JP2004348618A - Customer information collection and management method and system therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To more accurately judge customer's personal features as personal information and to provide an instantaneous sales promotion service corresponding to a customer segment based on the personal information. <P>SOLUTION: An image processing part 51 extracts and specifies the sex of a customer himself or herself, an age group, features such as avocation, staying places and time, noticed commodities in which the customer may be interested judging from the turned direction of the face, and a customer's walking course from a plurality of pictures of each buying customer which are continuously photographed by a plurality of cameras 11-18 and registers the extracted data in a visiting customer list 52. A customer management part 53 extracts feature data from the visiting customer list 52, extracts voice guide information/electronic bulletin information corresponding to the feature data and previously stored from a notice information DB 70, outputs announcement/electronic bulletins from an output part 40, and records the data of leaving customers in a customer DB 60. The walking courses of customers recorded in the customer DB 60 can be effectively utilized for the improvement of commodity display. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a method and a system for collecting and managing customer information, in which image information of the customer is acquired by a camera and used for marketing, and more particularly to a customer information characteristic that can be determined more accurately as personal information and based on the personal information. The present invention relates to a customer information collection / management method and system capable of providing a sales promotion service corresponding to each layer without losing time.
[0002]
[Prior art]
Conventionally, in this type of customer information collection and management system, the purpose of the system is to create an accurate database by reducing the input work and preventing the dispersion of the judgment of the customer's attributes, Based on the photographed image of the customer, the attribute of the customer is automatically determined by image processing (for example, see Patent Document 1).
[0003]
With reference to FIG. 7, this customer information collection management system will be described.
[0004]
In each in-store information analysis system 100, the control unit 108 determines gender, age group, and the like as attributes of the customer from the image information of the cash register camera 102 that images the customer at the register. Next, the clerk inputs the data of the product purchased by the customer to the register accurately using, for example, a barcode. As a result, the product data and the attribute of the customer are recorded in association with each other.
[0005]
That is, since the attribute of the customer is determined based on the image information of the customer who purchases the goods, not only the input work by the clerk is reduced, but also the judgment is prevented from being uniform based on the uniform reference from the image information. Further, these data at each store are sent from the in-store information analysis system 100 and centrally stored in the information analysis center 110, and are utilized for marketing.
[0006]
Further, there is a customer data processing system in which a terminal device acquires and analyzes customer data to determine the type of the customer, specifies product guidance data based on the determination result, and provides the guidance data to the customer (for example, , Patent Document 2).
[0007]
This terminal device is provided with a camera and a sensor, and when the customer stands in front, automatically acquires customer information by the camera and the sensor, determines the customer type from the acquired information, and provides guidance data suitable for the customer layer. To provide to its customers. The guidance data is centrally held in the server device corresponding to the customer layer data, and provided to a plurality of terminal devices. Here, the residence time of the customer is also measured.
[0008]
[Patent Document 1]
JP-A-2002-32553 (FIG. 1)
[0009]
[Patent Document 2]
JP-A-11-328266 (FIGS. 1 and 2)
[0010]
[Problems to be solved by the invention]
However, the above-described conventional customer information collection and management method and its system have the following problems.
[0011]
The first problem is the lack of accuracy in determining customer attributes such as age, gender, and clothing.
[0012]
The reason is that the photographing data for acquiring the attribute information of the customer is not continuously photographed for a plurality of frames, but is determined only by a single frame. In Patent Document 1, image information only when a product is purchased in a register, and in Patent Document 2, image information of a camera when facing a terminal device, a customer is determined only from a frontal image. There is a small amount of data for, and there is danger in accurately determining the attributes of a person such as age, gender, and clothes.
[0013]
The second problem is that it is difficult to flexibly respond to each store when promoting product sales based on personal information of customers visiting the store.
[0014]
The reason is that in Patent Documents 1 and 2, the information analysis center or the server device manages customer data and sales promotion product data in a concentrated manner at a plurality of stores, and it is difficult to quickly respond to changes at each store. It is.
[0015]
The third problem is that it is difficult to reflect the purchase information of customers who visit the store in improving the display of products in the store.
[0016]
The reason is that, in Patent Document 1, the data corresponding to the customer information is the purchased product data, and there is no data other than the purchased product. This is because Patent Literature 2 proposes that a terminal device be provided for each product for information collection for this purpose.
