Warehouse data intelligent checking method and system

Abstract

The invention discloses a warehouse data intelligent inventory system and method, the system comprises a warehouse intelligent system and a background server, the background server is used for loading a program to execute the following steps: obtaining the occurrence frequency of a first abnormal condition according to a set data statistics time period, the first abnormal condition is determined according to monitoring management data obtained from a warehouse intelligent system, and the starting time node of the data statistics time period is the ending time node of the last check work; determining a first inventory prompt value according to the occurrence frequency of the first abnormal condition; and when the first inventory prompt value is greater than the first early warning threshold value, outputting a first inventory early warning signal. By adopting the scheme of the invention, the timeliness and rationality of inventory work execution can be ensured, so that the accuracy of inventory work and the work processing efficiency are improved, and meanwhile, the increase of invalid operation cost is also avoided.

Description

Technical Field

[0001] The present invention relates to warehouse data analysis and processing technology, and in particular to a warehouse data intelligent inventory method and system. Background Art

[0002] Warehouse inventory is a crucial part of enterprise management. It can not only ensure the accuracy of inventory, optimize inventory management and serve as data support for enterprise decision-making, but also prevent financial risks and enhance corporate image. For the current warehouse inventory work, there are two ways of inventory: regular inventory and irregular inventory. For regular inventory, it is generally carried out at a set time point, such as monthly inventory, quarterly inventory and / or year-end inventory, while irregular inventory is arranged according to demand. However, the former inventory method has the disadvantage of low flexibility, while the latter inventory method, although more flexible, mainly relies on the historical work experience of warehouse managers to determine whether inventory work is needed at present, that is, the frequency of inventory work is too much affected by subjective factors, and there is a lack of reliable data as a basis for decision-making, which easily leads to a poor fit between the frequency of inventory work and the actual situation, resulting in the problem of low inventory accuracy due to insufficient arrangement of inventory work, or the problem of low efficiency of overall warehouse operation and greatly increased operating costs due to too frequent arrangement of inventory work. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a warehouse data intelligent inventory method and system.

[0004] In a first aspect, an embodiment of the present application provides a warehouse data intelligent inventory system, the system comprising a warehouse intelligent system and a backend server, wherein the warehouse intelligent system and the backend server are connected in communication and transmission, wherein:

[0005] The backend server includes at least one processor for loading a program to execute the following steps:

[0006] S1. Obtain the number of occurrences of a first abnormal situation according to a set data statistical time period, wherein the first abnormal situation is determined based on monitoring management data obtained from a warehouse intelligent system, and the start time node of the data statistical time period is the end time node of the last inventory work;

[0007] S2. Determine a first inventory count prompt value according to the number of occurrences of the first abnormal situation;

[0008] S3: When the first inventory count prompt value is greater than the first warning threshold, output a first inventory count warning signal.

[0009] In some embodiments, step S2 specifically includes:

[0010] S201. Obtain the severity of each first abnormal situation;

[0011] S202, determining a first weighted value corresponding to each impact severity; wherein the impact severity and the first weighted value are in direct proportion to each other;

[0012] S203, determining a first inventory counting prompt sub-value corresponding to each first abnormal situation by using the unit value and the first weighted value;

[0013] S204: Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result.

[0014] In some embodiments, step S204 specifically includes:

[0015] S2041. Obtain several historical inventory error rates;

[0016] S2042, calculating the average error rate of several historical inventory work errors to obtain an average error rate;

[0017] S2043, obtaining a second weighted value corresponding to the average value of the error rate;

[0018] S2044. Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result and the second weighted value.

[0019] In some embodiments, step S2043 specifically includes:

[0020] S20431. When the error rate average value is within a first allowable error range, obtain a first weighted sub-value, and use the first weighted sub-value as a second weighted value, wherein a lower limit value of the first allowable error range is 0;

[0021] S20432: When the error rate average value is greater than the upper limit of the first allowable error range, the first weighted sub-value is increased to obtain a second weighted sub-value, and the second weighted sub-value is used as the second weighted value.

