Data integrated management system based on artificial intelligence

Abstract

The invention discloses a data comprehensive management system based on artificial intelligence, and particularly relates to the technical field of logistics service management, which comprises a logistics service supervision area division module, a logistics service supervision data acquisition module, a logistics service supervision data analysis module, a logistics service supervision early warning module and a logistics service supervision comprehensive analysis module, and a logistics service supervision man-machine interaction module. The logistics service supervision area division module is used for determining a supervised catering logistics service department as a target area, and dividing the target area into a plurality of monitoring sub-areas according to equal time periods; according to the method, food safety abnormal parameters are analyzed to obtain an index to evaluate the quality and safety of food, so that logistics service supervision departments can find and process food materials about to be overdue in time, food safety problems possibly caused by deterioration of the food materials are prevented, the storage temperature is effectively controlled, the risk of bacterium breeding is reduced, and the safety of the food is improved. And the quality and safety of food are ensured.

Description

Technical Field

[0001] This invention relates to the field of logistics service management technology, specifically to a data integrated management system based on artificial intelligence. Background Technology

[0002] Artificial intelligence (AI) is an emerging technological science that studies and develops methods, technologies, and application systems to simulate, extend, and expand human intelligence. AI systems can perform a range of tasks, including but not limited to image processing, natural language processing, and decision-making, and possess the ability to learn and improve to meet challenges in different situations. They are widely used in healthcare, transportation, service industries, big data processing, and other fields, providing strong technical support for the transformation of regulatory methods in the traditional catering and logistics service industry.

[0003] While traditional methods of supervising catering logistics services have played a role to some extent, they suffer from high labor costs, low levels of informatization, a lack of modern supervisory tools and methods, an inability to process large amounts of catering data, insufficient comprehensiveness of supervision, and a lack of interconnected supervisory information. This results in the inability to promptly detect and address illegal and irregular activities, reducing the timeliness and effectiveness of supervision. In the catering industry, the supervision of catering logistics services is a key link in ensuring food safety and improving service quality. With the continuous advancement of technology, more and more companies are using artificial intelligence technology for supervision.

[0004] Therefore, this invention proposes an artificial intelligence-based data integrated management system to solve the above problems, especially in the supervision of catering logistics services. By introducing advanced technologies such as artificial intelligence, big data, and the Internet of Things, the system provides powerful data analysis, pattern recognition, and predictive analysis functions for the catering logistics service supervision system. Based on the analysis results, the system can automatically issue early warnings and convey the warnings and decision-making suggestions to relevant departments or personnel, ensuring that regulatory measures are effectively implemented. This achieves real-time, comprehensive, and intelligent supervision of catering enterprises, which not only improves the efficiency and quality of supervision but also reduces labor costs, providing a strong guarantee for the healthy development of the catering industry. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an artificial intelligence-based data integrated management system to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an artificial intelligence-based data integrated management system, comprising a logistics service supervision area division module, a logistics service supervision data collection module, a logistics service supervision data analysis module, a logistics service supervision early warning module, a logistics service supervision comprehensive analysis module, and a logistics service supervision human-computer interaction module;

[0007] The logistics service supervision area division module is used to identify the supervised catering logistics service departments as target areas, and to divide the target areas into several monitoring sub-areas according to equal time periods, which are denoted as 1, 2, 3, ..., n in sequence;

[0008] The logistics service supervision data acquisition module is used to collect data from each monitoring sub-area, obtain various monitoring parameters of abnormal indicators of catering logistics service supervision, and output various monitoring parameters to the logistics service supervision data analysis module.

[0009] The logistics service supervision data analysis module includes a food safety anomaly indicator analysis unit, a service quality anomaly indicator analysis unit, an environmental and hygiene anomaly indicator analysis unit, and an operation management anomaly indicator analysis unit. The food safety anomaly indicator analysis unit is used to calculate food safety anomaly parameters, the service quality anomaly indicator analysis unit is used to calculate service quality anomaly parameters, the environmental and hygiene anomaly indicator analysis unit is used to calculate environmental and hygiene anomaly parameters, and the operation management anomaly indicator analysis unit is used to calculate operation management anomaly parameters, and outputs the corresponding calculation results to the logistics service supervision early warning module.

[0010] The logistics service supervision and early warning module compares the abnormal indicators of catering logistics service supervision in each monitored sub-area within the target area with the set values, and transmits the indicators whose comparison results do not exceed the set values ​​to the logistics service supervision and comprehensive analysis module.