[0017]
It is an object of the present invention to solve such a problem, to obtain more accurate personal information from image information at each providing location of a product, and to quickly lose time at a change in circumstances at each providing location. It is an object of the present invention to provide a customer information collection / management method and system capable of providing corresponding product data and collecting information for improving a product display position.
[0018]
[Means for Solving the Problems]
The customer information collection and management method according to the present invention is to acquire customer's image information with a camera and utilize it for marketing, and regularly acquire images of all target customers with the camera, and continuously Judgment of the personal attributes of the customer from the acquired images of the plurality of frames to judge the individual, and further, for each of the judged individuals, a group of attention products of interest from the camera position, face orientation, and staying time, and use for marketing. It is to be.
[0019]
For this purpose, for example, in a store, a camera that periodically and continuously obtains images of customers in all aisles so that the positions and faces of the customers can be determined, and determines the personal attributes of the customers from the continuously obtained images of the cameras An image processing unit for comprehensively determining personal information, a customer visiting list for recording personal information based on the comprehensive determination of the image processing unit, and a customer utilizing for marketing based on the information recorded in the customer visiting list. And a management unit.
[0020]
With this configuration, a plurality of continuous image information can be acquired for one customer, so that personal information as a customer attribute can be collected more accurately. Further, it is possible to specify a product of interest or a group of products from the camera position and the face orientation analyzed from the image information, and to analyze the staying time and the duration of interest.
[0021]
In addition, when the customer's personal attribute and the product group of interest are acquired, the sales promotion information of the product prepared in advance corresponding to the product group of interest is immediately notified in an audible / visible manner to the store.
[0022]
That is, at the product display location, an audible / visual notification device such as a speaker, an electronic bulletin board, and / or an information terminal, and a notification in which a guidance notification including sales promotion products is stored in advance along with notification conditions corresponding to the notification device. An information database is further provided. The image processing unit selects the product of interest from the person position and face direction and the staying time of the continuous person image based on the same personal information, and records these information in the visiting customer list corresponding to the personal information. I do. Also, the customer management unit, when the information recorded in the customer list during the visit matches the notification condition, acquires the guidance notification corresponding to the notification condition from the notification information database and corresponds to the notification device. Provides audible / visible information.
[0023]
Since this notification information can be provided from the database in the same store, the provision conditions and the guidance of the provided product can be prepared as appropriate and quickly provided without losing time.
[0024]
Further, by determining a group of products of interest of the customer, the time of interest, and the travel route from the images obtained continuously, it is possible to utilize the product for marketing improvement such as improvement of product display positions in stores.
[0025]
That is, there are provided a register for registering a purchased product of a visiting customer and a customer database for recording information of past visiting customers. This image processing unit, when a purchased product is registered in the register, compares it with the purchaser's camera image and registers it in the in-store customer list, and when the exit camera image captures the customer, exits the store. Record in the customer list during the visit. In addition, the customer management unit additionally records, in the customer database, predetermined information of the customer correspondence information in which the customer has left the store in the visiting customer list.
[0026]
BEST MODE FOR CARRYING OUT THE INVENTION
Next, embodiments of the present invention will be described with reference to the drawings.
[0027]
FIG. 1 is a plan view showing an embodiment of the arrangement of the in-store camera and the face orientation of a person according to the present invention. The difference from the conventional example shown in FIG. 7 is that a plurality of cameras 11 to 18 are provided for acquiring images of customers 31 to 35 on a passage in a store.
[0028]
In the plan view shown in FIG. 1, an entrance camera 11, a cash register camera 12, an exit camera 14, and in-store cameras 15 to 18 are provided, for example, on a ceiling, and each of the cameras regularly shoots continuously. . The store is, for example, a so-called convenience store. A POS (point of sale information) terminal 20 serving as a register is provided in the store, customers 31 to 36 are visiting the store, and a speaker 41, an electronic bulletin board 42, and an information terminal 43 are provided other than the product display shelf. I have.
[0029]
The entrance camera 11 faces the entrance from inside the store and photographs the front of the customer entering the store. The cashier camera 12 takes an image of the front of a customer presenting a purchased product at the location of the POS terminal 20 serving as a register. The exit camera 14 faces the inside of the store from the doorway side, and photographs substantially the front of the exiting customer.
[0030]
The in-store cameras 15 to 18 photograph customers on the aisle. The in-store camera 15 in FIG. 1 is intended for a customer between a book shelf and a display shelf for daily necessities. The in-store camera 16 is intended for customers between display shelves of food and confectionery. The in-store camera 17 is intended for breads, lunches, desserts, and customers facing the information equipment 43. The in-store camera 18 targets drinks and customers in front of the electronic bulletin board.
