Prompt tone broadcasting method, system and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a prompt tone broadcasting method, system and device, computer equipment, a storage medium and a computer program product. The method comprises the steps that when it is detected that a target person enters a target area, first feature information of the target person is collected, and the target staying duration of the target person is determined; within the target stay duration, collecting second feature information of each person leaving the target area, and collecting third feature information of each person interacting with the target device in the target area; and after the target stay duration, matching the first feature information with the second feature information and the third feature information, and when the first feature information is not matched with each piece of second feature information and each piece of third feature information, broadcasting a target prompt tone. The method can assist a merchant to detect customers needing to pay attention to.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a prompt tone broadcasting method, system, device, computer equipment, storage medium and computer program product. Background Art

[0002] With the promotion of the application of Internet of Things technology, smart devices have been widely used in people's daily lives. For example, convenience stores, small supermarkets, restaurants and other merchants usually place devices with voice broadcasts in the stores, so that they can understand the status of customers by listening to voice in time when there are many customers.

[0003] In the related art, there are intelligent devices such as induction doorbells that can play welcome voices, or payment cloud speakers that can play payment voices. However, such devices usually only play voices for certain behaviors of customers (entering a merchant or completing payment). In actual applications, in addition to understanding individual behaviors of customers, merchants usually also need to understand which customers need attention through their behaviors. Therefore, it is necessary to provide a method that can help merchants determine the target customers that need attention at present. Summary of the invention

[0004] Based on this, it is necessary to provide a prompt sound broadcast method, system, device, computer equipment, storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a prompt tone broadcasting method. The method comprises:

[0006] When a target person is detected to enter a target area, first feature information of the target person is collected, and a target stay time of the target person is determined;

[0007] During the target stay time, collecting second feature information of each person leaving the target area, and collecting third feature information of each person interacting with the target device in the target area;

[0008] After the target stay time has elapsed, the first feature information is matched with the second feature information and the third feature information. If the first feature information does not match with each of the second feature information and each of the third feature information, a target prompt sound is broadcast.

[0009] In one embodiment, determining a target stay time for the target person includes:

[0010] Determining a collection period for the target person according to the time point when the target person enters the target area;

[0011] Acquire the amount of first feature information collected during the collection period;

[0012] The target stay duration is determined according to at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

[0013] In one embodiment, determining a target stay time for the target person further includes:

[0014] Acquire the amount of second characteristic information and the amount of third characteristic information collected during the collection period;

[0015] The target stay duration is determined according to a first difference between the amount of the second feature information and the amount of the third feature information, and the target stay duration is negatively correlated with the first difference.

[0016] In one embodiment, the broadcasting of the target prompt tone includes:

[0017] Obtaining a second difference between the amount of second feature information collected during the target's stay time and the amount of first feature information collected during the target's stay time;

[0018] When the second difference is greater than a preset quantity threshold, a target volume of the target prompt sound is determined according to the second difference, and the target prompt sound is broadcast based on the target volume; the target volume is positively correlated with the second difference.

[0019] In one embodiment, collecting the third characteristic information of each person interacting with the target device in the target area includes:

[0020] receiving interaction notification information sent by the target device, where the interaction notification information is sent when a person interacts with the target device;

[0021] Image information of the area where the target device is located is collected, and third feature information of a person interacting with the target device is extracted from the image information.

[0022] In a second aspect, the present application also provides a prompt tone broadcasting device. The device comprises:

[0023] A first acquisition module is used to acquire first characteristic information of the target person and determine the target stay time of the target person when detecting that the target person enters the target area;

[0024] A second collection module is used to collect second characteristic information of each person who leaves the target area within the target stay time, and collect third characteristic information of each person who interacts with the target device in the target area;

[0025] A matching module is used to match the first characteristic information with the second characteristic information and the third characteristic information after the target stays for a certain period of time, and to broadcast a target prompt sound when the first characteristic information does not match any of the second characteristic information and the third characteristic information.

