CN109522475A - A kind of merchant recommendation method based on user's history consumption data - Google Patents

A kind of merchant recommendation method based on user's history consumption data Download PDF

Info

Publication number
CN109522475A
CN109522475A CN201811255149.9A CN201811255149A CN109522475A CN 109522475 A CN109522475 A CN 109522475A CN 201811255149 A CN201811255149 A CN 201811255149A CN 109522475 A CN109522475 A CN 109522475A
Authority
CN
China
Prior art keywords
user
consumption
merchant
location
score
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
Application number
CN201811255149.9A
Other languages
Chinese (zh)
Other versions
CN109522475B (en
Inventor
潘建
汤绍雄
奚家字
吴攀峰
王攀峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201811255149.9A priority Critical patent/CN109522475B/en
Publication of CN109522475A publication Critical patent/CN109522475A/en
Application granted granted Critical
Publication of CN109522475B publication Critical patent/CN109522475B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G06Q30/0282—Rating or review of business operators or products

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种基于用户历史消费数据的商家推荐方法，包括以下步骤：步骤1、用户设定搜索半径r，搜索关键词；步骤2、设备获取用户位置P0，并以周期T将关键词、r和P0发送给服务器；步骤3、根据P0搜索附近商家，得到附近半径r范围内的商家列表Lin；步骤4、选择Lin中第一个商家m；步骤5、如果m不存在，前往步骤6，否则计算m评分的平均分；步骤6、服务器根据计算的平均分从高到低排序输出的列表Lout，并将Lout返回给设备，结束。本方法提高综合评分的有效性，对于准确查找优质商家具有重大意义。

A merchant recommendation method based on user historical consumption data, including the following steps: Step 1, the user sets the search radius r, and searches for keywords; Step 2, the device obtains the user's position P 0 , and uses the period T to search keywords, r and P 0 Send to the server; step 3. Search for nearby merchants according to p 0 to get the list of merchants within the range R range of nearby R. Step 6, otherwise the average score of the M score is calculated; step 6. The server is based on the calculated average score of the list L OUT from high to low, and returns L OUT to the device to end. This method improves the effectiveness of comprehensive scoring, which is of great significance for accurately finding high-quality merchants.