[0031]
In FIG. 1, a customer 31 faces his / her bookshelf. The customer 32 is heading for the electronic bulletin board 42. For example, if the face orientation is fixed in the direction of the electronic bulletin board 42, it can be determined that the electronic bulletin board 42 is receiving attention. The customers 33 and 34 are paying attention to groceries and lunches, respectively. The customer 35 accesses the information terminal 43, and the customer 36 pays for the purchased merchandise at the register.
[0032]
Next, a customer information collection and management system according to the present invention will be described with reference to FIG. 1 and FIG.
[0033]
This customer information collection and management system includes an input unit 10, a POS terminal 20, an output unit 40, a control unit 50, a customer DB (database) 60, and a notification information DB 70 in a store. The customer DB 60 may be commonly or centrally managed at a plurality of stores.
[0034]
The information input unit 10 includes an entrance camera 11, a cash register camera 12, an exit camera 14, and in-store cameras 15 to 18. The illustrated POS terminal 20 includes a keyboard 21, a screen display 22, and a purchased product information acquisition unit 23. The information output unit 40 includes a speaker 41, an electronic bulletin board 42, and an information terminal 43. The control unit 50 includes an image processing unit 51, a visiting customer list 52, and a customer management unit 53. The notification information DB 70 has voice guidance product information 71 and electronic criminal product information 72.
[0035]
The cameras 11 to 18 have already been described with reference to FIG. 1. For example, image information obtained by continuously shooting several frames per second is sequentially sent to the image processing unit 51 of the control unit 50. In the POS terminal 20, the information input includes, for example, a barcode reader (not shown) other than the keyboard 21. The information output includes, for example, a receipt output (not shown) other than the screen display 22 that displays various information on the screen. Accordingly, a purchase merchandise information acquisition unit 23 that records and retains purchase merchandise information of customers is provided.
[0036]
The speaker 41 receives product information and the like stored in the voice guidance product information 71 under the control of the customer management unit 53 and broadcasts the received information to the store. The electronic bulletin board 42 receives product information and the like stored in the electronic posted product information 72 under the control of the customer management unit 53 and displays the screen. Although the illustrated electronic bulletin board 42 faces in the direction of the doorway, a plurality of electronic bulletin boards may be provided and may be directed to the outside of the store depending on information to be posted. The information terminal 43 receives the operation of the customer and can provide the customer not only with the product stored in the notification information DB 70 but also with other information in a visible / audible manner.
[0037]
The image processing unit 51 performs image processing on a plurality of frames of image information obtained from the input unit 10 for each frame, and extracts personal characteristics such as gender, age, and clothes for tracking customers. By image processing, it is possible to specify a person and specify attention product information obtained from a camera position, a face direction, and a stay time, and furthermore, movement of one customer in a store in association with the passage of time. Track your route. Accordingly, the extracted personal information to which the customer ID (identifier) is assigned is sent to the customer list 52 during visit to the store, and is organized by ID for each customer. When it is determined from the image information that the customer has left the store, the customer's leaving is sent to the visiting customer list 52.
[0038]
The customer management unit 53 repeatedly scans the customer information recorded in the customer list 52 during the visit to the store, and when the condition matches a preset condition, the voice guidance product information 71 and / or the voice guidance product information 71 stored in the notification information DB 70. Appropriate notice information is extracted from the electronic notice product information 72 and sent to the output unit 40. When the customer leaves the store, the data of the corresponding customer is checked against the customer DB 60, and new customer information is transferred to the customer DB 60 and added, while the same information is discarded. In particular, when the information in the customer DB 60 changes significantly, this can be detected and reflected in sales promotion.
[0039]
The customer DB 60 records, in addition to the characteristics of each customer as a person, information on a product of interest such as a purchased product, a travel route, and a stay time for the customer class. Therefore, the customer DB 60 is useful for selecting sales promotion products corresponding to gender, age group, occupation, etc., and improving the display of products in the store.
[0040]
The notification information DB 70 stores information on recommended products corresponding to the customer segment created for sales promotion based on the information up to that time, voice information as voice guide product information 71, video information as electronic posted product information 72, Each of them is stored in advance together with the customer demographic conditions to be promoted, for example, gender, age group, occupation, and the like. This information is periodically revised based on information stored in the customer DB 60.