[0026] In one embodiment, the first acquisition module is further used for:

[0027] Determining a collection period for the target person according to the time point when the target person enters the target area;

[0028] Acquire the amount of first feature information collected during the collection period;

[0029] The target stay duration is determined according to at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

[0030] In one embodiment, the first acquisition module is further used for:

[0031] Acquire the amount of second characteristic information and the amount of third characteristic information collected during the collection period;

[0032] The target stay duration is determined according to a first difference between the amount of the second feature information and the amount of the third feature information, and the target stay duration is negatively correlated with the first difference.

[0033] In one embodiment, the matching module is further used for:

[0034] Obtaining a second difference between the amount of second feature information collected during the target's stay time and the amount of first feature information collected during the target's stay time;

[0035] When the second difference is greater than a preset quantity threshold, a target volume of the target prompt sound is determined according to the second difference, and the target prompt sound is broadcast based on the target volume; the target volume is positively correlated with the second difference.

[0036] In one embodiment, the second acquisition module is further used for:

[0037] receiving interaction notification information sent by the target device, where the interaction notification information is sent when a person interacts with the target device;

[0038] Image information of the area where the target device is located is collected, and third feature information of a person interacting with the target device is extracted from the image information.

[0039] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any one of the above methods is implemented.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, any of the above methods is implemented.

[0041] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, any of the above methods is implemented.

[0042] The above-mentioned prompt tone broadcast method, system, device, computer equipment, storage medium and computer program product, after detecting that the target person enters the target area, sets a target stay time for the target person, and detects whether the target person has left the target area or whether the target person interacts with the target device in the target area during the target stay time. If the target person still stays in the target area after the target stay time, but does not interact with any target device, the merchant can be reminded by the target prompt tone to indicate that the target person may be a person that the merchant needs to focus on and provide help for. The embodiment of the present application determines whether the target person needs to be paid attention to based on whether the target person has taken an action of leaving the target area or interacting with the target device in the target area during the target stay time, so it can assist the merchant in identifying the person who needs to be paid attention to. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a flow chart of a prompt tone broadcasting method in one embodiment;

[0044] Figure 2 is a flow chart of step 102 in one embodiment;

[0045] Figure 3 is a flow chart of step 102 in one embodiment;

[0046] Figure 4 is a flow chart of step 106 in one embodiment;

[0047] Figure 5 is a flow chart of step 104 in one embodiment;

[0048] Figure 6 is a schematic diagram of an induction doorbell module in one embodiment;

[0049] Figure 7 A schematic diagram of a payment cloud speaker module in one embodiment;

[0050] Figure 8 It is a structural block diagram of a prompt tone broadcasting device in one embodiment;

[0051] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] In one embodiment, Figure 1 As shown, a prompt tone broadcast method is provided. This embodiment takes the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0054] Step 102, when it is detected that the target person enters the target area, the first characteristic information of the target person is collected, and the target stay time of the target person is determined.

[0055] In the embodiment of the present application, the target person is any person who enters the target area, and the target area is an area set by the technicians in which the customer behavior needs to be detected. For example, the target area can be the sales area of ​​a store, the dining area of ​​a restaurant, etc.

[0056] Detection equipment that can detect people entering and leaving the target area and collect information about people entering and leaving the target area can be installed at the entrance and exit area of ​​the target area, such as image acquisition equipment, infrared sensing equipment, sound acquisition equipment, etc. When the detection equipment detects that a target person has entered the target area, the detection equipment can send notification information about the target person entering the target area to the server and upload the collected information about the target person, such as images taken of the target person, collected sounds, etc.

[0057] The server can extract characteristic information of the target person based on the target person information. The characteristic information can be any information that can identify a specific target person, such as facial features of the target person, clothing color features of the target person, height features of the target person, etc. The embodiment of the present application does not specifically limit how the server extracts characteristic information, and the server can use any existing pre-trained neural network model to extract characteristic information.

[0058] In order to distinguish the feature information extracted by the server for people performing different activities, the information extracted by the server for people entering the target area is referred to as the first feature information, the information extracted by the server for people leaving the target area is referred to as the second feature information, and the information extracted by the server for people interacting with the target device in the target area is referred to as the third feature information.

[0059] The target device refers to the device that provides payment services to customers in the target area, such as cash registers, vending machines, etc. If a customer interacts with the target device, it may indicate that the customer has received the required service in the target area, and the probability that the merchant needs to pay attention to these customers is low.