[0022] In some embodiments, step S2044 specifically includes:

[0023] S20441. Obtaining a product turnover rate within a data statistical period, wherein the product turnover rate is determined based on a total number of outbound shipments, a total number of inbound shipments, and a total number of days within the data statistical period;

[0024] S20442, determining a third weighted value corresponding to the product turnover rate, wherein the product turnover rate and the third weighted value are in a positive proportional relationship;

[0025] S20443. Summing the first inventory count prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory count prompt value according to the first summation result, the second weighted value, and the third weighted value.

[0026] In some embodiments, the product turnover rate is determined by the following steps:

[0027] S20411, calculating the second summation result between the total number of outbound times and the total number of inbound times;

[0028] S20412, calculating the division result between the second summation result and the total number of days;

[0029] S20413. Determine the product turnover rate based on the division result.

[0030] In some embodiments, the backend server is further used to load a program to perform the following steps:

[0031] S4. When it is determined that the current inventory counting error rate is greater than the upper limit of the first allowable error range, the first abnormal situations are divided according to the inbound and outbound process nodes, so that the first abnormal situations belonging to the same inbound and outbound process node are divided into the same first subset;

[0032] S5. Determine the first audit priority value corresponding to the inbound and outbound process node according to the number of first abnormal situations included in the first subset;

[0033] S6. Arrange the first audit priority values ​​corresponding to the inbound and outbound process nodes in order from large to small.

[0034] In some embodiments, step S5 specifically includes:

[0035] S501. Determine a first audit priority value corresponding to an inbound and outbound process node according to the number of first abnormal situations included in the first subset and a first weighted value corresponding to each abnormal situation.

[0036] In some embodiments, the warehouse intelligence system includes:

[0037] Warehouse intelligent execution operation system, used for intelligent and automated execution of warehouse work;

[0038] Warehouse intelligent monitoring system, used to monitor warehouse scenes;

[0039] The semantic recognition system is used to perform semantic recognition on the input speech content.

[0040] In a second aspect, an embodiment of the present application provides a method for intelligent inventory of warehouse data, the method comprising the following steps:

[0041] S1. Obtain the number of occurrences of a first abnormal situation according to a set data statistical time period, wherein the first abnormal situation is determined based on monitoring management data obtained from a warehouse intelligent system, and the start time node of the data statistical time period is the end time node of the last inventory work;

[0042] S2. Determine a first inventory count prompt value according to the number of occurrences of the first abnormal situation;

[0043] S3: When the first inventory count prompt value is greater than the first warning threshold, output a first inventory count warning signal.

[0044] The present application can achieve at least one of the following technical effects: the present application scheme obtains the number of occurrences of the first abnormal situation according to the set data statistical time period, and then determines the first inventory prompt value according to the number of occurrences of the first abnormal situation, and outputs the first inventory warning signal when the first inventory prompt value is greater than the first warning threshold value, so that the greater the frequency of the abnormal situation, the faster the reminder arrangement of the inventory work will be triggered, and vice versa, the slower the reminder arrangement of the inventory work will be triggered, which not only ensures the timeliness of the execution of the inventory work, avoiding the problem of low inventory accuracy due to untimely arrangement of the inventory work, but also avoids the problem of low warehouse operation efficiency and increased operating costs due to too frequent inventory work arrangements. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments.

[0046] Figure 1 A schematic diagram of the architecture of a warehouse data intelligent inventory system is provided for an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the steps of a first embodiment of a method for intelligent inventory counting of warehouse data is provided for the embodiment of the present application;

[0048] Figure 3 A schematic flow chart of the steps of a second embodiment of a method for intelligent inventory counting of warehouse data is provided for the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described through the implementation method with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0050] According to the current warehouse management workflow, compared with regular inventory counting, irregular inventory counting can be set according to actual conditions, which is more flexible. However, for the current irregular inventory counting work triggering, it is generally based on the subjective judgment results based on the work experience of senior staff as the decision-making basis, which is too situational and cannot fit the actual situation well, resulting in the problem that the inventory counting work is not triggered in time or too frequently.

