Store service strategy generation method and device, equipment and medium

Abstract

The invention relates to the technical field of data processing, and provides a store service strategy generation method and device, equipment and a medium, which can start a pre-deployed multi-modal data acquisition device to acquire multi-modal data of a user in real time when a human body sensing device detects that the user enters a target store, so as to generate a store service strategy. The real-time performance and multi-dimensional coverage of the data are ensured; the multi-modal features are analyzed by using the user state recognition model, and the drunkenness risk reasoning model is used for reasoning to obtain the target drunkenness risk level, so that accurate reasoning can be performed through the multi-modal features, and misjudgment caused by a single data dimension is avoided; the target drunkenness risk level is utilized to perform traversal in the grading response strategy set to obtain the target store service strategy, and the target store service strategy is executed, so that targeted service can be performed after the drunkenness state is automatically identified, and the reasonability, safety and efficiency of store service are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, equipment and medium for generating store service strategies. Background Technology

[0002] Currently, in order to increase sales, more and more chain retail stores are operating until late at night (such as from 10 p.m. to 7 a.m. the next day), or even 24 hours a day.

[0003] Therefore, some stores near bars or barbecue restaurants may encounter customers who have drunk excessively or are intoxicated entering the store to buy goods late at night. In this case, it is necessary to quickly identify the customer's drinking status and take appropriate service measures to avoid customers' excessive words or actions, which may cause safety hazards. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method, device, equipment and medium for generating store service strategies, which aims to solve the problem of not being able to analyze the user's intoxication state in a timely manner and provide targeted service strategies.

[0005] A method for generating a store service strategy, the method comprising: In response to a service policy generation command triggered by a target store, when a user is detected entering the target store by a human body sensor, a pre-deployed multimodal data acquisition device is activated to collect the user's multimodal data in real time. Feature extraction is performed on the multimodal data to obtain multimodal features; The target user's state is obtained by analyzing the multimodal features using a user state recognition model. The target intoxication risk level is obtained by using an intoxication risk inference model based on the target user's state. Obtain a pre-built set of graded response strategies, and use the target intoxication risk level to traverse the set of graded response strategies to obtain the target store service strategy. Implement the target store service strategy.

[0006] A store service strategy generation device, the store service strategy generation device comprising: The data acquisition unit is used to respond to the service policy generation command triggered based on the target store. When the human body sensor detects that a user has entered the target store, it activates the pre-deployed multimodal data acquisition device to collect the user's multimodal data in real time. An extraction unit is used to extract features from the multimodal data to obtain multimodal features; The analysis unit is used to analyze the multimodal features using a user state recognition model to obtain the target user state; The reasoning unit is used to infer the target user's state based on the intoxication risk reasoning model to obtain the target intoxication risk level. The traversal unit is used to obtain a pre-built set of graded response strategies and to traverse the set of graded response strategies using the target intoxication risk level to obtain the target store service strategy. An execution unit is used to execute the target store service strategy.

[0007] A computer device, the computer device comprising: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the store service strategy generation method.

[0008] A computer-readable storage medium storing at least one instruction, which is executed by a processor in a computer device to implement the store service strategy generation method.

[0009] As can be seen from the above technical solutions, this invention can activate a pre-deployed multimodal data acquisition device to collect multimodal data of users in real time when a user is detected entering a target store based on a human body sensing device, ensuring the real-time nature and multi-dimensional coverage of the data; it analyzes multimodal features using a user state recognition model and infers the target intoxication risk level using an intoxication risk inference model, enabling accurate inference through multimodal features and avoiding misjudgments caused by a single data dimension; it uses the target intoxication risk level to traverse the hierarchical response strategy set to obtain the target store service strategy and executes the target store service strategy, thereby enabling targeted services after automatically identifying the intoxication state, improving the rationality, safety, and efficiency of store services. Attached Figure Description

[0010] Figure 1 This is a flowchart of a preferred embodiment of the store service strategy generation method of the present invention.

