CN111861139A - Merchant recommendation method and device and computer equipment - Google Patents
Merchant recommendation method and device and computer equipment Download PDFInfo
- Publication number
- CN111861139A CN111861139A CN202010598552.2A CN202010598552A CN111861139A CN 111861139 A CN111861139 A CN 111861139A CN 202010598552 A CN202010598552 A CN 202010598552A CN 111861139 A CN111861139 A CN 111861139A
- Authority
- CN
- China
- Prior art keywords
- merchant
- recommendation
- score
- recommended
- value 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012216 screening Methods 0.000 claims abstract description 53
- 238000005516 engineering process Methods 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000012552 review Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 230000009193 crawling Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 235000019633 pungent taste Nutrition 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a merchant recommendation method, a merchant recommendation device and computer equipment, relates to a block chain technology, and can solve the problems that the existing recommendation system is only limited to serve each C-end user, and cannot perform comprehensive screening and targeted recommendation, so that the generated recommendation result is not accurate enough. The method comprises the following steps: receiving a merchant recommendation request, wherein the merchant recommendation request carries merchant screening conditions; calculating the recommended value score of each merchant according to a preset index; determining the commercial tenant which meets the commercial tenant screening condition and has the recommended value score larger than a preset score threshold value as a target recommended commercial tenant; and generating a merchant recommendation list based on the recommendation value score of the target recommended merchant, and outputting the merchant recommendation list. The method and the device are suitable for determining the target recommendation users with higher recommendation value scores and meeting the merchant screening conditions, and automatically generating recommendations according to the target recommendation users.
Description
Technical Field
The present application relates to a block chain technology, and in particular, to a merchant recommendation method, apparatus, and computer device.
Background
With the rapid development of the internet, the information explosion era is gradually entered, and more services are provided by the internet platform. For example, for different users, the interests and hobbies are different, and when the individual needs of the user are not clear, each platform faces the problem of how to recommend merchants in which the user is interested, and the recommendation system is developed.
The existing recommendation systems are widely applied, such as e-commerce websites, music and life service platforms, but the recommendation systems are only limited to serve each C-end user and cannot perform comprehensive screening and targeted recommendation, so that the generated recommendation results are not accurate enough.
Disclosure of Invention
In view of this, the application provides a merchant recommendation method, a merchant recommendation device and a computer device, and mainly aims to solve the problems that the existing recommendation system is only limited to serve each C-end user, and cannot perform comprehensive screening and targeted recommendation, so that the generated recommendation result is not accurate enough.
According to an aspect of the present application, there is provided a merchant recommendation method, including:
receiving a merchant recommendation request, wherein the merchant recommendation request carries merchant screening conditions;
Calculating the recommended value score of each merchant according to a preset index;
determining the commercial tenant which meets the commercial tenant screening condition and has the recommended value score larger than a preset score threshold value as a target recommended commercial tenant;
and generating a merchant recommendation list based on the recommendation value score of the target recommended merchant, and outputting the merchant recommendation list.
According to another aspect of the present application, there is provided a merchant recommending apparatus, including:
the system comprises a receiving module, a selecting module and a processing module, wherein the receiving module is used for receiving a merchant recommending request which carries merchant screening conditions;
the calculation module is used for calculating the recommended value scores of all the merchants according to preset indexes;
the determining module is used for determining the commercial tenant which has the recommended value score larger than a preset score threshold and meets the commercial tenant screening condition as a target recommended commercial tenant;
and the output module is used for generating a merchant recommendation list based on the recommendation value score of the target recommended merchant and outputting the merchant recommendation list.
According to yet another aspect of the present application, there is provided a non-transitory readable storage medium having stored thereon a computer program which, when executed by a processor, implements the merchant recommendation determination method described above.
According to yet another aspect of the present application, there is provided a computer device comprising a non-volatile readable storage medium, a processor, and a computer program stored on the non-volatile readable storage medium and executable on the processor, the processor implementing the merchant recommendation method when executing the program.
