CN112700055A - Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system - Google Patents
Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system Download PDFInfo
- Publication number
- CN112700055A CN112700055A CN202110009930.3A CN202110009930A CN112700055A CN 112700055 A CN112700055 A CN 112700055A CN 202110009930 A CN202110009930 A CN 202110009930A CN 112700055 A CN112700055 A CN 112700055A
- Authority
- CN
- China
- Prior art keywords
- shop
- neural network
- artificial neural
- location
- data
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010187 selection method Methods 0.000 title description 4
- 230000002093 peripheral effect Effects 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007306 turnover Effects 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0204—Market segmentation
- G06Q30/0205—Location or geographical consideration
Abstract
The invention provides a training method, a shop location method, a storage medium and a shop location system, which enable an artificial neural network to have shop location capability, wherein the training method executes a sample acquisition step for multiple times under the condition that a plurality of shops with the same brand exist: acquiring the point of business interest data and the number of target consumers in a preset range around one existing shop; acquiring business data of the shop; using the commercial interest point data and the number of target consumers as input signals, and using whether business data reaches a preset value corresponding to a shop location standard as output signals to form a group of learning samples for an artificial neural network to train the shop location; and carrying out shop location training on the artificial neural network by adopting the plurality of groups of learning samples until the artificial neural network has the capability of predicting whether business data of the shop to be located reaches the preset value according to the business interest point data in the peripheral preset range of the shop location and the number of target consumers.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a training method, a shop address selecting method, a storage medium and a system for enabling an artificial neural network to have shop address selecting capability.
Background
In order to make the shop business status good, shop location selection needs to be performed reasonably before shops with the same brand, such as chain shops and franchised shops, are opened. In the currently common shop address selection method, an experimenter inspects all candidate addresses in the field, so as to obtain the surrounding environment and the surrounding people flow of all the candidate addresses, and then shop address selection is performed according to the surrounding environment and the surrounding people flow. However, this shop location method is performed based on the personal experience of the experimenter, which makes the result of shop location highly subjective and reduces the rationality of the result of shop location.
The Point of Interest (POI) is used as a new spatial data source, the distribution mode and the distribution density of the POI have important significance in infrastructure planning and urban space analysis, wherein the commercial POI data comprises spatial position information and commercial attribute information of different business state shops, has the characteristics of abundant data volume and strong situational property, and is beneficial to improving the accuracy of urban commercial space hotspot judgment. In the shop location process, the surrounding environment and the surrounding people flow of each shop location can be obtained based on the business interest point data, so that the shop location is facilitated, the shop location result is reasonable, but the surrounding environment and the surrounding people flow are only partial main factors influencing the shop business condition, even if the surrounding environment of the shop is good and the surrounding people flow is large, if the shop cannot attract enough target consumers to enter the shop for consumption, the shop business condition is not good, and the shop location is limited only by the business interest point data.
Disclosure of Invention
The invention aims to solve the technical problem of how to improve the rationality of shop location selection.
In order to solve the technical problem, the invention provides a training method for enabling an artificial neural network to have store address selection capability, which comprises the following steps:
p. in the case where there are a plurality of stores of the same brand already, a plurality of sets of learning samples are obtained by performing the following sample obtaining steps a plurality of times, each of the sample obtaining steps including A, B, C:
obtaining the point of business interest data and the number of target consumers in a preset range around one existing shop;
b, obtaining business data of the shop;
c, using the commercial interest point data and the number of target consumers as input signals, and using whether business data reach a preset value corresponding to a shop location standard as output signals to form a group of learning samples for the artificial neural network to carry out shop location training;
and Q, carrying out shop location training on the artificial neural network by adopting the multiple groups of learning samples until the artificial neural network has the capability of predicting whether business data of the shop to be located reaches the preset value according to the business interest point data in the peripheral preset range of the shop location and the number of target consumers, so that the artificial neural network can select the shop to be located at the shop location of which the business data reaches the preset value.
Preferably, in the step a, the number of the population living in each age interval within a predetermined range around the store is acquired, and the number of the population living in a preset age interval is taken as the number of the target consumers.
Preferably, in the step A, the consumption capacity of the target consumer is also acquired; accordingly, in said step C, the consuming ability of the target consumer is also taken as an input signal.
Preferably, in the step a, a room price mean value within a predetermined range around the store is obtained, and the consuming ability of the target consumer is analyzed according to the room price mean value.
The invention also provides a shop address selecting method, which is characterized by comprising the following steps:
a. obtaining a shop place to be selected;
b. obtaining the commercial interest point data and the number of target consumers in a preset range around the shop location;
c. and inputting the obtained commercial interest point data and the number of target consumers into a trained artificial neural network, predicting whether business data of the shop to be addressed reaches a preset value corresponding to the shop addressing standard or not by the artificial neural network, and addressing the shop to be addressed at the shop location if the business data of the shop to be addressed reaches the preset value.