[0011] Figure 2 This is a schematic diagram of the display data state of the present invention.

[0012] Figure 3 This is a schematic diagram illustrating the installation instructions for the store equipment of this invention.

[0013] Figure 4 This is a functional block diagram of a preferred embodiment of the store service strategy generation device of the present invention.

[0014] Figure 5This is a schematic diagram of the structure of a computer device that implements the store service strategy generation method of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0016] like Figure 1 The diagram shown is a flowchart of a preferred embodiment of the store service strategy generation method of the present invention. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different needs.

[0017] The store service strategy generation method is applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0018] The computer device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, interactive network television (IPTV), smart wearable device, etc.

[0019] The computer equipment may also include network equipment and / or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0020] The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0021] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0022] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0023] The network in which the computer device is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0024] S10, in response to the service policy generation instruction triggered based on the target store, when a user is detected entering the target store based on the human body sensing device, a pre-deployed multimodal data acquisition device is activated to collect the user's multimodal data in real time.

[0025] In this embodiment, the target store can be a convenience store, supermarket, etc.

[0026] In this embodiment, the service policy generation instruction can be automatically triggered when the target store puts on service, so as to achieve comprehensive monitoring of the target store.

[0027] In this embodiment, before activating the pre-deployed multimodal data acquisition device to collect the user's multimodal data in real time, the method further includes: With the goal of eliminating blind spots in data collection, the multimodal data acquisition device is deployed in the target store to establish an Internet of Things (IoT) transmission link. The multimodal data acquisition device includes a non-contact microwave radar device and an image acquisition device deployed on the ceiling of the target store, as well as a microphone array installed in a designated area.

[0028] For example, the image acquisition device may include a panoramic camera, etc. The installation location of the multimodal data acquisition device needs to cover the store entrance, passageways, and shopping areas. The multimodal data acquisition device needs to be connected and debugged with the central control host, and an IoT transmission link needs to be established to collect data and upload it to the central control host in real time. Simultaneously, the central control host can also establish a data interaction channel with the cloud-based backend customer service system.

[0029] In this embodiment, the basic parameters of the multimodal data acquisition device can also be initialized to establish a baseline model of customer physiology and behavior. For example, a resting heart rate range of 60-100 beats / minute can be set as the heart rate baseline based on historical healthy population data; stride uniformity standards and body sway amplitude thresholds can be determined through training with a large number of normal walking samples as gait feature baselines; a normal communication volume range (such as less than or equal to 70dB) can be set, and a conventional semantic database (such as excluding abnormal semantics such as repetitive sensitive words) can be established as a speech feature baseline.

[0030] Through the above embodiments, it is possible to achieve synchronous collection of multi-dimensional data after customers enter the store, covering physiological signals (heartbeat), behavioral actions (gait, posture), and voice information (volume, semantics). The multi-modal data collection device is seamlessly connected with the store service system and clearly defines various basic judgment criteria, ensuring the real-time and multi-dimensional coverage of data collection. This provides hardware support and reference for the accurate collection and analysis of subsequent multi-modal data, thereby ensuring the comprehensiveness and standardization of data collection.

[0031] S11, perform feature extraction on the multimodal data to obtain multimodal features.

[0032] In this embodiment, the step of extracting features from the multimodal data to obtain multimodal features includes: The user's heart rate is obtained from the multimodal data and collected in real time by the non-contact microwave radar device. Environmental interference signals in the user's heart rate are filtered to extract the effective heart rate fluctuation curve. The mean heart rate and heart rate fluctuation coefficient are extracted from the effective heart rate fluctuation curve as physiological features. The user image acquired by the image acquisition device is obtained from the multimodal data. The user's walking trajectory and standing posture in the user image are captured as visual feature data using a gait recognition algorithm. Background interference elements in the visual feature data are removed to extract the user's main action features. From the user's main action features, stride uniformity, maximum body sway amplitude, and number of times the user holds onto the wall are extracted as behavioral features. The user's voice, which is collected in real time by the microphone array, is obtained from the multimodal data. Environmental noise in the user's voice is removed to extract a clean voice signal. Volume peak, semantic matching degree, and whether there are repetitive sensitive words are extracted from the clean voice signal as voice features. The physiological features, behavioral features, and speech features are combined to form the multimodal features.