[0051] In order to solve the above situation, the applicant believes in the research process that it is necessary to use reliable and effective monitoring data as an effective decision-making basis, so that it can be more objective and more in line with the actual situation. Based on this, after analyzing the data of the current warehouse intelligent system, it is found that the more abnormal situations occur, the more likely it is to cause the accuracy of the inventory work to be low, and even the accuracy rate to be lower. For example, the abnormal situation that occurs may at least include the system network information difference causing data packet loss or data delayed upload, the execution time of the execution equipment (such as AGV trolley, sorting robot arm) abnormal, the movement trajectory abnormal, etc., and these abnormal situations will cause errors in the identification of goods information, the wrong position is placed, the invalid grabbing of goods during sorting, and data delayed upload. Problems, this will cause the inventory data in the background warehouse management information to be inconsistent with the actual situation. Therefore, when the frequency of abnormal situations is large, the frequency of inventory work also needs to be larger, otherwise, the triggering frequency of inventory work can be reduced. Based on this, the embodiment of the present application provides a warehouse data intelligent inventory solution, which uses the frequency of abnormal situations as a decision-making basis to trigger the inventory work.

[0052] Reference Figure 1 The embodiment of the present application provides a warehouse data intelligent inventory system, which includes a warehouse intelligent system and a backend server, wherein the warehouse intelligent system and the backend server are connected in communication and transmission. The warehouse intelligent system and the backend server are described in detail as follows.

[0053] The warehouse intelligent system is mainly used for the intelligent and automated execution and monitoring of the entire warehouse work. Specifically, the warehouse intelligent system may include at least the following subsystems:

[0054] Warehouse intelligent execution and operation system, used for intelligent and automated execution of warehouse work; for example, it may include intelligent sorting systems (including goods conveying systems) implemented by robotic arms, stackers, intelligent handling robots that can automatically place goods from designated shelf locations on transport vehicles or from transport vehicles to designated shelf locations, unmanned automatic transport vehicles that only realize goods handling, and other intelligent and automated execution equipment;

[0055] Warehouse intelligent monitoring system, used to monitor warehouse scenes; for example, it may include intelligent monitoring equipment such as camera equipment installed in the warehouse, unmanned aerial vehicles (with cameras) that can fly in the warehouse, environmental monitoring equipment (such as temperature and humidity monitoring equipment, etc.), and smoke monitoring equipment;

[0056] The semantic recognition system is used to perform semantic recognition on the input voice content; specifically, this system is mainly used to obtain the voice work log data recorded by the recording staff in the form of voice recording, and then use the semantic recognition deep learning model to recognize and process the work log data to obtain the corresponding different named entity contents, wherein, based on the recognition of the named entity content, the abnormal operation of the work involved in the voice work log data can be identified.

[0057] Of course, the above-mentioned warehouse intelligent system may also include other specific intelligent automation equipment, which will not be further elaborated here.

[0058] The background server comprises at least one processor for loading a program to execute steps of a warehouse data intelligent inventory method.

[0059] Reference Figure 2 , an embodiment of the present application provides a method for intelligent inventory of warehouse data, which specifically includes the following steps.

[0060] S1. Obtain the number of occurrences of a first abnormal situation according to a set data statistical time period, wherein the first abnormal situation is determined based on monitoring management data obtained from a warehouse intelligent system, and the start time node of the data statistical time period is the end time node of the last inventory work.

[0061] S2. Determine a first inventory count prompt value according to the number of occurrences of the first abnormal situation;

[0062] S3: When the first inventory count prompt value is greater than the first warning threshold, output a first inventory count warning signal.

[0063] Specifically, if the inventory error rate does not meet the requirements after the inventory work, data analysis will inevitably be performed to determine the corresponding influencing factors, so as to make modifications to make the inventory error rate meet the requirements. Therefore, for the triggering of the i+1th inventory work, the main statistics are the number of abnormal situations that occurred after the i-th inventory work was completely completed. Therefore, for the start time node of the data statistical time period, it is the end time node of the previous inventory work. When the first inventory prompt value is greater than the first warning threshold, this moment is used as the end time node of the data statistical time period.

