Method and device for identifying material category, electronic equipment and storage medium

Abstract

The application discloses a kind of material category identification method, device, electronic equipment and storage medium, the method includes: determining the corresponding to be used characteristic value of to be identified material, and the corresponding to each to be matched characteristic value of to be matched material;Determine the Euclidean distance between the to be used characteristic value and each to be matched characteristic value, and determine the to be used weight between the to be identified material relative to the to be matched material based on the Euclidean distance;Determine the target matching material matched with the to be identified material based on each to be used weight, and the material category of the target matching material is used as the material category of the to be identified material.The technical scheme of the embodiment of the application solves the phenomenon of misjudgment, missing judgment and other phenomena when determining the material category by AI technology in the prior art, i.e. There is the problem of inaccurate material category identification, and the technical effect of efficiently identifying materials is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer processing, and in particular to a material category identification method and device, electronic equipment and storage medium. BACKGROUND

[0002] Due to the influence of demand, supply, early warning, etc., material rolling is becoming more and more important in inventory management. According to the actual scene, early detection of material rolling risks can reduce the shortage of materials and reduce the loss of manpower. However, it is difficult to identify material rolling by manual means. With the development of computer artificial intelligence, computer-aided computing systems are increasingly applied to warehouse materials, which can reduce the workload of personnel and improve the accuracy of material rolling identification. Therefore, it is particularly important to use deep learning and other technologies to automatically identify material rolling.

[0003] With the rapid development of artificial intelligence, more and more material rolling automatic detection algorithms have gradually entered the warehouse. However, automatic detection by AI may result in missed judgment and misjudgment. In particular, the same material may be repeatedly allocated, resulting in inaccurate results. Therefore, how to accurately identify whether the same material is repeatedly allocated and improve detection accuracy is a problem that needs to be solved. SUMMARY

[0004] The present application provides a material category identification method and device, electronic equipment and storage medium to achieve effective and accurate identification of materials.

[0005] According to an aspect of the present application, a material category identification method is provided, which comprises:

[0006] determining a to-be-used feature value corresponding to a to-be-identified material, and a to-be-matched feature value corresponding to each to-be-matched material;

[0007] determining the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determining the to-be-used weight between the to-be-identified material and the to-be-matched material based on the Euclidean distance;

[0008] determining a target matching material matching the to-be-identified material based on each to-be-used weight, and taking the material category of the target matching material as the material category of the to-be-identified material.

[0009] Further, determining the to-be-matched feature value corresponding to each to-be-matched material comprises:

[0010] determining a to-be-used influence factor corresponding to each to-be-matched material according to the to-be-processed historical scheduling data corresponding to each to-be-matched material in each historical period;

[0011] Determine the to-be-used influence factor of each to-be-matched material according to the to-be-used influence factor and the target function of each to-be-matched material.

[0012] Further, the to-be-used influence factor corresponding to each to-be-matched material is determined according to the to-be-processed historical scheduling data corresponding to each to-be-matched material in each historical period, including:

[0013] For each to-be-matched material in each historical period, determine the to-be-averaged influence factor corresponding to the current to-be-matched material according to the to-be-processed scheduling data of the current to-be-matched material in the current historical period, wherein the to-be-processed scheduling data includes the number of times of being transferred in, the number of times of being transferred out, the average allocation data, the maximum allocation inventory data, the average allocation time interval, and the maximum allocation time interval.

[0014] Determine the to-be-used influence factor according to the to-be-averaged influence factor of the current to-be-matched material in each historical period.

[0015] Further, the to-be-averaged influence factor corresponding to the current to-be-matched material is determined according to the to-be-processed scheduling data of the current to-be-matched material in the current historical period, including:

[0016] Determine the transfer-in influence factor and the transfer-out influence factor according to the number of times of scheduling, the number of times of being transferred out, the first weight, and the second weight.

[0017] Determine the allocation inventory influence factor according to the average allocation quantity, the maximum allocation inventory quantity, and the third weight.

[0018] Determine the allocation time influence factor according to the average allocation time interval, the maximum allocation time interval, and the fourth weight.