By means of the technical scheme, compared with the current mode of generating merchant recommendations, the merchant recommendation method, the merchant recommendation device and the computer equipment provided by the application can determine merchants with recommendation value scores larger than a preset threshold and meeting merchant screening conditions as target recommended merchants by calculating the recommendation value scores of all merchants, further determine the target recommended merchants as recommended merchants matched with merchant recommendation requests, and output the target recommended merchants according to the high-low sequence of the recommendation value scores for targeted selection of users. According to the method and the system, the attributes of the merchants and the attributes of the positions of the merchants can be comprehensively considered, the recommendation indexes of the merchants are fully calculated from multiple aspects, and the accuracy of merchant recommendation can be guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application to the disclosed embodiment. In the drawings:
Fig. 1 is a schematic flowchart illustrating a merchant recommendation method according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating another merchant recommendation method provided by an embodiment of the application;
fig. 3 is a schematic structural diagram illustrating a merchant recommending apparatus according to an embodiment of the present application;
fig. 4 shows a schematic structural diagram of another merchant recommending apparatus provided in the embodiment of the present application.
Detailed Description
The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Aiming at the problems that the conventional recommendation system is only limited to serve each C-end user and cannot perform comprehensive screening and targeted recommendation, and the generated recommendation result is not accurate enough, the embodiment of the application provides a merchant recommendation method, as shown in fig. 1, the method comprises the following steps:
101. and receiving a merchant recommendation request, wherein the merchant recommendation request carries merchant screening conditions.
The executing body of this embodiment may be a merchant recommending system, configured to receive a merchant recommending request, screen out a target recommending user with a higher recommending index according to a merchant screening condition carried in the merchant recommending request, and feed back the target recommending user to the request sending end. It should be noted that, in the present application, the request sending end is not limited to each C-end user, but may also send a corresponding merchant recommendation request to the merchant recommendation system for each terminal system of each enterprise, both individuals and enterprises, so as to find out a target merchant that meets the individual personalized requirements or meets the screening requirements of the enterprise financial cooperation merchants.
It should be emphasized that, in order to further ensure the privacy and security of the merchant recommendation request, after receiving the merchant recommendation request, the block chain underlying platform may be used to perform validity verification on the merchant recommendation request, and perform operations such as relationship maintenance, risk prevention and control, and data encryption storage.
The block chain underlying platform may include processing modules such as user management, basic service, intelligent contract, operation monitoring and the like. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.
102. And calculating the recommended value scores of all the merchants according to preset indexes.
For this embodiment, in a specific application scenario, merchant information may be created by using a plurality of preset index dimensions, where the preset indexes may be: the method and the system have the advantages that people flow information, merchant evaluation information, regional popularity degree information and the like can be obtained, the attributes of merchants and the attributes of positions where the merchants are located can be comprehensively considered on the basis of a plurality of preset indexes, and the recommendation coefficients of the merchants are fully calculated, so that corresponding target recommended merchants can be screened out.
103. And determining the commercial tenant which has the recommended value score larger than a preset score threshold and meets the commercial tenant screening condition as a target recommended commercial tenant.
The preset scoring threshold may be set according to a specific application scenario and a screening requirement, which is not limited herein. For this embodiment, after calculating the recommended value score of each merchant, the recommended value score may be greater than a preset score threshold, and the merchant meeting the merchant screening condition is determined as the target recommended merchant for the request sending end to select.
104. And generating a merchant recommendation list based on the recommendation value score of the target recommended merchant, and outputting the merchant recommendation list.
For this embodiment, in a specific application scenario, because a plurality of determined target recommended merchants are often provided, in order to visually display a target recommended user and conveniently request a sending end to select a desired merchant with reference to a recommended value score, a recommendation list can be generated for the screened target recommended merchants according to the recommended value score, and then a recommendation list corresponding to the target recommended merchants is output.
By the merchant recommending method in the embodiment, merchants with recommended value scores larger than a preset threshold and meeting merchant screening conditions are determined as target recommended merchants by calculating the recommended value scores of the merchants, and the target recommended merchants are further determined as recommended merchants matched with the merchant recommending requests so that users can select the target recommended merchants in a targeted manner. According to the method and the system, the attributes of the merchants and the attributes of the positions of the merchants can be comprehensively considered, the recommendation indexes of the merchants are fully calculated from multiple aspects, and the accuracy of merchant recommendation can be guaranteed.
Further, as a refinement and an extension of the specific implementation of the foregoing embodiment, in order to fully illustrate the specific implementation process in this embodiment, another merchant recommendation method is provided, as shown in fig. 2, where the method includes:
201. and receiving a merchant recommendation request, wherein the merchant recommendation request carries merchant screening conditions.
