Adaptive supervision and control method for logistics warehousing scheduling

Abstract

The present invention discloses an adaptive supervision and control method for logistics warehousing scheduling, which relates to the field of data processing technology. The method includes: obtaining information of multiple logistics storage points of a target logistics warehousing station at the current moment; obtaining a set of scheduling requirements of multiple logistics storage points; obtaining multiple first scheduling factors; performing scheduling retrieval difficulty analysis to obtain multiple second scheduling factors; configuring multiple scheduling supervision and control submodules of a warehousing scheduling supervision and control platform; obtaining multiple operating rate factors; updating multiple scheduling supervision and control submodules based on multiple operating rate factors, and performing adaptive supervision and control of a target logistics warehousing station according to the updated multiple scheduling supervision submodules. The present invention solves the technical problems of poor stability of logistics warehousing scheduling supervision and control and low matching degree with logistics warehousing conditions in the prior art, and achieves the technical effect of improving the reliability of warehousing scheduling supervision and control.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to an adaptive supervision and control method for logistics warehousing scheduling. Background Art

[0002] As the volume of logistics and warehousing increases, the reliability of logistics and warehousing scheduling gradually decreases, and it is impossible to respond quickly to warehousing scheduling, and there is often a delay in processing, resulting in a backlog of goods. The existing technology has the technical problems of poor stability in logistics and warehousing scheduling supervision and control, and low matching degree with logistics and warehousing conditions. Summary of the invention

[0003] The present application provides an adaptive supervision and control method for logistics warehousing scheduling, which is used to solve the technical problems in the prior art of poor stability of logistics warehousing scheduling supervision and control and low matching degree with logistics warehousing conditions.

[0004] In view of the above problems, the present application provides an adaptive supervision and control method for logistics warehousing scheduling.

[0005] In a first aspect of the present application, an adaptive supervision and control method for logistics warehousing scheduling is provided, wherein the method is applied to a warehousing scheduling supervision and control platform, and the method comprises:

[0006] Acquire information of multiple logistics storage points of the target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity one by one;

[0007] Collecting the scheduling requirements of the target logistics storage station within a preset historical window to obtain a plurality of logistics storage point scheduling requirement sets, wherein the plurality of logistics storage point scheduling requirement sets correspond to the plurality of logistics storage points;

[0008] Perform scheduling volume analysis according to the scheduling demand sets of the multiple logistics storage points to obtain multiple first scheduling factors;

[0009] Performing a scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple stored item types and the multiple stored item quantities to obtain multiple second scheduling factors;

[0010] Configuring multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform based on the multiple first scheduling factors and the multiple second scheduling factors;

[0011] Obtaining the operation data of multiple dispatching supervision control submodules within a preset supervision window, and obtaining multiple operation rate factors;

[0012] The multiple scheduling supervision control submodules are updated based on the multiple operating rate factors, and adaptive supervision control of the target logistics storage station is performed according to the updated multiple scheduling supervision submodules.

[0013] The second aspect of the present application provides an adaptive supervision control system for logistics warehousing scheduling, the system comprising:

[0014] A storage point information obtaining unit, used to obtain information of multiple logistics storage points of a target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to a storage item quantity in a one-to-one manner;

[0015] A scheduling demand set obtaining unit is used to collect the scheduling demand of the target logistics storage station within a preset historical window, and obtain a plurality of logistics storage point scheduling demand sets, wherein the plurality of logistics storage point scheduling demand sets correspond to a plurality of logistics storage points;

[0016] A first scheduling factor obtaining unit, configured to perform scheduling volume analysis according to the plurality of logistics storage point scheduling demand sets to obtain a plurality of first scheduling factors;

[0017] A second scheduling factor obtaining unit, configured to perform scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple storage item types and the multiple storage item quantities, to obtain multiple second scheduling factors;

[0018] A control submodule configuration unit, configured to configure a plurality of scheduling supervision control submodules of the warehouse scheduling supervision control platform based on the plurality of first scheduling factors and the plurality of second scheduling factors;

[0019] An operation rate factor obtaining unit is used to obtain operation data of multiple scheduling supervision control submodules within a preset supervision window to obtain multiple operation rate factors;