[0019] Determine the to-be-averaged influence factor based on the transfer-in influence factor, the transfer-out influence factor, the allocation inventory influence factor, and the allocation time influence factor.

[0020] Further, the Euclidean distance between the to-be-used feature value and each to-be-matched feature value is determined, and the to-be-used weight between the to-be-identified material and the to-be-matched material is determined based on the Euclidean distance, including:

[0021] For each to-be-matched feature value, determine the difference between the to-be-used feature value and the current to-be-matched feature value, and determine the Euclidean distance based on the difference.

[0022] Take the reciprocal of the Euclidean distance as the to-be-used weight of the to-be-identified material relative to the to-be-matched material.

[0023] Further, the target matching material matched with the to-be-identified material is determined based on each to-be-used weight, including:

[0024] The target matching resource corresponding to the to-be-used weight maximum is taken as the target matching resource.

[0025] Further, the method further comprises:

[0026] The resource category corresponding to the target matching resource is invoked, and the resource category is taken as the resource category of the to-be-identified resource, so as to schedule the to-be-identified resource based on the resource category, and update the resource information and the scheduling data corresponding to the to-be-identified resource.

[0027] According to another aspect of the present application, there is provided a resource category identification device, which comprises:

[0028] The feature value determination module is configured to determine a to-be-used feature value corresponding to a to-be-identified resource, and a to-be-matched feature value corresponding to each to-be-matched resource;

[0029] The weight determination module is configured to determine the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determine the to-be-used weight of the to-be-identified resource relative to each to-be-matched resource based on the Euclidean distance;

[0030] The resource category identification module is configured to determine a target matching resource matched with the to-be-identified resource based on each to-be-used weight, and take the resource category of the target matching resource as the resource category of the to-be-identified resource.

[0031] According to another aspect of the present application, there is provided an electronic device, which comprises:

[0032] at least one processor; and

[0033] a memory connected with the at least one processor in communication; wherein

[0034] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the resource category identification method according to any one of the embodiments of the present application.

[0035] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to execute the resource category identification method according to any one of the embodiments of the present application.

[0036] The technical scheme of the embodiment of the present application determines the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material, determines the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determines the to-be-used weight between the to-be-identified material and each to-be-matched material based on the Euclidean distance. The target matching material matched with the to-be-identified material is determined based on each to-be-used weight, and the material category of the target matching material is taken as the material category of the to-be-identified material, thereby solving the problems of misjudgment, missed judgment and the like in the prior art when the material category is determined by AI technology, i.e., the problem of inaccurate material category identification, and achieving the technical effect of efficiently identifying materials.

[0037] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 is a flowchart of a material category identification method according to the first embodiment of the present application;

[0040] Figure 2 is a flowchart of a material category identification method according to the second embodiment of the present application;

[0041] Figure 3 is a structural schematic diagram of a material category identification device according to the third embodiment of the present application;

[0042] Figure 4 is a structural schematic diagram of an electronic device implementing the data processing method of the embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0044] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and above-described drawings are intended to distinguish similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data thus designated can be interchanged, where appropriate, so that the embodiments of the application described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a list of steps or units is not necessarily limited to those steps or units that are clearly listed, but can include other steps or units that are not clearly listed or inherent to such processes, methods, products, or apparatuses.

[0045] Embodiment one

[0046] Figure 1 is a flowchart of a material category identification method according to an embodiment of the present application. The embodiment can be applied to the identification of materials when they are in and out of the warehouse. The material category identification method can be implemented by a material category identification device. The device can be implemented in the form of hardware and / or software. The hardware can be integrated into a computer device. The computer device can be a mobile terminal or a PC, etc.

[0047] As shown in Figure 1 , the method comprises:

[0048] S110, determining the to-be-used feature value corresponding to the to-be-identified material, and the to-be-matched feature value corresponding to each to-be-matched material.

[0049] The to-be-identified material can be a material in and out of the warehouse, and the material whose category needs to be determined. The to-be-matched material is some material stored in the material warehouse. The to-be-used feature value corresponds to the to-be-identified material, and the to-be-matched feature value corresponds to the to-be-matched material. The feature value can represent the corresponding material.