The merchant screening condition is a key for screening out a target recommended merchant, different request sending ends can correspond to different merchant screening conditions, for example, when the request sending end is a personal terminal, a user may be used for screening dining restaurants, hotels living in, scenic spots and the like, and the corresponding merchant screening condition may include an area to be screened and a type of the target merchant to be screened; when the request sending end is an enterprise terminal, the enterprise may be used for screening collaborators, such as a bank searching for collaborating merchants for financial products, and the corresponding merchant screening conditions may include an area to be screened, a target merchant level, a target merchant operation scale, and the like.
202. And calculating the first recommended value score of each merchant under the first index according to a track space-time clustering algorithm.
When the first indicator is human traffic information, the embodiment step 202 may specifically include: dividing the map into areas to be detected according to the preset grid size; counting the number of staying persons of all merchants in the area to be detected within the same preset time period by utilizing a track space-time clustering algorithm; and determining the number of the staying persons as the first recommended value score of each merchant.
For the embodiment, as the number of the merchants is large, in order to better count, a map in the national scope can be divided into each area to be detected according to the preset grid size, and the recommended value scores of all the merchants are integrated and calculated through detection and identification of each area to be detected. The preset grid size may be preset in combination with a specific application scenario, for example, 100m × 100m may be set as one grid unit, and the map may be divided into each independent 100 × 100 area to be detected, so as to perform merchant analysis on each area to be detected.
Correspondingly, in order to utilize the trajectory space-time clustering algorithm to count the number of people staying in the same preset time period at each merchant in the area to be detected, the method specifically includes: determining the density clustering result of each user in a preset time period based on a preset clustering algorithm; and counting the number of the staying persons in the region of the corresponding commercial tenant of each commercial tenant in the preset time period by using the density clustering result.
Where clustering is an unsupervised machine learning technique involving grouping of data points, given a set of data points, a clustering algorithm can be used to classify each data point into a particular group. The user's trajectory is a collection of points, each containing information: time and longitude and latitude, which represent that a certain user visits a certain place at a certain time. These places can be classified into several specific groups by a clustering algorithm, each group representing the active area of the user. The main purpose of clustering the track points is to identify the staying area of each user and exclude the places where the user stays briefly, that is, the areas with high density are the expected results and the areas with low density are the expected results, so that the density clustering is most suitable for the track clustering. In this embodiment, the preset clustering algorithm may adopt a DBSCAN density clustering algorithm, and the density-based method is characterized by not depending on the distance but depending on the density, thereby overcoming the disadvantage that the distance-based algorithm can only find "spherical" clusters. The core idea is to add the density of points in a region to its neighboring clusters whenever it is above a certain threshold.
Correspondingly, after the density clustering result of each user in the preset time period is determined by adopting a DBSCAN density clustering algorithm, the staying area of the user can be further determined by utilizing the density clustering result. The track of a person is divided into two situations, namely a dense area (a plurality of areas are possible), a scattered area, the dense area is a place which is frequently visited by the user, such as a shopping mall, a work unit and the like, and the scattered area is a place where the user stays for a short time and is not counted in the stay area statistics. The prediction of the parking area may reflect the traffic information around each business, and if there are more parking users around the business, it means that the business is more likely to be accessed. The scoring of the spatio-temporal clustering part of each merchant can be defined as the number of staying persons within the range of 100 meters of the merchant, so that the region of the merchant corresponding to the merchant can be set to be within the range of 100 meters, and correspondingly, the calculation formula of the first recommendation value scoring can be as follows:
Score1(poi)＝count(staypoint|dis(staypoint-poi)≤100m)。
203. and calculating a second recommended value score of each merchant under the second index based on the web crawler data.
For this embodiment, in a specific application scenario, when the second index is merchant evaluation information, step 203 in the embodiment may specifically include: acquiring merchant evaluation information of each merchant based on a web crawler technology, wherein the merchant evaluation information comprises merchant star scores, merchant matching scores and merchant comment scores; determining weights corresponding to the merchant star score, the merchant matching score and the merchant comment score by using a parameter optimization algorithm so that a correlation coefficient of the merchant evaluation information and the second recommendation value score is greater than a preset threshold value; and calculating a weighted sum of the merchant star score, the merchant matching score and the merchant comment score, and determining the weighted sum as a second recommendation value score.