[0020] The supervision control unit is used to update the multiple scheduling supervision control submodules based on the multiple operating rate factors, and perform adaptive supervision control of the target logistics storage station according to the updated multiple scheduling supervision submodules.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] The present application obtains information of multiple logistics storage points of the target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity one by one, and then collects the scheduling requirements of the target logistics storage station in the preset historical window, obtains multiple logistics storage point scheduling requirement sets, and multiple logistics storage point scheduling requirement sets correspond to multiple logistics storage points, and then performs scheduling volume analysis according to the multiple logistics storage point scheduling requirement sets, obtains multiple first scheduling factors, and then performs scheduling retrieval difficulty analysis on multiple logistics storage points based on multiple storage item types and multiple storage item quantities, obtains multiple second scheduling factors, configures multiple scheduling supervision control submodules of the storage scheduling supervision control platform based on multiple first scheduling factors and multiple second scheduling factors, obtains multiple operation rate factors according to the operation data of multiple scheduling supervision control submodules in the preset supervision window, and then updates multiple scheduling supervision control submodules based on multiple operation rate factors, and performs adaptive supervision control of the target logistics storage station according to the updated multiple scheduling supervision submodules. The technical effect of improving the reliability of adaptive supervision control and improving control stability is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of an adaptive supervision and control method for logistics warehousing scheduling provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a process for obtaining multiple first scheduling factors in the adaptive supervision and control method for logistics warehousing scheduling provided in an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the structure of an adaptive supervision and control system for logistics warehousing scheduling provided in an embodiment of the present application.

[0027] Explanation of the reference numerals: storage point information obtaining unit 11, scheduling requirement set obtaining unit 12, first scheduling factor obtaining unit 13, second scheduling factor obtaining unit 14, control submodule configuration unit 15, operation rate factor obtaining unit 16, supervision control unit 17. DETAILED DESCRIPTION

[0028] The present application provides an adaptive supervision and control method for logistics warehousing scheduling, which is used to solve the technical problems in the prior art of poor stability of logistics warehousing scheduling supervision and control and low matching degree with logistics warehousing conditions.

[0029] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 this application.

[0030] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] like Figure 1 As shown, the present application provides an adaptive supervision and control method for logistics warehousing scheduling, wherein the method is applied to a warehousing scheduling supervision and control platform, and the method includes:

[0033] Acquire information of multiple logistics storage points of the target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity one by one;

[0034] In one possible embodiment, the storage status of items in multiple logistics storage points in the target logistics storage station at the current moment is collected to obtain the information of the multiple logistics storage points. The target logistics storage station is any logistics station that needs to be controlled by storage scheduling supervision. The information of each logistics storage point includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity. The storage item types include commodity categories, industrial categories, cold chain categories, etc. The storage item quantity is the storage quantity of each storage item and the amount of space occupied. By obtaining the information of the multiple logistics storage points, the technical effect of providing reliable data support for the subsequent supervision that fits the actual situation of the target logistics storage station is achieved.

[0035] Collecting the scheduling requirements of the target logistics storage station within a preset historical window to obtain a plurality of logistics storage point scheduling requirement sets, wherein the plurality of logistics storage point scheduling requirement sets correspond to the plurality of logistics storage points;

[0036] In a possible embodiment, the preset historical window is a historical time period set by technicians in this field for analyzing the scheduling needs of storage stations, which may be half a month, a month, etc. The scheduling needs received by the target logistics storage station within the preset historical window are acquired, and the acquired scheduling need data are clustered according to multiple logistics storage points, and the scheduling needs belonging to the same logistics storage point are added to a demand set to obtain multiple logistics storage point scheduling need sets. Among them, the multiple logistics storage point scheduling need sets correspond to multiple logistics storage points. By acquiring the multiple logistics storage point scheduling need sets, the groundwork is laid for the subsequent individual scheduling supervision of each logistics storage point.