[0060] After the server extracts the first characteristic information, it caches the first characteristic information and determines a target stay time for the target person, which is used to indicate the reasonable length of time that the target person stays in the target area and does not interact with any target device in the target area. The target stay time can be preset, for example, to half an hour, one hour, etc. It can also be dynamically adjusted according to actual conditions, for example, to set the target stay time according to the flow of people in the target area, etc.

[0061] It should be noted that the personnel entering the target area may also include staff members of the merchant. The characteristic information of these staff members may be entered into the server in advance. After extracting the first characteristic information, the server compares the first characteristic information with the characteristic information of each staff member. If the similarity between the first characteristic information and the characteristic information of a staff member exceeds a threshold, the server discards the first characteristic information.

[0062] Step 104, within the target stay time, collect the second feature information of each person leaving the target area, and collect the third feature information of each person interacting with the target device in the target area.

[0063] In an embodiment of the present application, after determining the target stay time, the server can send the target stay time to the detection devices located in the entrance and exit areas and the area where the target device is located, so as to notify these detection devices to collect information on persons leaving the target area and persons interacting with the target device within the target stay time, and upload the collected personnel information to the server.

[0064] It should be noted that there may be multiple target persons entering the target area within a period of time, and the server will determine a target stay time for each target person, and these target stay times may overlap. After the server determines the target stay time for a certain target person, it can determine whether the current time point is within the coverage of a certain valid target stay time. If so, the server can determine the latest end time point among the end time points of each target stay time, and send the latest end time point to each detection device to notify these detection devices that they need to continue collecting information before the latest end time point.

[0065] The server extracts the second characteristic information and the third characteristic information from the personnel information uploaded by each detection device, and can store the second characteristic information and the third characteristic information.

[0066] Step 106, after the target stay time has elapsed, the first characteristic information is matched with the second characteristic information and the third characteristic information. If the first characteristic information does not match with each of the second characteristic information and each of the third characteristic information, a target prompt tone is broadcasted.

[0067] In an embodiment of the present application, after the end time point of the target stay time of a target person arrives, the server obtains each second feature information and third feature information collected within the target stay time of the target person, and matches the first feature information of the target person with each second feature information and third feature information. The matching method can be to calculate the similarity between the first feature information and the second feature information or the third feature information. If the similarity is greater than a threshold value, it is considered that the first feature information and the second feature information or the third feature information match.

[0068] If the first characteristic information matches one of the second characteristic information or one of the third characteristic information, it means that the target person has a high probability of obtaining the required service in the target area within the target stay time, or even if he or she has not obtained the required service, he or she has left the target area within the target stay time. The probability that the merchant needs to pay attention to the target person is low.

[0069] If the first characteristic information does not match each of the second characteristic information and each of the third characteristic information, it indicates that the target person is likely to still be in the target area, and the target person is likely to not have received the required service. In this case, the target person is a person who needs the merchant's attention.

[0070] A sound broadcast device can be set up in the target area, and the server can send a broadcast prompt tone notification to the sound broadcast device, instructing the sound broadcast device to broadcast the target prompt tone to remind the merchant. The target prompt tone can be pre-set by the technician.

[0071] The prompt tone broadcast method provided in the embodiment of the present application sets a target stay time for the target person after detecting that the target person has entered the target area, and detects whether the target person has left the target area or whether the target person has interacted with the target device in the target area during the target stay time. If the target person still stays in the target area after the target stay time, but has not interacted with any target device, the merchant can be reminded by the target prompt tone to indicate that the target person may be a person that the merchant needs to focus on and provide help for. The embodiment of the present application determines whether the target person needs to be paid attention to based on whether the target person has taken an action of leaving the target area or interacting with the target device in the target area during the target stay time, so it can assist the merchant in identifying the person who needs to be paid attention to.

[0072] In one embodiment, Figure 2 As shown, in step 102, determining the target stay time for the target person includes:

[0073] Step 202, determining a collection period for the target person according to the time point when the target person enters the target area.

[0074] Step 204, obtaining the amount of first characteristic information collected during the collection period.