[0011] The logistics service supervision and comprehensive analysis module is used to comprehensively analyze the percentage of abnormal indicators of catering logistics services calculated by the above module that does not exceed the set value, obtain the comprehensive supervision indicators of catering logistics services, and output the comprehensive analysis results to the logistics service supervision human-computer interaction module.

[0012] The logistics service supervision human-computer interaction module is used to output the comprehensive supervision indicators passed in by the above module to the information terminal of the logistics service supervision personnel.

[0013] Preferably, the monitoring parameters in the logistics service supervision data collection module include target area information, identity verification information of catering logistics service supervisors, food safety anomaly parameters, service quality anomaly parameters, environmental and hygiene anomaly parameters, and operation management anomaly parameters. Specifically, food safety anomaly parameters include the abnormal quantity of ingredients, total ingredient purchase quantity, quantity of ingredients nearing expiration, quantity of expired ingredients, total ingredient inventory, number of storage temperature records that do not meet requirements, and total number of temperature records. Service quality anomaly parameters include the number of orders with overdue meal preparation time, total order quantity, and total number of orders... The parameters for abnormal items include: number of orders, number of customers waiting beyond the delivery time limit, total number of customers, number of orders with late delivery, customer satisfaction rating, number of customer complaints, and number of food quality issues; environmental and hygiene-related abnormal parameters include: number of records of substandard air quality, total number of air quality records, area of ​​areas with substandard cleanliness, total area of ​​cleaned areas, number of kitchen utensils with substandard hygiene, and total number of kitchen utensils; operational management-related abnormal parameters include: cost of wasted ingredients, total cost of ingredients, amount of backlogged ingredients, total amount of ingredients inventory, cost of outbound products, beginning inventory cost, and ending inventory cost.

[0014] Preferably, the model for food safety anomaly indicators in the logistics service supervision data analysis module is: Sai i =a1 Afr+Wr+Acr Sai i This represents the abnormal food safety index in the i-th monitored sub-region, where a1 is a constant (0 < a1 < 1), and Afr represents the abnormal rate of food freshness. Na represents the abnormal quantity of ingredients, and Pq represents the total quantity of ingredients purchased. Wr represents the image recognition impact factor, and Wr represents the food shelf life impact factor. Weq represents the quantity of food items nearing their expiration date, Eq represents the quantity of food items that have already expired, and In represents the total food inventory. This indicates the impact factor of artificial intelligence monitoring; Acr represents the rate of control over abnormal food storage temperatures. Ab represents the number of storage temperature records that do not meet the requirements, and T_ab represents the total number of temperature records. This indicates the influence factor of the temperature sensor.

[0015] Preferably, the model for service quality anomaly indicators in the logistics service supervision data analysis module is as follows: Among them, Qai i This represents the service quality anomaly index for the i-th monitored sub-region, where a2 is a constant (0 < a2 < 1), and Ear represents the service efficiency anomaly index.

[0016] Npo represents the number of orders with delayed food preparation, T_no represents the total number of orders, α1 represents the food preparation influencing factor, Nt represents the number of customers waiting beyond their delivery time, T_nt represents the total number of customers, Ndo represents the number of orders with delayed delivery, α2 represents the delivery influencing factor, and Far represents the customer satisfaction decline index. Cr represents the total customer satisfaction score of the i-th monitoring sub-region, Pe represents the total customer satisfaction score of the (i-1)-th monitoring sub-region, α3 represents the customer rating influencing factor, Ccn represents the number of complaints in the i-th monitoring sub-region, Pcn represents the number of complaints in the (i-1)-th monitoring sub-region, Qq represents the number of food quality issues, α4 represents the customer complaint influencing factor, and l1 and l2 represent the weights of the service efficiency anomaly index and the customer satisfaction decline index, respectively.