[0041]
Next, the function of the image processing unit 51 will be described in detail with reference to FIGS.
[0042]
The image processing unit 51 has the functions of image reception 511, 512,... For example, the image reception 511 sequentially receives image data captured by the entrance camera 11, adds the camera number and time to the image data, and sends the image data to the ID editor 510.
[0043]
The ID editor 510 performs image processing on the received images of a plurality of frames for each frame, and extracts characteristics of a person such as gender, age, and clothes as person information. More specifically, for each image frame, a determination probability that a person is a man with a probability of 90% and a probability of 30s is in his 30s with a probability of 30% is calculated, and a person feature is determined from the height of the determination probability. On the other hand, in each of the person images, the point of interest can be determined at the same time from the camera position and the face direction, so that a group of products or products that are of interest or to be purchased are specified.
[0044]
Then, similar image information is collected in a time series, and as shown in FIG. 4, more accurate feature extraction is realized by comprehensively judging information of a plurality of image frames 81 to 86 for one customer. Then, comprehensive judgment of personal information is made, and a customer ID is given. As described above, for the characteristics of a person, a method of adopting a more reliable determination result from the determination results of a large number of image frames by tracking a plurality of cameras is adopted.
[0045]
Specifically, in the comprehensive judgment, only the image frames whose judgment probability is equal to or more than a certain threshold are adopted. For example, when the threshold value of the determination probability is set to 80%, two image frames of an image frame 81 of 93% for male and an image frame 85 of 81% for male are adopted, and the image is determined to be male. By such a method of eliminating ambiguous determination, accurate person characteristics can be extracted.
[0046]
As a result, even when a small number of unreliable judgment results are mixed in with a large number of highly reliable judgment results, more accurate human feature extraction can be performed by removing the unreliable judgment results. In addition, even when a large number of unreliable judgment results have a small number of highly reliable judgment results, a small number of highly reliable judgment results can be adopted in the same manner. It is possible.
[0047]
The customer tracking information and characteristic information obtained by the image processing unit 51 are sent to the customer list 52 during the visit and are additionally recorded. That is, for example, personal information indicating the characteristics of the customer, the entry time, the place of stay, the length of stay, and the like are recorded for each ID, and the exit time can be recorded when exit from the exit is detected. As described above, the customer information in which the store exit time is recorded is extracted from the in-store customer list 52 by the customer management unit 53.
[0048]
Next, the in-store customer list 52 will be described in detail with reference to FIG.
[0049]
The contents of the in-store customer list 52A shown in FIG. 5A include attributes such as an ID for identifying the customer, gender, age, clothes, status obtained from the face direction, and stay time. The information is updated by the image processing unit 51 in real time. Further, in FIG. 5 (B), gait in which the place where the stay time exists is sequentially recorded is acquired as the data of the moving course.
[0050]
Next, an operation procedure of the control unit 50 will be described with reference to FIGS. FIG. 6 is a flowchart showing an embodiment of a procedure centering on the main operation of the customer management unit 53.
[0051]
In the control unit 50, the image processing unit 51 knows from the image data received from the entrance camera 11 that the customer has visited the store (YES in step S1), acquires the customer's personal data (step S2), and assigns an ID code. Then, it is recorded in the customer list 52 during the visit. The visiting customer is photographed by any of the cameras 11 to 18 in the store, and the image is processed, and the processing result is sequentially recorded in the visiting customer list 52.
[0052]
The customer management unit 53 repeatedly scans the visiting customer list 52 to investigate the characteristics of the acquired data (step S3). Characteristics include not only individuals, but also general conditions such as, for example, many male customers wearing suits buying lunch and drinks during lunchtime, or many young female customers are visiting the store. is there.
[0053]
If step S3 is “YES” and the acquired data from the visiting customer list 52 has characteristics, the customer management unit 53 compares the registered data in the notification information DB 70 with, for example, recommendation to a male customer at lunch. It confirms the presence or absence of corresponding PR (advertisement, advertisement) products, such as today's products, or cosmetics recommended to a large number of young female customers (step S4).
[0054]
If the procedure S4 is “YES” and there is a corresponding PR product, the customer management unit 53 extracts the corresponding data from the notification information DB 70 and passes it to the output unit 40, and the PR product is announced by voice or / and electronic bulletin. The image is notified (step S5). For example, in the case of the voice guidance product information 71, voice guidance by announcement is played from the speaker 41. In the case of the electronically posted product information 72, a customer who is visiting the store is notified by a screen display on the electronic bulletin board 42.