[0037] Perform scheduling volume analysis according to the scheduling demand sets of the multiple logistics storage points to obtain multiple first scheduling factors;

[0038] Further, such as Figure 2 As shown, a scheduling density analysis is performed according to the scheduling demand sets of the multiple logistics storage points to obtain multiple first scheduling volume factors. The embodiment of the present application also includes:

[0039] Taking the scheduling frequency as an index, extracting data from the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of scheduling frequencies;

[0040] Taking the scheduling space volume as an index, extracting data from the scheduling demand sets of the multiple logistics storage points to obtain multiple scheduling space volumes;

[0041] Taking the scheduling subdivision granularity as an index, extracting data from the scheduling demand set of the plurality of logistics storage points to obtain a plurality of scheduling subdivision granularities;

[0042] A scheduling volume analysis is performed based on multiple scheduling frequencies, multiple scheduling space volumes, and multiple scheduling subdivision granularities to obtain multiple first scheduling factors.

[0043] In an embodiment of the present application, the amount of resources required to respond to storage scheduling for each logistics storage point is analyzed based on the scheduling demand sets of the multiple logistics storage points, that is, the scheduling volume analysis is performed to obtain the multiple first scheduling factors. Among them, the multiple first scheduling factors describe the degree of resource consumption of each logistics storage point scheduling from the perspective of the scheduling demand response volume. According to the multiple first scheduling factors, data support is provided for the subsequent accurate and reasonable analysis of the resources that can be allocated by the multiple scheduling supervision control submodules corresponding to each logistics storage point.

[0044] In a possible embodiment, the scheduling frequency is the number of scheduling requirements for logistics storage points per unit time. The scheduling space volume is the number of bytes of demand data that need to be scheduled at the logistics storage point. The scheduling subdivision granularity is the ratio of the types of items scheduled in the demand of the logistics storage point to all the types of items stored in the target logistics storage station, reflecting the degree of subdivision of the items that need to be scheduled. The higher the scheduling subdivision granularity, the more resources need to be consumed. Then, data is extracted from the scheduling demand sets of the multiple logistics storage points based on the scheduling frequency, scheduling space volume and scheduling subdivision granularity, so as to obtain the multiple scheduling frequencies, multiple scheduling space volumes and multiple scheduling subdivision granularities. A comprehensive analysis is performed on the multiple scheduling frequencies, multiple scheduling space volumes and multiple scheduling subdivision granularities to obtain the multiple first scheduling factors. The technical effect of analyzing the scheduling volume from multiple dimensions and improving the reliability of the analysis is achieved.

[0045] Furthermore, the embodiment of the present application also includes:

[0046] Acquire multiple sample scheduling frequencies, multiple sample scheduling space volumes, multiple sample scheduling subdivision granularities, and multiple sample first scheduling factors as construction data;

[0047] Constructing a three-dimensional initial scheduling volume analysis space, wherein the x-axis of the scheduling volume analysis space is the scheduling frequency, the y-axis is the scheduling space volume, and the z-axis is the scheduling subdivision granularity;

[0048] The construction data is input into the initial scheduling volume analysis space to obtain a target scheduling volume analysis space, wherein the target scheduling volume analysis space includes a plurality of sample points, and each sample point has a corresponding sample first scheduling factor.

[0049] Furthermore, the embodiment of the present application also includes:

[0050] The target scheduling volume analysis space is limited by a plurality of scheduling frequencies, a plurality of scheduling space volumes, and a plurality of scheduling subdivision granularities, respectively, to obtain a plurality of limited scheduling volume analysis spaces, wherein the plurality of limited scheduling volume analysis spaces have a plurality of limited sample points;

[0051] By calculating the mean of the coordinates of multiple defined sample points, multiple defined center points are obtained;

[0052] A plurality of defined search steps are matched according to the spatial densities of the plurality of defined scheduling volume analysis spaces, wherein the plurality of defined search steps are distances of a single movement when searching in the plurality of defined scheduling volume spaces.

