <mi>j</mi> </mrow> </msub> <mo>=</mo> <mi>&Sigma;</mi> <mi>i</mi> <mo>&Element;</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>&cap;</mo> <mi>S</mi> <msup> <mrow> <mo>(</mo> <mi>j</mi> <mo>,</mo> <mi>k</mi> <mo>)</mo> </mrow> <mrow> <msub> <mi>W</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>r</mi> <mrow> <mi>u</mi> <mi>i</mi> </mrow> </msub> </mrow> </msup> </mrow>Wherein, PujFor the interest-degree of the user, N (u) is the set for the article that the user likes, and S (j, k) is is and article The set of k similar j article, w are the similarities of article j and i, and r is interest of the user u to article i.
- 5. the recommendation method according to claim 1 based on O2O data, it is characterised in that the service data information bag User data information, customer consumption data message and product data information, the method is included to further include:Judge whether the user data information or the product data information have renewal;If the user data information or the product data information have renewal, to the user data information or the thing Product data message is updated or deletes.
- A kind of 6. commending system based on O2O data, it is characterised in that the system comprises:First updating block, carries out more for capturing service data message, and to the service data information in preset time Newly;Statistic unit, for counting consumption data information, the consumption data information includes the number of users, same of each businessman consumption The consumption number of times of number of users that one user consumes in different businessmans and each user in different businessmans;Computing unit, disappears for the number of users to each businessman's consumption and the same user in the different businessmans The number of users of expense is calculated, and obtains remaining profound similarity;Interest-degree acquiring unit, in the consumption number of times of the different businessmans, being obtained described according to each user The interest-degree of user;Preference unit, for the interest-degree and the weight model of distance according to the user, obtains the preference of the user.
- 7. the commending system according to claim 6 based on O2O data, it is characterised in that the computing unit includes:Matrix acquisition module, for the number of users to each businessman's consumption and the same user in the different business The number of users of family's consumption is calculated, and obtains the first matrix and the second matrix;Remaining profound similarity acquisition module, for according to first matrix and second matrix, obtaining the remaining profound similarity.
- 8. the commending system according to claim 7 based on O2O data, it is characterised in that the remaining profound similarity obtains Module includes:The remaining profound similarity is calculated according to the following formula:<mrow> <msub> <mi>W</mi> <mrow> <mi>u</mi> <mi>v</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>&cap;</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> <msqrt> <mrow> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>|</mo> <mo>&times;</mo> <mo>|</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> </msqrt> </mfrac> </mrow>Wherein, WuvFor the remaining profound similarity, N (u) ∩ N (v) are first matrix, | N (u) | × | N (v) | it is described second Matrix.
- 9. the commending system according to claim 6 based on O2O data, it is characterised in that the interest-degree acquiring unit Including:The interest-degree of the user is calculated according to the following formula:<mrow> <msub> <mi>P</mi> <mrow> <mi>u</mi> <mi>j</mi> </mrow> </msub> <mo>=</mo> <mi>&Sigma;</mi> <mi>i</mi> <mo>&Element;</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>&cap;</mo> <mi>S</mi> <msup> <mrow> <mo>(</mo> <mi>j</mi> <mo>,</mo> <mi>k</mi> <mo>)</mo> </mrow> <mrow> <msub> <mi>W</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>r</mi> <mrow> <mi>u</mi> <mi>i</mi> </mrow> </msub> </mrow> </msup> </mrow>Wherein, PujFor the interest-degree of the user, N (u) is the set for the article that the user likes, and S (j, k) is is and article The set of k similar j article, w are the similarities of article j and i, and r is interest of the user u to article i.