Description

A kind of merchant recommendation method based on user's history consumption data
Technical field
The present invention relates to a kind of merchant recommendation methods based on user's history consumption data.
Technical background
Currently, exist on the market it is various purchase by group, shopping guide website and cell phone software, can be according to user location and right Neighbouring businesses lists are recommended user by the evaluation situation of businessman, and people play increasingly obtain by these channels out Relevant Business Information.
Meanwhile a group also generates therewith referred to as the netizen of " waterborne troops ", " waterborne troops " is to send out in a network for specific content Cloth specific information, the network writer that is employed.They are by common netizen or the consumer of disguising oneself as, by brushing single favorable comment etc. accidentally Normal users are led, therefore some businessmans employ " waterborne troops " to comment to brush, then just produce to keep oneself in the top False welcome businessman, and occupy list front row.What is more, some to go together businessmans to improve the ranking of oneself, asks People's malice carries out difference to other businessmans and comments.These behaviors violate the fairness of commercial competition, so that some really good quotient People's discovery that family can not be required.
Therefore, how to be commented based on the historical consumption data of user by the malice of the single favorable comment of brush of " waterborne troops " and the businessman that goes together are poor Etc. being filtered, to recommend to generate more true businesses lists, there is stronger real value.
Summary of the invention
In order to improve the confidence level of businessman's ranking, filtering brushes single favorable comment and comments data with maliciously poor, and consumer can search To the high-quality businessman for really needing searching, the present invention provides a kind of merchant recommendation methods based on user's history consumption data.
The technical scheme adopted by the invention is that:
A kind of merchant recommendation method based on user's history consumption data, comprising the following steps:
Step 1, user set search radius r, search key；
Step 2, equipment obtain user location P0, and with cycle T by keyword, radius r and P0It is sent to server；
Step 3, server are according to P0Businessman nearby is searched for, the businesses lists L within the scope of neighbouring radius r is obtainedin；
Step 4, selection LinIn first businessman m；
If step 5, m are not present, step 6 is gone to, otherwise calculates the average mark of m scoring:
The calculating process are as follows:
(5.1) businessman m nearest one month customer consumption data list L is obtainedm；
(5.2) by LmThe consumer record that middle user location and businessman m positional distance are greater than the set value d is deleted, and is calculated To the number of users n and consumption number of times C of each useri, i=1,2 ..., n；
(5.3) it calculates businessman m and amounts to sales volume Ctotal, according to user account grade weights omegagWith nearest one month Buy the scoring summation S for each user of interval computation that number dividesi, i=1,2 ..., n, wherein ωgIt is user account grade Weight, ω1、ω2And ω3It is to buy the weight of time intervals, and count the scoring summation S that a nearest month businessman obtainstotal, Are as follows:
(5.4) according to scoring total score StotalWith sales volume Ctotal, calculate the average mark S of businessman's scoringavg, are as follows:
(5.5) m is added to recommendation list LoutIn, and from LinDelete m, return step 4；
Step 6, server sort the list L of output from high to low according to the average mark of calculatingout, and by LoutIt returns to and sets It is standby.
Further, in the step 1, user uses equipment, and the equipment (such as computer, mobile phone) can pass through GPS Current specific location is obtained, and is able to access that internet, search radius r is that user is customized apart from size, and unit is kilometer, Distance d ' is according to calculation of longitude & latitude between two positions；
D '=arccos (sin (y0)*sin(y1)+cos(y0)*cos(ye)*cos(x0-x1))*Re,
Wherein, ReIt is earth radius, (x0,y0) and (x1,y1) be respectively two location points latitude and longitude coordinates.
Further, in the step 2, cycle T is the time pre-defined, and unit is minute.
Further, in the step 3, obtained businesses lists LinIn businessman from the near to the remote arranged according to distance Good sequence.