[0064] The number of occurrences of the first abnormal situation is mainly determined by detecting the number of records of the abnormal situation. When a new record of the abnormal situation is detected, the number of occurrences of the first abnormal situation is increased by 1; then, it is determined whether the first inventory prompt value determined based on the current number of occurrences exceeds the first warning threshold. If so, the first inventory warning signal is output to remind the staff to arrange the inventory work as soon as possible. Otherwise, the records of the abnormal situation continue to be detected. If a new record of the abnormal situation is detected, the process returns to the step of increasing the number of occurrences of the first abnormal situation by 1, and then determining whether the first inventory prompt value determined based on the current number of occurrences exceeds the first warning threshold, until the first inventory prompt value determined based on the current number of occurrences exceeds the first warning threshold.

[0065] The steps for determining the first abnormal situation specifically include: 1. Obtaining the operation status information of the intelligent automation execution equipment from the warehouse intelligent execution operation system. When it is determined that the operation status information does not meet the preset regulations, it is determined that an abnormal situation occurs. At this time, the first abnormal situation includes abnormal execution time, abnormal movement path, abnormal cargo grabbing, etc.; 2. Obtaining the scene monitoring data monitored by the intelligent monitoring equipment from the warehouse intelligent monitoring system. When it is determined that the scene monitoring data does not meet the preset regulations, it is determined that an abnormal situation occurs. At this time, the first abnormal situation includes placing goods in an area where goods are not allowed to be placed, the time when the goods are placed on the open space exceeds the preset time, and the employee behavior / operation is abnormal (for example, the employee's misoperation behavior, or the employee's illegal and irregular behavior) , abnormal environmental parameters (such as too high temperature, which may cause safety hazards or goods to deteriorate; too high humidity may cause goods to deteriorate, and changes in goods will lead to goods loss, and if the goods loss is not recorded in time, it will easily increase the inventory error rate), etc.; 3. Obtain the named entity content in the voice work log data output by the semantic recognition system, and obtain the corresponding first abnormal situation after content recognition of the named entity content. For example, when the staff completes the corresponding work or performs work handover, they will use voice to record and report the work. Especially when an abnormal situation occurs, the staff will communicate with relevant personnel in the form of voice communication. At this time, these information data as voice work logs can be identified, so as to identify the specific abnormal content of the abnormal situation. That is, for the monitoring management data, it may include the operating status information of the intelligent automation execution equipment, the scene monitoring data obtained by the intelligent monitoring equipment, and the named entity content in the voice work log data.

[0066] It can be seen that the faster the frequency of abnormal situations, the faster the first inventory prompt value determined based on the number of occurrences of the first abnormal situation exceeds the first warning threshold, which means that the inventory work is triggered and arranged sooner, and vice versa. This can avoid the problem of low accuracy of inventory work due to the fact that there are many abnormal situations but the inventory work is still not arranged, and can also avoid the problem of low efficiency of the overall warehouse operation and increased operating costs due to too frequent inventory work arrangements. In other words, by using the solution of the embodiment of the present application, the timeliness and rationality of triggering the execution of inventory work are improved, thereby improving the accuracy and efficiency of the inventory work, and reducing the ineffective loss of operating costs.

[0067] In some embodiments, for different abnormal situations, different severity levels of impact may be configured according to factors such as the location of the abnormal situation, the difference of the abnormal situation (i.e., the difference between the abnormal situation and the normal situation), and the degree of negative impact on subsequent workflow nodes. The severity level of impact may be expressed as a numerical value, and the greater the severity level of an abnormal situation, the faster the inventory work should be triggered and arranged, thereby further ensuring the accuracy of the inventory work. Therefore, for the step S2, it may specifically include the following steps.

[0068] S201. Obtain the severity of the impact of each first abnormal situation.

