JP2015005019A - Accounting processor and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enhance the security of a shop without loading to clerks.SOLUTION: An accounting processor 1 includes: acquisition means; extraction means; determination means; and notification means. The acquisition means acquires an image data representing images taken by a camera 3. The extraction means extracts an area corresponding to a person from the image represented by the image data acquired by the acquisition means. The determination means determines whether a condition which is predetermined with respect to at least either one of appearance and behavior of the person on the basis of the area extracted by the extraction means is satisfied. When the determination means determines the condition is satisfied, the notification means notifies to the external.

Description

  Embodiments described herein relate generally to an accounting processing apparatus and a program.

  Conventionally, in order to improve security in a store, a button for reporting to a security company and the police may be provided near the cash register. Usually, such a button is arranged in a place where a store clerk can operate and is not visible to the customer.

  The decision as to whether or not to press the button is left to the store clerk. The store clerk does not know what happens when the button is pressed, and may ask for it. If reporting to the security company or the police is delayed, the situation can worsen.

Japanese Patent Laid-Open No. 10-105830

  The problem to be solved by the present invention is to improve the security of the store without placing a burden on the store clerk.

  An accounting processing apparatus according to an embodiment includes an acquisition unit, an extraction unit, a determination unit, and a notification unit. The acquisition unit acquires image data representing an image captured by the camera. The extraction unit extracts a region corresponding to a person from the image represented by the image data acquired by the acquisition unit. The determination means determines whether a predetermined condition regarding at least one of a person's appearance and behavior is satisfied based on the region extracted by the extraction means. The notification means notifies the outside when the determination means determines that the condition is satisfied.

The figure which shows the main components of the security system in one Embodiment. The block diagram which shows the principal part structure of the POS terminal contained in the said system. The figure which shows an example of the frequency | count file which the auxiliary storage device of the said POS terminal memorize | stores. The flowchart of the security process which CPU of the said POS terminal performs. The flowchart of the determination process included in the said security process.

An embodiment will be described with reference to the drawings.
In the present embodiment, a security system using a POS (Point Of Sales) system operating in a retail store such as a convenience store is disclosed.

  FIG. 1 shows the main components of the security system. The security system includes a POS terminal 1, a drawer 2, a camera 3, a microphone 4, a store server 5, and an external device 6. The drawer 2, the camera 3, and the microphone 4 are communicatively connected to the POS terminal 1 via a communication cable. The POS terminal 1 and the store server 5 are communicatively connected via a communication cable. The store server 5 and the external device 6 are communicatively connected via a network 7 which is the Internet, for example.

  The POS terminal 1 is placed on the drawer 2. The POS terminal 1 functions as an accounting processing device that processes customer accounting.

  The drawer 2 is placed on the cashier counter 8 disposed in the store. The drawer 2 includes a storage portion that opens and closes in a sliding manner. This storage unit stores banknotes, coins, and the like. One area partitioned by the cashier counter 8 is a standing position of a clerk in charge of accounting, and the other area is a standing position of a customer who receives accounting.

  The camera 3 images the imaging range A at a predetermined frame rate, and generates image data for each frame. The camera 3 is disposed at a position where at least the upper body of the customer who receives the transaction falls within the imaging range A. As the camera 3, a device equipped with a CCD (Charge Coupled Device) or the like can be used as appropriate.

  The microphone 4 generates sound data representing surrounding sounds. The microphone 4 is disposed at a position where at least the voice of a customer who receives a transaction can be collected.

  The store server 5 executes various processes for managing store operations. For example, the store server 5 stores in the auxiliary storage device price information of products sold at the store, transaction history information processed by the POS terminal 1, and store sales information, and uses these information. Various processes are performed.

  The external device 6 is, for example, a computer disposed in a security company office. The external device 6 includes an output device such as a display and a speaker. When the external device 6 receives a security-related report from the store, the external device 6 notifies the operator to that effect.