In the step 5, the information and customer consumption historical data of businessman has been stored in advance in the database, businessman Information includes Name & Location (longitude and latitude) information, and customer consumption historical data includes consumption account grade, the name of consumer Claim, consume position, consumption time and the scoring to businessman, the value d that customer consumption position differs setting with merchant location is used to Judge whether customer consumption position meets with merchant location, unit is rice, and scoring range is 0-5 points every time, is all integer, most The resulting average score of businessman retains a decimal afterwards.
Further, t1And t2Indicate the lower and upper limit of normal purchase time intervals, t3Indicate that excessively abnormal quantity purchase rises Initial value exceeds t3User scoring all 0, different weights omegas1, ω2And ω3For the score conversion of corresponding purchase time intervals Percentage, ω2>ω1≥ω3, ωgPercentage is converted for the corresponding score of different account grades, different consumption number of times sections are commented Dividing with the product of corresponding consumption number of times interval weight and account grade respective weights is that corresponding real consumption time intervals are commented Score value.
Technical concept of the invention are as follows: user's search key, server is according to equipment search radius obtained, user Position and keyword obtain businesses lists, and the historical consumption data for being then based on user is poor to the brush list favorable comment and malice of businessman Situations such as commenting is filtered, and to obtain user's scoring of relative efficiency, is finally counted according to the overall score of user and consumption number of times The average mark of businessman is calculated, and is sorted with this, comprehensive score validity is improved.
In the search process of user, timing is detected user position by this algorithm, for example is within 1 minute the period, if with Family position changes, and re-searches for businessman around, provides effective search result for user.
Beneficial effects of the present invention are mainly manifested in: filtering what some businessmans employed based on the historical consumption data of user Brush single favorable comment situation and colleague's malice be poor comments situation, effective user's evaluation is obtained with this, thus based on these evaluate come Calculate the ranking of businessman, the businessman that user can be helped accurately to have found out.
Detailed description of the invention
Fig. 1 is user's search behavior schematic diagram.
Fig. 2 is the flow chart that the present invention realizes businessman's sort method.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
Referring to Figures 1 and 2, a kind of merchant recommendation method based on user's history consumption data sets search half in user When diameter and search key, equipment obtains user position, and it is sent jointly to server, server root with keyword According to keyword and position acquisition businesses lists, is then calculated according to the nearest one month historical consumption data of user and count businessman Gained scoring finally calculates businessman's averaging of income scoring, and businesses lists according to marking and queuing and is returned to equipment, institute's commentary Estimate method the following steps are included:
Step 1, user set search radius r, search key.As shown in Figure 1, user can on different devices, Such as mobile phone, computer etc., it scans for.
In the present embodiment, 0.5 kilometer of search radius r value, keyword is dining room, current date value August 10 in 2018 Day.
Step 2, equipment obtain user current location P0(120.048749,30.234343), and with search radius r and close Keyword sends jointly to server；
Step 3, server are according to P0The businessman that radius nearby is r is searched for, list L is obtainedin.As shown in Figure 1, it is assumed that 3 businessmans are searched, are m respectively1, m2And m3, and the distance relationship shown in Fig. 1 represents actual range distant relationships, Lin As shown in table 1 (distance is calculated according to user current location and merchant location):
Table 1
Step 4-1, L is selectedinIn first businessman, m=m at this time1；
Step 5-1, the scoring average mark of m is calculated:
The comment list L of (5-1.1) acquisition mm, as shown in table 2:
Consumer's title Account grade Consume position Consumption time Scoring
U1-1 1 120.049036,30.233672 On August 6th, 2018 5
U1-2 3 120.049019,30.23109 On August 6th, 2018 4
U1-3 6 120.04918,30.233555 On August 5th, 2018 2
… … … … …
U1-n 2 120.04918,30.233555 On July 11st, 2018 5
Table 2
(5-1.2) is by LmThe consumer record of middle user location and businessman m positional distance greater than 100 meters is deleted, and is calculated To the number of users n=150 and consumption number of times C of each useri(i=1,2 ..., 150), as shown in table 3:
Table 3