[0075] Step 206, determining the target stay time according to at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

[0076] In the embodiment of the present application, the target stay time is determined based on the information collected by the server in a collection period. The length of the collection period can be pre-set by the technician, for example, it can be set to 1 hour, 1 day, etc.

[0077] The collection period corresponding to the time point when the target person enters the target area may be a completed collection period closest to the time point. For example, if the collection period is 1 hour and the time point when the target person enters the target area is 10:36, the completed collection period closest to the time point is the collection period from 9:00 to 10:00.

[0078] Or the collection period corresponding to the time point when the target person enters the target area can also be the collection period to which the same time point belongs on the previous day, the same day of the previous week (for example, if today is Friday of this week, the same day of the previous week refers to Friday of the previous week), or the same day of the previous month (for example, if today is the 22nd of this month, the same day of the previous month refers to the 22nd of the previous month). For example, if the length of the collection period is 1 hour and the time point when the target person enters the target area is 10:36, the collection period to which the same time point of the previous day belongs is the collection period from 10:00 to 11:00 of the previous day.

[0079] The collection cycle itself is correlated with the reasonable length of time that the target person stays in the target area (for example, when the target area is a dining area, since the dining time for dinner is generally longer than that for breakfast, the target length of time corresponding to the evening collection cycle should be longer than the target length of time corresponding to the morning collection cycle). The amount of first feature information collected within the collection cycle represents the flow of people entering the target area within a collection cycle. The personnel characteristics of the target person may include any characteristics that can be extracted from the information collected by the detection equipment, such as the gender, age group, etc. of the target person. The above information is related to the reasonable target length of time that the target person stays.

[0080] The target stay time can be determined based on at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person. Exemplarily, the duration of the target person who enters the target area staying in the target area can be obtained within a preset duration (the duration can be calculated based on the difference between the time point when the first feature information is collected for the target person and the time point when the second feature information is collected for the target person), and the start time point and end time point of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person are used as inputs, and the duration of the target person staying in the target area is used as output to train the neural network model. In the application, the trained neural network model can be used to obtain the target stay time of the target person based on the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

[0081] Alternatively, a fixed preset stay time may be preset for each collection cycle, and then the fixed preset stay time may be increased or decreased according to the amount of first characteristic information collected during the collection cycle or the characteristics of the target person, to obtain the target stay time. Exemplarily, the amount of first characteristic information collected during the collection cycle may be positively correlated with the time required to be increased (the time required to be increased may be negative), and after obtaining the collection cycle and the amount of first characteristic information collected during the collection cycle, the time required to be increased may be calculated according to the amount of first characteristic information collected, and the time required to be increased and the preset stay time corresponding to the collection cycle may be added to obtain the target stay time.

[0082] In one embodiment, Figure 3 As shown, in step 102, determining the target stay time for the target person also includes:

[0083] Step 302, obtaining the amount of second characteristic information and the amount of third characteristic information collected during the collection period;

[0084] Step 304: Determine the target stay time according to the first difference between the amount of the second characteristic information and the amount of the third characteristic information, wherein the target stay time is negatively correlated with the first difference.

[0085] In an embodiment of the present application, in addition to determining the target stay duration based on the collection period, the amount of first feature information collected during the collection period, and the personal characteristics of the target person, the target stay duration can also be determined based on the amount of second feature information collected during the collection period and the amount of third feature information collected during the collection period.

[0086] Since the number of the second feature information represents the number of people who leave the target area during the collection period, and the number of the third feature information represents the number of people who interact with the target device during the collection period, the difference between the number of the second feature information and the number of the third feature information (the first difference) can roughly represent the number of people who did not interact with the target device during the collection period, that is, the number of people who left the target area.

[0087] Since the length of time a person stays in the target area is generally shorter when the person does not interact with the target device, the target length of stay can be negatively correlated with the first difference. That is, if more people leave the target area without interacting with the target device during a certain collection period, the target length of stay for the target person in that collection period can be set shorter. If most people interact with the target device before leaving during a certain collection period, the target length of stay for the target person in that collection period can be set longer.