For the embodiment, in a specific application scenario, the calculation formula of the second recommendation value score may be set as: score2The parameter optimizing scheme of the application adopts a correlation coefficient index, gives an optimizing space of three parameters and continuously iterates until the merchant star level (poi), the merchant matching Score (poi) and the merchant comment Score (poi) are compared with the Score2The correlation coefficients of (poi) are all greater than 0.6, and in a specific application scenario, that is, the preset threshold in this embodiment is set to 0.6, and finally, a is 3, b is 1, and c is 1. The calculation formula corresponding to the second recommendation value score is: score2(poi) ═ 3 × level (poi) + (score (poi) + review (poi) ((poi)),. level (poi)) scores 0-5 stars obtained by crawling, score (poi) scores 0-10, review (poi) scores a composite of review count and rating type, i.e., review (poi) ═ f (review _ count) > g (review _ type), where f (review _ count) is the review count, g (review _ type) is the rating type ratio, which may reflect the degree of hotness of one merchant, and the greater the number of merchants traffic, the greater the rating number, the review type may reflect the quality of service of one merchant, the greater the rating ratio (goodper) is more likely to attract customers, and the greater the poor rating ratio (bayer) is less likely to attract customers.
In a specific application scenario, scores corresponding to different comment numbers and different comment type fractions may be defined individually according to actual needs, and may be set as:
204. and determining a third recommended value score of each merchant under a third index by calculating the position entropy.
For this embodiment, in a specific application scenario, when the third index is the regional popularity, the step 204 in the embodiment may specifically include: calculating the position entropy of each merchant through a first calculation formula; determining the location entropy as a third recommendation value score.
Wherein the first calculation formula is:
Accordingly, the position entropy reflects the degree of hotness of a certain area, and the larger the position entropy is, the more hotness of the position is indicated, so the calculation formula of the third recommendation value score can be set as: score3(poi)＝Hl。
205. And determining the accumulated sum of the first recommended value score, the second recommended value score and the third recommended value score as the recommended value score of the corresponding merchant.
For this embodiment, in a specific application scenario, after the first recommended value Score, the second recommended value Score, and the third recommended value Score corresponding to each merchant are obtained through calculation, the final recommended value Score of the merchant, that is, Score (poi) Score, may be further obtained through calculation 1(poi)+Score2(poi)+Score3(poi)。
206. And determining the commercial tenant which has the recommended value score larger than a preset score threshold and meets the commercial tenant screening condition as a target recommended commercial tenant.
For this embodiment, in a specific application scenario, when the merchant screening condition includes an area to be screened and a target merchant type to be screened, the step 206 of the embodiment may specifically include: screening out first commercial tenants with recommended value scores larger than a preset score threshold; and determining a first merchant matched with the type of the target merchant in the area to be screened as a target recommended merchant.
Correspondingly, through the embodiment step 202-205, the final recommended value score of each merchant can be calculated, and then the screening of the target recommended merchants can be performed in merchants with higher recommended value scores based on the merchant screening conditions, and at this time, different recommendation results can be obtained according to different merchant screening conditions corresponding to different application scenarios. For example, when the merchant recommendation request is sent by a personal terminal device, the merchant screening condition may include an area to be screened and a target merchant type to be screened, if the area to be screened is within 1km of the shanghai rainbow bridge station, and the target merchant type is a cafe, the first merchant whose final recommendation value score is greater than a preset score threshold may be further screened, and the first merchant whose location is within 1km of the shanghai rainbow bridge station and merchant type is the cafe is determined as the target recommendation merchant.
As another application scenario of this embodiment, when a target merchant is screened for a bank financial product, since the level of the merchant, the consumption level of the user, and the demanders of the financial product are different, the financial product, the merchant, and the user need to be in one-to-one correspondence to form different consumption groups. Specifically, the merchant screening conditions can be set as a per-person consumption price interval and a merchant operation scale, namely, per-person consumption and the merchant operation scale correspond to financial products, and merchants with the per-person consumption price interval and the merchant operation scale matched with the value attributes of the financial products are selected as target recommended merchants. For example, the user consumption level of the large loan is higher, so the target recommended merchants needing to be screened out are merchants with higher grade; the consumption level of the small loan is general, so the target recommended merchant needing to be screened is a merchant of a general grade.
207. And generating a merchant recommendation list based on the recommendation value score of the target recommended merchant, and outputting the merchant recommendation list.