- 10. the commending system according to claim 6 based on O2O data, it is characterised in that the system also includes:Judging unit, for judging whether the user data information or the product data information have renewal;Second updating block, if having renewal for the user data information or the product data information, to the use User data information or the product data information are updated or delete.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711236424.8A CN108022150B (en) | 2017-11-29 | 2017-11-29 | Recommendation method and system based on O2O data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711236424.8A CN108022150B (en) | 2017-11-29 | 2017-11-29 | Recommendation method and system based on O2O data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108022150A true CN108022150A (en) | 2018-05-11 |
CN108022150B CN108022150B (en) | 2021-07-06 |
Family
ID=62077925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711236424.8A Expired - Fee Related CN108022150B (en) | 2017-11-29 | 2017-11-29 | Recommendation method and system based on O2O data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108022150B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
CN111444439A (en) * | 2020-03-24 | 2020-07-24 | 北京航空航天大学 | Off-line store recommendation method, device and system and storage medium |
CN111612512A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Resource allocation method and device and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104063589A (en) * | 2014-06-16 | 2014-09-24 | 百度移信网络技术(北京)有限公司 | Recommendation method and system |
US20150019373A1 (en) * | 2013-07-09 | 2015-01-15 | International Business Machines Corporation | Providing a consumer advocate recommendation utilizing historic purchasing data |
CN104537095A (en) * | 2015-01-08 | 2015-04-22 | 吴锦锋 | Accurate information pushing method and system based on attraction model |
CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
CN105678578A (en) * | 2016-01-05 | 2016-06-15 | 重庆邮电大学 | Method for measuring user brand preference on the basis of online shopping behavior data |
CN106846132A (en) * | 2017-04-12 | 2017-06-13 | 杭州纳戒科技有限公司 | Merchandise news method for pushing, device and system |
-
2017
- 2017-11-29 CN CN201711236424.8A patent/CN108022150B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150019373A1 (en) * | 2013-07-09 | 2015-01-15 | International Business Machines Corporation | Providing a consumer advocate recommendation utilizing historic purchasing data |
CN104063589A (en) * | 2014-06-16 | 2014-09-24 | 百度移信网络技术(北京)有限公司 | Recommendation method and system |
CN104537095A (en) * | 2015-01-08 | 2015-04-22 | 吴锦锋 | Accurate information pushing method and system based on attraction model |
CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
CN105678578A (en) * | 2016-01-05 | 2016-06-15 | 重庆邮电大学 | Method for measuring user brand preference on the basis of online shopping behavior data |
CN106846132A (en) * | 2017-04-12 | 2017-06-13 | 杭州纳戒科技有限公司 | Merchandise news method for pushing, device and system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
CN111444439A (en) * | 2020-03-24 | 2020-07-24 | 北京航空航天大学 | Off-line store recommendation method, device and system and storage medium |
CN111612512A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Resource allocation method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108022150B (en) | 2021-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20120089461A1 (en) | Method for improved advertising on a mobile device | |
CN108416614A (en) | Sending method, device, electronic equipment and the storage medium of virtual objects | |
EP3353731A1 (en) | Systems and methods for locating merchant terminals based on transaction data | |
CN102667840A (en) | Context information utilizing systems, apparatus and methods | |
CN101814170A (en) | Control device and control method for releasing advertisement in advertisement releasing and controlling system | |
US20150220983A1 (en) | Systems and Methods of Determining Predictors Based on Transaction Data and Social Network Data | |
CN109325845A (en) | A kind of financial product intelligent recommendation method and system | |
JP6799097B2 (en) | Information processing device, control program, information processing method and information processing program | |
CN107807997A (en) | User's portrait building method, device and computing device based on big data | |
CN110033120A (en) | For providing the method and device that risk profile energizes service for trade company | |
CN110163724A (en) | Information-pushing method, device, server-side and system | |
CN108022150A (en) | recommendation method and system based on O2O data | |
US20140222535A1 (en) | Method and system for card marketing using expenditure details of an individual | |
WO2021036184A1 (en) | Method and system for recommending target transaction code laying area | |
US20160005060A1 (en) | Method and system for predicting spending on travel | |
JP7193514B2 (en) | Information processing device, information processing method, and program | |
CN114467106A (en) | Graph learning and automatic behavior coordination platform | |
KR20130107040A (en) | System and method for information providing service using contents combined with 2-dimensional code | |
JP2023011316A (en) | Providing device, providing method and providing program | |
CN104751234B (en) | A kind of prediction technique and device of user's assets | |
CN111464337B (en) | Resource allocation method and device and electronic equipment | |
CN111488407A (en) | Data processing method, system and device | |
KR101306141B1 (en) | Server for providing personalized discount service and method thereof | |
KR20110137274A (en) | Method for providing specialized service at merchant | |
KR101853476B1 (en) | A System Providing Payment Service By Virtual Point About Contract Deposit Cash In Advance |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210706 Termination date: 20211129 |
|
CF01 | Termination of patent right due to non-payment of annual fee |