  FIG. 2 is a block diagram showing a main configuration of the POS terminal 1. The POS terminal 1 includes a central processing unit (CPU) 10, a read only memory (ROM) 11, a random access memory (RAM) 12, a communication device 13, an auxiliary storage device 14, a keyboard 15, a scanner 16, a store clerk display 17, a customer A side display 18, a printer 19, a connection I / F (Interface) 20, and a bus line 21 are provided.

  The bus line 21 connects the CPU 10, ROM 11, RAM 12, communication device 13, auxiliary storage device 14, keyboard 15, scanner 16, clerk side display 17, customer side display 18, printer 19, and connection I / F 20 so that they can communicate with each other. To do.

  The CPU 10 corresponds to the central part of the computer. The CPU 10 controls each unit to implement various functions as the POS terminal 1 according to an OS (Operating System) and application programs.

  The ROM 11 corresponds to a main storage portion of the computer. The ROM 11 stores the above operating system and application programs. The ROM 11 may store data necessary for the CPU 10 to execute various processes.

  The RAM 12 corresponds to the main storage portion of the computer. The RAM 12 stores data necessary for the CPU 10 to execute various processes as necessary. The RAM 12 is also used as a work area when the CPU 10 performs various processes.

  The communication device 13 communicates with the store server 5. The communication device 13 may communicate with the external device 6 via the store server 5.

  The auxiliary storage device 14 corresponds to the auxiliary storage portion of the computer. The auxiliary storage device 14 is, for example, an EEPROM (Electric Erasable Programmable Read-Only Memory), an HDD (Hard Disk Drive), or an SSD (Solid State Drive). The auxiliary storage device 14 stores a first security DB (Data Base) 101, a second security DB 102, a frequency file 103, and the like. The auxiliary storage device 14 may store the above application program.

  The keyboard 15 includes various keys such as a numeric keypad for inputting a numerical value, a subtotal key for inputting a subtotal instruction, and a current total key for inputting a current total instruction.

  The scanner 16 optically reads a barcode attached to a product.

  The clerk-side display 17 is, for example, an LCD (Liquid Crystal Display) or an OELD (Organic ElectroLuminescence Display). The clerk-side display 17 displays information necessary for the clerk to proceed with the accounting process.

  The customer side display 18 is, for example, an LCD or an OELD. The customer side display 18 displays information to be conveyed to the customer, for example, the total amount of the transaction and commercial information.

  The printer 19 prints a receipt including information such as the name and price of the purchased product, the total amount of the transaction, the amount deposited from the customer, and the change amount.

  The connection I / F 20 connects the POS terminal 1 to the drawer 2, the camera 3, and the microphone 4 via the communication cable described above. When the user performs a predetermined operation on the keyboard 15, the CPU 10 instructs the drawer 2 to open the storage unit via the connection I / F 20. When this command is received, the drawer 2 opens the storage unit. The POS terminal 1 takes in the image data generated by the camera 3 and the sound data generated by the microphone 4 through the connection I / F 20 under the control of the CPU 10.

  The application program stored in the ROM 11 or the auxiliary storage device 14 includes a security program describing security processing to be described later. The POS terminal 1 is transferred with the security program stored in the ROM 11 or the auxiliary storage device 14, for example. However, a security program individually assigned to the computer apparatus may be written in a writable storage device included in the computer apparatus in response to an operation by a user or the like. The security program can be transferred by recording on a removable recording medium or by communication via a network. The storage medium may be in any form, such as a magnetic disk, a magneto-optical disk, an optical disk, or a semiconductor memory, as long as it can be read by a reading device built in or connected to the computer device. When the auxiliary storage device 14 stores the security program, the security program may be temporarily stored in the auxiliary storage device 14 during a period in which the security process needs to be executed.

