Intelligent storage information acquisition method and system

Abstract

The invention relates to the technical field of intelligent warehousing, and particularly discloses an intelligent warehousing information acquisition method and system, and the method comprises the steps: obtaining the cargo amount at regular time according to a sensor installed at a warehousing space; arranging the cargo quantity according to the time information to obtain a cargo quantity array, and synchronously calculating an autocorrelation coefficient and a lag time difference of the cargo quantity data; comparing the self-correlation coefficient and the lag time difference of each storage space to obtain the similarity between any two storage spaces; and for any storage space, determining the image acquisition frequency according to the similarity between the storage space and all other storage spaces. According to the method, the goods change information of each storage space is periodically analyzed, the goods change similarity between each storage space and other storage spaces is determined according to the periodic analysis result, the importance degree of each storage space is evaluated, then the data acquisition frequency is adjusted, and the traditional fixed acquisition frequency is optimized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent warehousing technology, and in particular to an intelligent warehousing information collection method and system. Background Art

[0002] Intelligent warehousing refers to the deployment of various sensors, RFID tags, drones, robots and other intelligent hardware devices to comprehensively and accurately collect cargo information, inventory status and environmental parameters in the warehouse in real time, thereby achieving accurate prediction of inventory levels, rapid positioning of cargo, and optimal planning of picking routes.

[0003] In the existing warehouse information collection scheme, each storage space is actually analyzed separately, and each storage space collects data at an independent information collection frequency, which puts a lot of pressure on data transmission. In fact, for warehousing scenarios, goods almost never change until a long time later. The actual data collection actually contains a lot of invalid data. How to optimize the existing data collection process is the technical problem that the technical solution of the present invention aims to solve. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent warehouse information collection method and system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent storage information collection method, the method comprising:

[0007] The amount of goods is obtained regularly according to sensors installed in the storage space; the obtained amount of goods contains time information; the working frequencies of the sensors in the storage space are the same;

[0008] Arrange the cargo quantity according to the time information to obtain a cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly;

[0009] Compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces;

[0010] For any storage space, the image acquisition frequency is determined based on the similarity between it and all other storage spaces.

[0011] Furthermore, the steps of arranging the cargo quantity according to the time information to obtain a cargo quantity array and synchronously calculating the autocorrelation coefficient and the lag time difference of the cargo quantity data include:

[0012] Arrange the cargo quantity according to the time information to obtain a cargo quantity array;

[0013] Starting from the end of the cargo quantity array, obtain a preset number of cargo quantities in reverse order as the array to be analyzed;

[0014] Create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values;

[0015] For each serial number difference in the serial number difference series, the autocorrelation coefficient is calculated once for the cargo quantity array;

[0016] Select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient;

[0017] Read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

[0018] Furthermore, the process of calculating the autocorrelation coefficient includes:

[0019]

[0020] Where ρ(k) represents the autocorrelation coefficient with a sequence number difference of k, Cov(k) represents the autocovariance with a sequence number difference of k, and Var(k) represents the variance of the array to be analyzed with a sequence number difference of k; x t represents the kth element in the array to be analyzed, μ is the mean of each element in the array to be analyzed; x t+k represents the t+kth element in the array to be analyzed; N represents the total number of elements in the array to be analyzed.

[0021] Furthermore, the step of comparing the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces includes:

[0022] The distance range for receiving staff to enter;

[0023] For any storage space, take it as the center, query the storage spaces within the distance range in turn, and pair them with the storage space at the center;

[0024] For each pair of storage spaces, read the autocorrelation coefficients and their lag time difference between the two storage spaces;

[0025] Compare the correlation coefficient and its lag time difference to calculate the similarity;

[0026] Among them, the similarity between any two storage spaces is calculated only once.