[0033] The gait recognition algorithm may include the stick figure algorithm, etc.

[0034] The environmental noise may include the sound of store equipment running and external noise.

[0035] The heart rate fluctuation coefficient can be the quotient of the standard deviation of heart rate and the mean of heart rate.

[0036] The stride uniformity can be the quotient of the sum of the absolute values ​​of the stride differences and the total number of strides.

[0037] The amplitude of body swaying can be calculated as follows: Draw a baseline rectangle based on the human body's standing contour (the top and bottom edges are the width, and the left and right edges are the height). Then, rotate the left and right edges (the height) of the baseline rectangle outwards based on the normal swaying amplitude to expand the width. This results in a new rectangle formed by the body swaying (the width of this new rectangle is the width obtained after rotating the height). When the body sways normally, the aspect ratio is less than 1:3 (less than 0.3); when the swaying amplitude is abnormal, the aspect ratio is greater than 1:2 (greater than 0.5). Therefore, the change in the shape of the baseline rectangle caused by body swaying can be converted into a quantified value of the aspect ratio change. This allows for subsequent warnings based on the numerical changes, providing early warning and response guidelines for emergencies.

[0038] The semantic matching degree can be the quotient of the number of words that match the collected semantics with the regular semantic database and the total number of words.

[0039] The above embodiments can eliminate invalid and interfering data, extract core features that are strongly correlated with customers' drinking status, reduce data redundancy, and improve the computational efficiency and recognition accuracy of subsequent analysis models.

[0040] S12, the multimodal features are analyzed using a user state recognition model to obtain the target user state.

[0041] In this embodiment, the step of analyzing the multimodal features using a user state recognition model to obtain the target user state includes: The multimodal features are detected using the user state recognition model. When the average heart rate is detected to be consistently greater than a heart rate threshold, and the heart rate fluctuation coefficient exceeds a preset range, the target user's state is determined to be abnormal heartbeat; and / or When the stride uniformity is detected to be less than a uniformity threshold and the maximum body sway amplitude is greater than a sway amplitude threshold, and / or the number of times the user leans against a wall exceeds a threshold for the number of times the user leans against a wall within a preset time period, the target user's gait is determined to be abnormal; and / or When the volume peak is detected to be greater than the peak threshold, and / or the semantic matching degree is less than the matching degree threshold and there are repeated sensitive words, the target user's state is determined to be abnormal voice emotion.

[0042] The heart rate threshold, the preset range, the uniformity threshold, the swaying amplitude threshold, the number of times the user needs to lean against the wall threshold, the peak value threshold, and the matching degree threshold can be configured based on historical data. For example, the heart rate threshold can be configured to 120 beats / minute, the swaying amplitude threshold can be configured to 15°, and the peak value threshold can be configured to 70dB.

[0043] S13, using the intoxication risk reasoning model to reason based on the target user's state, the target intoxication risk level is obtained.

[0044] In this embodiment, the step of using the intoxication risk inference model to infer the target user's state and obtain the target intoxication risk level includes: When the target user's status only includes the abnormal heartbeat, the target's intoxication risk level is determined to be low risk. When the target user's state includes abnormal gait and abnormal voice emotion, the target's intoxication risk level is determined to be medium risk. When the target user's state includes abnormal heart rate, abnormal gait, and abnormal voice emotion, the target's intoxication risk level is determined to be high risk.

[0045] In the above embodiments, through comprehensive analysis and quantitative scoring of multimodal features, it is possible to accurately identify the drinking status of customers and scientifically classify the risk level, avoiding misjudgments caused by a single data dimension and providing a clear basis for subsequent graded response.