[0069] Specifically, the step S201 may be specifically as follows: obtaining attribute parameters of the first abnormal situation as training input data, wherein the attribute parameters of the first abnormal situation may at least include the location where the first abnormal situation occurs, the time point when the abnormal situation occurs, the difference of the abnormal situation and / or the degree of negative impact on subsequent workflow nodes; then, the training input data is input into the trained first deep learning training machine for processing, and the corresponding impact severity level number is output, and the larger the value of the impact severity level number, the greater the impact severity.

[0070] S202, determining a first weighted value k1 corresponding to each impact severity; wherein the impact severity and the first weighted value are in direct proportion, that is, the higher the impact severity level, the greater the first weighted value.

[0071] Specifically, in this embodiment, the first weighted value k1 may be greater than or equal to 1. Further preferably, the value range of the first weighted value may be between [a, b], where a is 1 and b is greater than or equal to 3. Alternatively, the specific value of b may be determined based on the number of levels affecting the severity.

[0072] S203: Determine the first inventory reminder sub-value corresponding to each first abnormal situation by using the unit value and the first weighted value. In this embodiment, the unit value may be 1, indicating that one more abnormal situation is identified.

[0073] Specifically, the step S203 may be as follows: calculating the unit value M and the first weighted value k1 i+1 The product of the two, where k1 i+1 It is represented as the first weighted value corresponding to the i+1th first abnormal situation, and the product result is used as the first inventory reminder sub-value corresponding to the i+1th first abnormal situation.

[0074] S204: Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result.

[0075] Specifically, since the unit value is 1, the first inventory prompt sub-values ​​corresponding to the first abnormal situations are summed to obtain a first sum result. i+1 That is, it is equal to k11+k12+…+k1 i+1 , where k11 represents the first weighted value corresponding to the first abnormal situation, k12 represents the first weighted value corresponding to the second abnormal situation, and so on. i+1 The first weighted value corresponding to the i+1th abnormal situation is equivalent to superimposing and summing the first weighted values ​​corresponding to each first abnormal situation detected. In addition, for determining the first inventory reminder value according to the first summation result, the first summation result can be directly used as the first inventory reminder value, or the first summation result can be further processed accordingly to obtain a result that is used as the first inventory reminder value.

[0076] It can be seen that the present embodiment adjusts the first inventory prompt sub-value corresponding to each abnormal situation by adding the factor of the severity of the impact of the abnormal situation, thereby realizing the adjustment of the first inventory prompt value, so that the triggering of the inventory work is more closely matched with the abnormal frequency and the severity of the impact, thereby further ensuring the accuracy of the inventory work.

[0077] In some embodiments, generally, the more frequent the inventory work, that is, the shorter the time interval between the inventory work, the higher the work accuracy will be, and even the zero error rate can be maintained continuously. Therefore, by identifying and judging the error rate of the historical inventory work, it can be determined whether the triggering speed of the inventory work needs to be adjusted. For example, if the error rate of the historical inventory work is high, the inventory work needs to be triggered faster, otherwise, there is no need to speed up the triggering of the inventory work, and even based on the consideration of warehouse work efficiency, the triggering of the inventory work can be slowed down. Therefore, for the step S204, it can specifically include the following steps.

[0078] S2041. Obtain several historical inventory error rates.

[0079] Specifically, the historical inventory work error rate refers to the original inventory work error rate obtained after the inventory work results, that is, the error rate that has not been modified (because if it is found that the error rate is greater than the set threshold, it will generally be modified through cause analysis to make the final error rate meet the requirements). In addition, the selection of the historical inventory work error rate can be set according to actual needs. In this embodiment, in order to be more in line with the actual situation, the selection method is to select the first 10 historical inventory work error rates. For example, if the current inventory work is the 11th time, then the error rates corresponding to the 1st...10th historical inventory work are obtained.

[0080] S2042, calculating the average of several historical inventory work error rates to obtain an average error rate. Specifically, the average error rate is used as a basis for determining the subsequent second weighted value, and the data accuracy is higher and closer to the actual situation.