[0017] Preferably, the model for environmental and hygiene anomaly indicators in the logistics service supervision data analysis module is as follows: Among them Eai i This represents the abnormal indicators of the environment and sanitation in the i-th monitored sub-area, where a3 is a constant (0 < a3 < 1), and Aar represents the air quality non-compliance rate. Arn represents the number of records of air quality non-compliance, T_arn represents the total number of air quality records, η1 represents the influencing factor of excessive monitoring concentrations, and Acr represents the non-compliance rate of desktop and floor cleanliness. Nr represents the area of ​​the region where cleanliness does not meet the standard, T_nr represents the total area of ​​the cleaned area, η2 represents the cleanliness monitoring influencing factor, and Kar represents the rate of kitchenware hygiene non-compliance. Nk represents the number of kitchen utensils that do not meet hygiene standards, T_nk represents the total number of kitchen utensils, η3 represents the impact factor of kitchen utensils hygiene monitoring, and β1, β2 and β3 represent the weights of the air quality non-compliance rate, the table and floor cleanliness non-compliance rate and the kitchen utensils hygiene non-compliance rate, respectively.

[0018] Preferably, the model for operational management-related abnormal indicators in the logistics service supervision data analysis module is as follows: Oai i This represents the abnormal indicators for the operation and management of the i-th monitored sub-area, where a4 is a constant (0 < a4 < 1), and Fwr represents the food waste rate. Fwc represents the cost of wasted ingredients, Fc represents the total cost of ingredients, ξ1 represents the factor influencing ingredient waste, and Ibr represents the ingredient inventory backlog rate. Bi represents the amount of food inventory backlog, In represents the total food inventory, ξ2 represents the food inventory backlog influencing factor, and Atr represents the inventory turnover abnormality rate. Itr represents the actual inventory turnover rate. Oc represents outbound cost, Sc represents beginning inventory cost, Ec represents ending inventory cost, Itr0 represents expected turnover rate, and ξ3 represents the factor affecting food inventory turnover. and These represent the weights of food waste rate and abnormal inventory management, respectively.

[0019] Preferably, the comparison module in the service monitoring and early warning module includes the following steps:

[0020] Step 1: Obtain the analysis and calculation results of food safety anomaly indicators from each monitoring sub-region in the food safety anomaly indicator analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Sai0 represents the set value.

[0021] Step 2: Obtain the service quality anomaly index analysis and calculation results for each monitored sub-area from the service quality anomaly index analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Qai0 represents the set value.

[0022] Step 3: Obtain the analysis and calculation results of environmental and health anomaly indicators for each monitored sub-area from the environmental and health anomaly indicator analysis unit. i Substitute into the formula: Wherein represents The percentage of abnormal indicators; Eai0 represents the set value.

[0023] Step 4: Obtain the analysis and calculation results of the operation and management anomaly indicators for each monitored sub-area from the operation and management anomaly indicator analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Oai0 represents the set value.

[0024] Preferably, the comprehensive analysis model in the logistics service supervision and comprehensive analysis module is as follows: Cri represents the comprehensive regulatory index for catering and logistics services, and λ1, λ2, λ3, and λ4 represent the weights of each abnormal indicator.

[0025] The technical effects and advantages of this invention are as follows:

[0026] 1. This invention analyzes abnormal parameters related to food safety to obtain an index for assessing food quality and safety. This helps logistics service supervision departments to promptly detect and handle food that is about to expire, prevent its spoilage and potential food safety problems, effectively control storage temperature, reduce the risk of bacterial growth, and ensure food quality and safety.

[0027] 2. This invention analyzes abnormal parameters related to service quality to obtain an index for evaluating catering service quality and customer satisfaction. This helps catering logistics service supervision identify bottlenecks or problems in the food preparation and delivery process, thereby optimizing the food preparation process and improving service efficiency. It can also promptly detect service quality problems and take measures to improve them in order to maintain or enhance customer satisfaction.

[0028] 3. This invention analyzes abnormal parameters related to environment and hygiene to obtain an index for evaluating a restaurant's performance in terms of environment, hygiene, and cleanliness. This helps to improve the supervision of catering logistics services by emphasizing the cleanliness and tidiness of restaurants, avoiding a decline in customers' overall impression of the restaurant due to substandard quality, and even potentially causing food safety issues. This provides a strong guarantee for improving the quality of catering services and customer satisfaction. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of the overall process of the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Please see Figure 1 As shown, the present invention provides a data integrated management system based on artificial intelligence, including a logistics service supervision area division module, a logistics service supervision data collection module, a logistics service supervision data analysis module, a logistics service supervision early warning module, a logistics service supervision comprehensive analysis module, and a logistics service supervision human-computer interaction module.