[0046] S14, obtain a pre-built set of graded response strategies, and use the target intoxication risk level to traverse the set of graded response strategies to obtain the target store service strategy.

[0047] In this embodiment, the tiered response strategy set is used to store the mapping relationship between the intoxication risk level and the store service strategy.

[0048] In this embodiment, the target intoxication risk level is used to traverse the set of graded response strategies, and the store service strategy that matches the target intoxication risk level is determined as the target store service strategy.

[0049] S15, execute the target store service strategy.

[0050] In this embodiment, executing the target store service strategy includes: When the target store service strategy corresponds to the low-risk level, refreshing beverage recommendations are displayed on the screen, the user is guided to the rest area of ​​the target store through voice prompts, and the user status is continuously monitored through the multimodal data acquisition device. When the target store service strategy corresponds to the medium risk level, the order transfer button is triggered to transfer the service of the target store to the expert customer service seat, a store processing notification is sent to the designated personnel of the target store, and an early warning is issued when the distance between the store staff and the user is less than or equal to the safe distance. When the target store service strategy corresponds to the high-risk level, the user is guided to leave the store by pushing the door open through the store equipment function buttons. After the user leaves the store, the target store is controlled to lock the door with a magnetic lock. The multimodal data acquisition device continuously monitors whether the target store has eliminated the security risks, and triggers the alarm function when excessive behavior is detected, and links with the store security system. After detecting that the user has left the store, the multimodal data acquisition device is turned off, and the service data for the user is recorded to the designated database.

[0051] The safe distance can be configured based on factors such as the size of the target store and the merchandise display. For example, the safe distance can be configured to 1.5 meters to ensure that staff maintain a safe distance of 1.5 meters when communicating with customers, in accordance with regulations.

[0052] Specifically, after detecting that the user has left the store, the system controls the target store to lock the door with a magnetic lock, which can prevent the customer from re-entering the store and causing security problems.

[0053] The user's service data may include data from the entire service process, such as collected multimodal data, intoxication risk level assessment results, response measures, and processing results.

[0054] The user's service data can be used to optimize various models and algorithms.

[0055] Through the above embodiments, it is possible to accurately match risk levels with response measures. In low-risk scenarios, the focus is on improving customer experience, while in medium- and high-risk scenarios, the focus is on effectively avoiding excessive behavior, ensuring store safety and customer service efficiency. At the same time, the system model is continuously optimized through data accumulation to improve the accuracy of subsequent identification and response.

[0056] In this embodiment, the method further includes: The multimodal data, the target user's status, and the target's intoxication risk level are displayed on the monitor in real time.

[0057] For example: Please see Figure 2This is a schematic diagram illustrating the data display status of the display of the present invention. The display may also show store number, store equipment function buttons, order transfer buttons, voice broadcast buttons, camera switching display, panoramic camera display, etc. When the store equipment function buttons are clicked, users can access button options such as open door, close door, alarm, start intercom, transfer, and more. When the voice broadcast button is clicked, users can access button options such as inquiry message, shopping bag, departure message, verification message, and more.

[0058] Please see also Figure 3 This is a schematic diagram illustrating the installation of the store equipment according to the present invention. Figure 3 The system includes a ceiling, cameras, speakers, microwave radar, human body sensors, magnetic door locks, microphones, and a central control unit. After the service is completed, a service report can be generated, including customer entry and exit times, detailed data collection, risk level assessment results, response implementation status, and customer satisfaction feedback. The generated service report can be integrated into a historical database, and related models can be optimized through algorithmic iteration. For example, the baseline heart rate can be updated to include post-drinking heart rate changes in customers of different ages and genders; gait recognition algorithm parameters can be optimized to improve the accuracy of gait feature recognition in complex scenarios (such as crowded stores); and the semantic library of the NLP (Natural Language Processing) model can be expanded to include more common post-drinking abnormal semantic samples.