[0081] S2043. Obtain a second weighted value corresponding to the average value of the error rate.

[0082] Specifically, the step S2043 may specifically include the following steps.

[0083] S20431. When the error rate average value is within a first allowable error range, obtain a first weighted sub-value, and use the first weighted sub-value as a second weighted value, wherein a lower limit value of the first allowable error range is 0, that is, [0, c];

[0084] S20432. When the average value of the error rate is greater than the upper limit c of the first allowable error range, the first weighted sub-value is increased to obtain a second weighted sub-value, and the second weighted sub-value is used as the second weighted value. It can be seen that in this way, when the historical error rate does not meet the accuracy requirement, the weighted value of the first summation result can be increased, thereby speeding up the triggering of the inventory work, so that the error rate of the next triggered inventory work becomes lower until it meets the requirement.

[0085] Furthermore, the first difference between the second weighted sub-value and the first weighted sub-value is directly proportional to the second difference between the average value of the error rate and the upper limit value c of the first allowable error range, which means that the greater the degree to which the average value of the error rate exceeds the specified accuracy requirement, the faster the inventory work needs to be triggered. In addition, since the first difference represents the degree of increase in the value of the first weighted sub-value, and considering that too frequent triggering of the inventory work will increase the operating cost, the maximum value of the first difference is constrained by the increase in operating cost, that is, for the first difference, its maximum value is determined based on the increase in operating cost, so that the increased operating cost will not exceed the specified budget under the premise of shortening the duration of the inventory work triggering.

[0086] S2044. Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result and the second weighted value.

[0087] Specifically, the first inventory reminder value is determined according to the first summation result and the second weighted value. The first product result between the first summation result and the second weighted value k2 is calculated, that is, k2*I i+1 , and use the first product result as the first inventory prompt value.

[0088] In some embodiments, if the goods have high liquidity, that is, the frequency of goods entering and leaving the warehouse is high, then it means that the inventory changes quickly and the number of times the goods enter and leave the warehouse is high, which is likely to cause the error rate of the inventory work to become larger. Therefore, the time for triggering the inventory work should be shortened. Therefore, the step S2044 can specifically include the following steps.

[0089] S20441. Obtain the goods turnover rate within the data statistical time period, wherein the goods turnover rate is determined based on the total number of outbound shipments, the total number of inbound shipments, and the total number of days in the data statistical time period.

[0090] S20442. Determine a third weighted value k3 corresponding to the product turnover rate, wherein the product turnover rate and the third weighted value are in positive proportion.

[0091] S20443. Summing the first inventory count prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory count prompt value according to the first summation result, the second weighted value, and the third weighted value.

[0092] Specifically, the first inventory reminder value is determined according to the first summation result, the second weighted value k2 and the third weighted value k3, which is: calculating the second product result of the first summation result, the second weighted value k2 and the third weighted value k3, that is, k3*k2*I i+1 , and the second product result is used as the first inventory reminder value. It can be seen that in this way, the triggering time of the inventory work can be adjusted by comprehensively considering the severity of the impact, the error rate, and the flow of goods, which is further in line with the actual situation. Under the condition of meeting the three specific requirements of the severity of the impact of the abnormal situation, the error rate of the inventory work, and the flow rate of goods, the accuracy of the inventory work is improved while ensuring the work efficiency and operating costs.

[0093] In some embodiments, in order to improve the accuracy of determining the product turnover rate, the product turnover rate is determined by the following steps:

[0094] S20411, calculating the second summation result between the total number of outbound times and the total number of inbound times;

[0095] S20412, calculating the division result between the second summation result and the total number of days, that is, the division result = (total number of outbound times + total number of inbound times) / total number of days;

[0096] S20413. Determine the product turnover rate based on the division result.

[0097] Specifically, in this embodiment, the division result can be directly used as the product turnover rate, or the division result can be adjusted using the empirical weighted value k4, and the adjusted result can be used as the product turnover rate, that is, the product turnover rate at this time is k4*division result.