[0053] Further, after matching multiple limited search steps according to the spatial density of the multiple limited scheduling volume analysis spaces, the embodiment of the present application further includes:

[0054] Searching in the multiple defined scheduling volume spaces based on the multiple defined center points and the multiple defined search step sizes to obtain multiple defined search points;

[0055] Determine whether the point set density of the plurality of defined central points is greater than the point set density of the plurality of defined search points, and if so, accept updating the plurality of defined central points to a plurality of defined search points according to a certain probability;

[0056] Continue searching according to the multiple limited search points and the multiple limited search step sizes until a preset number of searches is reached, and use the multiple limited search points corresponding to the maximum values ​​of the multiple point set densities during the search as the multiple target search points;

[0057] The multiple sample first scheduling factors corresponding to the multiple target search points are used as multiple first scheduling volume factors.

[0058] In a possible embodiment, by using the target logistics storage station as an index to perform data retrieval, multiple sample scheduling frequencies, multiple sample scheduling space volumes, multiple sample scheduling subdivision granularities, and multiple sample first scheduling factors are obtained as construction data. The initial scheduling volume analysis space is constructed with the scheduling frequency as the x-axis, the scheduling space volume as the y-axis, and the scheduling subdivision granularity as the z-axis. The construction data is input into the initial scheduling volume analysis space to obtain the target scheduling volume analysis space, wherein the target scheduling volume analysis space includes multiple sample points, and each sample point has a corresponding sample first scheduling factor.

[0059] In a possible embodiment, the target scheduling volume analysis space is defined by multiple scheduling frequencies, multiple scheduling space volumes, and multiple scheduling subdivision granularities, that is, the target scheduling volume analysis space is defined by a space formed by the interaction of three planes that are perpendicular to the x-axis, y-axis, and z-axis, respectively, through multiple scheduling frequencies, multiple scheduling space volumes, and multiple scheduling subdivision granularities, to obtain multiple defined scheduling volume analysis spaces, wherein multiple defined scheduling volume analysis spaces have multiple defined sample points. The goal of defining the target scheduling volume analysis space from three dimensions is achieved. Then, the coordinates of multiple defined sample points are averaged to obtain multiple defined center points. The multiple defined center points reflect the average scheduling volume of multiple defined scheduling volume analysis spaces. Then, multiple defined search steps are matched according to the spatial density of the multiple defined scheduling volume analysis spaces, wherein the multiple defined search steps are the distances of a single move when searching in the multiple defined scheduling volume analysis spaces. The spatial density is the ratio of the number of sample points in the multiple defined scheduling volume analysis spaces to the volume of the multiple defined scheduling volume analysis spaces. The spatial densities of multiple limited scheduling volume analysis spaces are compared with the sum of the spatial densities of multiple limited scheduling volume analysis spaces, and the ratio is multiplied by the preset limited search step length to obtain multiple limited search step lengths. The goal of providing a single moving distance for efficient and accurate search is achieved.

[0060] Then, based on the multiple defined center points and the multiple defined search steps, a search is performed in the multiple defined scheduling volume spaces to obtain multiple defined search points. It is determined whether the point set density of the multiple defined center points is greater than the point set density of the multiple defined search points. If so, the multiple defined center points are updated to multiple defined search points according to a certain probability. The point set density of the defined center point is the ratio of the number of multiple sample points whose distance to the defined center point is the defined search step to the area surrounded by the outermost sample points of the multiple sample points whose distance to the defined center point is the defined search step. Based on the same calculation principle, the point set density of the multiple defined search points is obtained. According to the multiple defined search points and the multiple defined search steps, the search is continued until the preset search times are reached, and the multiple defined search points corresponding to the maximum value of the multiple point set density in the search process are used as multiple target search points. Among them, the multiple target search points are the sample points with the densest surrounding distribution in the multiple defined scheduling volume analysis spaces, which are most consistent with the scheduling volume conditions of the corresponding multiple item storage points. Then, the multiple sample first scheduling factors corresponding to the multiple target search points are used as multiple first scheduling volume factors.