Preferably, in the step b, the number of the population living in each age interval around the store location is acquired, and the number of the population living in a preset age interval is used as the number of the target consumers.
Preferably, in the step b, the consumption capability of the target consumer is also acquired; accordingly, in said step c, the consuming ability of the target consumer is also input into the trained artificial neural network.
Preferably, in the step b, a mean value of the room prices in a predetermined range around the store location is obtained, and the consuming capacity of the target consumer is analyzed according to the mean value of the room prices around the store location.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the training method and/or the store addressing method as described above.
The invention also provides a store addressing system comprising a computer readable storage medium and a processor connected to each other, the computer readable storage medium being as described above.
The invention has the following beneficial effects: in the shop addressing process, compared with the prior art that only the commercial interest point data in the peripheral preset range of the shop location is considered, the invention also considers the number of target consumers in the peripheral preset range of the shop location, so that under the condition that the peripheral environment reflected by the commercial interest point data in the peripheral preset range of the shop location is good and the peripheral pedestrian volume is large, the shop is addressed to the shop locations with the large number of target consumers, the business data of the shop can reach the preset value corresponding to the shop addressing standard, the business condition of the shop is improved, and the invention can more reasonably address.
Detailed Description
Before shops with the same brand, such as chain shops and franchised shops, are opened, in order to enable good business conditions of the shops in the future, business data of the shops opened at different places are predicted by using a shop addressing system, and then the shops are addressed according to the predicted business data of the shop places. The business data can be influenced by the surrounding environment of the shop site, the surrounding people flow, the number of target consumers and the consumption capacity of the target consumers; the business interest point data in the peripheral preset range of the shop site can reflect the peripheral environment and the peripheral pedestrian volume of the shop; the number of the regular population in each age interval in the peripheral preset range of the shop location can reflect the number of target consumers of the shop, and taking the child-shop to be selected as an example, the target consumers are young parents aged 25 to 35 years, so that the number of the regular population aged 25 to 35 years in the peripheral preset range of the child-shop location can be obtained from census data, and the number of the target consumers can be obtained; the average value of the room prices in the predetermined range around the store location can reflect the consumption ability of the target consumer of the store, the higher the average value of the room prices is, the stronger the consumption ability of the target consumer is, in this embodiment, the consumption ability corresponding to the average value of the room prices below 5000 yuan/square meter is poor, the consumption ability corresponding to the average value of the room prices between 5000 to 12000 yuan/square meter is general, the consumption ability corresponding to the average value of the room prices between 12000 to 20000 yuan/square meter is stronger, and the consumption ability corresponding to the average value of the room prices above 20000 yuan/square meter is strong. In this embodiment, the predetermined range of the periphery refers to within 5 kilometers of a square circle, and optionally, the predetermined range of the periphery may be within 3 kilometers of a square circle, within 8 kilometers of a square circle, within 10 kilometers of a square circle, or any other settable range.
The shop addressing system can realize a training method for enabling the artificial neural network to have shop addressing capability based on business interest point data in a preset range around a shop location, the number of the regular population in each age interval and a room price mean value, taking the children's garment shop as an example, the training method trains the artificial neural network by adopting a plurality of groups of learning samples under the condition that a plurality of children's garment shops with the same brand exist, and each group of learning samples obtains the following A, B, C:
A. the method comprises the steps of obtaining business interest point data in a peripheral preset range of one existing children's shop, the number of the constant population in each age interval and a room price mean value, taking the number of the constant population between the ages of 25 and 35 as the number of target consumers, and analyzing the consumption capacity of the target consumers according to the room price mean value in the peripheral preset range of the location of the children's shop.
B. And acquiring business data of the children's garment shop.
C. And forming a group of learning samples for the artificial neural network to train the shop location by taking the commercial interest point data, the number of target consumers and the consumption capacity of the target consumers as input signals and taking whether business data reaches a preset value corresponding to the shop location standard as an output signal. The preset value corresponding to the shop address standard is the annual turnover of the children's garment shop, for example, 100 ten thousand yuan, if the business data reaches the preset value corresponding to the shop address standard, the output signal in the omic learning sample is yes, and if the business data does not reach the preset value corresponding to the shop address standard, namely, 100 ten thousand yuan, the output signal in the omic learning sample is no. Alternatively, the preset value corresponding to the store address selection criteria may be 80 ten thousand yuan, 150 ten thousand yuan, 200 ten thousand yuan or any other settable value.