[0027] Furthermore, the step of determining the image acquisition frequency for any storage space according to the similarity between it and all other storage spaces includes:

[0028] For any storage space, read the similarity between it and all other storage spaces;

[0029] Calculating the mean of the read similarities, and determining the image acquisition frequency according to the mean;

[0030] Among them, the relationship between image acquisition frequency and mean is:

[0031] Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

[0032] Furthermore, the step of obtaining the amount of goods at regular intervals according to the sensor installed in the storage space includes:

[0033] Read the image of storage space regularly;

[0034] Performing contour recognition on the image, locating the cargo, and simultaneously calculating the cargo volume;

[0035] The accuracy of determining cargo quantity based on cargo volume;

[0036] When the accuracy is less than a preset accuracy threshold, an inspection request directed to the storage space is generated.

[0037] The technical solution of the present invention also provides an intelligent storage information collection system, the system comprising:

[0038] A cargo quantity acquisition module is used to obtain the cargo quantity according to the sensors installed in the storage space at regular intervals; the obtained cargo quantity contains time information; the working frequencies of the sensors in the storage space are the same;

[0039] A correlation judgment module is used to arrange the cargo quantity according to the time information, obtain the cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly;

[0040] The similarity calculation module is used to compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces;

[0041] The image acquisition module is used to determine the image acquisition frequency for any storage space based on the similarity between it and all other storage spaces.

[0042] Furthermore, the relevance determination module includes:

[0043] A cargo quantity arrangement unit, used for arranging the cargo quantity according to the time information to obtain a cargo quantity array;

[0044] A data interception unit is used to obtain a preset number of cargo quantities in reverse order starting from the end of the cargo quantity array as an array to be analyzed;

[0045] A sequence creation unit, used to create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values;

[0046] A calculation execution unit, for calculating an autocorrelation coefficient of the cargo quantity array once for each serial number difference in the serial number difference series;

[0047] A maximum value selection unit is used to select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient;

[0048] The time difference calculation unit is used to read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

[0049] Furthermore, the similarity calculation module includes:

[0050] A distance range receiving unit is used to receive the distance range entered by the staff;

[0051] The pairing unit is used to query the storage spaces within the distance range of any storage space with it as the center, and pair them with the storage space at the center;

[0052] A parameter reading unit, used for reading the autocorrelation coefficient and the lag time difference of the two storage spaces for each pair of storage spaces;

[0053] A parameter comparison unit is used to compare the correlation coefficient and its lag time difference and calculate the similarity;

[0054] Among them, the similarity between any two storage spaces is calculated only once.

[0055] Furthermore, the image acquisition module includes:

[0056] A similarity reading unit is used to read the similarity between any storage space and all other storage spaces;

[0057] A frequency determination unit, used to calculate the mean of the read similarities, and determine the image acquisition frequency according to the mean;

[0058] Among them, the relationship between image acquisition frequency and mean is:

[0059] Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

[0060] Compared with the prior art, the beneficial effects of the present invention are: the present invention periodically analyzes the cargo change information of each storage space, determines the similarity of cargo changes between each storage space and other storage spaces based on the periodic analysis results, evaluates the importance of each storage space, and then adjusts the data collection frequency, thereby optimizing the traditional fixed collection frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0062] Figure 1 This is a flowchart of the intelligent warehouse information collection method.

[0063] Figure 2 This is a structural block diagram of the intelligent warehousing information collection system. DETAILED DESCRIPTION

[0064] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] Figure 1 The flowchart of the intelligent warehouse information collection method is as follows. In an embodiment of the present invention, an intelligent warehouse information collection method is provided, and the method includes:

[0066] Step S100: obtaining the amount of goods at regular intervals according to sensors installed in the storage space; the obtained amount of goods contains time information; the working frequencies of the sensors in the storage space are the same;

[0067] The storage space is generally a warehouse, and the sensor is generally a pressure sensor, which is used to obtain the quantity of goods; the quantity of goods is used to characterize the amount of goods; for some more intelligent environments, a recording module will be set at the entrance of each storage space, and the goods entering and leaving the warehouse will need to be recorded (equivalent to filing). At this time, even if the sensor is not installed, the quantity of goods in each storage space can be obtained.