[0050] In the embodiment, the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material can be determined as follows: determining the to-be-used influence factor corresponding to each to-be-matched material according to the to-be-processed historical scheduling data corresponding to each to-be-matched material in each historical period; and determining the to-be-matched feature value corresponding to each to-be-matched material according to the to-be-used influence factor of each to-be-matched material and the target function.

[0051] The to-be-matched feature value corresponding to each to-be-matched material can be determined based on a period. For each historical period, historical scheduling data of the current to-be-matched material can be obtained, and the to-be-matched feature value is determined based on the historical scheduling data. That is, the historical scheduling data is used as to-be-processed historical scheduling data. The to-be-processed historical scheduling data can be the number of times of being transferred in, the number of times of being transferred out, the average transfer-in value, and the like. Based on the historical scheduling data, the influence factor corresponding to the to-be-matched material can be determined, and the influence factor is used as a to-be-used influence factor. The objective function can be understood as a function of further processing the to-be-used influence factor to determine the to-be-matched feature value.

[0052] In this embodiment, the to-be-matched feature value corresponding to each to-be-matched material in each historical period can be determined based on the to-be-processed historical scheduling data of the to-be-matched material in the current historical period. For each to-be-matched material in each historical period, the to-be-processed scheduling data of the current to-be-matched material in the current historical period is used to determine the to-be-averaged influence factor corresponding to the current to-be-matched material, wherein the to-be-processed scheduling data includes the number of times of being transferred in, the number of times of being transferred out, the average transfer-in data, the maximum transfer-in inventory data, the average transfer-in time interval, and the maximum transfer-in time interval. The to-be-used influence factor is determined based on the to-be-averaged influence factor of the current to-be-matched material in each historical period.

[0053] It should be noted that the determination method of the to-be-used influence factor corresponding to each to-be-matched material is the same, and in this embodiment, the to-be-used influence factor of a to-be-matched material is taken as an example for illustration.

[0054] The number of times of being transferred in can be understood as the number of times of being transferred into the warehouse in the current historical period, and the number of times of being transferred out can be the number of times of being transferred out of the warehouse in the current historical period. The average transfer-in quantity can be the average transfer-in quantity of the to-be-matched material, that is, the average quantity value determined by combining the transfer-in quantity and the transfer-out quantity. The maximum transfer-in inventory quantity can be the inventory quantity determined by combining the transfer-in quantity and the transfer-out quantity. The average transfer-in time interval can be the average time interval determined by combining the transfer-in time and the transfer-out time. The maximum transfer-in time interval can be the longest time interval between two adjacent time points, which is determined by combining the transfer-in time and the transfer-out time, and the longest time interval is used as the maximum transfer-in time interval. Based on the to-be-processed historical scheduling data, the to-be-averaged influence factor corresponding to the current to-be-matched material in the current historical period can be determined. After determining the to-be-averaged influence factor corresponding to the current to-be-matched material in each historical period, the to-be-used influence factor of the current to-be-matched material can be determined.

[0055] That is, when determining the to-be-used influence factor corresponding to each to-be-matched material, the to-be-averaged influence factor corresponding to each to-be-matched material can be determined first. Optionally, the to-be-averaged influence factor can be determined according to the scheduling times, the call-out times, the first weight, and the second weight, to determine the call-in influence factor and the call-out influence factor; according to the average allocation quantity, the maximum allocation inventory quantity, and the third weight, to determine the allocation inventory influence factor; according to the average allocation time interval, the maximum allocation time interval, and the fourth weight, to determine the allocation time influence factor; and based on the call-in influence factor, the call-out influence factor, the allocation inventory influence factor, and the allocation time influence factor, to determine the to-be-averaged influence factor.