[0055]
Furthermore, for example, if there are many young student customers in their late teens to early 20s who are browsing in the magazine corner late at night, we recommend a special PR snack, or personalized services, or the whole Can automatically and in real time provide services for the customer group, so that customers' motivation to purchase can be increased.
[0056]
On the other hand, when the image processing unit 51 identifies a customer leaving the store from the image data received from the exit camera 14 (YES in step S6), the store exit is recorded in a corresponding location of the customer visiting store list 52 by, for example, time. Is done. The customer management unit 53 compares the personal characteristic data of the customer who has a record of leaving the store in the in-store customer list 52 with that stored in the customer DB 60. When it is determined that the exiting customer is a new customer (YES in step S7), the customer management unit 53 newly assigns an ID number and registers the customer's personal data in the customer DB 60 (step S8). Predetermined data such as the product of interest and the stay time at the place are additionally registered as customer data, and the corresponding data is deleted from the visiting customer list 52 (step S9).
[0057]
If the above step S7 is "NO" and the individual customer has already been registered, the customer management unit 53 skips the above step S8 and proceeds to the above step S9, where the number of visits, the purchased product information, the interesting product different from the conventional one, etc. Then, predetermined customer data is additionally registered in the corresponding location, and the corresponding data is deleted from the visiting customer list 52.
[0058]
Next, the customer management unit 53 confirms the presence of the in-store customer in the in-store customer list 52 (step S10). Since there is no record of the customer in the visiting customer list 52, if this step S10 is "NO", the procedure ends.
[0059]
If the procedure S10 is “YES” and there are still visiting customers in the store, the procedure S3 is “NO” and there is no characteristic acquired data in the visiting customer list 52, or the procedure S4 is “NO”. Similarly, when there is no corresponding PR product, the process returns to the above-described step S2, and the above-described procedure is continuously repeated from the operation of collecting customer data of the customer during the visit.
[0060]
In the above description, the ID of the customer data during the visit and the ID of the customer DB are assigned independently, but the image processing unit assigns the ID matching the personal characteristic data to the customer DB when assigning the ID to the visitor. It is good also as taking out from and giving.
[0061]
In the above description, the imaging data of all customers in the store is obtained by using a plurality of cameras. However, a method in which an omnidirectional camera is installed on the ceiling in the center of the store and the entire store is tracked by one camera. May be.
[0062]
In addition, with respect to the processing of a plurality of image frames with reference to FIG. 4, only those having a certain threshold value or more are adopted, but a method of averaging all the image frames 81 to 85 is also conceivable. Specifically, a method of calculating a male as 72 (= (93 + 67 + 45 + 74 + 81 + 74) / 6) percent and a female as 28 (= (7 + 33 + 55 + 26 + 19 + 26) / 6) percent is used to determine a male. This method is more reliable than a determination made from only one image, because the customer can capture all the information that has been captured. Furthermore, if the expression can be recognized in the image processing technology, it can be added to the information on the degree of interest in the product.
[0063]
In addition, although the description has been made using the image processing technology for acquiring the customer data, it is also possible to further improve the recognition performance by combining voice. In this case, for example, a method may be added in which a microphone is installed in the store, the male and female are analyzed from the utterance, or the reputation of the product is analyzed from the content of the conversation using voice recognition technology.
[0064]
In the above description, the store is targeted, but the user is tracked and the feature is extracted by a vending machine or an ATM (automatic teller machine), and a specific service is executed to the user, or a minor is used. You can also use it to restrict
[0065]
As described above, the customer information management in the store has been described with reference to the illustrated functional blocks and procedures. However, changes such as distribution and merging of functions or replacement of procedures before and after the functions are free as long as the above functions are satisfied. However, the target is not limited to the product display shelf. That is, the above description is not intended to limit the present invention, and the present function is applicable to general information management of customers using facilities capable of photographing with a camera.
[0066]
【The invention's effect】
As described above, according to the present invention, the following effects can be expected.
[0067]
The first effect is that efficient marketing automation is possible.
[0068]
The reason for this is that the same person is image-processed on a large number of image capturing screens from various directions by continuously photographing at a plurality of cameras in the store. That is, the characteristics of an individual obtained from this image processing are more reliable and can be distinguished more accurately from others, and also the products of interest can be analyzed based on the place and time of stay in the store.
[0069]
The second effect is that it is possible to increase the willingness to purchase customers who are visiting the store.