[0068] It should be noted that the process of obtaining the quantity of goods is a timed process, for example, it is obtained every five minutes; in order to make the data more regular, this application assumes that all storage spaces have the same working time cycle, that is, the quantity of goods in all storage spaces is obtained once every period of time;

[0069] Step S200: Arrange the cargo quantity according to the time information to obtain a cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly;

[0070] Arrange the cargo quantity in chronological order to obtain a cargo quantity array. Perform autocorrelation analysis on the cargo quantity array to determine whether the cargo quantity is repeated. It actually evaluates the periodic characteristics. Among them, the autocorrelation coefficient represents the probability of periodicity, and the lag time difference is the corresponding period.

[0071] It should be noted that, when calculating the cargo quantity array, the relationship between the elements of each serial number is calculated, and it is multiplied by the cargo quantity acquisition cycle to obtain the data in time format, that is, the lag time difference.

[0072] Step S300: Compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces;

[0073] After the autocorrelation coefficient and its lag time difference of each storage space are determined, they are used as the characteristics of each storage space and compared pairwise to calculate the similarity between any two storage spaces.

[0074] Step S400: for any storage space, determine the image acquisition frequency according to the similarity between it and all other storage spaces;

[0075] After the similarity calculation is completed, for any storage space, the similarity between it and all other storage spaces is read, the similarity mean is calculated, and the image acquisition frequency is determined according to the similarity mean.

[0076] In one example of the technical solution of the present invention, the final output is to adjust the image acquisition frequency in each storage space, obtain actual visual information with the help of cameras installed in each storage space, and further identify it by the staff; when there are many storage spaces, the technical solution of this application can greatly simplify the number of storage spaces that require manual identification, that is, the staff only needs to manually identify some of the more important storage spaces.

[0077] Regarding step S200: the step of arranging the cargo quantity according to the time information to obtain a cargo quantity array and synchronously calculating the autocorrelation coefficient and the lag time difference of the cargo quantity data includes:

[0078] Arrange the cargo quantity according to the time information to obtain a cargo quantity array;

[0079] Starting from the end of the cargo quantity array, obtain a preset number of cargo quantities in reverse order as the array to be analyzed;

[0080] Create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values;

[0081] For each serial number difference in the serial number difference series, the autocorrelation coefficient is calculated once for the cargo quantity array;

[0082] Select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient;

[0083] Read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

[0084] In an example of the technical solution of the present invention, the autocorrelation analysis process is described in detail, and the cargo quantity is arranged in chronological order to obtain a cargo quantity array. For some cargo quantities that are relatively old, there is actually no analytical significance. Therefore, the present application performs data screening on the cargo quantity array, first determines a range, such as ten days, and intercepts the data within ten days in the cargo quantity array, which is called the array to be analyzed.

[0085] After obtaining the array to be analyzed, multiple serial number differences are determined. The present application adopts a gradually increasing manner to determine the serial number differences, that is, the serial number difference series; for each serial number difference, the autocorrelation coefficient is calculated once; the actual role of the serial number difference is that, assuming the serial number difference is five, each data is compared with the fifth data before it, and the comparisons are made in sequence to determine the autocorrelation coefficient; the final result is that each serial number difference corresponds to an autocorrelation coefficient.

[0086] Specifically, the process of calculating the autocorrelation coefficient includes:

[0087]

[0088] Where ρ(k) represents the autocorrelation coefficient with a sequence number difference of k, Cov(k) represents the autocovariance with a sequence number difference of k, and Var(k) represents the variance of the array to be analyzed with a sequence number difference of k; x t represents the kth element in the array to be analyzed, μ is the mean of each element in the array to be analyzed; x t+k represents the t+kth element in the array to be analyzed; N represents the total number of elements in the array to be analyzed.