[0032] The logistics service supervision area division module is connected to the logistics service supervision data acquisition module. The logistics service supervision data analysis module is connected to both the logistics service supervision early warning module and the logistics service supervision data acquisition module. The logistics service supervision comprehensive analysis and control module is connected to both the logistics service supervision human-computer interaction module and the logistics service supervision early warning module. The logistics service supervision human-computer interaction module is connected to both the logistics service supervision early warning module and the logistics service supervision data analysis module.

[0033] The logistics service supervision area division module is used to identify the supervised catering logistics service departments as target areas, and to divide the target areas into several monitoring sub-areas according to equal time periods, which are denoted as 1, 2, 3, ..., n in sequence;

[0034] The logistics service supervision data acquisition module is used to collect data from each monitoring sub-area, obtain various monitoring parameters of abnormal indicators of catering logistics service supervision, and output various monitoring parameters to the logistics service supervision data analysis module. The data is collected through monitoring equipment and sensors.

[0035] This embodiment requires specific explanation of the various monitoring parameters, including target area information, identity verification information of catering logistics service supervisors, food safety anomaly parameters, service quality anomaly parameters, environmental and hygiene anomaly parameters, and operational management anomaly parameters. Specifically, food safety anomaly parameters include the abnormal quantity of ingredients, total ingredient purchase quantity, quantity of ingredients nearing expiration, quantity of expired ingredients, total ingredient inventory, number of storage temperature records that do not meet requirements, and total number of temperature records. Service quality anomaly parameters include the number of orders with overdue preparation time, total number of orders, number of customers waiting overtime, total number of customers, number of orders with overdue delivery time, customer satisfaction rating, number of customer complaints, and number of food quality issues. Environmental and hygiene anomaly parameters include the number of records of substandard air quality, total number of air quality records, area of ​​areas with substandard cleanliness, total clean area, number of kitchen utensils with substandard hygiene, and total number of kitchen utensils. Operational management anomaly parameters include wasted ingredient costs, total ingredient costs, amount of backlogged ingredient inventory, total ingredient inventory, outbound costs, beginning inventory costs, and ending inventory costs.

[0036] The logistics service supervision data analysis module includes a food safety anomaly indicator analysis unit, a service quality anomaly indicator analysis unit, an environmental and hygiene anomaly indicator analysis unit, and an operation management anomaly indicator analysis unit. The food safety anomaly indicator analysis unit is used to calculate food safety anomaly parameters, the service quality anomaly indicator analysis unit is used to calculate service quality anomaly parameters, the environmental and hygiene anomaly indicator analysis unit is used to calculate environmental and hygiene anomaly parameters, and the operation management anomaly indicator analysis unit is used to calculate operation management anomaly parameters. The corresponding calculation results are output to the logistics service supervision early warning module. Its data analysis includes the following steps.

[0037] Step 1: By analyzing abnormal parameters related to food safety, the quality and safety of food are ensured. The abnormality rate of ingredient freshness directly reflects the food management level of catering enterprises. Accurate monitoring of the shelf-life warning rate of ingredients allows logistics service supervision departments to promptly identify and handle ingredients nearing their expiration date, preventing spoilage and potential food safety issues. Appropriate temperature storage can slow down the oxidation and spoilage process of ingredients, thereby extending their shelf life. The model for obtaining food safety abnormality indicators in each monitoring sub-area of ​​the food safety abnormality indicator analysis unit in the logistics service supervision data analysis module is as follows: Sai i =a1 Afr+Wr+Acr Sai i This represents the abnormal food safety index in the i-th monitored sub-region, where a1 is a constant (0 < a1 < 1), and Afr represents the abnormal rate of food freshness. Na represents the number of ingredients with abnormalities in color, texture, etc., detected through artificial intelligence image recognition technology, and Pq represents the total quantity of ingredients purchased. Wr represents the image recognition impact factor, and Wr represents the food shelf life impact factor. Weq represents the quantity of food items nearing their expiration date as monitored by artificial intelligence, Eq represents the quantity of food items already expired as monitored by artificial intelligence, and In represents the total food inventory. This indicates the impact factor of artificial intelligence monitoring; Acr represents the rate of control over abnormal food storage temperatures. Ab represents the number of non-compliant storage temperature records monitored by artificial intelligence, and T_ab represents the total number of temperature records. Indicates the influence factor of the temperature sensor;