The first security DB 101, the second security DB 102, and the frequency file 103 will be described.
The first security DB 101 includes determination criterion information for determining success or failure of a first condition defined for at least one of a person's appearance, action, loudness, and content of a statement. The first condition represents an action that can be directly determined as a burglar or a dangerous person. In the present embodiment, the first condition is defined as the following X1 to X3.
[X1] The person shown in the image represented by the image data generated by the camera 3 takes out the dangerous substance.
[X2] A person shown in the image represented by the image data generated by the camera 3 leans out of the register counter 8 and tries to operate the POS terminal 1 or the drawer 2.
[X3] The sound represented by the sound data generated by the microphone 4 includes a statement that can be determined as a burglar.

  Dangerous goods in condition X1 are a knife, a gun, etc. The statement in the condition X3 is, for example, a statement requesting money, such as “give out money”.

The second security DB 102 includes determination criterion information for determining success or failure of a second condition defined for at least one of a person's appearance, action, loudness, and content of a statement. The second condition represents suspicious behavior, although it cannot be determined directly as a burglar or dangerous person. In the present embodiment, the second condition is defined as Y1 to Y6 below.
[Y1] The person shown in the image represented by the image data generated by the camera 3 covers the facial features.

[Y2] A person shown in the image represented by the image data generated by the camera 3 grabs the clerk.

[Y3] Although the person shown in the image represented by the image data generated by the camera 3 does not reach the operation of the POS terminal 1 or the drawer 2, the person gets out of the register counter 8.

[Y4] The volume of the voice included in the sound represented by the sound data generated by the microphone 4 exceeds a predetermined reference value.

[Y5] The sound expressed by the sound data generated by the microphone 4 includes a statement that threatens the store clerk.

[Y6] Before the barcode attached to the product is scanned by the scanner 16, an operation for opening the drawer 2 is performed.

  Condition Y1 is assumed to be satisfied when a person wears a mask, sunglasses, a helmet, or the like. The statement in the condition Y5 is, for example, a statement that does not apply to the statement in the condition X3 and threatens the store clerk. The operation like the condition Y6 is unnatural in view of the fact that there are many stores that refuse to exchange money.

  As in the conditions X1, X2, Y1 to Y3, the determination criterion information regarding the person displayed in the image represented by the image data includes various threshold values for determining, for example, the posture, appearance, or belongings of the person. It can be defined by image data or the like.

  Further, as in the conditions X3, Y4, and Y5, the determination criterion information related to the sound represented by the sound data can be defined by, for example, text data representing the content of a person's utterance, a voice loudness threshold, and the like.

  FIG. 3 shows an example of the data structure of the frequency file 103. The frequency file 103 defines the frequency S for each time zone. The number of times S is used in the security processing by the security program. The number of times S is set to a larger value in a time zone where there is less traffic around the store. In the example of FIG. 3, the number of times S in the time zone “0: 0 to 5:59” is “3”, and the number of times S in the time zone “6: 0 to 17:59” is “10” and “18:00”. The number of times S in the time period of ˜23: 59 ”is set to“ 5 ”.

  The POS terminal 1 executes security processing in the operating state. The security process is realized by the CPU 10 executing the security program. In the security process, the CPU 10 operates according to the flowchart of FIG.

  First, the CPU 10 captures image data generated by the camera 3 via the connection I / F 20 (Act 101). The CPU 10 stores the captured image data in the RAM 12.

  After Act 101, the CPU 10 tries to extract an area corresponding to a person from the image represented by the image data stored in the RAM 12 (Act 102). For this process, a known image recognition technique can be used as appropriate. For example, the CPU 10 attempts to extract a characteristic portion such as a person's head or hand from an image represented by the image data.

  Subsequently, the CPU 10 determines whether an area corresponding to a person has been extracted in Act 102 (Act 103). When it determines with having recognized (Yes of Act103), CPU10 performs the determination process which determines the success or failure of the 1st condition mentioned above and a 2nd condition (Act104). After the determination process, or when it is determined in Act 103 that the person cannot be recognized (No in Act 103), the CPU 10 ends the security process.

