Unmanned store risk identification intelligent management system based on big data analysis

Abstract

The invention discloses an unmanned store risk identification intelligent management system based on big data analysis, and belongs to the technical field of risk identification management. The method and the device are used for solving the technical problem of poor commodity settlement and display and placement risk identification and management effects during unmanned store operation in the existing scheme. In the supervision processing unmanned store operation process, different users carry out settlement of different articles, supervision processing data of different users are analyzed and combined, supervision statistical data of all settlement commodities are processed and analyzed, and an existing settlement risk prevention scheme is dynamically managed according to an analysis result. According to the method, the falling conditions of all the placed commodities in the unmanned store are monitored and counted, data processing and analysis are carried out on the display abnormity degrees corresponding to all the display racks for placing the commodities in the unmanned store, the display abnormity degrees corresponding to different display racks are determined according to analysis results, and targeted local display rack commodity placement management is implemented.

Description

Technical Field

[0001] The present invention relates to the technical field of risk identification management, and in particular to an intelligent management system for risk identification of unmanned stores based on big data analysis. Background Art

[0002] Unmanned stores refer to a new retail model in which customers can shop and pay by themselves without the need for human cashiers or sales staff. This model relies on advanced technologies such as automatic identification systems, sensor networks, intelligent monitoring and payment processing. However, unmanned stores also face a variety of risks during their operations, and effective risk identification is an important step to ensure their smooth operation and customer experience.

[0003] When implementing existing unmanned store risk identification and management solutions, most of them still stay at the stage of supervision and processing analysis of sales items. They cannot actively supervise and analyze the accuracy and authenticity of goods sold in unmanned stores at the time of settlement. There is a risk of product labels being tampered with or replaced to conduct false settlement. At the same time, they cannot actively supervise and adjust the safety and stability of the placement of unmanned goods, resulting in poor risk identification management effects at the time of settlement of goods sold in unmanned stores, as well as poor risk identification management effects for the placement of goods. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management system for risk identification of unmanned stores based on big data analysis, which is used to solve the technical problems of poor risk identification and management of commodity settlement and display placement in unmanned stores in existing solutions.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An intelligent management system for risk identification of unmanned stores based on big data analysis, including: The unmanned store settlement service supervision and processing module is used to supervise and process the settlement of different items by different users during the operation of unmanned stores, and analyze and combine the supervision processing data of different users to obtain the individual settlement supervision data corresponding to the settlement of different users; The unmanned store settlement risk analysis management module is used to process the supervision statistics of all settlement commodities, obtain the settlement risk status values ​​corresponding to all settlement commodities, and dynamically manage the existing settlement risk prevention plan by analyzing the settlement risk status values; the settlement risk status values ​​are used to calculate the abnormal settlement supervision data corresponding to all commodity categories, so as to digitally represent the settlement risk status of commodities during unmanned store operations; The unmanned store placement point risk supervision module is used to monitor and count the drop conditions of all placed goods in the unmanned store, process and analyze the drop supervision data, determine the drop impact degree corresponding to different product coordinates, and implement targeted local coordinate product placement management; The unmanned store display surface risk supervision module is used to process and analyze the data of the display abnormality levels corresponding to all display shelves where goods are placed in the unmanned store, determine the display abnormality levels corresponding to different display shelves based on the analysis results, and implement targeted local display shelf product placement management.

[0006] Preferably, the user entering the unmanned store is supervised, and a supervision instruction is generated when the user picks up a product, and the product code and product coordinates corresponding to the picked up product are obtained according to the supervision instruction; When the user puts the picked-up goods back to their original location, a supervision end instruction is generated, and the product code and product coordinates corresponding to the picked-up goods are deleted; When the user moves to the settlement area for settlement, a settlement instruction is generated, and the commodity code set and commodity coordinate set corresponding to all commodities picked up by the user are obtained according to the settlement instruction. At the same time, the settlement commodity codes corresponding to different commodities when the user settles are obtained, and data analysis is performed through the settlement reliability identification function to output the settlement reliability value JKi corresponding to the settlement commodity; Among them, the expression of the settlement reliable identification function is: ; In the formula, JSi is the settlement commodity code corresponding to the user's settlement of different commodities, i is the different commodities settled by the user, i=1, 2, 3, ..., n; n is a positive integer; UJ is the commodity code set corresponding to all commodities picked up by the user.