[0098] In some embodiments, reference Figure 3 , this method embodiment also includes the following steps.

[0099] S4. When it is determined that the current inventory counting error rate is greater than the upper limit of the first allowable error range, the first abnormal situations are divided according to the inbound and outbound process nodes, so that the first abnormal situations belonging to the same inbound and outbound process node are divided into the same first subset.

[0100] Specifically, when the error rate of the current inventory work exceeds the preset range, it is necessary to conduct an inventory analysis of the process of entering and leaving the warehouse to find out the reasons for the excessive error rate and make subsequent modifications. Based on the above content, it can be obtained that the abnormal situation that occurs is the main factor causing the error rate. Therefore, all first abnormal situations can be divided according to the entry and exit process nodes as the basis for division, so that the first abnormal situations belonging to the same entry and exit process node are divided into the same first subset. Among them, according to the occurrence location, occurrence time point, corresponding execution operation, etc. of the first abnormal situation, it can be determined at which entry and exit process node the first abnormal situation occurs.

[0101] S5. Determine the first audit priority value corresponding to the inbound and outbound process node according to the number of first abnormal situations included in the first subset.

[0102] S6. Arrange the first audit priority values ​​corresponding to the inbound and outbound process nodes in order from large to small. In this way, the corresponding inbound and outbound process nodes can be checked and audited in order from large to small according to the number of occurrences / occurrences of abnormal situations. This makes it easier and faster to check and audit problems, greatly improving work processing efficiency.

[0103] In some embodiments, the method embodiment further includes the following steps.

[0104] S7. For the first abnormal situations included in the first subset, the first abnormal situations are divided according to the locations where the first abnormal situations occur, so that the first abnormal situations belonging to the same location area are divided into the same second subset;

[0105] S8. Determine the second audit priority values ​​corresponding to different location area ranges according to the number of first abnormal situations included in the second subset;

[0106] S9. Arrange the second audit priority values ​​corresponding to the location area ranges in order from large to small. In this way, during the investigation and audit of any inbound and outbound process node, the investigation can be started from the location area range where the most abnormal situations occur, thereby further improving the efficiency of the investigation and audit processing.

[0107] In some embodiments, step S5 specifically includes:

[0108] S501. Determine a first audit priority value corresponding to an inbound and outbound process node according to the number of first abnormal situations included in the first subset and a first weighted value corresponding to each abnormal situation.

[0109] Specifically, the specific implementation method of this step is: after summing up the first weighted numerical values ​​corresponding to each first abnormal situation contained in the first subset, the summation result is determined as the first audit priority value corresponding to the first subset, and a warehouse entry and exit process node corresponds to a first subset.

[0110] Similarly, the step S8 may specifically include:

[0111] S801. Determine the second audit priority values ​​corresponding to different location area ranges based on the number of first abnormal situations included in the second subset and the first weighted numerical value corresponding to each abnormal situation.

[0112] Similarly, the specific implementation method of this step is: after summing up the first weighted numerical values ​​corresponding to each first abnormal situation contained in the second subset, the summation result is determined as the second audit priority value corresponding to the second subset, and a location area range corresponds to a second subset.

[0113] In addition, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above method embodiment.

[0114] For the processors mentioned in the above storage medium embodiment and the system embodiment, the number can be at least 1, and at least any step in the above method embodiment can be executed. When the number is at least two, at least two processors can be connected to each other by communication, not limited to wired or wireless communication connection, and the at least one processor can be connected to various intelligent terminal devices by communication. In addition, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0115] Finally, it should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A warehouse data intelligent inventory system, characterized in that: The system includes a warehouse intelligent system and a backend server, wherein the warehouse intelligent system and the backend server are connected in communication and transmission, wherein: The backend server includes at least one processor for loading a program to execute the following steps: S1. Obtain the number of occurrences of a first abnormal situation according to a set data statistical time period, wherein the first abnormal situation is determined based on monitoring management data obtained from a warehouse intelligent system, and the start time node of the data statistical time period is the end time node of the last inventory work; S2. Determine a first inventory count prompt value according to the number of occurrences of the first abnormal situation; S3: When the first inventory count prompt value is greater than the first warning threshold, output a first inventory count warning signal.