[0038] Step 2: By analyzing service quality anomaly parameters, service quality and customer satisfaction can be reflected from different perspectives. The food preparation and delivery timeout rates reflect the efficiency issues in the food preparation and delivery processes; the dish quality anomaly rate directly reflects the stability and reliability of dish quality, and a high dish quality anomaly rate may lead to customer dissatisfaction and complaints; the customer satisfaction decline index reflects changes in service quality by comparing customer satisfaction scores over different time periods; and the complaint growth rate reflects the degree of customer dissatisfaction with the service. The model for obtaining service quality anomaly indicators for each monitored sub-area in the logistics service supervision data analysis module is as follows: Among them, Qai i This represents the service quality anomaly index for the i-th monitored sub-region, where a2 is a constant (0 < a2 < 1), and Ear represents the service efficiency anomaly index. Npo represents the number of orders with delayed food preparation, T_no represents the total number of orders, α1 represents the food preparation influencing factor, Nt represents the number of customers waiting beyond their delivery time, T_nt represents the total number of customers, Ndo represents the number of orders with delayed delivery, α2 represents the delivery influencing factor, and Far represents the customer satisfaction decline index. Cr represents the total customer satisfaction score for the i-th monitored sub-region, Pe represents the total customer satisfaction score for the (i-1)-th monitored sub-region, α3 represents the customer rating influencing factor, Ccn represents the number of complaints in the i-th monitored sub-region, Pcn represents the number of complaints in the (i-1)-th monitored sub-region, Qq represents the number of food quality issues (such as missing ingredients or excessive saltiness) identified through customer feedback or AI image recognition technology, and α4 represents the customer complaint influencing factor. and These represent the weights of the service efficiency anomaly index and the customer satisfaction decline index, respectively.

[0039] Step 3: By analyzing environmental and hygiene anomaly parameters, the restaurant's performance in terms of environment, hygiene, and cleanliness can be quantitatively evaluated. The air quality non-compliance rate reflects the restaurant's air quality management, ensuring a healthier and more comfortable environment; the cleanliness non-compliance rate measures the effectiveness of the restaurant's cleaning work; and the kitchenware hygiene non-compliance rate directly relates to food safety and quality. The model for obtaining environmental and hygiene anomaly indicators for each monitored sub-area in the logistics service supervision data analysis module is as follows: Among them Eai i This represents the abnormal indicators of the environment and sanitation in the i-th monitored sub-area, where a3 is a constant (0 < a3 < 1), and Aar represents the air quality non-compliance rate. Arn represents the number of records of substandard air quality, which refers to instances where the concentration of PM2.5, CO2, etc., exceeded the standards as monitored by artificial intelligence in the restaurant. T_arn represents the total number of air quality records, η1 represents the influencing factor for exceeding the monitoring concentration standards, and Acr represents the rate of non-compliance with table and floor cleanliness standards. Nr represents the area of ​​substandard cleanliness recorded by the AI-powered inspection system, T_nr represents the total cleaned area, η2 represents the cleanliness monitoring influencing factor, and Kar represents the rate of substandard kitchenware hygiene. Nk represents the number of kitchen utensils that fail to meet hygiene standards through artificial intelligence monitoring. Whether the kitchen utensils meet hygiene standards is determined by using artificial intelligence technology to identify unclean marks such as stains and oil stains on the surface of the kitchen utensils, and then quantitatively assessing them. The hygiene level of the kitchen utensils is quantitatively assessed based on indicators such as the area and quantity of stains. T_nk represents the total number of kitchen utensils. η3 represents the kitchen utensils hygiene monitoring influencing factor. β1, β2, and β3 represent the weights of the air quality non-compliance rate, the table and floor cleanliness non-compliance rate, and the kitchen utensils hygiene non-compliance rate, respectively.

[0040] Step 4: Then, analyze the abnormal parameters related to operation and management to promptly identify and resolve problems in the operation process, improve operational efficiency and service quality. The food waste rate directly reflects the efficiency of food management in the catering business; the inventory backlog rate reflects problems in the restaurant's inventory management; and the inventory turnover anomaly rate reflects the efficiency of the restaurant's inventory turnover, helping the restaurant to promptly identify and resolve issues such as unstable sales and poor inventory management. The model for obtaining the abnormal operation and management indicators for each monitored sub-area in the operation and management anomaly indicator analysis unit of the logistics service supervision data analysis module is as follows: Oai i This represents the abnormal indicators for the operation and management of the i-th monitored sub-area, where a4 is a constant (0 < a4 < 1), and Fwr represents the food waste rate. Fwc represents the cost of wasted ingredients, Fc represents the total cost of ingredients, ξ1 represents the factor influencing ingredient waste, and Ibr represents the ingredient inventory backlog rate. Bi represents the amount of food inventory backlog, In represents the total food inventory, ξ2 represents the food inventory backlog influencing factor, and Atr represents the inventory turnover abnormality rate. Itr represents the actual inventory turnover rate. Oc represents outbound cost, Sc represents beginning inventory cost, Ec represents ending inventory cost, Itr0 represents expected turnover rate, and ξ3 represents the factor affecting food inventory turnover. and These represent the weights of food waste rate and abnormal inventory management, respectively.