[0089] The calculation result of the autocorrelation coefficient means that if ρ(k) is close to 1, it means that at lag k, there is a high positive correlation between the data; if ρ(k) is close to 1, it means that at lag k, there is almost no correlation; if ρ(k) is close to -1, it means that at lag k, there is a strong negative correlation between the data. In the technical solution of the present invention, whether it is close to 1 or close to -1, it is considered to have correlation; selecting the maximum value of the autocorrelation coefficient is actually selecting the maximum value of the absolute value of the autocorrelation coefficient.

[0090] Regarding step S300: the step of comparing the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces includes:

[0091] The distance range for receiving staff to enter;

[0092] For any storage space, take it as the center, query the storage spaces within the distance range in turn, and pair them with the storage space at the center;

[0093] For each pair of storage spaces, read the autocorrelation coefficients and their lag time difference between the two storage spaces;

[0094] Compare the correlation coefficient and its lag time difference to calculate the similarity;

[0095] Among them, the similarity between any two storage spaces is calculated only once.

[0096] Receive the distance range input by the staff, where the distance range is a numerical value and can be understood as a radius; for any storage space, determine a range with the storage space as the center and the distance range as the radius, query the storage spaces within the range, pair them up with each other, and calculate the similarity; the process of calculating the similarity is to compare the autocorrelation coefficients and the lag time difference of the two storage spaces, that is, the similarity is the dependent variable, and the autocorrelation coefficients and the lag time difference of the two storage spaces are the independent variables.

[0097] It is worth mentioning that the similarity between A and B is the same as the similarity between B and A. Therefore, before calculating the similarity, you can check in the historical calculation records whether the calculation has been completed. If the calculation is completed, there is no need to repeat the calculation; this also means that the calculated similarity needs to be recorded and stored in real time.

[0098] Regarding step S400: the step of determining the image acquisition frequency for any storage space according to the similarity between it and all other storage spaces includes:

[0099] For any storage space, read the similarity between it and all other storage spaces;

[0100] Calculating the mean of the read similarities, and determining the image acquisition frequency according to the mean;

[0101] In an example of the technical solution of the present invention, the process of determining the image acquisition frequency is specifically described. For any storage space, the similarity between it and all other storage spaces is read, the average of the read similarities is calculated, and the image acquisition frequency is determined according to the average; wherein the relationship between the image acquisition frequency and the average is:

[0102] Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

[0103] The physical meaning of the above relationship is that the closer the similarity mean is to the preset threshold, the smaller the corresponding image acquisition frequency will be. The farther it is from the preset threshold, the more it means that the similarity mean is too small or too large. If it is too small, it means that the storage space is relatively special, and if it is too large, it means that the storage space is more universal. Both require higher frequencies.

[0104] Regarding step S100: the step of obtaining the amount of goods regularly according to the sensor installed in the storage space includes:

[0105] Read the image of storage space regularly;

[0106] Performing contour recognition on the image, locating the cargo, and simultaneously calculating the cargo volume;

[0107] The accuracy of determining cargo quantity based on cargo volume;

[0108] When the accuracy is less than a preset accuracy threshold, an inspection request directed to the storage space is generated.

[0109] In an example of the technical solution of the present invention, step S100 is supplemented with an explanation that the function of the sensor is to obtain the quantity of goods. On the basis of having an image acquisition device, the image acquisition device can also be used as a way to obtain the quantity of goods. The image of the storage space is read at regular intervals, the contour of the image is recognized, the goods are located, and the volume of the goods is calculated synchronously. The quantity of goods can be determined based on the volume of the goods, but it is not very accurate. In the technical solution of the present invention, it is not necessary to calculate the precise quantity of goods through the volume of the goods. Instead, the accuracy of the calculation process of the quantity of goods is judged based on the volume of the goods, thereby introducing a self-correction function. This self-correction actually detects two aspects, one is the sensor, and the other is the camera. As long as their results do not match, there may be problems between the sensor and the camera.