[0059] Through the above embodiments, a complete service loop can be formed, and continuous optimization of the system model can be achieved through data review, thereby improving the adaptability and advancement of the technical solution and providing more accurate support for services in similar scenarios in the future.

[0060] As can be seen from the above technical solutions, this invention can activate a pre-deployed multimodal data acquisition device to collect multimodal data of users in real time when a user is detected entering a target store based on a human body sensing device, ensuring the real-time nature and multi-dimensional coverage of the data; it analyzes multimodal features using a user state recognition model and infers the target intoxication risk level using an intoxication risk inference model, enabling accurate inference through multimodal features and avoiding misjudgments caused by a single data dimension; it uses the target intoxication risk level to traverse the hierarchical response strategy set to obtain the target store service strategy and executes the target store service strategy, thereby enabling targeted services after automatically identifying the intoxication state, improving the rationality, safety, and efficiency of store services.

[0061] like Figure 4The diagram shown is a functional block diagram of a preferred embodiment of the store service strategy generation device of the present invention. The store service strategy generation device 11 includes a data acquisition unit 110, an extraction unit 111, an analysis unit 112, a reasoning unit 113, a traversal unit 114, and an execution unit 115. The module / unit referred to in this invention is a series of computer program segments that can be executed by a processor and perform a fixed function, and are stored in memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0062] The acquisition unit 110 is used to respond to the service strategy generation instruction triggered based on the target store. When the human body sensing device detects that a user has entered the target store, it activates the pre-deployed multimodal data acquisition device to collect the user's multimodal data in real time. The extraction unit 111 is used to extract features from the multimodal data to obtain multimodal features; The analysis unit 112 is used to analyze the multimodal features using a user state recognition model to obtain the target user state; The reasoning unit 113 is used to use the intoxication risk reasoning model to reason based on the target user's state to obtain the target intoxication risk level. The traversal unit 114 is used to obtain a pre-built set of graded response strategies and traverse the set of graded response strategies using the target intoxication risk level to obtain the target store service strategy. The execution unit 115 is used to execute the target store service strategy.

[0063] As can be seen from the above technical solutions, this invention can activate a pre-deployed multimodal data acquisition device to collect multimodal data of users in real time when a user is detected entering a target store based on a human body sensing device, ensuring the real-time nature and multi-dimensional coverage of the data; it analyzes multimodal features using a user state recognition model and infers the target intoxication risk level using an intoxication risk inference model, enabling accurate inference through multimodal features and avoiding misjudgments caused by a single data dimension; it uses the target intoxication risk level to traverse the hierarchical response strategy set to obtain the target store service strategy and executes the target store service strategy, thereby enabling targeted services after automatically identifying the intoxication state, improving the rationality, safety, and efficiency of store services.

[0064] like Figure 5 The diagram shown is a schematic representation of the computer device used to implement the store service strategy generation method of the present invention.

[0065] The computer device 1 may include a memory 12, a processor 13, and a bus (the arrow in the figure represents the bus), and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a store service strategy generation program.

[0066] Those skilled in the art will understand that the schematic diagram is merely an example of computer device 1 and does not constitute a limitation on computer device 1. Computer device 1 can be either a bus topology or a star topology. Computer device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, computer device 1 may also include input / output devices, network access devices, etc.

[0067] It should be noted that the computer device 1 described is merely an example. Other existing or future electronic products that are adaptable to this invention should also be included within the scope of protection of this invention and are incorporated herein by reference.

[0068] The memory 12 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the computer device 1, such as a portable hard drive of the computer device 1. In other embodiments, the memory 12 can be an external storage device of the computer device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 1. Furthermore, the memory 12 can include both internal and external storage units of the computer device 1. The memory 12 can be used not only to store application software and various types of data installed on the computer device 1, such as the code of a store service strategy generation program, but also to temporarily store data that has been output or will be output.