The sample obtaining step is executed for multiple times to obtain multiple groups of learning samples to carry out store site selection capability training on the artificial neural network until the artificial neural network has the capability of predicting whether business data of the store reaches a preset value corresponding to a store site selection standard according to business interest point data, the number of target consumers and the consumption capability of the target consumers in a peripheral preset range of the store site, the artificial neural network can select the children's clothes store site at the store site with the business data reaching the preset value, and therefore, the store site selection method can be realized by using the store site selection system, and the following steps a, b and c are detailed:
a. a store location is obtained.
b. And acquiring the business interest point data in a peripheral preset range of the shop location, the number of the constant population in each age interval and the room price mean value, taking the number of the constant population between 25 years old and 35 years old as the number of target consumers, and analyzing the consumption capacity of the target consumers according to the room price mean value in the peripheral preset range of the shop location.
c. Inputting the obtained business interest point data, the number of target consumers and the consumption capacity of the target consumers into a trained artificial neural network, predicting whether business data of the children's clothes shop reaches a preset value corresponding to shop location standards by the artificial neural network, if so, locating the children's clothes shop at the shop location, and if not, locating the children's clothes shop at the shop location.
In the embodiment, in the shop location process, the number and the consumption capacity of target consumers in the peripheral preset range of the shop location are also considered in addition to the business interest point data in the peripheral preset range of the shop location, so that under the condition that the peripheral environment reflected by the business interest point data in the peripheral preset range of the shop location is good and the peripheral people flow is large, the children's clothes shop is located at the shop location with the large number of target consumers and high consumption capacity, the business data of the children's clothes shop can reach the preset value corresponding to the shop location standard, and the business condition of the children's clothes shop is improved.
In this embodiment, the store addressing system includes a computer-readable storage medium and a processor connected to each other, and a computer program is stored in the computer-readable storage medium, and when executed by the processor, the computer program implements the training method for making the artificial neural network have the store addressing capability and/or the store addressing method.
Claims (10)
1. The training method for enabling the artificial neural network to have the shop address selection capability is characterized by comprising the following steps of:
p. in the case where there are a plurality of stores of the same brand already, a plurality of sets of learning samples are obtained by performing the following sample obtaining steps a plurality of times, each of the sample obtaining steps including A, B, C:
obtaining the point of business interest data and the number of target consumers in a preset range around one existing shop;
b, obtaining business data of the shop;
c, using the commercial interest point data and the number of target consumers as input signals, and using whether business data reach a preset value corresponding to a shop location standard as output signals to form a group of learning samples for the artificial neural network to carry out shop location training;
and Q, carrying out shop location training on the artificial neural network by adopting the multiple groups of learning samples until the artificial neural network has the capability of predicting whether business data of the shop to be selected reaches the preset value according to the business interest point data in the peripheral preset range of the shop to be selected and the number of target consumers, so that the artificial neural network can locate the shop to be selected at the shop location of which the business data reaches the preset value.
2. The training method as claimed in claim 1, wherein in the step a, the number of the population living in each age zone within a predetermined range around the shop is acquired, and the number of the population living in a predetermined age zone is used as the number of the target consumers.
3. Training method according to claim 1 or 2, characterized in that: in the step A, the consumption capacity of the target consumer is also acquired; accordingly, in said step C, the consuming ability of the target consumer is also taken as an input signal.
4. The training method as claimed in claim 3, wherein in the step A, a mean value of the room rates within a predetermined range around the store is obtained, and the consuming ability of the target consumer is analyzed based on the mean value of the room rates.
5. The shop address selecting method is characterized by comprising the following steps:
a. obtaining a shop place to be selected;
b. obtaining the commercial interest point data and the number of target consumers in a preset range around the shop location;
c. and inputting the obtained commercial interest point data and the number of target consumers into a trained artificial neural network, predicting whether business data of the shop to be addressed reaches a preset value corresponding to the shop addressing standard or not by the artificial neural network, and addressing the shop to be addressed at the shop location if the business data of the shop to be addressed reaches the preset value.
6. A store addressing method according to claim 5, further comprising: in the step b, the number of the population living in each age interval around the shop location is acquired, and the number of the population living in a preset age interval is used as the number of the target consumers.
7. A store addressing method according to claim 5, further comprising: in the step b, the consumption capacity of the target consumer is also acquired; accordingly, in said step c, the consuming ability of the target consumer is also input into the trained artificial neural network.
8. A store addressing method according to claim 7, wherein in step b, a mean value of the room prices in a predetermined range around the store location is obtained, and the consuming ability of the target consumer is analyzed based on the mean value of the room prices around the store location.
9. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the training method of any one of claims 1 to 4 and/or the store addressing method of any one of claims 5 to 8.