[0056] Specifically, the total scheduling times can be determined according to the call-in times and the call-out times. The ratio of the call-in times to the total scheduling times is calculated, and the product of the ratio and the first weight is calculated to determine the call-in influence factor. The ratio of the call-out times to the total scheduling times is calculated, and the product of the ratio and the second weight is calculated to determine the call-out influence factor. The ratio of the average allocation quantity to the maximum allocation inventory quantity is calculated, and the product of the ratio and the third weight is calculated to determine the allocation inventory influence factor. The ratio of the average allocation time interval to the maximum allocation time interval is calculated, and the product of the ratio and the fourth weight is calculated to determine the allocation time influence factor. The call-in influence factor, the call-out influence factor, the allocation inventory influence factor, and the allocation time influence factor are summed up to obtain the to-be-averaged influence factor.

[0057] For example, the to-be-averaged influence factor can be determined based on the following formula:

[0058]

[0059] wherein w1 is the first weight, w2 is the second weight, w3 is the third weight, w4 is the fourth weight, a1 is the call-in times, a2 is the call-out times, a3 is the average allocation quantity, a4 is the maximum allocation inventory quantity, a5 is the average allocation time interval, and a6 is the maximum allocation time interval.

[0060] It can be understood that the to-be-averaged influence factor corresponding to each to-be-matched material in the corresponding historical period can be determined based on the above formula. Based on the to-be-averaged influence factor corresponding to each to-be-matched material in each historical period, the to-be-used influence factor can be determined. Optionally, the to-be-averaged influence factors of the same to-be-matched material in each historical period are averaged to determine the to-be-used influence factor.

[0061] Based on the above technical solutions, after determining the to-be-used influence factor corresponding to each to-be-matched material, the to-be-matched characteristic value corresponding to the corresponding to-be-matched material can be determined based on the objective function.

[0062] Optionally, the target function can be a function determined based on a normalized influence factor, and optionally, the normalized influence factor can be determined based on the scheduling times of the corresponding to-be-matched materials. The normalized influence factors of different to-be-matched materials can be different or the same, and whether the normalized influence factors are the same or not can be determined based on the scheduling data.

[0063] The normalized influence factor value

[0064] wherein y2 is a normalized value, a1 is an actual value, a2 is a minimum value, and a3 is a maximum value.

[0065] Based on the above formula, the normalized influence factor can be determined as a target function.

[0066] After the normalized influence factor is determined, the historical scheduling data of each to-be-matched material can be processed to obtain a corresponding normalized value, and then based on the normalized value and the target function, the to-be-matched feature value corresponding to each to-be-matched material can be determined. The historical scheduling data can be processed by multiplying the corresponding value by the normalized influence factor.

[0067] The target function can be: y3=[y1·a1,y1·a2,y1·a3,y1·a4]

[0068] wherein y3 is a normalized value, y1 is an influence factor value, a1 is a normalized number of calls in, a2 is a normalized number of calls out, a3 is a normalized average number of allocations, and a4 is a normalized average allocation time interval.

[0069] The to-be-identified material corresponding to the to-be-used feature value can be determined based on the same manner as described above.

[0070] S120, determine the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determine the to-be-used weight of the to-be-identified material relative to the to-be-matched material based on the Euclidean distance.

[0071] The Euclidean distance can represent the similarity between the to-be-identified material and each to-be-matched material, and optionally, the smaller the Euclidean distance, the more similar, and correspondingly, the larger the Euclidean distance, the less similar.

[0072] Specifically, the Euclidean distance between the to-be-used feature value and each to-be-matched feature value can be determined by using a target formula. The to-be-used weight of each to-be-identified material relative to the to-be-matched material can be determined based on the Euclidean distance.

[0073] S130, determine the target matching material matched with the to-be-identified material based on each to-be-used weight, and take the material category of the target matching material as the material category of the to-be-identified material.

[0074] It can be understood that the to-be-matched material includes a material matched with the to-be-identified material. The material consistent with the to-be-identified material is taken as a target matched material, and accordingly, the material category of the target matched material can be taken as the material category of the to-be-identified material.

[0075] Optionally, the to-be-matched material corresponding to the maximum to-be-used weight is taken as the target matched material.

[0076] It can be understood that the to-be-matched material corresponding to the maximum to-be-used weight value can be taken as the target matched material, and further the material category of the target matched material can be taken as the material category of the to-be-matched material.