[0110] Figure 2The structure diagram of the intelligent warehouse information collection system is shown in FIG. 1 . The technical solution of the present invention further provides an intelligent warehouse information collection system, wherein the system 10 includes:

[0111] The cargo quantity acquisition module 11 is used to obtain the cargo quantity according to the sensors installed in the storage space at regular intervals; the obtained cargo quantity contains time information; the working frequencies of the sensors in the storage space are the same;

[0112] The correlation judgment module 12 is used to arrange the cargo quantity according to the time information, obtain the cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly;

[0113] The similarity calculation module 13 is used to compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces;

[0114] The image acquisition module 14 is used to determine the image acquisition frequency for any storage space according to the similarity between it and all other storage spaces.

[0115] Furthermore, the relevance determination module 12 includes:

[0116] A cargo quantity arrangement unit, used for arranging the cargo quantity according to the time information to obtain a cargo quantity array;

[0117] A data interception unit is used to obtain a preset number of cargo quantities in reverse order starting from the end of the cargo quantity array as an array to be analyzed;

[0118] A sequence creation unit, used to create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values;

[0119] A calculation execution unit, for calculating an autocorrelation coefficient of the cargo quantity array once for each serial number difference in the serial number difference series;

[0120] A maximum value selection unit is used to select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient;

[0121] The time difference calculation unit is used to read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

[0122] Specifically, the similarity calculation module 13 includes:

[0123] A distance range receiving unit is used to receive the distance range entered by the staff;

[0124] The pairing unit is used to query the storage spaces within the distance range of any storage space with it as the center, and pair them with the storage space at the center;

[0125] A parameter reading unit, used for reading the autocorrelation coefficient and the lag time difference of the two storage spaces for each pair of storage spaces;

[0126] A parameter comparison unit is used to compare the correlation coefficient and its lag time difference and calculate the similarity;

[0127] Among them, the similarity between any two storage spaces is calculated only once.

[0128] Furthermore, the image acquisition module 14 includes:

[0129] A similarity reading unit is used to read the similarity between any storage space and all other storage spaces;

[0130] A frequency determination unit, used to calculate the mean of the read similarities, and determine the image acquisition frequency according to the mean;

[0131] Among them, the relationship between image acquisition frequency and mean is:

[0132] Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

[0133] The functions that can be achieved by the above-mentioned intelligent warehouse information collection method are all completed by computer equipment, and the computer equipment includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to realize the functions of the intelligent warehouse information collection method.

[0134] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.

[0135] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0136] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0137] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0138] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.); the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0139] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0140] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0141] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent warehouse information collection method, characterized in that: The method comprises: The amount of goods is obtained regularly according to sensors installed in the storage space; the obtained amount of goods contains time information; the working frequencies of the sensors in the storage space are the same; Arrange the cargo quantity according to the time information to obtain a cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly; Compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces; For any storage space, the image acquisition frequency is determined based on the similarity between it and all other storage spaces.

2. The intelligent warehouse information collection method according to claim 1 is characterized in that: The steps of arranging the cargo quantity according to the time information to obtain a cargo quantity array and synchronously calculating the autocorrelation coefficient and the lag time difference of the cargo quantity data include: Arrange the cargo quantity according to the time information to obtain a cargo quantity array; Starting from the end of the cargo quantity array, obtain a preset number of cargo quantities in reverse order as the array to be analyzed; Create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values; For each serial number difference in the serial number difference series, the autocorrelation coefficient is calculated once for the cargo quantity array; Select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient; Read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

3. The intelligent warehouse information collection method according to claim 2 is characterized in that: The process of calculating the autocorrelation coefficient includes: Where ρ(l) represents the autocorrelation coefficient with a sequence number difference of k, Cov(k) represents the autocovariance with a sequence number difference of k, and Var(k) represents the variance of the array to be analyzed with a sequence number difference of k; x t represents the kth element in the array to be analyzed, μ is the mean of each element in the array to be analyzed; x t+k represents the t+kth element in the array to be analyzed; N represents the total number of elements in the array to be analyzed.