[0007] Preferably, the settlement information of the commodity is deleted according to the settlement reliability value of 1, and the user is prompted that the settlement of the commodity has failed and the same commodity is replaced; Obtain the commodity category corresponding to the commodity whose settlement reliability value is 1, increase the total number of abnormal settlements corresponding to the commodity category by one, and update the total abnormal settlement price of the commodity category according to the price corresponding to the commodity; The settlement reliability values ​​obtained from processing all commodities settled by the user are sorted and combined to obtain the individual settlement supervision data corresponding to the user's settlement.

[0008] Preferably, when analyzing the risk of settlement of goods in unmanned stores, the total number of abnormal settlements and the total price of abnormal settlements corresponding to all product categories are obtained, and data analysis is performed through the settlement risk identification function to output the settlement risk status value JF corresponding to all product categories; Among them, the expression of settlement risk identification function is: ; In the formula, NY and NJ are the total number of abnormal settlements and the total price of abnormal settlements for all commodity categories respectively; A and B are the total number of abnormal settlement standards and the total price of abnormal settlement standards respectively; is the floor function.

[0009] Preferably, data analysis is performed on the settlement risk status value, and the existing settlement risk prevention plan is dynamically managed based on the analysis results; If the settlement risk status value is 0, the existing settlement risk prevention plan will be implemented in the future; If the settlement risk status value is not 0, the subsequent implementation of the existing settlement risk prevention plan will be optimized and adjusted.

[0010] Preferably, when monitoring and counting the dropping of all displayed commodities in the unmanned store, the commodity codes and commodity coordinates of different dropped commodities are counted, and all the commodity coordinates that appear are sorted and combined, and the total number of dropped commodities corresponding to all commodity coordinates is counted, and the total number of dropped commodities corresponding to different commodity coordinates is analyzed; If the total number of dropped items is 1, the coordinates of the corresponding items will be associated with the normal drop label; If the total number of dropped items is not 1, the coordinates of the corresponding items will be associated with the drop exception label; The normal drop labels or abnormal drop labels obtained by the corresponding analysis of different product coordinates are sorted and combined to obtain the local product coordinate supervision set.

[0011] Preferably, when performing supervision analysis on the placement of local coordinate commodities based on the local commodity coordinate supervision set, the formula Calculate and obtain the drop impact value DY of the product coordinates corresponding to different drop abnormal labels in the local product coordinate supervision set; where NZ is the total number of dropped products corresponding to the product coordinates of the drop abnormal label; NB is the standard total number of dropped products; DJj is the unit price of different dropped products corresponding to the product coordinates of the drop abnormal label, j is the different dropped products corresponding to the product coordinates of the drop abnormal label, j=1, 2, 3, ..., NZ; NZ is a positive integer; BJ is the standard value of the total price of the dropped products corresponding to the product coordinates; α and β are different calculation correction factors, and their value ranges are both (0, 1).

[0012] Preferably, data analysis is performed on the drop impact value to determine the drop impact degree corresponding to the corresponding commodity coordinates and implement targeted local coordinate commodity placement management; If the drop impact value is 0, the associated product coordinates will be slightly affected, and the existing product placement of the associated product coordinates will be maintained; If the drop impact value is greater than 0, the corresponding product coordinates will be associated with the drop heavy impact, and targeted local coordinate product placement adjustments will be implemented for the associated drop heavy impact product coordinates.

[0013] Preferably, the display rack where the coordinates of the products with associated light drop impact or heavy drop impact are located is obtained and marked as the target display rack, and the total number of light drop impact and heavy drop impact associated with the coordinates of all products in the target display rack is counted, and the total number of light drop impact and heavy drop impact associated with the coordinates of all products in the target display rack is calculated, and the formula is used to calculate the total number of light drop impact and heavy drop impact. Calculate and obtain the display abnormality value CZ corresponding to the target display rack; where N1 and N2 are the total number of light drop impacts and the total number of heavy drop impacts corresponding to the target display rack, respectively; η is the impact correction factor, which is a constant greater than 1; CB is the standard value of the display status.