[0069] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the computer device 1, connecting various components of the computer device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing a store service strategy generation program) and calls data stored in the memory 12 to perform various functions of the computer device 1 and process data.

[0070] The processor 13 executes the operating system of the computer device 1 and various installed applications. The processor 13 executes these applications to implement the steps in the various store service strategy generation method embodiments described above, for example... Figure 1 The steps are shown.

[0071] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, which describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a data acquisition unit 110, an extraction unit 111, an analysis unit 112, a reasoning unit 113, a traversal unit 114, and an execution unit 115.

[0072] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the store service strategy generation method described in the various embodiments of this invention.

[0073] If the modules / units integrated in the computer device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0074] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0075] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0076] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0077] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 5 The bus is represented by only one straight line, but this does not mean that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0078] Although not shown, the computer device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 13 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0079] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the computer device 1 and other computer devices.

[0080] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the computer device 1 and to display a visual user interface.

[0081] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0082] It will be understood by those skilled in the art that Figure 5 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0083] Combination Figure 1 The memory 12 in the computer device 1 stores multiple instructions to implement a store service strategy generation method, and the processor 13 can execute the multiple instructions to achieve the following: In response to a service policy generation command triggered by a target store, when a user is detected entering the target store by a human body sensor, a pre-deployed multimodal data acquisition device is activated to collect the user's multimodal data in real time. Feature extraction is performed on the multimodal data to obtain multimodal features; The target user's state is obtained by analyzing the multimodal features using a user state recognition model. The target intoxication risk level is obtained by using an intoxication risk inference model based on the target user's state. Obtain a pre-built set of graded response strategies, and use the target intoxication risk level to traverse the set of graded response strategies to obtain the target store service strategy. Implement the target store service strategy.

[0084] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 1The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0085] It should be noted that all data involved in this case was legally obtained. Software tools or components not belonging to this company that appear in the embodiments of this application are merely illustrative examples and do not represent actual use.

[0086] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0087] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0088] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0090] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0091] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0092] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this invention can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for generating store service strategies, characterized in that, The method for generating the store service strategy includes: In response to a service policy generation command triggered by a target store, when a user is detected entering the target store by a human body sensor, a pre-deployed multimodal data acquisition device is activated to collect the user's multimodal data in real time. Feature extraction is performed on the multimodal data to obtain multimodal features; The target user's state is obtained by analyzing the multimodal features using a user state recognition model. The target intoxication risk level is obtained by using an intoxication risk inference model based on the target user's state. Obtain a pre-built set of graded response strategies, and use the target intoxication risk level to traverse the set of graded response strategies to obtain the target store service strategy. Implement the target store service strategy.

2. The store service strategy generation method as described in claim 1, characterized in that, Before activating the pre-deployed multimodal data acquisition device to collect the user's multimodal data in real time, the method further includes: With the goal of eliminating blind spots in data collection, the multimodal data acquisition device is deployed in the target store to establish an Internet of Things (IoT) transmission link. The multimodal data acquisition device includes a non-contact microwave radar device and an image acquisition device deployed on the ceiling of the target store, as well as a microphone array installed in a designated area.

3. The store service strategy generation method as described in claim 2, characterized in that, The feature extraction from the multimodal data to obtain multimodal features includes: The user's heart rate is obtained from the multimodal data and collected in real time by the non-contact microwave radar device. Environmental interference signals in the user's heart rate are filtered to extract the effective heart rate fluctuation curve. The mean heart rate and heart rate fluctuation coefficient are extracted from the effective heart rate fluctuation curve as physiological features. The user image acquired by the image acquisition device is obtained from the multimodal data. The user's walking trajectory and standing posture in the user image are captured as visual feature data using a gait recognition algorithm. Background interference elements in the visual feature data are removed to extract the user's main action features. From the user's main action features, stride uniformity, maximum body sway amplitude, and number of times the user holds onto the wall are extracted as behavioral features. The user's voice, which is collected in real time by the microphone array, is obtained from the multimodal data. Environmental noise in the user's voice is removed to extract a clean voice signal. Volume peak, semantic matching degree, and whether there are repetitive sensitive words are extracted from the clean voice signal as voice features. The physiological features, behavioral features, and speech features are combined to form the multimodal features.