[0061] Performing a scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple stored item types and the multiple stored item quantities to obtain multiple second scheduling factors;

[0062] In one embodiment, multiple sample storage item types, multiple sample storage item quantities, and multiple sample second scheduling factors are obtained, and a mapping relationship between the multiple sample storage item types, multiple sample storage item quantities, and multiple sample second scheduling factors is constructed, thereby obtaining a second scheduling factor mapping relationship. According to the multiple storage item types and multiple storage item quantities, matching mapping is performed in the second scheduling factor mapping relationship to obtain multiple second scheduling factors. The second scheduling factor reflects the difficulty of retrieval when multiple logistics storage points are scheduled for warehousing.

[0063] Configuring multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform based on the multiple first scheduling factors and the multiple second scheduling factors;

[0064] Further, based on the multiple first scheduling factors and the multiple second scheduling factors, multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform are configured, and the embodiment of the present application also includes:

[0065] Obtain the number of servers of the warehouse scheduling supervision control platform and generate computing resources to be allocated;

[0066] Performing weighted calculation on the multiple first scheduling factors and the multiple second scheduling factors to obtain multiple scheduling factors;

[0067] The multiple scheduling supervision control sub-modules are configured based on multiple scheduling factors and the computing power resources to be allocated.

[0068] In a possible embodiment, a comprehensive analysis is performed based on the multiple first scheduling factors and the multiple second scheduling factors to configure the computing resources that can be allocated by the multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform, thereby achieving the goal of independent and efficient scheduling supervision for each logistics storage point.

[0069] In one embodiment, the number of servers of the warehouse scheduling supervision control platform is obtained to generate computing power resources to be allocated. The computing power resources to be allocated include CPU resources, memory capacity, storage capacity, network bandwidth, etc. The multiple first scheduling factors and the multiple second scheduling factors are weightedly calculated according to the weight ratio set by technicians in this field to obtain multiple scheduling factors. The multiple scheduling factors reflect the degree of resources that multiple scheduling supervision control sub-modules need to occupy. The ratio of multiple scheduling factors to the sum of multiple scheduling factors is calculated respectively, and the calculation result is multiplied by the computing power resources to be allocated, and the multiple scheduling supervision control sub-modules are configured according to the product.

[0070] Obtaining the operation data of multiple dispatching supervision control submodules within a preset supervision window, and obtaining multiple operation rate factors;

[0071] The multiple scheduling supervision control submodules are updated based on the multiple operating rate factors, and adaptive supervision control of the target logistics storage station is performed according to the updated multiple scheduling supervision submodules.

[0072] Furthermore, the embodiment of the present application also includes:

[0073] Enumerate the distances between the multiple logistics storage sites in pairs to obtain multiple site distance sets, each site distance set corresponding to a logistics storage site;

[0074] generating a target update scheme according to the plurality of operating rate factors and the plurality of site distance sets;

[0075] The target update scheme is used to update the multiple scheduling supervision control submodules.

[0076] In one possible embodiment, the operation data of multiple scheduling supervision control submodules within a preset supervision window are obtained, and the delay duration in the operation data is used as multiple operation rate factors. The preset supervision window is a time period set by technicians in this field to analyze the degree of operation delay of the submodules. Among them, the multiple operation rate factors reflect the degree of operation delay of multiple scheduling supervision control submodules. Based on the multiple operation rate factors, the multiple scheduling supervision control submodules are updated, resources are reallocated, and adaptive supervision control of the target logistics storage station is performed according to the updated multiple scheduling supervision submodules.

[0077] In one possible embodiment, the distances between the multiple logistics storage sites are enumerated in pairs to obtain multiple site distance sets, each of which corresponds to a logistics storage site. The multiple operating rate factors and multiple site distance sets are input into the update scheme identification network to obtain a target update scheme. By obtaining multiple sample operating rate factors, multiple sample site distance sets, and multiple sample target update schemes as training data, supervised training is performed on the convolutional neural network until the output reaches convergence, and the trained update scheme identification network is obtained. The multiple scheduling supervision and control submodules are updated using the target update scheme. The goal of re-allocating computing power for multiple scheduling supervision and control submodules is achieved, and the technical effect of improving the degree of fit between supervision and control and the actual storage conditions of items in the target logistics storage station is achieved.