[0014] Preferably, data analysis is performed on display abnormality values ​​to determine the display abnormality degree corresponding to the target display shelf and implement targeted merchandise placement management on the local display shelf; If the display abnormality value is greater than η, the target display rack is associated with the display severity abnormality, and targeted local display rack merchandise placement adjustments are implemented on the target display rack according to the associated display severity abnormality.

[0015] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention realizes the autonomous identification and management of settlement risks of different commodities during unmanned store operation by supervising and processing the settlement of different items by different users during unmanned store operation, and analyzes and combines the supervision and processing data of different users, thereby improving the initiative and reliability of the identification and management of settlement risks of individual commodities.

[0016] The present invention processes and analyzes the regulatory statistical data of all settled commodities, and dynamically manages the existing settlement risk prevention scheme according to the analysis results, thereby realizing comprehensive settlement risk identification and management of commodity settlement in unmanned stores, and improving the identification and management effects of commodity settlement risks in unmanned stores.

[0017] The present invention monitors and counts the falling conditions of all commodities displayed in unmanned stores, processes and analyzes the falling supervision data, and implements targeted local coordinate commodity placement management according to the degree of falling impact obtained by corresponding analysis of different commodity coordinates. It realizes active risk identification and management of commodity display and placement in unmanned stores, and improves the diversity and reliability of risk identification and management of commodity display and placement in different location areas in unmanned stores.

[0018] The present invention processes and analyzes the display abnormality levels corresponding to all display shelves where goods are placed in unmanned stores, determines the display abnormality levels corresponding to different display shelves based on the analysis results, and implements targeted management of the placement of goods on local display shelves, thereby expanding and analyzing the supervision and analysis data of the placement of goods in local coordinates in the early stage, and improving the risk identification and management effects of the display of goods in unmanned stores. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] Figure 1 This is a module block diagram of an unmanned store risk identification intelligent management system based on big data analysis in the present invention.

[0021] Figure 2 This is a flowchart of the operation of an unmanned store risk identification intelligent management system based on big data analysis in the present invention.

[0022] Figure 3 The flowchart is a flow chart of data analysis and management of drop impact value in the present invention.

[0023] Figure 4 It is a flowchart of data analysis and management of display outliers in the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] like Figure 1 to Figure 2 As shown, the present invention is an unmanned store risk identification intelligent management system based on big data analysis, including an unmanned store settlement service supervision processing module, an unmanned store settlement risk analysis management module, an unmanned store placement point risk supervision module and an unmanned store placement surface risk supervision module; The unmanned store settlement service supervision and processing module is used to supervise and process the settlement of different items by different users during the operation of unmanned stores, and analyze and combine the supervision processing data of different users to obtain the individual settlement supervision data corresponding to the settlement of different users; including: Monitor users entering unmanned stores, generate supervision instructions when users pick up products, and obtain product codes and product coordinates corresponding to the picked-up products based on the supervision instructions; It should be noted that corresponding monitoring points are set for different placement areas on the display shelf according to different commodity types. Several pressure sensors are set in the monitoring points. The monitoring points are used to monitor whether the placed commodities in the corresponding placement areas have left. The commodity types can be determined according to the existing classification rules. When the user puts the picked-up goods back to their original location, a supervision end instruction is generated, and the product code and product coordinates corresponding to the picked-up goods are deleted; When the user moves to the settlement area for settlement, a settlement instruction is generated. The settlement area can be divided according to the area where the settlement device is located. The specific division requirements can be customized according to the application requirements of the actual application scenario. The commodity code set and commodity coordinate set corresponding to all commodities picked up by the user are obtained according to the settlement instruction. At the same time, the settlement commodity codes corresponding to different commodities when the user settles are obtained, and data analysis is performed through the settlement reliability identification function to output the settlement reliability value JKi corresponding to the settlement commodity; Among them, the expression of the settlement reliable identification function is: ; In the formula, JSi is the settlement commodity code corresponding to the user's settlement of different commodities, i is the different commodities settled by the user, i=1, 2, 3, ..., n; n is a positive integer, which is the total number of all commodities picked up by the user; UJ is the commodity code set corresponding to all commodities picked up by the user; The settlement reliability value contains a value of 0 or 1; A settlement reliability value of 0 indicates that the settlement status of the corresponding product is reliable; A settlement reliability value of 1 indicates that the settlement status of the corresponding product is unreliable; It should be noted that the settlement reliability value is used to match and analyze the consistency of the corresponding goods and prices when users settle accounts, and to provide a digital representation; Different from the existing technical solutions, which cannot supervise and analyze whether the goods and prices settled by users are consistent, resulting in tampering or replacement of product labels for false settlement; in the embodiment of the present invention, the position change information of displayed goods and the user's settlement information are matched and analyzed by implementing different types of goods on the display shelf, so as to obtain the consistency and integrity of the goods settled by the user.