[0070]
The reason for this is that, as described above, the characteristics of the customer obtained from the image processing are more reliable, and it is possible to analyze and record and store in the database a product of interest from the place of stay and the length of stay in the store. . Therefore, it is possible to prepare recommended advertisements and advertisements of the recommended products in advance in accordance with the characteristics of the stored data. This is because it is possible to provide a specific service corresponding to.
[0071]
The third effect is that it is effective for improving the display of goods in a store.
[0072]
The reason is that, as described above, the behavior of the customer in the store can be analyzed in more detail. In other words, this is because the customer's stay location and stay time in the store, and the face orientation can be used to identify the interest level of the product of interest or the product and the travel course from the customer database.
[Brief description of the drawings]
FIG. 1 is a plan view showing an embodiment of an arrangement of a camera in a store and a face direction of a person according to the present invention.
FIG. 2 is a functional block diagram showing an embodiment of the present invention.
FIG. 3 is a functional block diagram illustrating an embodiment of the image processing unit in FIG. 2;
FIG. 4 is an explanatory diagram showing an embodiment of a plurality of image frames collected for personal information comprehensive judgment in the ID editing of FIG. 3;
5 (A) is a functional block diagram showing an embodiment in the visiting customer list of FIG. 2; FIG. 5 (B) is a functional block showing an embodiment in the visiting customer list different from FIG. 2 (A); FIG.
FIG. 6 is a flowchart showing an embodiment of a main operation procedure in the control unit of FIG. 2;
FIG. 7 is a functional block diagram showing an example of the related art.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 10 Input part 11 Entrance camera 12 Cash register camera 14 Exit camera 15-18 In-store camera 20 POS terminal 31-36 Customer 40 Output part 41 Speaker 42 Electronic bulletin board 43 Information terminal 50 Control part 51 Image processing part 52, 52A, 52B List 53 customer management section 60 customer DB
70 Notification information DB
71 Voice guidance product information 72 Electronically posted product information 81 to 86 Image frame 510 ID editing 511, 512 Image reception

Claims (6)

In a customer information collection and management method in which customer image information is acquired by a camera and used for marketing, images of all target customers are periodically acquired by the camera, and the customer's personal attribute is obtained from the continuously acquired images. A customer information collection and management method characterized by determining a group of products of interest from a camera position, a face direction, and a staying time for each determined individual, and utilizing the group for attention in marketing. 2. The method according to claim 1, wherein when the personal attribute of the customer and the product group of interest are acquired, the sales promotion information of the product prepared in advance corresponding to the product group of interest is immediately notified to the customer in an audible / visual manner. To collect and manage customer information. 2. The customer information collection and management method according to claim 1, wherein a group of products of interest of the customer, a time of interest thereof, and a moving route are determined from the images obtained continuously. In a customer information collection and management system that uses a camera to acquire customer image information and utilize it for marketing, a camera that periodically and continuously acquires person images of all target customers so that the person position and face direction can be determined, An image processing unit that determines the personal attributes of the customer from the consecutively acquired images of the camera to comprehensively determine the personal information of the customer; a list of visiting customers who records personal information based on the comprehensive determination of the image processing unit; A customer information collection and management system, comprising: a customer management unit that utilizes the information recorded in the list for marketing. The notification according to claim 4, wherein at least one of a speaker, an electronic bulletin board, and an information terminal, a notification device, and guidance notification information including a sales promotion product are stored in advance in a product providing location corresponding to the notification device along with notification conditions. An information database is further provided,
The image processing unit selects the product of interest based on the person position and face direction and the staying time of a continuous person image based on the same personal information, and records these information in the visiting customer list corresponding to the personal information. And
The customer management unit, when the information recorded in the visiting customer list matches the notification condition, acquires the guidance notification information corresponding to the notification condition from a notification information database and provides the notification notification information to the notification device. A customer information collection and management system, characterized in that: 5. The system according to claim 4, further comprising a register for registering a purchased product of a customer who is visiting the store, and a customer database for recording information of the customers who have visited the store.
The image processing unit, when a purchased product is registered in the register, compares the purchased product with the camera image of the purchasing customer, registers the customer in the in-store customer list, and exits when the exit camera image captures the customer. Is recorded in the visiting customer list, and
The customer information collection and management system according to claim 1, wherein the customer management unit additionally records, in the customer database, predetermined information from the customer correspondence information in which the customer has left the store in the visiting customer list.

Images