For this embodiment, in a specific application scenario, when a target recommended merchant is screened, the top five merchants to be screened in the national recommendation list may be intercepted, and each merchant marks a corresponding recommendation index, where the recommendation index is a recommendation value score calculated correspondingly, so that the request sending end may screen the target merchant according to its own needs.
By means of the merchant recommending method, the recommended value scores of all merchants can be calculated from three dimensions, namely a first recommended value score corresponding to the pedestrian volume information is calculated through a track space-time clustering algorithm, a second recommended value score corresponding to the merchant evaluation information is calculated based on the obtained comment data obtained through crawling, a third recommended value score corresponding to the regional popularity degree is obtained through calculating the position entropy, and the recommended value scores of all merchants are further obtained through integration of the three recommended value scores. And determining the commercial tenant of which the recommended value score is larger than a preset score threshold value and which meets the commercial tenant screening condition as a target recommended commercial tenant, and generating the recommendation. In the application, the self attribute and the position attribute of the merchant are comprehensively considered based on the three indexes, so that the recommendation index of each merchant can be comprehensively determined. The target recommended merchants are further determined in a targeted mode according to the merchant screening conditions, and the target merchant recommendation list is output according to the recommendation value scores, so that the merchant recommendation accuracy is guaranteed, the selection of a user is facilitated, the merchant screening operation is simplified, and the screened merchants can better meet the personalized requirements of the user.
Further, as a specific implementation of the method shown in fig. 1 and fig. 2, an embodiment of the present application provides a merchant recommending apparatus, as shown in fig. 3, the apparatus includes: a receiving module 31, a calculating module 32, a determining module 33, and an output module 34;
The receiving module 31 is configured to receive a merchant recommendation request, where the merchant recommendation request carries merchant screening conditions;
the calculation module 32 is used for calculating the recommended value scores of all the merchants according to preset indexes;
the determining module 33 is configured to determine, as a target recommended merchant, a merchant whose recommended value score is greater than a preset score threshold and which meets the merchant screening condition;
and the output module 34 is configured to generate a merchant recommendation list based on the recommendation value score of the target recommended merchant, and output the merchant recommendation list.
In a specific application scenario, the preset indexes at least include a first index, a second index, and a third index, and in order to calculate and obtain the recommended value score of each merchant, as shown in fig. 4, the calculation module 32 may specifically include: a first calculation unit 321, a second calculation unit 322, a third calculation unit 323, a determination unit 324;
the first calculating unit 321 is specifically configured to calculate, according to a trajectory spatiotemporal clustering algorithm, a first price recommendation score recommendation value score of each merchant under a first index;
the second calculating unit 322 is specifically configured to calculate, based on the web crawler data, a second value recommendation score recommendation value score for each merchant under the second index;
The third calculating unit 323 is specifically configured to determine, by calculating the position entropy, a third-value recommendation score recommendation value score of each merchant under the third index;
the determining unit 324 may be specifically configured to determine an accumulated sum of the first value recommendation score, the second value recommendation score, and the third value recommendation score as the recommendation value score of the corresponding merchant.
Correspondingly, when the first index is the human traffic information, in order to calculate the first recommended value score of each merchant under the first index, the first calculating unit 321 is specifically configured to divide the map into each to-be-detected area according to the preset grid size; counting the number of staying persons of all merchants in the area to be detected within the same preset time period by utilizing a track space-time clustering algorithm; and determining the number of the staying persons as the first recommended value score of each merchant.
In a specific application scenario, in order to utilize a track spatio-temporal clustering algorithm to count the number of people staying in the same preset time period for each merchant in the region to be detected, the first calculating unit 321 is specifically configured to determine a density clustering result of each user in the preset time period based on the preset clustering algorithm; and counting the number of the staying persons in the region of the corresponding commercial tenant of each commercial tenant in the preset time period by using the density clustering result.
Correspondingly, when the second index is merchant evaluation information, in order to calculate a second recommended value score of each merchant under the second index, the second calculating unit 322 may be specifically configured to obtain merchant evaluation information of each merchant based on a web crawler technology, where the merchant evaluation information includes a merchant star score, a merchant matching score, and a merchant comment score; determining weights corresponding to the merchant star score, the merchant matching score and the merchant comment score by using a parameter optimization algorithm so that a correlation coefficient of the merchant evaluation information and the second recommendation value score is greater than a preset threshold value; and calculating a weighted sum of the merchant star score, the merchant matching score and the merchant comment score, and determining the weighted sum as a second recommendation value score.