[0026] According to the settlement reliability value of 1, the settlement information of the product is deleted, and the user is prompted that the settlement of the product has failed and the same product is replaced; Obtain the commodity category corresponding to the commodity whose settlement reliability value is 1, increase the total number of abnormal settlements corresponding to the commodity category by one, and update the total abnormal settlement price of the commodity category according to the price corresponding to the commodity; Sort and combine the settlement reliability values ​​obtained from all commodities settled by the user to obtain the individual settlement supervision data corresponding to the user's settlement; In the embodiment of the present invention, by supervising the settlement of different items by different users during the operation of an unmanned store, and analyzing and combining the supervision processing data of different users, autonomous identification and management of settlement risks of different commodities during the operation of an unmanned store is achieved, thereby improving the initiative and reliability of identification and management of settlement risks of individual commodities.

[0027] The unmanned store settlement risk analysis management module is used to process the regulatory statistical data of all settlement commodities, obtain the settlement risk status values ​​corresponding to all settlement commodities, and dynamically manage the existing settlement risk prevention plan by performing data analysis on the settlement risk status values; including: When analyzing the risk of settlement of goods in unmanned stores, the total number of abnormal settlements and the total price of abnormal settlements corresponding to all product categories are obtained, and data analysis is performed through the settlement risk identification function to output the settlement risk status value JF corresponding to all product categories; Among them, the expression of settlement risk identification function is: ; In the formula, NY and NJ are the total number of abnormal settlements and the total price of abnormal settlements for all product categories respectively; A and B are the total number of abnormal settlement standards and the total price of abnormal settlement standards respectively, which can be determined based on the design requirements data for the operation of unmanned stores, or based on the test data of the early trial operation of unmanned stores; is the floor rounding function; It should be noted that the settlement risk status value is used to calculate the abnormal settlement supervision data corresponding to all commodity categories to digitally represent the settlement risk status of commodities when operating unmanned stores; By expanding the calculation and data analysis of all previous individual commodity settlement risk identification data, determining the settlement risk identification and prevention status corresponding to the existing settlement risk prevention plan, and implementing targeted settlement risk prevention management, the diversity and comprehensiveness of settlement risk identification management can be effectively improved.

[0028] Conduct data analysis on settlement risk status values ​​and dynamically manage existing settlement risk prevention plans based on the analysis results; If the settlement risk status value is 0, the existing settlement risk prevention plan will be implemented in the future; If the settlement risk status value is not 0, the subsequent implementation of the existing settlement risk prevention plan will be optimized and adjusted; Among them, the subsequent implementation of the existing settlement risk prevention plan will be optimized and adjusted, specifically by adding new prevention content and rules to the existing settlement risk prevention plan.

[0029] In the embodiment of the present invention, by processing and analyzing the regulatory statistical data of all settlement commodities, and dynamically managing the existing settlement risk prevention plan based on the analysis results, comprehensive settlement risk identification and management of commodity settlement during unmanned store operations are achieved, thereby improving the identification and management effects of commodity settlement risks during unmanned store operations.