(5-1.3) calculates m and amounts to sales volume Ctotal, according to user account grade weight and nearest purchase in one month time The scoring summation S for each user of interval computation that number dividesi(i=1,2 ..., 150), and count a nearest month businessman and obtain Scoring summation Stotal, are as follows:
Ctotal=2+3+5+ ...+20=350；
S1=25%*50%*5=0.625；
S2=80%*50%* (2+4+3)=3.6；
S3=50%*50%* (5+4+5)+50%*70%* (4+5)=6.55；
…
S150=0；
Stotal=0.625+3.6+6.55+ ...+0=1064；
The average score of (5-1.4) calculating m, it may be assumed that Savg=1064/350=3.0；
(5-1.5) is by m1It is added to Lout, and by m1From LinIt deletes, return step 4；
Step 4-2, L is selectedinIn first businessman, m=m at this time3；
Step 5-2, the scoring average mark of m is calculated:
The customer consumption historical data list L of (5-2.1) acquisition mm, as shown in table 4:
Consumer's title Account grade Consume position Consumption time Scoring
U3-1 3 120.047267,30.235045 On August 9th, 2018 5
U3-2 2 120.048138,30.231714 On August 9th, 2018 1
U3-3 4 120.052594,30.232876 On August 8th, 2018 4
… … … … …
U3-j 5 120.047267,30.235045 On July 11st, 2018 5
Table 4
(5-2.2) is by LmThe consumer record of middle user location and businessman m positional distance greater than 100 meters is deleted, and is calculated To the number of users n=120 and consumption number of times C of each useri(i=1,2 ..., 120), as shown in table 5:
Table 5
(5-2.3) calculates m and amounts to sales volume Ctotal, according to user account grade weight and nearest purchase in one month time The scoring summation S for each user of interval computation that number dividesi(i=1,2 ..., 120), and count a nearest month businessman and obtain Scoring summation Stotal, are as follows:
Ctotal=1+1+2+ ...+10=300；
S1=50%*50%*3=0.75；
S2=25%*50%*3=0.375；
S3=50%*50%* (4+4)=2；
…
S120=50%*50%* (4+3+3)+50%*70%* (3+3+3)+50%*30%* (4+3+3+4)=7.75；
Stotal=0.75+0.375+2+ ...+7.75=756；
The average score of (5-2.4) calculating m, it may be assumed that Savg=756/300=2.5；
(5-2.5) is by m3It is added to Lout, and from LinDelete m3, return step 4；
Step 4-3, L is selectedinIn first businessman, m=m at this time2；
Step 5-3, the scoring average mark of m is calculated:
The customer consumption historical data list L of (5-3.1) acquisition mm, as shown in table 6:
Consumer's title Account grade Consume position Consumption time Scoring
U2-1 4 120.048758,30.230708 On August 9th, 2018 5
U2-2 1 120.048758,30.230708 On August 9th, 2018 1
U2-3 5 120.048758,30.230708 On August 9th, 2018 5
… … … … …
U2-k 7 120.048399,30.230333 On July 13rd, 2018 5
Table 6
(5-3.2) is by LmThe consumer record of middle user location and businessman m positional distance greater than 100 meters is deleted, and is calculated To the number of users n=180 and consumption number of times C of each useri(i=1,2 ..., 180), as shown in table 7:
Table 7
(5-3.3) calculates m and amounts to sales volume Ctotal, according to user account grade weight and nearest purchase in one month time The scoring summation S for each user of interval computation that number dividesi(i=1,2 ..., 180), and count a nearest month businessman and obtain Scoring summation Stotal, are as follows:
Ctotal=1+1+2+ ...+10=330；
S1=50%*50%*5=1.25；
S2=0；
S3=50%*50%*5=1.25；
…
S180=80%*50%* (4+5)=3.6；
Stotal=1.25+0+1.25+ ...+3.6=1398；
The average score of (5-3.4) calculating m, it may be assumed that Savg=1398/330=4.2；
(5-3.5) is by m2It is added to Lout, and from LinMiddle deletion m2Return step 4；
Step 4-4, optional without businessman；
Step 5-4, step 6 is gone to；
Step 6, sort businesses lists according to average score, obtains LoutAnd export, as shown in Fig. 1 and table 8:
Businessman Distance (unit: kilometer) Position Average score
m2 0.48 120.048758,30.230708 4.2
m1 0.08 120.047267,30.235045 3.0
m3 0.12 120.048758,30.230708 2.5
Table 8
In the present embodiment, setting value d takes 100.
In the present embodiment, user account grade is divided into 1-3 grades, corresponding ωg25%, 50% and 80% is taken respectively, Different weight percentage, t can be taken under concrete condition1、t2And t3Respectively 4,7 and 15 can take different numbers in particular situations Value, corresponding ω1、ω2And ω3Respectively 50%, 70% and 30% can take different conversion percentages in particular situations Than.
In the present embodiment, since user can be moved to any position at any time, it is mutual that search equipment used need to have access at any time The ability of networking avoids server that from can not obtaining user location and can not carry out so as to obtain position and access server It calculates.
Those of ordinary skill in the art is it should be appreciated that the above content is intended merely to illustrate the present invention, and simultaneously It is non-to be used as limitation of the invention, as long as all will in spirit of the invention to variation, the modification of above example It falls within the scope of claims of the present invention.