[0077] The technical scheme of the embodiment of the present application determines the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material, determines the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determines the to-be-used weight of the to-be-identified material relative to the to-be-matched material based on the Euclidean distance. The target matched material matched with the to-be-identified material is determined based on each to-be-used weight, and the material category of the target matched material is taken as the material category of the to-be-identified material. The problem of inaccurate material category identification is solved, and the technical effect of efficiently identifying materials is achieved.

[0078] Embodiment two

[0079] Figure 2 It is a flowchart of a method for identifying a material category provided by the embodiment two of the present application. On the basis of the above-mentioned embodiment, the Euclidean distance between the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value of each to-be-matched material can be determined, and further the to-be-used weight of the to-be-identified material relative to each to-be-matched material is determined based on the Euclidean distance. The specific implementation manner can be referred to the detailed description of the present embodiment. The same or corresponding technical terms as the above-mentioned embodiment are not described herein.

[0080] As shown in Figure 2 , the method comprises:

[0081] S210, determining the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material.

[0082] S220, for each to-be-matched feature value, determining the difference value between the to-be-used feature value and the current to-be-matched feature value, and determining the Euclidean distance based on the difference value.

[0083] In this embodiment, the way of determining the Euclidean distance between the to-be-used feature value and the to-be-matched feature value is the same, and one of them can be taken as an example to introduce.

[0084] wherein the to-be-matched feature value currently introduced is taken as the current to-be-matched feature value. Optionally, the difference between the current to-be-matched feature value and the to-be-used feature value can be calculated. The reciprocal of the difference can be taken as the Euclidean distance between the current to-be-matched feature value and the to-be-used feature value.

[0085] Exemplarily, for the distance between the test data point t and the training data point i, the Euclidean distance is used: The to-be-used weight is:

[0086] S230, taking the reciprocal of the Euclidean distance as the to-be-used weight of the to-be-identified material relative to the to-be-matched material.

[0087] S240, determining the target matching material matched with the to-be-identified material based on each to-be-used weight, and taking the material category of the target matching material as the material category of the to-be-identified material.

[0088] Exemplarily, for the determination of the material category, the weighted voting method can be used, and the weight of the neighbor is used to determine:

[0089]

[0090] t: test data point, i.e. the material or sample to be classified. It has a feature value, which is used to compare and classify with the training data point, i: training data point, i.e. historical data with known classification. It has the same features as the test data point, which is used to calculate the distance between the test data point and the training data point, d(t,i): Euclidean distance, used to measure the similarity between the test data point t and the training data point i. It is the square root of the sum of the squares of the feature value difference, w(i): weight, indicating the reciprocal of the distance between the test data point and the training data point. The weight measures the similarity of the neighbor, the closer the distance, the greater the weight, the farther the distance, the smaller the weight, k: number of neighbors, indicating the number of nearest training data points to be considered in classification. j : the category of the jth neighbor, i.e. the category to which the training data point i belongs.

[0091] The indicator function is 1 when the category c i of the training data point i is equal to the category c j of the jth neighbor, and 0 otherwise. It is used to determine whether the category of the neighbor is the same as the category of the test data point.

[0092] On the basis of the above technical solutions, after the target matching material is determined, the method further comprises: calling a material category corresponding to the target matching material, and taking the material category as a material category of the to-be-identified material, so as to dispatch the to-be-identified material based on the material category, and update material information and dispatch data corresponding to the to-be-identified material.

[0093] It can be understood that the material category corresponding to the target matching material is called, and the material category is taken as the material category of the to-be-identified material, after identification, the material information and the dispatch data corresponding to the target matching material can be updated according to the dispatch-in or dispatch-out data of the to-be-identified material. The material information can be the quantity of the material, and the dispatch data can be the dispatch-in times, the dispatch-out times and the like mentioned above. The advantage of updating the above data is that after the to-be-identified material is received again, the material category of the to-be-identified material can be determined based on the updated dispatch data.