2. The system according to claim 1, characterized in that The step S2 specifically includes: S201, obtaining the severity of each first abnormal situation; S202, determining a first weighted value corresponding to each impact severity; wherein the impact severity and the first weighted value are in direct proportion to each other; S203, determining a first inventory counting prompt sub-value corresponding to each first abnormal situation by using the unit value and the first weighted value; S204: Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result.

3. The system according to claim 2, characterized in that The step S204 specifically includes: S2041. Obtain several historical inventory error rates; S2042, calculating the average error rate of several historical inventory work errors to obtain an average error rate; S2043, obtaining a second weighted value corresponding to the average value of the error rate; S2044: Summing the first inventory counting prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory counting prompt value according to the first summation result and the second weighted value.

4. The system according to claim 3, characterized in that The step S2043 specifically includes: S20431. When the error rate average value is within a first allowable error range, obtain a first weighted sub-value, and use the first weighted sub-value as a second weighted value, wherein a lower limit value of the first allowable error range is 0; S20432: When the error rate average value is greater than the upper limit of the first allowable error range, the first weighted sub-value is increased to obtain a second weighted sub-value, and the second weighted sub-value is used as the second weighted value.

5. The system according to claim 3, characterized in that The step S2044 specifically includes: S20441. Obtaining a product turnover rate within a data statistical period, wherein the product turnover rate is determined based on a total number of outbound shipments, a total number of inbound shipments, and a total number of days within the data statistical period; S20442, determining a third weighted value corresponding to the product turnover rate, wherein the product turnover rate and the third weighted value are in a positive proportional relationship; S20443. Summing the first inventory count prompt sub-values ​​corresponding to the plurality of first abnormal situations to obtain a first summation result, and determining a first inventory count prompt value according to the first summation result, the second weighted value, and the third weighted value.

6. The system according to claim 5, characterized in that The product turnover rate is determined by the following steps: S20411, calculating the second summation result between the total number of outbound times and the total number of inbound times; S20412, calculating the division result between the second summation result and the total number of days; S20413. Determine the product turnover rate based on the division result.

7. The system according to claim 4, characterized in that The backend server is also used to load a program to perform the following steps: S4. When it is determined that the current inventory counting error rate is greater than the upper limit of the first allowable error range, the first abnormal situations are divided according to the inbound and outbound process nodes, so that the first abnormal situations belonging to the same inbound and outbound process node are divided into the same first subset; S5. Determine the first audit priority value corresponding to the inbound and outbound process node according to the number of first abnormal situations included in the first subset; S6. Arrange the first audit priority values ​​corresponding to the inbound and outbound process nodes in order from large to small.

8. The system according to claim 7, characterized in that The step S5 specifically includes: S501. Determine a first audit priority value corresponding to an inbound and outbound process node according to the number of first abnormal situations included in the first subset and a first weighted value corresponding to each abnormal situation.

9. The system according to any one of claims 1 to 8, characterized in that: The warehouse intelligent system includes: a warehouse intelligent execution and operation system for intelligently and automatically executing warehouse work; Warehouse intelligent monitoring system, used to monitor warehouse scenes; The semantic recognition system is used to perform semantic recognition on the input speech content.

10. A method for intelligent inventory counting of warehouse data, characterized in that: The method comprises the following steps: S1. Obtain the number of occurrences of a first abnormal situation according to a set data statistical time period, wherein the first abnormal situation is determined based on monitoring management data obtained from a warehouse intelligent system, and the start time node of the data statistical time period is the end time node of the last inventory work; S2. Determine a first inventory count prompt value according to the number of occurrences of the first abnormal situation; S3: When the first inventory count prompt value is greater than the first warning threshold, output a first inventory count warning signal.

Images