[0030] The unmanned store placement point risk supervision module is used to monitor and count the drop of all placed goods in the unmanned store, process and analyze the drop supervision data, determine the drop impact degree corresponding to different product coordinates, and implement targeted local coordinate product placement management; including: When monitoring and counting the falling of all displayed goods in the unmanned store, the monitoring can be performed according to a number of infrared detectors set between different display racks and the ground, in conjunction with a number of monitoring points set on the display racks. For example, when a monitoring point detects that the goods in the display area to which it belongs have changed, and the ground of the display rack to which the monitoring point belongs has not detected any data changes, it means that the goods have been taken away normally; if a monitoring point detects that the goods in the display area to which it belongs have changed, and the ground of the display rack to which the monitoring point belongs has detected any data changes, it means that the goods have been accidentally knocked down; the goods codes and goods coordinates of different dropped goods are counted, and all the coordinates of the goods that appear are sorted and combined, and the total number of dropped goods corresponding to all the coordinates of the goods is counted, and the total number of dropped goods corresponding to different coordinates of the goods is analyzed; If the total number of dropped items is 1, the coordinates of the corresponding items will be associated with the normal drop label, and the existing items at the corresponding item coordinates will be maintained; If the total number of dropped items is not 1, the coordinates of the corresponding items will be associated with the drop exception label; The normal drop labels or abnormal drop labels obtained by the corresponding analysis of different product coordinates are sorted and combined to obtain a local product coordinate supervision set; When conducting supervision analysis on the placement of local coordinate products based on the local product coordinate supervision set, the formula Calculate and obtain the drop impact value DY of the product coordinates corresponding to different drop abnormal labels in the local product coordinate supervision set; where NZ is the total number of dropped products corresponding to the product coordinates of the drop abnormal label; NB is the standard total number of dropped products; DJj is the unit price of different dropped products corresponding to the product coordinates of the drop abnormal label, j is the different dropped products corresponding to the product coordinates of the drop abnormal label, j=1, 2, 3, ..., NZ; NZ is a positive integer, indicating the total number of dropped products corresponding to the corresponding product coordinates; BJ is the standard value of the total price of dropped products corresponding to the product coordinates, the standard total number of dropped products and the standard value of the total price of dropped products can be determined according to the design requirements data of the unmanned store operation, or according to the test data of the early trial operation of the unmanned store; α and β are different calculation correction factors, and the value range is (0, 1), α can be 0.467, and β can be 0.533; It should be noted that the drop impact value is used to calculate the drop data of all products corresponding to the product coordinates of the drop abnormality label to digitally represent the corresponding drop impact degree; like Figure 3 As shown, data analysis is performed on the drop impact value to determine the drop impact degree corresponding to the corresponding product coordinates and implement targeted local coordinate product placement management; If the drop impact value is 0, the associated product coordinates will be slightly affected, and the existing product placement of the associated product coordinates will be maintained; If the drop impact value is greater than 0, the corresponding product coordinates will be associated with the heavy drop impact, and targeted local coordinate product placement adjustments will be implemented for the associated heavy drop impact product coordinates, for example, the corresponding product coordinates will be adjusted to the type of product that is not easily knocked off; In the embodiment of the present invention, by monitoring and counting the falling conditions of all displayed commodities in the unmanned store, processing and analyzing the falling supervision data, and implementing targeted local coordinate commodity placement management according to the degree of falling impact obtained by corresponding analysis of different commodity coordinates, it is possible to actively identify and manage the risks of commodity display during unmanned store operation, thereby improving the diversity and reliability of risk identification and management of commodity display in different location areas during unmanned store operation.

[0031] The unmanned store display surface risk supervision module is used to process and analyze the display abnormality levels of all display shelves in the unmanned store, determine the display abnormality levels of different display shelves based on the analysis results, and implement targeted local display shelf product placement management; including: Get the display rack where the coordinates of the products with associated light or heavy drops are located and mark it as the target display rack. Count the total number of light drops and heavy drops associated with the coordinates of all products in the target display rack, and calculate the total number of light drops by the formula Calculate and obtain the display abnormality value CZ corresponding to the target display shelf; where N1 and N2 are the total number of light drop impacts and the total number of heavy drop impacts corresponding to the target display shelf, respectively; η is the impact correction factor, and is a constant greater than 1, which can be taken as 1.75; CB is the display status standard value, which can be determined based on the design requirement data of the unmanned store operation, or based on the test data of the early trial operation of the unmanned store; It should be noted that the display abnormality value is used to calculate the drop risk identification data of all the coordinates of the dropped abnormal commodities corresponding to the target display shelf, so as to digitally represent the corresponding display abnormality degree; like Figure 4 As shown, data analysis is performed on display abnormal values ​​to determine the display abnormality degree corresponding to the target display shelf and implement targeted merchandise placement management on local display shelves; If the display abnormality value is less than or equal to η, the corresponding target display shelf is associated with a slight display abnormality; If the display anomaly value is greater than η, the target display shelf will be associated with the display severity anomaly, and targeted local display shelf merchandise placement adjustments will be made to the target display shelf based on the associated display severity anomaly; specifically, all merchandise types displayed on the target display shelf may be replaced with merchandise types that are not easily knocked off, or the display position of the target display shelf may be adjusted.