In a specific application scenario, when the third index is the regional popularity, in order to calculate a third recommended value score of each merchant under the third index, the third calculating unit 323 may be specifically configured to calculate a position entropy of each merchant through a first calculating formula; determining the location entropy as a third recommended value score; the first calculation formula is:
Correspondingly, in order to determine the target recommended merchant when the merchant screening condition corresponds to the area to be screened and the target merchant type to be screened, as shown in fig. 4, the determining module 33 may specifically include: a screening unit 331, a determination unit 332;
the screening unit 331 is specifically configured to screen out a first merchant whose recommended value score is greater than a preset score threshold;
the determining unit 332 may be specifically configured to determine, as the target recommended merchant, a first merchant in the area to be screened, which is matched with the target merchant type.
It should be noted that other corresponding descriptions of the functional units related to the merchant recommending apparatus provided in this embodiment may refer to the corresponding descriptions in fig. 1 to fig. 2, and are not repeated herein.
Based on the above-mentioned methods shown in fig. 1 to fig. 2, correspondingly, the present embodiment further provides a non-volatile storage medium, on which computer readable instructions are stored, and the computer readable instructions, when executed by a processor, implement the above-mentioned merchant recommendation method shown in fig. 1 to fig. 2.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present application.
Based on the method shown in fig. 1 to fig. 2 and the virtual device embodiments shown in fig. 3 and fig. 4, in order to achieve the above object, the present embodiment further provides a computer device, where the computer device includes a storage medium and a processor; a nonvolatile storage medium for storing a computer program; a processor for executing a computer program to implement the merchant recommendation method as described above in fig. 1-2.
Optionally, the computer device may further include a user interface, a network interface, a camera, Radio Frequency (RF) circuitry, sensors, audio circuitry, a WI-FI module, and so forth. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
It will be understood by those skilled in the art that the present embodiment provides a computer device structure that is not limited to the physical device, and may include more or less components, or some components in combination, or a different arrangement of components.
The nonvolatile storage medium can also comprise an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the computer device described above, supporting the operation of information handling programs and other software and/or programs. The network communication module is used for realizing communication among components in the nonvolatile storage medium and communication with other hardware and software in the information processing entity device.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and can also be implemented by hardware.
By applying the technical scheme, compared with the prior art, the recommendation value scores of all the merchants can be calculated from three dimensions, namely a first recommendation value score corresponding to the pedestrian flow information is calculated through a track space-time clustering algorithm, a second recommendation value score corresponding to the merchant evaluation information is calculated based on the obtained comment data obtained through crawling, a third recommendation value score corresponding to the regional enthusiasm degree is obtained through calculating the position entropy, and the recommendation value scores of all the merchants are further obtained through integration of the three recommendation value scores. And determining the commercial tenant of which the recommended value score is larger than a preset score threshold value and which meets the commercial tenant screening condition as a target recommended commercial tenant, and generating the recommendation. In the application, the self attribute and the position attribute of the merchant are comprehensively considered based on the three indexes, so that the recommendation index of each merchant can be comprehensively determined. The target recommended merchants are further determined in a targeted mode according to the merchant screening conditions, and the target merchant recommendation list is output according to the recommendation value scores, so that the merchant recommendation accuracy is guaranteed, the selection of a user is facilitated, the merchant screening operation is simplified, and the screened merchants can better meet the personalized requirements of the user.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.
Claims (10)
1. A merchant recommendation method, comprising:
receiving a merchant recommendation request, wherein the merchant recommendation request carries merchant screening conditions;
calculating the recommended value score of each merchant according to a preset index;
determining the commercial tenant which meets the commercial tenant screening condition and has the recommended value score larger than a preset score threshold value as a target recommended commercial tenant;
And generating a merchant recommendation list based on the recommendation value score of the target recommended merchant, and outputting the merchant recommendation list.
2. The method according to claim 1, wherein the preset indexes at least include a first index, a second index and a third index, and the calculating the recommended value score of each merchant according to the preset indexes comprises:
calculating a first recommended value score of each merchant under the first index according to a track space-time clustering algorithm;
calculating a second recommended value score of each merchant under a second index based on the web crawler data;
determining a third recommended value score of each merchant under a third index by calculating the position entropy;
and determining the accumulated sum of the first recommended value score, the second recommended value score and the third recommended value score as the recommended value score of the corresponding commercial tenant.