[0094] The technical solutions of the embodiments of the present application determine the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material, determine the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determine the to-be-used weight between the to-be-identified material and the to-be-matched material based on the Euclidean distance, determine the target matching material matched with the to-be-identified material based on each to-be-used weight, and take the material category of the target matching material as the material category of the to-be-identified material, thereby solving the misjudgment, omission and the like in the prior art when the material category is determined by AI technology, i.e., the problem of inaccurate material category identification, and achieving the technical effect of efficiently identifying the material.

[0095] Embodiment three

[0096] Figure 3 is a structural schematic diagram of a data processing device according to the embodiment three of the present application. As shown in the figure, the device comprises a feature value determination module 310, a weight determination module 320 and a material category identification module 330. Figure 3

[0097] The feature value determination module 310 is configured to determine the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material. The weight determination module 320 is configured to determine the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determine the to-be-used weight between the to-be-identified material and the to-be-matched material based on the Euclidean distance. The material category identification module 330 is configured to determine the target matching material matched with the to-be-identified material based on each to-be-used weight, and take the material category of the target matching material as the material category of the to-be-identified material.

[0098] ​On the basis of the technical scheme, the characteristic value determination module comprises:

[0099] The to-be-used influence factor determination unit is configured to determine, according to the to-be-processed historical scheduling data corresponding to each to-be-matched material in each historical period, the to-be-used influence factor corresponding to each to-be-matched material.

[0100] The to-be-matched characteristic value determination unit is configured to determine, according to the to-be-used influence factor of each to-be-matched material and the target function, the to-be-matched characteristic value corresponding to each to-be-matched material.

[0101] On the basis of the technical scheme, the to-be-used influence factor determination unit comprises:

[0102] The to-be-average influence factor determination subunit is configured to determine, for each to-be-matched material in each historical period, the to-be-average influence factor corresponding to the current to-be-matched material according to the to-be-processed scheduling data of the current to-be-matched material in the current historical period, wherein the to-be-processed scheduling data comprises the number of times of being transferred in, the number of times of being transferred out, the average allocation data, the maximum allocation inventory data, the average allocation time interval, and the maximum allocation time interval; and the to-be-used influence factor determination subunit is configured to determine the to-be-used influence factor according to the to-be-average influence factor of the current to-be-matched material in each historical period.

[0103] On the basis of each of the technical schemes, the to-be-average influence factor determination subunit comprises:

[0104] The first influence factor determination subunit is configured to determine the transfer-in influence factor and the transfer-out influence factor according to the number of times of scheduling, the number of times of being transferred out, a first weight, and a second weight; the second influence factor determination subunit is configured to determine the allocation inventory influence factor according to the average allocation data, the maximum allocation inventory data, and a third weight; the third influence factor determination subunit is configured to determine the allocation time influence factor according to the average allocation time interval, the maximum allocation time interval, and a fourth weight; and the fourth influence factor determination subunit is configured to determine the to-be-average influence factor based on the transfer-in influence factor, the transfer-out influence factor, the allocation inventory influence factor, and the allocation time influence factor.

[0105] On the basis of each of the technical schemes, the weight value determination module comprises:

[0106] The Euclidean distance determination unit is configured to determine, for each to-be-matched characteristic value, the difference between the to-be-used characteristic value and the current to-be-matched characteristic value, and determine the Euclidean distance based on the difference; and the weight determination unit is configured to take the reciprocal of the Euclidean distance as the to-be-used weight of the to-be-identified material relative to the to-be-matched material.

[0107] On the basis of each of the technical solutions above, the material category identification module is further configured to take the to-be-matched material corresponding to the maximum to-be-used weight as the target matched material.

[0108] On the basis of each of the technical solutions above, the device further comprises a data retrieval module configured to retrieve a material category corresponding to the target matched material, and take the material category as the material category of the to-be-identified material, so as to schedule the to-be-identified material based on the material category, and update the material information and the scheduling data corresponding to the to-be-identified material.