In the determination process, the CPU 10 operates according to the flowchart of FIG.
First, the CPU 10 generates a counter N in the RAM 12 and resets the value to zero (Act 201).

  Subsequently, the CPU 10 determines the number of times S used in the subsequent processing (Act 202). In this process, for example, the CPU 10 accesses a clock circuit (not shown) to acquire the current time, specifies the time zone to which the acquired time belongs from the number-of-times file 103, and sets a numerical value determined for the specified time zone. Is determined as the number of times S used in the subsequent processing.

  After Act 202, the CPU 10 starts capturing image data generated by the camera 3 (Act 203). The CPU 10 stores the captured image data in the RAM 12. After Act 203, the CPU 10 repeatedly executes fetching of image data and storage in the RAM 12 until the determination process is completed.

  After Act 203, the CPU 10 starts capturing sound data generated by the microphone 4 (Act 204). The CPU 10 stores the acquired sound data in the RAM 12. After Act 204, the CPU 10 repeatedly executes acquisition of sound data and storage in the RAM 12 until the determination process is completed.

  After Act 204, the CPU 10 determines whether or not a predetermined end condition is satisfied (Act 205). Details of the termination condition will be described later.

  If it is determined that the end condition is not satisfied (No in Act 205), the CPU 10 tries to extract an area corresponding to a person from the image represented by the image data stored in the RAM 12 (Act 206), as in Act 102. . Specifically, when Act 206 is executed for the first time after the determination process is started, the CPU 10 corresponds to a person with at least one image data saved in the RAM 12 as a target after starting the capture of the image data in Act 203, for example. Attempt to extract regions. In Act 206 executed after the determination process is started for the second time or later, the CPU 10 extracts an area corresponding to a person for at least one image data stored in the RAM 12 after executing the previous Act 206, for example. Try. When the CPU 10 can extract an area corresponding to a person, the CPU 10 generates image data representing the area and stores it in the RAM 12. Hereinafter, this image data is referred to as person area data.

  After Act 206, the CPU 10 attempts to recognize a human voice from the sound represented by the sound data stored in the RAM 12 (Act 207). Specifically, when Act 207 is executed for the first time after the determination process is started, the CPU 10 tries to recognize the voice for a series of sound data stored in the RAM 12 after starting the capture in Act 204, for example. In Act 207 to be executed for the second and subsequent times after the determination process is started, the CPU 10 tries to recognize the voice for a series of sound data stored in the RAM 12 after executing the previous Act 207, for example. In this process, a known voice recognition technique can be used as appropriate. When the CPU 10 can recognize the voice of the person, the CPU 10 generates text data representing the content of the speech and volume data representing the loudness of the voice, and stores them in the RAM 12. The volume data may be, for example, the maximum volume [dB] during the duration of the recognized voice.

  After Act 207, the CPU 10 refers to the determination criterion information in the first security DB 101 to determine whether the first condition, that is, the conditions X1 to X3 are successful (Act 208). For the conditions X1 and X2, the CPU 10 determines success / failure based on the person area data stored in the RAM 12 in Act 206 and the determination criterion information of these conditions. If the area corresponding to the person cannot be extracted in the immediately preceding Act 206, the conditions X1 and X2 are not satisfied. In addition, regarding the condition X3, the CPU 10 determines success / failure based on the text data stored in the RAM 12 in Act 207 and the determination criterion information of this condition. If the voice cannot be recognized in the immediately preceding Act 207, the condition X3 is not satisfied.