[0032] In the embodiment of the present invention, by performing data processing and analysis on the display abnormality levels corresponding to all display shelves where goods are placed in an unmanned store, determining the display abnormality levels corresponding to different display shelves based on the analysis results and implementing targeted management of the placement of goods on local display shelves, it is possible to expand and analyze the supervision and analysis data of the previous local coordinate commodity placement, thereby improving the risk identification and management effects of the display of goods during the operation of unmanned stores.

[0033] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0034] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0035] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0036] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0037] It is obvious to a person 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 essential characteristics of the present invention.

[0038] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent management system for risk identification of unmanned stores based on big data analysis, characterized in that: include: The unmanned store settlement service supervision and processing module is used to supervise and process the settlement of different items by different users during the operation of unmanned stores, and analyze and combine the supervision processing data of different users to obtain the individual settlement supervision data corresponding to the settlement of different users; The unmanned store settlement risk analysis management module is used to process the supervision statistics of all settlement commodities, obtain the settlement risk status values ​​corresponding to all settlement commodities, and dynamically manage the existing settlement risk prevention plan by analyzing the settlement risk status values; the settlement risk status values ​​are used to calculate the abnormal settlement supervision data corresponding to all commodity categories, so as to digitally represent the settlement risk status of commodities during unmanned store operations; The unmanned store placement point risk supervision module is used to monitor and count the drop conditions of all placed goods in the unmanned store, process and analyze the drop supervision data, determine the drop impact degree corresponding to different product coordinates, and implement targeted local coordinate product placement management; The unmanned store display surface risk supervision module is used to process and analyze the data of the display abnormality levels corresponding to all display shelves where goods are placed in the unmanned store, determine the display abnormality levels corresponding to different display shelves based on the analysis results, and implement targeted local display shelf product placement management.

2. According to claim 1, the unmanned store risk identification intelligent management system based on big data analysis is characterized in that: Monitor users entering unmanned stores, generate supervision instructions when users pick up products, and obtain product codes and product coordinates corresponding to the picked products based on the supervision instructions; When the user puts the picked-up goods back to their original location, a supervision end instruction is generated, and the product code and product coordinates corresponding to the picked-up goods are deleted; When the user moves to the settlement area for settlement, a settlement instruction is generated, and the commodity code set and commodity coordinate set corresponding to all commodities picked up by the user are obtained according to the settlement instruction. At the same time, the settlement commodity codes corresponding to different commodities when the user settles are obtained, and data analysis is performed through the settlement reliability identification function to output the settlement reliability value JKi corresponding to the settlement commodity; Among them, the expression of the settlement reliable identification function is: ; In the formula, JSi is the settlement commodity code corresponding to the user's settlement of different commodities, i is the different commodities settled by the user, i=1, 2, 3, ..., n; n is a positive integer; UJ is the product code set corresponding to all products picked up by the user.

3. According to claim 2, the intelligent management system for risk identification of unmanned stores based on big data analysis is characterized in that: According to the settlement reliability value of 1, the settlement information of the product is deleted, and the user is prompted that the settlement of the product has failed and the same product is replaced; Obtain the commodity category corresponding to the commodity whose settlement reliability value is 1, increase the total number of abnormal settlements corresponding to the commodity category by one, and update the total abnormal settlement price of the commodity category according to the price corresponding to the commodity; The settlement reliability values ​​obtained from processing all commodities settled by the user are sorted and combined to obtain the individual settlement supervision data corresponding to the user's settlement.