[0041] The logistics service supervision and early warning module compares the abnormal indicators of catering logistics service supervision in each monitored sub-area within the target area with the set values, and transmits the indicators whose comparison results do not exceed the set values ​​to the logistics service supervision and comprehensive analysis module. The comparison module includes the following steps:

[0042] Step 1: Obtain the analysis and calculation results of food safety anomaly indicators from each monitoring sub-region in the food safety anomaly indicator analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Sai0 represents the set value.

[0043] This embodiment needs to be specifically explained as follows: This indicates that the supervision of catering logistics services is good; conversely, it generates warning signals to supervisory personnel, which helps the logistics service supervision department to promptly detect and handle ingredients that are about to expire, prevent them from spoiling and causing potential food safety problems, effectively control storage temperature, reduce the risk of bacterial growth, and ensure food quality and safety.

[0044] Step 2: Obtain the service quality anomaly index analysis and calculation results for each monitored sub-area from the service quality anomaly index analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Qai0 represents the set value.

[0045] This embodiment needs to be specifically explained as follows: This indicates that the supervision of catering and logistics services is good; conversely, it generates warning signals to supervisors, which helps the supervision of catering and logistics services to identify bottlenecks or problems in the food preparation and delivery process, thereby optimizing the food preparation process and improving service efficiency. It also enables timely detection of service quality issues and the implementation of measures to improve them, in order to maintain or enhance customer satisfaction.

[0046] Step 3: Obtain the analysis and calculation results of environmental and health anomaly indicators for each monitored sub-area from the environmental and health anomaly indicator analysis unit. i Substitute into the formula: Wherein represents The percentage of abnormal indicators; Eai0 represents the set value.

[0047] This embodiment needs to be specifically explained as follows: This indicates that the supervision of catering and logistics services is good; conversely, it generates a warning signal to the supervisors, which helps to increase the supervision of catering and logistics services to pay more attention to the cleanliness and tidiness of the restaurant, avoid the decline in customers' overall impression of the restaurant due to substandard quality, and even prevent food safety issues from arising. This provides a strong guarantee for improving the quality of catering services and customer satisfaction.

[0048] Step 4: Obtain the analysis and calculation results of the operation and management anomaly indicators for each monitored sub-area from the operation and management anomaly indicator analysis unit. i Substitute into the formula: in This indicates the percentage of abnormal indicators; Oai0 represents the set value.

[0049] This embodiment needs to be specifically explained as follows: This indicates that the supervision of catering and logistics services is good. Conversely, it generates warning signals to supervisors, helping restaurants to identify and correct food waste caused by over-purchasing, improper storage, or non-standard employee operations in a timely manner, thereby reducing costs and improving profitability. It also helps restaurants to adjust their purchasing plans and sales strategies in a timely manner, reduce inventory backlog, and improve capital turnover.

[0050] The comprehensive analysis module for logistics service supervision is used to comprehensively analyze the percentage of abnormal indicators in catering logistics services calculated by the above modules that do not exceed the set value, to obtain comprehensive supervision indicators for catering logistics services, and output the comprehensive analysis results to the human-computer interaction module for logistics service supervision. Its comprehensive analysis model is as follows: Where Cri represents the comprehensive regulatory index for catering and logistics services, and λ1, λ2, λ3, and λ4 represent the weights of each abnormal indicator.

[0051] The aforementioned human-computer interaction module for logistics service supervision is used to output the comprehensive supervision indicators input from the above modules to the information terminal of logistics service supervisors. If the comprehensive supervision indicators for catering logistics services are within the set allowable range, it indicates that the overall supervision of catering logistics services is good. Conversely, it prompts supervisors to take timely measures to reduce food safety risks caused by expired ingredients, strengthen storage temperature management, optimize service processes, improve service quality, and enhance customer satisfaction; optimize inventory structure, increase inventory turnover, and reduce inventory costs, thereby improving the level of logistics service supervision.