4. The intelligent warehouse information collection method according to claim 1 is characterized in that: The step of comparing the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces includes: The distance range for receiving staff to enter; For any storage space, take it as the center, query the storage spaces within the distance range in turn, and pair them with the storage space at the center; For each pair of storage spaces, read the autocorrelation coefficients and their lag time difference between the two storage spaces; Compare the correlation coefficient and its lag time difference to calculate the similarity; Among them, the similarity between any two storage spaces is calculated only once.

5. The intelligent storage information collection method according to claim 3 is characterized in that: The step of determining the image acquisition frequency for any storage space according to the similarity between it and all other storage spaces comprises: For any storage space, read the similarity between it and all other storage spaces; Calculating the mean of the read similarities, and determining the image acquisition frequency according to the mean; Among them, the relationship between image acquisition frequency and mean is: Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

6. The intelligent warehouse information collection method according to claim 1 is characterized in that: The step of obtaining the amount of goods at regular intervals according to the sensor installed in the storage space comprises: Read the image of storage space regularly; Performing contour recognition on the image, locating the cargo, and simultaneously calculating the cargo volume; The accuracy of determining cargo quantity based on cargo volume; When the accuracy is less than a preset accuracy threshold, an inspection request directed to the storage space is generated.

7. An intelligent warehouse information collection system, characterized in that: The system comprises: A cargo quantity acquisition module is used to obtain the cargo quantity according to the sensors installed in the storage space at regular intervals; the obtained cargo quantity contains time information; the working frequencies of the sensors in the storage space are the same; A correlation judgment module is used to arrange the cargo quantity according to the time information, obtain the cargo quantity array, and synchronously calculate the autocorrelation coefficient of the cargo quantity data and its lag time difference; the lag time difference is related to the sequence number difference of the elements in the array and the period when the cargo quantity is obtained regularly; The similarity calculation module is used to compare the autocorrelation coefficients and lag time differences of each storage space to obtain the similarity between any two storage spaces; The image acquisition module is used to determine the image acquisition frequency for any storage space based on the similarity between it and all other storage spaces.

8. The intelligent warehouse information collection system according to claim 7 is characterized in that: The correlation determination module comprises: A cargo quantity arrangement unit, used for arranging the cargo quantity according to the time information to obtain a cargo quantity array; A data interception unit is used to obtain a preset number of cargo quantities in reverse order starting from the end of the cargo quantity array as an array to be analyzed; A sequence creation unit, used to create a sequence of sequence differences; the first term, step length and last term of the sequence of sequence differences are all preset values; A calculation execution unit, for calculating an autocorrelation coefficient of the cargo quantity array once for each serial number difference in the serial number difference series; A maximum value selection unit is used to select the maximum value of all calculated autocorrelation coefficients as the final autocorrelation coefficient; The time difference calculation unit is used to read the serial number difference corresponding to the final autocorrelation coefficient, read the period when the cargo quantity is obtained regularly, and multiply the serial number difference by the period to obtain the lag time difference.

9. The intelligent warehouse information collection system according to claim 8 is characterized in that: The similarity calculation module comprises: A distance range receiving unit is used to receive the distance range entered by the staff; The pairing unit is used to query the storage spaces within the distance range of any storage space with it as the center, and pair them with the storage space at the center; A parameter reading unit, used for reading the autocorrelation coefficient and the lag time difference of the two storage spaces for each pair of storage spaces; A parameter comparison unit is used to compare the correlation coefficient and its lag time difference and calculate the similarity; Among them, the similarity between any two storage spaces is calculated only once.

10. The intelligent warehouse information collection system according to claim 8, characterized in that: The image acquisition module comprises: A similarity reading unit is used to read the similarity between any storage space and all other storage spaces; A frequency determination unit, used to calculate the mean of the read similarities, and determine the image acquisition frequency according to the mean; Among them, the relationship between image acquisition frequency and mean is: Where f represents the final image acquisition frequency, f0 represents the preset reference frequency, E represents the mean similarity corresponding to a certain storage space, E0 is the preset mean threshold; α and c are both preset parameters.

Images