[0088] The prompt tone broadcast method provided in the embodiment of the present application can provide a relatively simple method for estimating the target stay time without matching each first feature information, second feature information and third feature information, so as to determine the actual stay time of each person entering the target area during the collection period, and then determine the target stay time based on the actual stay time. It is suitable for scenarios where the target area has a large flow of people and the server's computing power is not strong (for example, using a control chip built into an existing detection device to realize the server's function), reducing the burden on the server.

[0089] In one embodiment, Figure 4 As shown, in step 106, the target prompt tone is broadcasted, including:

[0090] Step 402, obtaining a second difference between the amount of second characteristic information collected during the target's stay time and the amount of first characteristic information collected during the target's stay time;

[0091] Step 404, when the second difference is greater than a preset quantity threshold, determine a target volume of the target prompt sound according to the second difference, and broadcast the target prompt sound based on the target volume; the target volume is positively correlated with the second difference.

[0092] In the embodiment of the present application, the second difference between the amount of the second characteristic information collected during the target stay time and the amount of the first characteristic information can be counted. The difference represents the number of people who enter and are still in the target area during the target stay time.

[0093] Since there are fewer people in the target area, merchants can generally determine the customers who need attention by themselves. At the same time, frequent broadcasting of reminder sounds when there are fewer people will also disturb customers. Therefore, the target reminder sound can be broadcast only when there are more people in the target area.

[0094] At the same time, the volume of the target prompt sound can also be set according to the number of people in the target area. A volume range can be set, and within the volume range, the volume of the target prompt sound is positively correlated with the second difference. For example, the difference between the maximum and minimum values ​​in the volume range can be calculated, and the difference between the largest second difference and the smallest second difference over a period of time can be counted, and the ratio between the difference between the maximum and minimum values ​​in the volume range and the difference between the largest second difference and the smallest second difference can be used as the volume coefficient. In practical applications, the product of the second difference and the volume coefficient can be used as the target volume of the target prompt sound.

[0095] The prompt tone broadcasting method provided in the embodiment of the present application can broadcast the target prompt tone at a higher volume when there are a large number of people in the target area, so that the merchant can still notice the target prompt tone in a noisy environment. When there are a small number of people in the target area, the volume of the target prompt tone is correspondingly reduced to avoid disturbing the people in the target area.

[0096] In one embodiment, Figure 5 As shown, in step 104, the third feature information of each person interacting with the target device in the target area is collected, including:

[0097] Step 502, receiving interaction notification information sent by the target device, where the interaction notification information is sent when a person interacts with the target device;

[0098] Step 504: collect image information of the area where the target device is located, and extract third feature information of the person interacting with the target device from the image information.

[0099] In the embodiment of the present application, the target device can send interaction notification information to the server when a person interacts with the target device. For example, when the target device is a vending machine, the vending machine can send interaction notification information to the server after a person interacts with the vending machine and completes the purchase of goods.

[0100] After receiving the interaction notification information, the server may notify the detection device in the area where the target device is located to collect images of the area where the target device is located. After receiving the collected image information, the server may extract the third feature information of the person interacting with the target device from the image information. For example, the server may determine the location of the target device from the image information, and identify the persons within a certain range around the location of the target device, and regard these persons as persons interacting with the target device, and extract the third feature information of these persons.

[0101] The prompt tone broadcast method provided in the embodiment of the present application can collect image information of the area where the target device is located and extract the third characteristic information from the image information when receiving a message that the user interacts with the target device. It can provide a relatively simple method for determining the timing of collecting the third characteristic information without continuously collecting information about the area where the target device is located, which can reduce the load on the device responsible for collecting information.

[0102] In one embodiment, a prompt sound broadcasting system is provided, the system includes an induction doorbell module, a payment cloud speaker module and a control module, wherein the induction doorbell module is used to collect first characteristic information of the person entering the target area when detecting that the person enters the target area, broadcast a first prompt sound, and send the first characteristic information to the control module; and is also used to collect second characteristic information of the person leaving the target area when detecting that the person leaves the target area, broadcast a second prompt sound, and send the second characteristic information to the control module; the payment cloud speaker module is used to prompt the person to make a payment by interacting with the payment cloud speaker module, and broadcast a successful payment message when receiving the successful payment message. The third prompt sound collects the third characteristic information of the person interacting with the payment cloud speaker module, and sends the third characteristic information to the control module; the control module is used to determine the target stay time corresponding to the first characteristic information for any first characteristic information, and after the target stay time has passed, match the first characteristic information with the second characteristic information and the third characteristic information collected within the target stay time; the control module is also used to send a target prompt sound broadcast request to the sensing doorbell module and / or the payment cloud speaker module when the first characteristic information does not match the second characteristic information and the third characteristic information, and the first prompt sound broadcast request is used to indicate the broadcast of the target prompt sound.