10. A store addressing system comprising a computer readable storage medium and a processor coupled to each other, wherein the computer readable storage medium is as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009930.3A CN112700055A (en) | 2021-01-05 | 2021-01-05 | Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009930.3A CN112700055A (en) | 2021-01-05 | 2021-01-05 | Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112700055A true CN112700055A (en) | 2021-04-23 |
Family
ID=75514763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110009930.3A Pending CN112700055A (en) | 2021-01-05 | 2021-01-05 | Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112700055A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611624A (en) * | 2022-03-22 | 2022-06-10 | 广东贤能数字科技有限公司 | Artificial intelligence-based business activity evaluation system and method for shops or business halls |
| CN115345530A (en) * | 2022-10-18 | 2022-11-15 | 广州数说故事信息科技有限公司 | Market address recommendation method, device and equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009379A (en) * | 2018-11-27 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of building of site selection model and site selecting method, device and equipment |
| CN110543999A (en) * | 2018-08-17 | 2019-12-06 | 杉数科技(北京)有限公司 | Method and device for store site selection |
| CN110648161A (en) * | 2019-08-05 | 2020-01-03 | 中移（杭州）信息技术有限公司 | Benefit evaluation method and device for commercial site selection and storage medium |
-
2021
- 2021-01-05 CN CN202110009930.3A patent/CN112700055A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543999A (en) * | 2018-08-17 | 2019-12-06 | 杉数科技(北京)有限公司 | Method and device for store site selection |
| CN110009379A (en) * | 2018-11-27 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of building of site selection model and site selecting method, device and equipment |
| CN110648161A (en) * | 2019-08-05 | 2020-01-03 | 中移（杭州）信息技术有限公司 | Benefit evaluation method and device for commercial site selection and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| HUCHUNMIAO: ""基于GIS和神经网络的超市选址方法研究"", 《HTTPS://WWW.DOC88.COM/P-4969174326949.HTML》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611624A (en) * | 2022-03-22 | 2022-06-10 | 广东贤能数字科技有限公司 | Artificial intelligence-based business activity evaluation system and method for shops or business halls |
| CN114611624B (en) * | 2022-03-22 | 2023-04-07 | 广东贤能数字科技有限公司 | Artificial intelligence-based business activity evaluation system and method for shops or business halls |
| CN115345530A (en) * | 2022-10-18 | 2022-11-15 | 广州数说故事信息科技有限公司 | Market address recommendation method, device and equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6141393B2 (en) | Method and apparatus for determining a target position | |
| Cord et al. | Inclusion of habitat availability in species distribution models through multi‐temporal remote‐sensing data? | |
| CN104965920B (en) | Method and apparatus for determining destination address | |
| Gupte et al. | A guide to pre‐processing high‐throughput animal tracking data | |
| DE202015009183U1 (en) | Analyzing semantic locations and related data from a variety of location data reports | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| CN106528531A (en) | Artificial intelligence-based intention analysis method and apparatus | |
| Yao et al. | Discovering the homogeneous geographic domain of human perceptions from street view images | |
| CN106021363A (en) | Course recommendation method and device | |
| CN109151890A (en) | A kind of mobile terminal locating method and device | |
| CN108830837A (en) | A kind of method and apparatus for detecting ladle corrosion defect | |
| CN112700055A (en) | Training method for making artificial neural network have shop site selection capability, shop site selection method, storage medium and shop site selection system | |
| CN110648161A (en) | Benefit evaluation method and device for commercial site selection and storage medium | |
| CN108960912A (en) | Method and apparatus for determining target position | |
| McCord et al. | Understanding rental prices in the UK: a comparative application of spatial modelling approaches | |
| CN111797188B (en) | Urban functional area quantitative identification method based on open source geospatial vector data | |
| CN110472999A (en) | Passenger flow pattern analysis method and device based on subway and shared bicycle data | |
| CN113393149A (en) | Method and system for optimizing urban citizen destination, computer equipment and storage medium | |
| CN111984701A (en) | Method, device, equipment and storage medium for predicting village settlement evolution | |
| Henrys et al. | Niche models for British plants and lichens obtained using an ensemble approach | |
| CN108154305A (en) | A kind of food safety detection information management platform and its implementation | |
| Gehrke et al. | Assessing the importance of housing, accessibility, and transportation characteristics on stated neighbourhood preference | |
| CN112766718A (en) | City business district boundary identification method, system, computer equipment and storage medium | |
| CN113379269A (en) | Urban business function zoning method, device and medium for multi-factor spatial clustering | |
| CN112561401A (en) | City vitality measurement and characterization method and system based on multi-source big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210423 |