3. The method of claim 2, wherein the first index is human traffic information, and the calculating the first recommended value score of each merchant according to the trajectory spatiotemporal clustering algorithm under the first index includes:
dividing the map into areas to be detected according to the preset grid size;
counting the number of staying persons of each merchant in the area to be detected within the same preset time period by utilizing a track space-time clustering algorithm;
And determining the number of the staying persons as a first recommended value score of each merchant.
4. The method according to claim 3, wherein the counting the number of remaining merchants in the area to be detected within the same preset time period by using a track spatiotemporal clustering algorithm comprises:
determining the density clustering result of each user in a preset time period based on a preset clustering algorithm;
and counting the number of the staying persons in the region of the commercial tenant corresponding to each commercial tenant in the preset time period by using the density clustering result.
5. The method according to claim 2, wherein the second index is merchant evaluation information, and the calculating a second recommended value score of each merchant under the second index based on the web crawler data comprises:
acquiring merchant evaluation information of each merchant based on a web crawler technology, wherein the merchant evaluation information comprises merchant star scores, merchant matching scores and merchant comment scores;
determining weights corresponding to the merchant star score, the merchant matching score and the merchant comment score by using a parameter optimization algorithm so that a correlation coefficient of the merchant evaluation information and a second recommendation value score is greater than a preset threshold;
Calculating a weighted sum of the merchant star score, the merchant matching score and the merchant review score, and determining the weighted sum as the second recommended value score.
6. The method of claim 2, wherein the third index is regional popularity, and the determining a third recommended value score for each merchant under the third index by calculating location entropy comprises:
calculating the position entropy of each merchant through a first calculation formula;
determining the location entropy as the third recommendation value score;
the first calculation formula is:
7. The method according to claim 2, wherein the merchant screening condition includes an area to be screened and a target merchant type to be screened, and the determining that the merchant meeting the merchant screening condition is a target recommended merchant that the recommended value score is greater than a preset score threshold includes:
screening out first commercial tenants with the recommended value scores larger than a preset score threshold;
And determining a first merchant matched with the target merchant type in the area to be screened as a target recommended merchant.
8. A merchant recommendation device, comprising:
the system comprises a receiving module, a selecting module and a processing module, wherein the receiving module is used for receiving a merchant recommending request which carries merchant screening conditions;
the calculation module is used for calculating the recommended value scores of all the merchants according to preset indexes;
the determining module is used for determining the commercial tenant which has the recommended value score larger than a preset score threshold and meets the commercial tenant screening condition as a target recommended commercial tenant;
and the output module is used for generating a merchant recommendation list based on the recommendation value score of the target recommended merchant and outputting the merchant recommendation list.
9. A non-transitory readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the merchant recommendation method as recited in any one of claims 1 to 7.
10. A computer device comprising a non-volatile readable storage medium, a processor, and a computer program stored on the non-volatile readable storage medium and executable on the processor, wherein the processor implements the merchant recommendation method as recited in any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598552.2A CN111861139A (en) | 2020-06-28 | 2020-06-28 | Merchant recommendation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598552.2A CN111861139A (en) | 2020-06-28 | 2020-06-28 | Merchant recommendation method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111861139A true CN111861139A (en) | 2020-10-30 |
Family
ID=72988566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010598552.2A Pending CN111861139A (en) | 2020-06-28 | 2020-06-28 | Merchant recommendation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861139A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360790A (en) * | 2021-06-08 | 2021-09-07 | 口碑(上海)信息技术有限公司 | Information recommendation method and device and electronic equipment |