[0078] In summary, the embodiments of the present application have at least the following technical effects:

[0079] This application obtains information on multiple logistics storage points of the target logistics storage station at the current moment, collects the scheduling requirements of multiple logistics storage points in the historical time, and then performs scheduling volume analysis on each logistics storage point according to the scheduling requirements set of multiple logistics storage points to obtain multiple first scheduling factors, and performs scheduling retrieval difficulty analysis on multiple logistics storage points based on multiple storage item types and multiple storage item quantities to obtain multiple second scheduling factors, thereby achieving the goal of analyzing the resource situation that each logistics storage point needs to consume from two dimensions, and then configures multiple scheduling supervision control submodules of the storage scheduling supervision control platform according to the analysis results, and obtains multiple operating rate factors according to the operating conditions, and updates multiple scheduling supervision control submodules, and performs adaptive supervision control of the target logistics storage station according to the updated multiple scheduling supervision submodules. The technical effect of improving the reliability of adaptive supervision control and the accuracy of storage scheduling supervision control is achieved.

[0080] Embodiment 2

[0081] Based on the same inventive concept as the adaptive supervision and control method for logistics warehousing scheduling in the aforementioned embodiment, Figure 3 As shown, the present application provides an adaptive supervision control system for logistics warehousing scheduling, and the system and method embodiments in the present application embodiments are based on the same inventive concept. The system includes:

[0082] The storage point information obtaining unit 11 is used to obtain information of multiple logistics storage points of the target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity one by one;

[0083] The scheduling demand set obtaining unit 12 is used to collect the scheduling demand of the target logistics storage station within a preset historical window, and obtain a plurality of logistics storage point scheduling demand sets, wherein the plurality of logistics storage point scheduling demand sets correspond to a plurality of logistics storage points;

[0084] A first scheduling factor obtaining unit 13 is used to perform scheduling volume analysis according to the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of first scheduling factors;

[0085] A second scheduling factor obtaining unit 14 is used to perform scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple storage item types and the multiple storage item quantities to obtain multiple second scheduling factors;

[0086] A control submodule configuration unit 15, configured to configure a plurality of scheduling supervision control submodules of the storage scheduling supervision control platform based on the plurality of first scheduling factors and the plurality of second scheduling factors;

[0087] The operation rate factor obtaining unit 16 is used to obtain the operation data of multiple scheduling supervision control submodules within a preset supervision window to obtain multiple operation rate factors;

[0088] The supervision control unit 17 is used to update the multiple scheduling supervision control submodules based on the multiple operating rate factors, and perform adaptive supervision control of the target logistics storage station according to the updated multiple scheduling supervision submodules.

[0089] Furthermore, the system also includes:

[0090] Taking the scheduling frequency as an index, extracting data from the scheduling demand set of the plurality of logistics storage points to obtain a plurality of scheduling frequencies;

[0091] Taking the scheduling space volume as an index, extracting data from the scheduling demand sets of the multiple logistics storage points to obtain multiple scheduling space volumes;

[0092] Taking the scheduling subdivision granularity as an index, extracting data from the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of scheduling subdivision granularities;

[0093] A scheduling volume analysis is performed based on multiple scheduling frequencies, multiple scheduling space volumes, and multiple scheduling subdivision granularities to obtain multiple first scheduling factors.

[0094] Furthermore, the system also includes:

[0095] Acquire multiple sample scheduling frequencies, multiple sample scheduling space volumes, multiple sample scheduling subdivision granularities, and multiple sample first scheduling factors as construction data;

[0096] Constructing a three-dimensional initial scheduling volume analysis space, wherein the x-axis of the scheduling volume analysis space is the scheduling frequency, the y-axis is the scheduling space volume, and the z-axis is the scheduling subdivision granularity;

[0097] The construction data is input into the initial scheduling volume analysis space to obtain a target scheduling volume analysis space, wherein the target scheduling volume analysis space includes a plurality of sample points, and each sample point has a corresponding sample first scheduling factor.