  In Act 208, when it is determined that all of the conditions X1 to X3 are not satisfied (No in Act 208), the CPU 10 refers to the determination criterion information in the second security DB 102 and determines whether the second condition, that is, the conditions Y1 to Y6 is successful. (Act 209). With respect to the conditions Y1 to Y3, the CPU 10 determines success / failure based on the person area data stored in the RAM 12 in Act 206 and the criterion information of these conditions. If the area corresponding to the person has not been extracted in the immediately preceding Act 206, the conditions Y1 to Y3 are not satisfied. Further, the CPU 10 determines success or failure based on the volume data stored in the RAM 12 in Act 207 for the condition Y4 and the criterion information for this condition, and the text data stored in the RAM 12 in Act 207 for the condition Y5. Success or failure is determined based on the determination criterion information of this condition. If the voice cannot be recognized in the immediately preceding Act 207, the conditions Y4 and Y5 are not satisfied. Further, the CPU 10 determines success or failure with reference to the history of input from the scanner 16 and the keyboard 15 regarding the condition Y6.

  If it is determined in Act 209 that any one of the conditions Y1 to Y6 is satisfied, the CPU 10 changes the value of the counter N to a value obtained by adding the number of satisfied conditions Y1 to Y6 to the current value of the counter N. (Act 210).

  After Act 210, the CPU 10 determines whether or not the value of the counter N has reached the number of times S determined in Act 202 (Act 211). When the value of the counter N has not reached the number of times S determined in Act 202 (No in Act 211), the CPU 10 executes the operation after Act 205 again.

  If it is determined in Act 208 that at least one of the conditions X1 to X3 is satisfied (Yes in Act 208), and if it is determined in Act 211 that the value of the counter N has reached the number of times S (Yes in Act 211), the CPU 10 (Act 212). In the notification process, the CPU 10 transmits notification data including store identification information such as a store name to the external device 6 via the communication device 13. The report data is sent to the external device 6 via the store server 5 and the network 7. When the notification data is received, the external device 6 notifies the operator of the notification using the output device and the store identification information included in the notification data.

  The CPU 10 may transmit not only the report data but also the image data generated by the camera 3 and the sound data generated by the microphone 4 to the external device 6. In this case, the external device 6 displays the received image data on the display, and outputs the received sound data from the speaker, so that the current store situation can be communicated to the operator.

  After Act 212, the CPU 10 ends the determination process. Even when it is determined in Act 205 that the end condition is satisfied (Yes in Act 205), the CPU 10 ends the determination process. As the termination condition, for example, a condition indicating that the accounting for one customer is terminated may be adopted. By adopting such conditions, the counter N can be reset for each customer to be accounted for and unnecessary notifications can be prevented. Specifically, the end condition may be that no person has been recognized in the immediately preceding Act 206. In this case, since the person has left the cashier counter 8, it is considered that the person is a normal customer and the accounting for the customer is completed. Note that in the first Act 205 in the determination process, Act 206 has not been performed. In this case, the CPU 10 may determine that the end condition is not satisfied. In addition, the end condition may be that the closing of the accounting is declared by the operation of the keyboard 15 through the input from the scanner 16 or the like, or that a predetermined time has elapsed from the start of the determination process.

  According to the present embodiment described above, even if a person who appears to be a burglar or a dangerous person appears, the POS terminal 1 reports to the outside without the store clerk operating the button. Therefore, the security of the store can be improved without imposing a burden on the store clerk. Furthermore, in a conventional system in which a store clerk operates a button to report, there is a possibility that the action of operating the button may stimulate a burglar or the like, but such a situation does not occur in the present embodiment.

  Further, in the present embodiment, the POS terminal 1 reports to the outside when the first condition is satisfied even once, and notifies the outside when the second condition is satisfied by the number of times S. By using two types of conditions in this way, it is possible to set conditions that assume various situations.

  In the present embodiment, the POS terminal 1 changes the number of times S according to the time zone. As a result, for example, it is possible to construct a security system that matches the store environment, such as setting the number of times S so that it is easy to report during times that are likely to be robbed, and difficult to report during times that are not. .

Several modifications of the present embodiment will be described.
For example, the security processing may be executed by an accounting processing device other than a POS terminal such as an ECR (Electric Cash Register) or a card payment terminal specialized for card payment.