Claims (6)

1.一种基于用户历史消费数据的商家推荐方法，其特征在于：所述方法包括以下步骤：1. A recommendation method based on user historical consumption data, which is characterized by: the method includes the following steps: 步骤1、用户设定搜索半径r，搜索关键词；Step 1. The user sets the search radius R, search for keywords; 步骤2、设备获取用户位置P0，并以周期T将关键词，半径r和P0发送给服务器；Step 2. The device obtains the user's position P 0 , and sends the keyword, radius r and P 0 to the server in a period T; 步骤3、服务器根据P0搜索附近商家，得到附近半径r范围内的商家列表Lin；Step 3, the server searches nearby merchants according to P 0 , and obtains a list of merchants L in within the radius r nearby; 步骤4、选择Lin中第一个商家m；Step 4. Select the first merchant m in Lin; 步骤5、如果m不存在，前往步骤6，否则计算m评分的平均分：Step 5. If M does not exist, go to step 6, otherwise calculate the average score of the M score: 所述计算过程为：The calculation process is: (5.1)获取商家m最近一个月的用户消费数据列表Lm；(5.1) Obtain the user consumption data list L m of the merchant m in the last month; (5.2)将Lm中用户位置与商家m位置距离大于设定值d的消费记录删除，并计算得到用户数量n以及每个用户的消费次数Ci，i＝1,2,…,n；(5.2) Delete the consumption records in L m where the distance between the user location and the merchant m location is greater than the set value d, and calculate the number n of users and the consumption times C i of each user, i=1,2,...,n; (5.3)计算商家m总计销售数量Ctotal，根据用户账户等级权重ωg和最近一个月的购买次数划分的区间计算每个用户的评分总和Si，i＝1,2,…,n，其中ωg是用户账户等级的权重，ω1、ω2和ω3是购买次数区间的权重，并统计最近一个月商家获得的评分总和Stotal，为：(5.3) Calculate the total sales quantity C total of merchant m, and calculate the sum of scores S i of each user according to the interval divided by the user account grade weight ω g and the number of purchases in the last month, i=1,2,...,n, where ω g is the weight of the user account level, ω 1 , ω 2 and ω 3 are the weights of the purchase frequency interval, and the sum of the scores S total obtained by the merchant in the last month is calculated as: (5.4)根据评分总分Stotal和销售数量Ctotal，计算商家评分的平均分Savg，为：(5.4) According to the total score S total and the sales quantity C total , calculate the average score S avg of the business rating, which is: (5.5)将m添加到推荐列表Lout中，并从Lin删除m,返回步骤4；(5.5) Add m to the recommendation list L out , and delete m from Lin, and return to step 4; 步骤6、服务器根据计算的平均分从高到低排序输出的列表Lout，并将Lout返回给设备。Step 6: The server sorts the output list L out from high to low according to the calculated average score, and returns L out to the device. 2.根据权利要求1所述一种基于用户历史消费数据的商家推荐方法，其特征在于：在所述步骤1中，用户使用设备，所述设备能够通过GPS获取当前的具体位置，且能够访问互联网，搜索半径r为用户自定义距离大小，单位为公里，两个位置间距离根据经纬度计算为；2. A method for recommending merchants based on user historical consumption data according to claim 1, characterized in that: in said step 1, the user uses a device that can obtain the current specific location through GPS, and can access The Internet, the search radius R is the user -defined distance, the unit is kilometers, and the distance between the two positions is calculated based on the latitude and longitude; d′＝arccos(sin(y0)*sin(y1)+cos(y0)*cos(ye)*cos(x0-x1))*Re，d'=arccos(sin(y 0 )*sin(y 1 )+cos(y 0 )*cos(y e )*cos(x 0 -x 1 ))*R e , 其中，Re是地球半径，(x0,y0)和(x1,y1)分别为两个位置点的经纬度坐标。Wherein, R e is the radius of the earth, (x 0 , y 0 ) and (x 1 , y 1 ) are the latitude and longitude coordinates of two locations respectively. 3.根据权利要求1或2所述一种基于用户历史消费数据的商家推荐方法，其特征在于：在所述步骤2中，周期T为预先定义好的时间，单位为分钟。3. A merchant recommendation method based on user historical consumption data according to claim 1 or 2, characterized in that: in said step 2, the period T is a predefined time, and the unit is minutes. 4.根据权利要求1或2所述一种基于用户历史消费数据的商家推荐方法，其特征在于：在所述步骤3中，得到的商家列表Lin中的商家已经根据距离由近到远排好序。4. According to claims 1 or 2, a business recommendation method based on user historical consumption data is characterized by: in the step 3 of the description, the merchants in the list of merchants have Good order. 5.根据权利要求1所述一种基于用户历史消费数据的商家推荐方法，其特征在于：在步骤5中，商家的信息和用户消费历史数据已经预先存储在数据库中，商家信息包括有名称和位置信息，用户消费历史数据包括有消费账号等级、消费者的名称、消费位置、消费时间以及对商家的评分，用户消费位置与商家位置相差设定的值d用来判断用户消费位置与商家位置是否符合，单位为米，且每次评分范围为0-5分，都是整数，最后商家所得的平均评分保留一位小数。5. A method for recommending merchants based on user history consumption data according to claim 1, characterized in that: in step 5, merchant information and user consumption history data have been pre-stored in the database, and merchant information includes name and Location information, user consumption history data includes consumption account level, consumer's name, consumption location, consumption time, and merchant ratings. The difference between the user's consumption location and the merchant's location is the set value d used to judge the user's consumption location and the merchant's location Whether it is in line, the unit is rice, and the score of each score is 0-5, which is an integer. In the end, the average score of the merchant retains a decimal. 6.根据权利要求5所述一种基于用户历史消费数据的商家推荐方法，其特征在于：在步骤5中，t1和t2表示正常购买次数区间的下限和上限，t3表示过于异常购买数量起始值，超出t3的用户评分全部为0，不同权重ω1，ω2和ω3为对应购买次数区间的分数折算百分比，ω2>ω1≥ω3，ωg为不同账号等级对应的分数折算百分比，不同消费次数区间的评分与对应消费次数区间权重以及账号等级对应权重的乘积为对应的实际消费次数区间评分值。6. According to claim 5, a business recommendation method based on user history consumption data is characterized in: in step 5, T 1 and T 2 represent the lower limit and upper limit of the number of normal purchases, T 3 indicates too abnormal purchases to buy too abnormal purchase. The starting value of the quantity, all the user scores exceeding the T 3 are 0 , different weights of ω 1 , ω 2 and ω 3 are the scores of the corresponding purchase number range. The corresponding scores are talleous, and the scores of different consumption range and corresponding consumption number range weights and account level corresponding weights are the corresponding actual actual consumption range scoring value.
CN201811255149.9A 2018-10-26 2018-10-26 Merchant recommendation method based on user historical consumption data Active CN109522475B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811255149.9A CN109522475B (en) 2018-10-26 2018-10-26 Merchant recommendation method based on user historical consumption data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811255149.9A CN109522475B (en) 2018-10-26 2018-10-26 Merchant recommendation method based on user historical consumption data