[0098] Furthermore, the system also includes:

[0099] The target scheduling volume analysis space is limited by a plurality of scheduling frequencies, a plurality of scheduling space volumes, and a plurality of scheduling subdivision granularities, respectively, to obtain a plurality of limited scheduling volume analysis spaces, wherein the plurality of limited scheduling volume analysis spaces have a plurality of limited sample points;

[0100] By calculating the mean of the coordinates of multiple defined sample points, multiple defined center points are obtained;

[0101] A plurality of defined search steps are matched according to the spatial densities of the plurality of defined scheduling volume analysis spaces, wherein the plurality of defined search steps are distances of a single movement when searching in the plurality of defined scheduling volume spaces.

[0102] Furthermore, the system also includes:

[0103] Searching in the multiple defined scheduling volume spaces based on the multiple defined center points and the multiple defined search step sizes to obtain multiple defined search points;

[0104] Determine whether the point set density of the plurality of defined central points is greater than the point set density of the plurality of defined search points, and if so, accept updating the plurality of defined central points to a plurality of defined search points according to a certain probability;

[0105] Continue searching according to the multiple limited search points and the multiple limited search step sizes until a preset number of searches is reached, and use the multiple limited search points corresponding to the maximum values ​​of the multiple point set densities during the search as the multiple target search points;

[0106] The multiple sample first scheduling factors corresponding to the multiple target search points are used as multiple first scheduling volume factors.

[0107] Furthermore, the system also includes:

[0108] Obtain the number of servers of the warehouse scheduling supervision control platform and generate computing resources to be allocated;

[0109] Performing weighted calculation on the multiple first scheduling factors and the multiple second scheduling factors to obtain multiple scheduling factors;

[0110] The multiple scheduling supervision control sub-modules are configured based on multiple scheduling factors and the computing power resources to be allocated.

[0111] Furthermore, the system also includes:

[0112] Enumerate the distances between the multiple logistics storage sites in pairs to obtain multiple site distance sets, each site distance set corresponding to a logistics storage site;

[0113] generating a target update scheme according to the plurality of operating rate factors and the plurality of site distance sets;

[0114] The target update scheme is used to update the multiple scheduling supervision control submodules.

[0115] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0117] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An adaptive supervision and control method for logistics warehousing scheduling, characterized in that: The method is applied to a warehouse scheduling supervision control platform, and the method comprises: Acquire information of multiple logistics storage points of the target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to the storage item quantity one by one; Collecting the scheduling requirements of the target logistics storage station within a preset historical window to obtain a plurality of logistics storage point scheduling requirement sets, wherein the plurality of logistics storage point scheduling requirement sets correspond to the plurality of logistics storage points; Perform scheduling volume analysis according to the scheduling demand sets of the multiple logistics storage points to obtain multiple first scheduling factors; Performing a scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple stored item types and the multiple stored item quantities to obtain multiple second scheduling factors; Based on the multiple first scheduling factors and the multiple second scheduling factors, configure the computing resources of multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform; Obtaining the operation data of multiple dispatching supervision control submodules within a preset supervision window, and obtaining multiple operation rate factors; The multiple scheduling supervision control submodules are updated based on the multiple operating rate factors, and adaptive supervision control of the target logistics storage station is performed according to the updated multiple scheduling supervision submodules.

2. The method according to claim 1, characterized in that Performing a scheduling density analysis according to the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of first scheduling volume factors, the method further comprising: Taking the scheduling frequency as an index, extracting data from the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of scheduling frequencies; Taking the scheduling space volume as an index, extracting data from the scheduling demand sets of the multiple logistics storage points to obtain multiple scheduling space volumes; Taking the scheduling subdivision granularity as an index, extracting data from the scheduling demand sets of the plurality of logistics storage points to obtain a plurality of scheduling subdivision granularities; A scheduling volume analysis is performed based on multiple scheduling frequencies, multiple scheduling space volumes, and multiple scheduling subdivision granularities to obtain multiple first scheduling factors.

3. The method according to claim 2, characterized in that The method further comprises: Acquire multiple sample scheduling frequencies, multiple sample scheduling space volumes, multiple sample scheduling subdivision granularities, and multiple sample first scheduling factors as construction data; Constructing a three-dimensional initial scheduling volume analysis space, wherein the x-axis of the scheduling volume analysis space is the scheduling frequency, the y-axis is the scheduling space volume, and the z-axis is the scheduling subdivision granularity; The construction data is input into the initial scheduling volume analysis space to obtain a target scheduling volume analysis space, wherein the target scheduling volume analysis space includes a plurality of sample points, and each sample point has a corresponding sample first scheduling factor.