  A security system may be constructed without using a POS system. In this case, for example, a security processing device that executes the security processing described with reference to FIGS. 4 and 5 is provided separately from the components of the POS system. The security processing device may be disposed in the store or may be disposed outside the store. An external device 6 can also be used as this security processing device. The camera 3 and the microphone 4 may be connected to the security processing apparatus without going through the POS terminal 1.

  A condition relating to any one of the image data generated by the camera 3 and the sound data generated by the microphone 4 may be excluded from the first condition and the second condition.

  The execution subject of the security process is not limited to the CPU, and may be any hardware having a function of executing information processing based on a program.

  The number of times S used for the determination process may be changed according to other conditions such as day of the week and season, as well as the time zone.

  A part or all of the functions realized by the CPU by the security processing can be realized by hardware that executes information processing not based on a program such as a logic circuit. Each of the above functions can also be realized by combining software control with hardware such as the above logic circuit.

  Part or all of the processing for obtaining each function realized by the CPU by security processing may be executed by an OS running on the computer, middleware such as database management software, network software, or the like.

  The storage medium for storing the security program is not limited to one, and the security program may be divided into a plurality of program modules, and the plurality of program modules may be distributed and stored in a plurality of storage media.

  The security processing may be realized by distributed processing by a plurality of CPUs. In this case, the plurality of CPUs may be mounted on a single device or may be mounted on a plurality of different devices.

  Cloud computing can also be used to implement security processing. In this case, for example, SaaS (Software as a Service) may be used to cause a server included in the cloud system to execute all or part of the security processing.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  A ... imaging range, 1 ... POS terminal, 2 ... drawer, 3 ... camera, 4 ... microphone, 5 ... store server, 6 ... external device, 7 ... network, 8 ... register counter, 10 ... CPU, 101 ... first security DB, 102 ... second security DB, 103 ... number-of-times file.

Claims (6)

Obtaining means for obtaining image data representing an image captured by the camera;
Extraction means for extracting a region corresponding to a person from the image represented by the image data acquired by the acquisition means;
A determination unit that determines whether a predetermined condition is satisfied for at least one of a person's appearance and behavior based on the region extracted by the extraction unit;
If the determination means determines that the condition is satisfied, a reporting means for reporting to the outside,
An accounting processing apparatus comprising: Obtaining means for obtaining sound data representing the sound collected by the microphone;
Recognition means for recognizing a human voice from the sound represented by the sound data acquired by the acquisition means;
Determination means for determining whether a predetermined condition is satisfied with respect to at least one of the volume of the voice and the content of the speech based on the voice recognized by the recognition means;
If the determination means determines that the condition is satisfied, a reporting means for reporting to the outside,
An accounting processing apparatus comprising: The conditions include a first condition and a second condition,
The notification means notifies the outside in response to determining that the determination means is satisfied even once for the first condition, and the determination means determines a predetermined number of times for the second condition. To report to the outside according to the decision that
The accounting processing apparatus according to claim 1 or 2. The reporting means changes the number of times according to a time zone,
The accounting processing apparatus according to claim 3. Computer
Acquisition means for acquiring image data representing an image captured by the camera;
Extraction means for extracting a region corresponding to a person from an image represented by the image data acquired by the acquisition means;
A determination unit that determines whether a predetermined condition is satisfied with respect to at least one of a person's appearance and behavior based on the region extracted by the extraction unit; and
If the determination means determines that the condition is satisfied, a reporting means for reporting to the outside,
Program to function as. Computer
Acquisition means for acquiring sound data representing the sound collected by the microphone;
Recognition means for recognizing a human voice from the sound represented by the sound data acquired by the acquisition means;
A determination unit that determines whether a predetermined condition is satisfied with respect to at least one of the volume of the voice and the content of the speech based on the voice recognized by the recognition unit; and
If the determination means determines that the condition is satisfied, a reporting means for reporting to the outside,
Program to function as.

Images