[0052] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other.

[0053] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A data integrated management system based on artificial intelligence, characterized in that: It includes a logistics service supervision area division module, a logistics service supervision data collection module, a logistics service supervision data analysis module, a logistics service supervision early warning module, a logistics service supervision comprehensive analysis module, and a logistics service supervision human-computer interaction module; The logistics service supervision area division module is used to identify the supervised catering logistics service departments as target areas, and to divide the target areas into several monitoring sub-areas according to equal time periods, which are denoted as 1, 2, 3, ..., n in sequence; The logistics service supervision data acquisition module is used to collect data from each monitoring sub-area, obtain various monitoring parameters of abnormal indicators of catering logistics service supervision, and output various monitoring parameters to the logistics service supervision data analysis module. The logistics service supervision data analysis module includes a food safety anomaly indicator analysis unit, a service quality anomaly indicator analysis unit, an environmental and hygiene anomaly indicator analysis unit, and an operation management anomaly indicator analysis unit. The food safety anomaly indicator analysis unit is used to calculate food safety anomaly parameters, the service quality anomaly indicator analysis unit is used to calculate service quality anomaly parameters, the environmental and hygiene anomaly indicator analysis unit is used to calculate environmental and hygiene anomaly parameters, and the operation management anomaly indicator analysis unit is used to calculate operation management anomaly parameters, and outputs the corresponding calculation results to the logistics service supervision early warning module. The logistics service supervision and early warning module compares the abnormal indicators of catering logistics service supervision in each monitored sub-area within the target area with the set values, and transmits the indicators whose comparison results do not exceed the set values ​​to the logistics service supervision and comprehensive analysis module. The logistics service supervision and comprehensive analysis module is used to comprehensively analyze the percentage of abnormal indicators of catering logistics services calculated by the above module that does not exceed the set value, obtain the comprehensive supervision indicators of catering logistics services, and output the comprehensive analysis results to the logistics service supervision human-computer interaction module. The logistics service supervision human-computer interaction module is used to output the comprehensive supervision indicators passed in by the above module to the information terminal of the logistics service supervision personnel.

2. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The monitoring parameters in the logistics service supervision data collection module include target area information, identity verification information of catering logistics service supervisors, food safety anomaly parameters, service quality anomaly parameters, environmental and hygiene anomaly parameters, and operation management anomaly parameters. Specifically, food safety anomaly parameters include the quantity of abnormal ingredients, total ingredient purchases, quantity of ingredients nearing expiration, quantity of expired ingredients, total ingredient inventory, number of storage temperature records that do not meet requirements, and total number of temperature records. Service quality anomaly parameters include the number of orders with overdue preparation time, total number of orders, number of customers waiting overtime, total number of customers, number of orders with overdue delivery time, customer satisfaction rating, number of customer complaints, and number of food quality issues. Environmental and hygiene anomaly parameters include the number of records of substandard air quality, total number of air quality records, area of ​​areas with substandard cleanliness, total clean area, number of kitchen utensils with substandard hygiene, and total number of kitchen utensils. Operation management anomaly parameters include wasted ingredient costs, total ingredient costs, amount of backlogged ingredient inventory, total ingredient inventory, outbound costs, beginning inventory costs, and ending inventory costs.

3. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The model for food safety anomaly indicators in the logistics service supervision data analysis module is: Sai i =a1 Afr+Wr+Acr Sai i This represents the abnormal food safety index in the i-th monitored sub-region, where a1 is a constant (0 < a1 < 1), and Afr represents the abnormal rate of food freshness. Na represents the abnormal quantity of ingredients, and Pq represents the total quantity of ingredients purchased. Wr represents the image recognition impact factor, and Wr represents the food shelf life impact factor. Weq represents the quantity of food items nearing their expiration date, Eq represents the quantity of food items that have already expired, and In represents the total food inventory. This indicates the impact factor of artificial intelligence monitoring; Acr represents the rate of control over abnormal food storage temperatures. Ab represents the number of storage temperature records that do not meet the requirements, and T_ab represents the total number of temperature records. This indicates the influence factor of the temperature sensor.

4. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The model for service quality anomaly indicators in the logistics service supervision data analysis module is as follows: Among them, Qai i This represents the service quality anomaly index for the i-th monitored sub-region, where a2 is a constant (0 < a2 < 1), and Ear represents the service efficiency anomaly index. Npo represents the number of orders with delayed food preparation, T_no represents the total number of orders, α1 represents the food preparation influencing factor, Nt represents the number of customers waiting beyond their delivery time, T_nt represents the total number of customers, Ndo represents the number of orders with delayed delivery, α2 represents the delivery influencing factor, and Far represents the customer satisfaction decline index. Cr represents the total customer satisfaction score of the i-th monitoring sub-region, Pe represents the total customer satisfaction score of the (i-1)-th monitoring sub-region, α3 represents the customer rating influencing factor, Ccn represents the number of complaints in the i-th monitoring sub-region, Pcn represents the number of complaints in the (i-1)-th monitoring sub-region, Qq represents the number of food quality issues, α4 represents the customer complaint influencing factor, and l1 and l2 represent the weights of the service efficiency anomaly index and the customer satisfaction decline index, respectively.

5. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The model for environmental and hygiene anomaly indicators in the logistics service supervision data analysis module is as follows: Among them Eai i This represents the abnormal indicators of the environment and sanitation in the i-th monitored sub-region, where a3 is a constant (0 < a3 < 1), and Aar represents the air quality non-compliance rate. Arn represents the number of records of air quality non-compliance, T_arn represents the total number of air quality records, η1 represents the influencing factor of excessive monitoring concentrations, and Acr represents the rate of non-compliance of desktop and floor cleanliness. Nr represents the area of ​​the region where cleanliness does not meet the standard, T_nr represents the total area of ​​the cleaned area, η2 represents the cleanliness monitoring influencing factor, and Kar represents the rate of kitchenware hygiene non-compliance. Nk represents the number of kitchen utensils that do not meet hygiene standards, T_nk represents the total number of kitchen utensils, η3 represents the impact factor of kitchen utensils hygiene monitoring, and β1, β2 and β3 represent the weights of the air quality non-compliance rate, the table and floor cleanliness non-compliance rate and the kitchen utensils hygiene non-compliance rate, respectively.

6. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The model for the operational management anomaly indicators in the logistics service supervision data analysis module is as follows: Oai i This represents the abnormal indicators for the operation and management of the i-th monitored sub-area, where a4 is a constant (0 < a4 < 1), and Fwr represents the food waste rate. Fwc represents the cost of wasted ingredients, Fc represents the total cost of ingredients, ξ1 represents the factor influencing ingredient waste, and Ibr represents the ingredient inventory backlog rate. Bi represents the amount of food inventory backlog, In represents the total food inventory, ξ2 represents the food inventory backlog influencing factor, and Atr represents the inventory turnover abnormality rate. Itr represents the actual inventory turnover rate. Oc represents outbound cost, Sc represents beginning inventory cost, Ec represents ending inventory cost, Itr0 represents expected turnover rate, and ξ3 represents the factor affecting food inventory turnover. and These represent the weights of food waste rate and abnormal inventory management, respectively.

7. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The comparison module in the duty service supervision and early warning module includes the following steps: Step 1: Obtain the analysis and calculation results of food safety anomaly indicators from each monitoring sub-region in the food safety anomaly indicator analysis unit. i Substitute into the formula: Among them, ▽Sai i This indicates the percentage of abnormal indicators; Sai0 represents the set value. Step 2: Obtain the service quality anomaly index analysis and calculation results for each monitored sub-area from the service quality anomaly index analysis unit. i Substitute into the formula: Among them, ▽Qai i This indicates the percentage of abnormal indicators; Qai0 represents the set value. Step 3: Obtain the analysis and calculation results of environmental and health anomaly indicators for each monitored sub-area from the environmental and health anomaly indicator analysis unit. i Substitute into the formula: Where ▽Eai i The percentage of abnormal indicators; Eai0 represents the set value. Step 4: Obtain the analysis and calculation results of the operation and management anomaly indicators for each monitored sub-area from the operation and management anomaly indicator analysis unit. i Substitute into the formula: Among them, ▽Oai i This indicates the percentage of abnormal indicators; Oai0 represents the set value.

8. The data integrated management system based on artificial intelligence according to claim 1, characterized in that: The comprehensive analysis model in the logistics service supervision and comprehensive analysis module is as follows: Cri represents the comprehensive regulatory index for catering and logistics services, and λ1, λ2, λ3, and λ4 represent the weights of each abnormal indicator.

Images