Publications (2)

Publication Number Publication Date
CN109522475A true CN109522475A (en) 2019-03-26
CN109522475B CN109522475B (en) 2022-04-22

Family

ID=65774057

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811255149.9A Active CN109522475B (en) 2018-10-26 2018-10-26 Merchant recommendation method based on user historical consumption data

Country Status (1)

Country Link
CN (1) CN109522475B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110032696A (en) * 2019-04-15 2019-07-19 拉扎斯网络科技（上海）有限公司 Display method, display device, electronic equipment and computer-readable storage medium
CN110415087A (en) * 2019-08-05 2019-11-05 江苏易汇聚软件科技有限公司 A kind of electronic commerce transaction system Internet-based
CN111160994A (en) * 2020-01-03 2020-05-15 北京明略软件系统有限公司 Customer loyalty evaluation method, apparatus, computer device and readable storage medium
CN111626825A (en) * 2020-05-28 2020-09-04 江苏金匮通供应链管理有限公司 System for cross-border e-commerce billing risk control
CN112070563A (en) * 2020-09-25 2020-12-11 汪洋 Market intelligent shopping guide system and method based on big data
CN112529505A (en) * 2020-12-21 2021-03-19 北京顺达同行科技有限公司 Illegal bill-swiping detection method and device and readable storage medium
CN113886722A (en) * 2021-12-08 2022-01-04 环球数科集团有限公司 Travel food recommendation method and device and computer equipment
CN116823409A (en) * 2023-08-29 2023-09-29 南京大数据集团有限公司 Intelligent screening method and system based on target search data
CN116911951A (en) * 2023-07-28 2023-10-20 北京数聚智连科技股份有限公司 E-commerce data analysis processing method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504043A (en) * 2014-12-16 2015-04-08 新余兴邦信息产业有限公司 Searching method and device for high-quality stores based on intelligent terminal
CN105025091A (en) * 2015-06-26 2015-11-04 南京邮电大学 A store recommendation method based on mobile user location
US20160379173A1 (en) * 2015-06-25 2016-12-29 Cardinal Health Technologies, Llc. Appointment scheduling system and methods
CN106408377A (en) * 2016-08-31 2017-02-15 广东华邦云计算股份有限公司 Shopping recommended method and system
TWM565841U (en) * 2018-05-23 2018-08-21 華南商業銀行股份有限公司 Appointed merchant recommendation system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504043A (en) * 2014-12-16 2015-04-08 新余兴邦信息产业有限公司 Searching method and device for high-quality stores based on intelligent terminal
US20160171594A1 (en) * 2014-12-16 2016-06-16 Xinyu Xingbang Information Industry Co., Ltd Method and a Device for Searching Premium Merchant Based on an Intelligent Terminal
US20160379173A1 (en) * 2015-06-25 2016-12-29 Cardinal Health Technologies, Llc. Appointment scheduling system and methods
CN105025091A (en) * 2015-06-26 2015-11-04 南京邮电大学 A store recommendation method based on mobile user location
CN106408377A (en) * 2016-08-31 2017-02-15 广东华邦云计算股份有限公司 Shopping recommended method and system
TWM565841U (en) * 2018-05-23 2018-08-21 華南商業銀行股份有限公司 Appointed merchant recommendation system