[0103] In the embodiment of the present application, the method in the above embodiment is performed using an induction doorbell and a payment cloud speaker. The control module can be a module independent of the induction doorbell and the payment cloud speaker, or it can be a control chip of the induction doorbell or the payment cloud speaker.

[0104] Induction doorbell module Figure 6 As shown, it includes a control chip, a sensing module and an audio playback module.

[0105] The main controller is used to interact with the payment cloud speaker module, extract feature information from the information collected by the sensing module, and push prompt sound information to the audio playback module. The audio playback module contains one or more speakers for playing prompt sounds, and the sensing module is used to detect people entering or leaving the target area and collect information about the people. The sensing module can be implemented using infrared sensors, camera motion detection, etc.

[0106] The specific functions of the induction doorbell module in the prompt sound broadcasting system are: when a person is detected to enter the target area, the first characteristic information is collected and the first prompt sound is broadcasted, and the first characteristic information is sent to the control module; when a person is detected to leave the target area, the second characteristic information is collected and the second prompt sound is broadcasted, and the second characteristic information is sent to the control module. The prompt sound broadcasting when a person leaves or enters the target area can be realized based on the functions of any existing induction doorbell, and the collection of characteristic information and the sending of characteristic information to the control module can be realized by modifying the program in the existing induction doorbell control chip.

[0107] The specific implementation method of each of the above steps can be found in the aforementioned embodiments, and will not be repeated in the embodiments of this application.

[0108] Furthermore, when the induction doorbell detects that a person enters the target area, it can also send a voice broadcast request to the payment cloud speaker module, so that the payment cloud speaker module synchronously plays a third prompt voice, and the third prompt voice can be the merchant's promotional information, etc.

[0109] Payment Cloud Speaker Module Figure 7 As shown, it includes a control chip, a wireless communication module, an audio playback module, a power module, a storage module and a display module.

[0110] Among them, the control chip is used to process data and control other hardware modules. The wireless communication module is used to connect to the Internet wirelessly, so that the payment cloud speaker module can access the Internet of Things device management platform, receive the payment confirmation information pushed by the management platform, and perform remote management. The wireless communication module can support communication protocols such as 4G (fourth generation mobile communication standard), Wi-Fi (wireless local area network), and Bluetooth. The audio playback module includes one or more speakers for playing prompt sounds. The power module is used to provide a stable power supply for the payment cloud speaker module and its internal component modules. It can be powered by an AC power adapter, a USB (universal serial bus) interface, and a built-in rechargeable battery. The storage module is used to store music files, prompt sounds, control software, and log information of the payment cloud speaker module and the induction doorbell module that can be played by the induction doorbell or the payment cloud speaker. The display module is used to display information such as the current time, the amount of the current payment, the battery power, and the network signal strength. The user interaction module may include buttons or LED (light-emitting diode) indicators to allow users to interact with the device, such as turning on and off, starting pairing mode, adjusting the volume, and listening repeatedly or selecting prompt sounds.

[0111] The specific function of the payment cloud speaker module in the prompt sound broadcast system is: the user can pay through the payment information displayed on the display module by the payment cloud speaker module, or can pay by other means. When the payment cloud speaker module is started, it actively connects and registers to the Internet of Things device management platform through the domain name, account name and account password preset during production, and binds with the merchant's account in the Internet of Things device management platform. When there is money entering the merchant's account, the Internet of Things device management platform will push the payment success message to the payment cloud speaker module. After receiving the payment success message, the payment cloud speaker module broadcasts the third prompt sound, collects the third feature information of the person interacting with the payment cloud speaker module, and sends the third feature information to the control module. Among them, the function of broadcasting the third prompt sound after receiving the payment success message can be realized based on the function of any payment cloud speaker. Collecting feature information and sending feature information to the control module can be realized by installing an image acquisition module on the existing payment cloud speaker and modifying the program in the existing payment cloud speaker control chip.