4. The store service strategy generation method as described in claim 3, characterized in that, The analysis of the multimodal features using the user state recognition model to obtain the target user state includes: The multimodal features are detected using the user state recognition model. When the average heart rate is detected to be consistently greater than a heart rate threshold, and the heart rate fluctuation coefficient exceeds a preset range, the target user's state is determined to be abnormal heartbeat; and / or When the stride uniformity is detected to be less than a uniformity threshold and the maximum body sway amplitude is greater than a sway amplitude threshold, and / or the number of times the user leans against a wall exceeds a threshold for the number of times the user leans against a wall within a preset time period, the target user's gait is determined to be abnormal; and / or When the volume peak is detected to be greater than the peak threshold, and / or the semantic matching degree is less than the matching degree threshold and there are repeated sensitive words, the target user's state is determined to be abnormal voice emotion.

5. The store service strategy generation method as described in claim 4, characterized in that, The intoxication risk inference model is used to infer the target user's state to obtain the target intoxication risk level, including: When the target user's status only includes the abnormal heartbeat, the target's intoxication risk level is determined to be low risk. When the target user's state includes abnormal gait and abnormal voice emotion, the target's intoxication risk level is determined to be medium risk. When the target user's state includes abnormal heart rate, abnormal gait, and abnormal voice emotion, the target's intoxication risk level is determined to be high risk.

6. The store service strategy generation method as described in claim 5, characterized in that, The execution of the target store service strategy includes: When the target store service strategy corresponds to the low-risk level, refreshing beverage recommendations are displayed on the screen, the user is guided to the rest area of ​​the target store through voice prompts, and the user status is continuously monitored through the multimodal data acquisition device. When the target store service strategy corresponds to the medium risk level, the order transfer button is triggered to transfer the service of the target store to the expert customer service seat, a store processing notification is sent to the designated personnel of the target store, and an early warning is issued when the distance between the store staff and the user is less than or equal to the safe distance. When the target store service strategy corresponds to the high-risk level, the user is guided to leave the store by pushing the door open through the store equipment function buttons. After the user leaves the store, the target store is controlled to lock the door with a magnetic lock. The multimodal data acquisition device continuously monitors whether the target store has eliminated the security risks, and triggers the alarm function when excessive behavior is detected, and links with the store security system. After detecting that the user has left the store, the multimodal data acquisition device is turned off, and the service data for the user is recorded to the designated database.

7. The store service strategy generation method as described in claim 6, characterized in that, The method further includes: The multimodal data, the target user's status, and the target's intoxication risk level are displayed on the monitor in real time.

8. A store service strategy generation device, characterized in that, The store service strategy generation device includes: The data acquisition unit is used to respond to the service policy generation command triggered based on the target store. When the human body sensor detects that a user has entered the target store, it activates the pre-deployed multimodal data acquisition device to collect the user's multimodal data in real time. An extraction unit is used to extract features from the multimodal data to obtain multimodal features; The analysis unit is used to analyze the multimodal features using a user state recognition model to obtain the target user state; The reasoning unit is used to infer the target user's state based on the intoxication risk reasoning model to obtain the target intoxication risk level. The traversal unit is used to obtain a pre-built set of graded response strategies and to traverse the set of graded response strategies using the target intoxication risk level to obtain the target store service strategy. An execution unit is used to execute the target store service strategy.

9. A computer device, characterized in that, The computer device includes: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the store service strategy generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is executed by a processor in a computer device to implement the store service strategy generation method as described in any one of claims 1 to 7.

Images