4. According to claim 3, the intelligent management system for risk identification of unmanned stores based on big data analysis is characterized in that: When analyzing the risk of settlement of goods in unmanned stores, the total number of abnormal settlements and the total price of abnormal settlements corresponding to all product categories are obtained, and data analysis is performed through the settlement risk identification function to output the settlement risk status value JF corresponding to all product categories; Among them, the expression of settlement risk identification function is: ; In the formula, NY and NJ are the total number of abnormal settlements and the total price of abnormal settlements for all commodity categories respectively; A and B are the total number of abnormal settlement standards and the total price of abnormal settlement standards respectively; is the floor function.

5. According to claim 4, the unmanned store risk identification intelligent management system based on big data analysis is characterized in that: Conduct data analysis on settlement risk status values ​​and dynamically manage existing settlement risk prevention plans based on the analysis results; If the settlement risk status value is 0, the existing settlement risk prevention plan will be implemented in the future; If the settlement risk status value is not 0, the subsequent implementation of the existing settlement risk prevention plan will be optimized and adjusted.

6. According to claim 1, the intelligent management system for risk identification of unmanned stores based on big data analysis is characterized in that: When monitoring and counting the dropped goods in the unmanned store, the product codes and product coordinates of different dropped goods are counted, and all the product coordinates that appear are sorted and combined. At the same time, the total number of dropped goods corresponding to all product coordinates is counted, and the total number of dropped goods corresponding to different product coordinates is analyzed; If the total number of dropped items is 1, the coordinates of the corresponding items will be associated with the normal drop label; If the total number of dropped items is not 1, the coordinates of the corresponding items will be associated with the drop exception label; The normal drop labels or abnormal drop labels obtained by the corresponding analysis of different product coordinates are sorted and combined to obtain the local product coordinate supervision set.

7. The unmanned store risk identification intelligent management system based on big data analysis according to claim 6 is characterized in that: When conducting supervision analysis on the placement of local coordinate products based on the local product coordinate supervision set, the formula Calculate and obtain the drop impact value DY of the product coordinates corresponding to different drop abnormal labels in the local product coordinate supervision set; where NZ is the total number of dropped products corresponding to the product coordinates of the drop abnormal label; NB is the standard total number of dropped products; DJj is the unit price of different dropped products corresponding to the product coordinates of the drop abnormal label, j is the different dropped products corresponding to the product coordinates of the drop abnormal label, j=1, 2, 3, ..., NZ; NZ is a positive integer; BJ is the standard value of the total price of the dropped products corresponding to the product coordinates; α and β are different calculation correction factors, and their value ranges are both (0, 1).

8. The unmanned store risk identification intelligent management system based on big data analysis according to claim 7 is characterized in that: Conduct data analysis on the drop impact value, determine the drop impact degree corresponding to the corresponding product coordinates, and implement targeted local coordinate product placement management; If the drop impact value is 0, the associated product coordinates will be slightly affected, and the existing product placement of the associated product coordinates will be maintained; If the drop impact value is greater than 0, the corresponding product coordinates will be associated with the drop heavy impact, and targeted local coordinate product placement adjustments will be implemented for the associated drop heavy impact product coordinates.

9. The unmanned store risk identification intelligent management system based on big data analysis according to claim 8, characterized in that: Get the display rack where the coordinates of the products with associated light or heavy drops are located and mark it as the target display rack. Count the total number of light drops and heavy drops associated with the coordinates of all products in the target display rack, and calculate the total number of light drops by the formula Calculate and obtain the display abnormality value CZ corresponding to the target display rack; where N1 and N2 are the total number of light drop impacts and the total number of heavy drop impacts corresponding to the target display rack, respectively; η is the impact correction factor, which is a constant greater than 1; CB is the standard value of the display status.

10. The unmanned store risk identification intelligent management system based on big data analysis according to claim 9, characterized in that: Conduct data analysis on display abnormality values, determine the display abnormality level corresponding to the target display shelf, and implement targeted merchandise placement management on local display shelves; If the display abnormality value is greater than η, the target display rack is associated with the display severity abnormality, and targeted local display rack merchandise placement adjustments are implemented on the target display rack according to the associated display severity abnormality.

Images