[0112] The specific implementation method of each of the above steps can be found in the aforementioned embodiments, and will not be repeated in the embodiments of this application.

[0113] The function of the control module is to set a target stay time for the first characteristic information, and after the target stay time has passed, match the first characteristic information with the second characteristic information and the third characteristic information collected during the target stay time. If the first characteristic information does not match the second characteristic information and the third characteristic information, the control module sends a target prompt sound broadcast request to the induction doorbell module and / or the payment cloud speaker module, and the target prompt sound broadcast request is used to instruct the broadcast of the target prompt sound.

[0114] The specific implementation method of each of the above steps can be found in the aforementioned embodiments, and will not be repeated in the embodiments of this application.

[0115] The specific device selected by the control module to broadcast the target prompt sound can be determined according to the device on which the control module is located. For example, when the control module is a control chip of an induction doorbell, the control module can control the audio playback module of the induction doorbell to play the target prompt sound, so that the control module can send a target prompt sound broadcast request through wired communication inside the device, thereby improving communication efficiency.

[0116] The induction doorbell module, the payment cloud speaker module and the control module can be in an integrated or split form. A wired interface can be set on the induction doorbell module, the payment cloud speaker module and the control module so that the three parts can be connected and communicated by wire when spliced ​​together, thereby improving communication efficiency.

[0117] Users can also remotely control the above three modules through smartphones, such as updating and setting the doorbell welcome message, adjusting the doorbell volume, and viewing historical payment records.

[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiment of the present application also provides a prompt sound broadcast device for implementing the prompt sound broadcast method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more prompt sound broadcast device embodiments provided below can refer to the limitations of the prompt sound broadcast method above, and will not be repeated here.

[0120] In one embodiment, Figure 8 As shown, a prompt sound broadcasting device 800 is provided, including: a first acquisition module 802, a second acquisition module 804, and a matching module 806, wherein:

[0121] The first collection module 802 is used to collect the first characteristic information of the target person and determine the target stay time of the target person when detecting that the target person enters the target area;

[0122] The second collection module 804 is used to collect the second characteristic information of each person who leaves the target area and collect the third characteristic information of each person who interacts with the target device in the target area within the target stay time;

[0123] The matching module 806 is used to match the first characteristic information with the second characteristic information and the third characteristic information after the target stays for a certain period of time, and to broadcast a target prompt sound when the first characteristic information does not match any of the second characteristic information and the third characteristic information.

[0124] The prompt tone broadcasting device provided in the embodiment of the present application sets a target stay time for the target person after detecting that the target person has entered the target area, and detects whether the target person has left the target area or whether the target person has interacted with the target device in the target area during the target stay time. If the target person still stays in the target area after the target stay time, but has not interacted with any target device, the merchant can be reminded by the target prompt tone to indicate that the target person may be a person that the merchant needs to focus on and provide help for. The embodiment of the present application determines whether the target person needs to be paid attention to based on whether the target person has taken an action of leaving the target area or interacting with the target device in the target area during the target stay time, so it can assist the merchant in identifying the person who needs to be paid attention to.

[0125] In one embodiment, the first acquisition module 802 is further used for:

[0126] Determining a collection period for the target person according to the time point when the target person enters the target area;

[0127] Acquire the amount of first feature information collected during the collection period;

[0128] The target stay duration is determined according to at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

[0129] In one embodiment, the first acquisition module 802 is further used for:

[0130] Acquire the amount of second characteristic information and the amount of third characteristic information collected during the collection period;

[0131] The target stay duration is determined according to a first difference between the amount of the second feature information and the amount of the third feature information, and the target stay duration is negatively correlated with the first difference.