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110032696A (en) * 2019-04-15 2019-07-19 拉扎斯网络科技（上海）有限公司 Display method, display device, electronic equipment and computer-readable storage medium
CN110415087A (en) * 2019-08-05 2019-11-05 江苏易汇聚软件科技有限公司 A kind of electronic commerce transaction system Internet-based
CN110415087B (en) * 2019-08-05 2020-09-18 江苏易汇聚软件科技有限公司 Electronic commerce transaction system based on internet
CN111160994A (en) * 2020-01-03 2020-05-15 北京明略软件系统有限公司 Customer loyalty evaluation method, apparatus, computer device and readable storage medium
CN111626825A (en) * 2020-05-28 2020-09-04 江苏金匮通供应链管理有限公司 System for cross-border e-commerce billing risk control
CN112070563A (en) * 2020-09-25 2020-12-11 汪洋 Market intelligent shopping guide system and method based on big data
CN113191799A (en) * 2020-09-25 2021-07-30 汪洋 Market intelligence shopping guide system based on big data
CN113191799B (en) * 2020-09-25 2024-10-15 汪洋 Intelligent shopping guide system for mall based on big data
CN112529505B (en) * 2020-12-21 2024-02-27 北京顺达同行科技有限公司 Method and device for detecting illegal bill, and readable storage medium
CN112529505A (en) * 2020-12-21 2021-03-19 北京顺达同行科技有限公司 Illegal bill-swiping detection method and device and readable storage medium
CN113886722A (en) * 2021-12-08 2022-01-04 环球数科集团有限公司 Travel food recommendation method and device and computer equipment
CN113886722B (en) * 2021-12-08 2022-03-04 环球数科集团有限公司 Travel food recommendation method, device and computer equipment
CN116911951A (en) * 2023-07-28 2023-10-20 北京数聚智连科技股份有限公司 E-commerce data analysis processing method and system
CN116911951B (en) * 2023-07-28 2024-03-08 北京数聚智连科技股份有限公司 E-commerce data analysis processing method and system
CN116823409B (en) * 2023-08-29 2023-12-01 南京大数据集团有限公司 Intelligent screening method and system based on target search data
CN116823409A (en) * 2023-08-29 2023-09-29 南京大数据集团有限公司 Intelligent screening method and system based on target search data

Also Published As

Publication number Publication date
CN109522475B (en) 2022-04-22

Similar Documents

Publication Publication Date Title
CN109522475A (en) A kind of merchant recommendation method based on user's history consumption data
Peled et al. Entity matching in online social networks
JP5596152B2 (en) Information matching method and system on electronic commerce website
CN103455515B (en) User recommendation method and system in SNS (social networking services) community
CN103944932B (en) Search for, determine the method and server of active regions
JP5560367B2 (en) Method, system and server for managing dynamic information of friends in a network
WO2017121251A1 (en) Information push method and device
US8015172B1 (en) Method of conducting searches on the internet to obtain selected information on local entities and provide for searching the data in a way that lists local businesses at the top of the results
US20160171557A1 (en) Customer Insight System Architecture
CN103246670B (en) Microblogging sequence, search, methods of exhibiting and system
CN107491996B (en) Webpage advertisement putting method and system
KR100889230B1 (en) Shopping mall product search service system and method
CN105787025B (en) Network platform public account classification method and device
TW201305944A (en) Providing social product recommendations
CN104102648A (en) User behavior data based interest recommending method and device
KR101869815B1 (en) Method and apparatus for spotting fake news using collective intelligence
WO2021208583A1 (en) Recommendation information generation method and apparatus, electronic device and readable storage medium
CN105894089A (en) Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof
WO2019153889A1 (en) Implementation of geographical location service
CN107896153B (en) Traffic package recommendation method and device based on mobile user internet surfing behavior
Zeng et al. Can dissimilar users contribute to accuracy and diversity of personalized recommendation?
CN107146161A (en) An Insurance Retrieval Method Based on Category Selection
CN109190033A (en) A kind of user's friend recommendation method and system
CN104794635A (en) Cellphone model recommendation system based on collaborative filtering recommendation algorithm
CN105978729B (en) A kind of cellphone information supplying system and method based on user's internet log and position

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