4. The method according to claim 3, characterized in that The method further comprises: The target scheduling volume analysis space is limited by a plurality of scheduling frequencies, a plurality of scheduling space volumes, and a plurality of scheduling subdivision granularities, respectively, to obtain a plurality of limited scheduling volume analysis spaces, wherein the plurality of limited scheduling volume analysis spaces have a plurality of limited sample points; By calculating the mean of the coordinates of multiple defined sample points, multiple defined center points are obtained; A plurality of defined search steps are matched according to the spatial densities of the plurality of defined scheduling volume analysis spaces, wherein the plurality of defined search steps are distances of a single movement when searching in the plurality of defined scheduling volume analysis spaces.

5. The method according to claim 4, characterized in that After matching a plurality of limited search steps according to the spatial densities of the plurality of limited scheduling volume analysis spaces, the method further includes: Searching in the multiple defined scheduling volume analysis spaces based on the multiple defined center points and the multiple defined search steps to obtain multiple defined search points; Determine whether the point set density of the plurality of defined central points is greater than the point set density of the plurality of defined search points, and if so, accept updating the plurality of defined central points to a plurality of defined search points according to a certain probability; Continue searching according to the multiple limited search points and the multiple limited search step sizes until a preset number of searches is reached, and use the multiple limited search points corresponding to the maximum values ​​of the multiple point set densities during the search as the multiple target search points; The multiple sample first scheduling factors corresponding to the multiple target search points are used as multiple first scheduling volume factors.

6. The method according to claim 1, characterized in that Based on the multiple first scheduling factors and the multiple second scheduling factors, multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform are configured, and the method further includes: Obtain the number of servers of the warehouse scheduling supervision control platform and generate computing resources to be allocated; Performing weighted calculation on the multiple first scheduling factors and the multiple second scheduling factors to obtain multiple scheduling factors; The multiple scheduling supervision control sub-modules are configured based on multiple scheduling factors and the computing power resources to be allocated.

7. The method according to claim 1, characterized in that The method further comprises: Enumerate the distances between the multiple logistics storage points in pairs to obtain multiple point distance sets, each point distance set corresponds to a logistics storage point; generating a target update scheme according to the plurality of operating rate factors and the plurality of point distance sets; The target update scheme is used to update the multiple scheduling supervision control submodules.

8. An adaptive supervision and control system for logistics warehousing scheduling, characterized in that: The system comprises: A storage point information obtaining unit, used to obtain information of multiple logistics storage points of a target logistics storage station at the current moment, wherein each logistics storage point information includes multiple storage item types and multiple storage item quantities, and each storage item type corresponds to a storage item quantity in a one-to-one manner; A scheduling demand set obtaining unit is used to collect the scheduling demand of the target logistics storage station within a preset historical window, and obtain a plurality of logistics storage point scheduling demand sets, wherein the plurality of logistics storage point scheduling demand sets correspond to a plurality of logistics storage points; A first scheduling factor obtaining unit, configured to perform scheduling volume analysis according to the plurality of logistics storage point scheduling demand sets to obtain a plurality of first scheduling factors; A second scheduling factor obtaining unit, configured to perform scheduling retrieval difficulty analysis on the multiple logistics storage points based on the multiple storage item types and the multiple storage item quantities, to obtain multiple second scheduling factors; A control submodule configuration unit, used to configure the computing resources of multiple scheduling supervision control submodules of the warehouse scheduling supervision control platform based on the multiple first scheduling factors and the multiple second scheduling factors; An operation rate factor obtaining unit is used to obtain operation data of multiple scheduling supervision control submodules within a preset supervision window to obtain multiple operation rate factors; The supervision control unit is used to update the multiple scheduling supervision control submodules based on the multiple operating rate factors, and perform adaptive supervision control of the target logistics storage station according to the updated multiple scheduling supervision submodules.

Images