[0132] In one embodiment, the matching module 806 is further configured to:

[0133] Obtaining a second difference between the amount of second feature information collected during the target's stay time and the amount of first feature information collected during the target's stay time;

[0134] When the second difference is greater than a preset quantity threshold, a target volume of the target prompt sound is determined according to the second difference, and the target prompt sound is broadcast based on the target volume; the target volume is positively correlated with the second difference.

[0135] In one embodiment, the second acquisition module 804 is further used to:

[0136] receiving interaction notification information sent by the target device, where the interaction notification information is sent when a person interacts with the target device;

[0137] Image information of the area where the target device is located is collected, and third feature information of a person interacting with the target device is extracted from the image information.

[0138] Each module in the above device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a prompt tone broadcasting method is implemented.

[0140] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0141] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0142] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0143] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0144] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0146] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A prompt tone broadcasting method, characterized in that: The method comprises: When a target person is detected to enter a target area, first feature information of the target person is collected, and a target stay time of the target person is determined; During the target stay time, collecting second feature information of each person leaving the target area, and collecting third feature information of each person interacting with the target device in the target area; After the target stay time has elapsed, the first feature information is matched with the second feature information and the third feature information. If the first feature information does not match with each of the second feature information and each of the third feature information, a target prompt sound is broadcast.

2. The method according to claim 1, characterized in that The determining of the target stay time for the target person includes: Determining a collection period for the target person according to the time point when the target person enters the target area; Acquire the amount of first feature information collected during the collection period; The target stay duration is determined according to at least one of the collection period, the amount of first feature information collected within the collection period, and the personnel characteristics of the target person.

3. The method according to claim 2, characterized in that The determining of the target stay time for the target person further includes: Acquire the amount of second characteristic information and the amount of third characteristic information collected during the collection period; The target stay duration is determined according to a first difference between the amount of the second feature information and the amount of the third feature information, and the target stay duration is negatively correlated with the first difference.

4. The method according to claim 1, characterized in that The target prompt tone broadcast includes: Obtaining a second difference between the amount of second feature information collected during the target's stay time and the amount of first feature information collected during the target's stay time; When the second difference is greater than a preset quantity threshold, a target volume of the target prompt sound is determined according to the second difference, and the target prompt sound is broadcast based on the target volume; the target volume is positively correlated with the second difference.

5. The method according to claim 1, characterized in that The collecting of third feature information of each person interacting with the target device in the target area includes: receiving interaction notification information sent by the target device, where the interaction notification information is sent when a person interacts with the target device; Image information of the area where the target device is located is collected, and third feature information of a person interacting with the target device is extracted from the image information.

6. A prompt tone broadcasting system, characterized in that: The system includes an induction doorbell module, a payment cloud speaker module and a control module, wherein: The induction doorbell module is used to collect first characteristic information of the person entering the target area, broadcast a first prompt tone, and send the first characteristic information to the control module when detecting that a person enters the target area, and is also used to collect second characteristic information of the person leaving the target area, broadcast a second prompt tone, and send the second characteristic information to the control module when detecting that a person leaves the target area; The payment collection cloud speaker module is used to broadcast a third prompt tone when receiving a payment success message, collect third characteristic information of the person interacting with the payment collection cloud speaker module, and send the third characteristic information to the control module; The control module is used to determine, for any of the first characteristic information, a target stay duration corresponding to the first characteristic information, and after the target stay duration has elapsed, match the first characteristic information with the second characteristic information and the third characteristic information collected within the target stay duration; The control module is also used to send a target prompt sound broadcast request to the induction doorbell module and / or the payment cloud speaker module when the first characteristic information does not match the second characteristic information and the third characteristic information, and the target prompt sound broadcast request is used to indicate the broadcast of the target prompt sound.

7. A prompt sound broadcasting device, characterized in that: The device comprises: A first acquisition module is used to acquire first characteristic information of the target person and determine the target stay time of the target person when detecting that the target person enters the target area; A second collection module is used to collect second characteristic information of each person who leaves the target area within the target stay time, and collect third characteristic information of each person who interacts with the target device in the target area; A matching module is used to match the first characteristic information with the second characteristic information and the third characteristic information after the target stays for a certain period of time, and to broadcast a target prompt sound when the first characteristic information does not match any of the second characteristic information and the third characteristic information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images