| CN113477548A (en) * | 2021-07-26 | 2021-10-08 | 北京沃东天骏信息技术有限公司 | Article screening device and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243815A1 (en) * | 2007-03-30 | 2008-10-02 | Chan James D | Cluster-based assessment of user interests |
| KR20120037597A (en) * | 2010-10-12 | 2012-04-20 | 에스케이플래닛 주식회사 | System and method for recommending shop based on user's location |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended commercial tenants |
| CN107368483A (en) * | 2016-05-11 | 2017-11-21 | 阿里巴巴集团控股有限公司 | Information recommendation method, device and server |
| CN108985898A (en) * | 2018-07-12 | 2018-12-11 | 广东工业大学 | A kind of place methods of marking, device and computer readable storage medium |
| CN109471984A (en) * | 2018-10-17 | 2019-03-15 | 浙江口碑网络技术有限公司 | Shop recommended method and device |
| CN109697657A (en) * | 2018-12-27 | 2019-04-30 | 厦门快商通信息技术有限公司 | A kind of dining recommending method, server and storage medium |
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN110942344A (en) * | 2019-11-22 | 2020-03-31 | 汉海信息技术(上海)有限公司 | Method, device, equipment and storage medium for generating food recommendation list |
-
2020
- 2020-06-28 CN CN202010598552.2A patent/CN111861139A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243815A1 (en) * | 2007-03-30 | 2008-10-02 | Chan James D | Cluster-based assessment of user interests |
| KR20120037597A (en) * | 2010-10-12 | 2012-04-20 | 에스케이플래닛 주식회사 | System and method for recommending shop based on user's location |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended commercial tenants |
| CN107368483A (en) * | 2016-05-11 | 2017-11-21 | 阿里巴巴集团控股有限公司 | Information recommendation method, device and server |
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN108985898A (en) * | 2018-07-12 | 2018-12-11 | 广东工业大学 | A kind of place methods of marking, device and computer readable storage medium |
| CN109471984A (en) * | 2018-10-17 | 2019-03-15 | 浙江口碑网络技术有限公司 | Shop recommended method and device |
| CN109697657A (en) * | 2018-12-27 | 2019-04-30 | 厦门快商通信息技术有限公司 | A kind of dining recommending method, server and storage medium |
| CN110942344A (en) * | 2019-11-22 | 2020-03-31 | 汉海信息技术(上海)有限公司 | Method, device, equipment and storage medium for generating food recommendation list |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360790A (en) * | 2021-06-08 | 2021-09-07 | 口碑(上海)信息技术有限公司 | Information recommendation method and device and electronic equipment |
| CN113477548A (en) * | 2021-07-26 | 2021-10-08 | 北京沃东天骏信息技术有限公司 | Article screening device and method |
| CN113477548B (en) * | 2021-07-26 | 2023-09-01 | 北京沃东天骏信息技术有限公司 | Article screening device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3320512B1 (en) | Mobile attribute time-series profiling analytics | |
| Gerell | Bus stops and violence, are risky places really risky? | |
| US20190045331A1 (en) | Systems and Methods for Using Geo-Blocks and Geo-Fences to Discover Lookalike Mobile Devices | |
| US8756011B2 (en) | Determining locations of interest based on user visits | |
| Zhou et al. | A commuting spectrum analysis of the jobs–housing balance and self-containment of employment with mobile phone location big data | |
| US20050222829A1 (en) | Method and system for forecasting events and results based on geospatial modeling | |
| JP6276106B2 (en) | Decision support system and decision support method | |
| US9846887B1 (en) | Discovering neighborhood clusters and uses therefor | |
| CN106101224A (en) | Identify the method and device of the classification of user geographic location | |
| US10542105B2 (en) | Geo-locating individuals based on a derived social network | |
| Agryzkov et al. | Analysing successful public spaces in an urban street network using data from the social networks Foursquare and Twitter | |
| CN112861972A (en) | Site selection method and device for exhibition area, computer equipment and medium | |
| Pulugurtha et al. | Modeling annual average daily traffic with integrated spatial data from multiple network buffer bandwidths | |
| CN111861139A (en) | Merchant recommendation method and device and computer equipment | |
| Hu et al. | Prioritizing disaster mapping tasks for online volunteers based on information value theory | |
| Zhang et al. | Analysis of street crime predictors in web open data | |
| Lansley et al. | Challenges to representing the population from new forms of consumer data | |
| Fu et al. | Exploration of the spatiotemporal heterogeneity of metro ridership prompted by built environment: A multi‐source fusion perspective | |
| Clark | Co-assessment through digital technologies | |
| Guo et al. | Fine-grained dynamic price prediction in ride-on-demand services: Models and evaluations | |
| WO2021028988A1 (en) | User location calculation device and method, activity area estimation device and method, and computer-readable medium | |
| TWM599429U (en) | Geographic Information System Combining Consumption Heat | |
| Voloshin et al. | Identifying venues for female commercial sex work using spatial analysis of geocoded advertisements | |
| US11138615B1 (en) | Location-based place attribute prediction | |
| Ribeiro et al. | Using passive Wi-Fi for community crowd sensing during the COVID-19 pandemic |
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 |