[0109] The technical solution of the embodiment of the present application determines the to-be-used feature value corresponding to the to-be-identified material and the to-be-matched feature value corresponding to each to-be-matched material, determines the Euclidean distance between the to-be-used feature value and each to-be-matched feature value, and determines the to-be-used weight of the to-be-identified material relative to the to-be-matched material based on the Euclidean distance, determines the target matched material matched with the to-be-identified material based on each to-be-used weight, and takes the material category of the target matched material as the material category of the to-be-identified material, thereby solving the problems of misjudgment, missed judgment and the like in the prior art when determining the material category by using the AI technology, i.e., the problem of inaccurate material category identification, and achieving the technical effect of efficiently identifying the material.

[0110] The material category identification device provided in the embodiment of the present application can execute the material category identification method provided in any embodiment of the present application, and has the function modules and beneficial effects corresponding to the execution method.

[0111] Embodiment Four

[0112] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0113] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication. The memory stores computer programs executable by the at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0115] The processor 11 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the identification method of the material category.

[0116] In some embodiments, the data processing method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the data processing method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the data processing method by any other appropriate means, such as by means of firmware.

[0117] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0118] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0119] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0120] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0121] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0122] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0123] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0124] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for identifying material categories, characterized in that, include: Determine the feature values ​​to be used for each material to be identified, and the feature values ​​to be matched for each material to be matched; Determine the Euclidean distance between the feature value to be used and each feature value to be matched, and determine the weight of the material to be identified relative to the material to be matched based on the Euclidean distance; Based on the weights to be used, a target matching material that matches the material to be identified is determined, and the material category of the target matching material is used as the material category of the material to be identified. The determination of the matching feature value corresponding to each material to be matched includes: Based on the pending historical scheduling data of each material to be matched in each historical period, determine the pending use impact factor for each material to be matched. Based on the usage impact factors and objective function of each material to be matched, determine the matching feature value corresponding to each material to be matched; The process involves determining the usage impact factor for each material to be matched based on the historical scheduling data corresponding to each material to be matched within each historical period, including: For each material to be matched in each historical period, the average impact factor corresponding to the material to be matched is determined based on the historical scheduling data to be processed for the material to be matched in the current historical period. The historical scheduling data to be processed includes the number of times the material is transferred in, the number of times it is transferred out, the average transfer quantity, the maximum transfer inventory quantity, the average transfer time interval, and the maximum transfer time interval. The influence factor to be used is determined based on the average influence factor of the current material to be matched in each historical period.

2. The method according to claim 1, characterized in that, The step of determining the average impact factor corresponding to the current material to be matched based on the pending scheduling data of the current material to be matched in the current historical period includes: The impact factors for transfer in and transfer out are determined based on the number of transfers in, the number of transfers out, the first weight, and the second weight. The allocation inventory influencing factor is determined based on the average allocation quantity, the maximum allocation inventory quantity, and the third weight. The allocation time influence factor is determined based on the average allocation time interval, the maximum allocation time interval, and the fourth weight. Based on the influencing factors of transfer in, transfer out, transfer of inventory, and transfer time, the influencing factor to be averaged is determined.

3. The method according to claim 1, characterized in that, The step of determining the Euclidean distance between the feature values ​​to be used and each feature value to be matched, and determining the weight of the material to be identified relative to the material to be matched based on the Euclidean distance, includes: For each feature value to be matched, the difference between the feature value to be used and the current feature value to be matched is determined, and the Euclidean distance is determined based on the difference; The reciprocal of the Euclidean distance is used as the weight of the material to be identified relative to the material to be matched.

4. The method according to claim 1, characterized in that, The step of determining the target matching material that matches the material to be identified based on each weight to be used includes: The material to be matched corresponding to the one with the highest weight is taken as the target matching material.

5. The method according to claim 1, characterized in that, Also includes: The material category corresponding to the target matching material is retrieved, and the material category is used as the material category of the material to be identified, so as to schedule the material to be identified based on the material category, and update the material information and scheduling data corresponding to the material to be identified.

6. A material category identification device, characterized in that, include: The feature value determination module is used to determine the feature values ​​to be used for the materials to be identified, as well as the feature values ​​to be matched for each material to be matched. The weight determination module is used to determine the Euclidean distance between the feature value to be used and each feature value to be matched, and to determine the weight to be used between the material to be identified and the material to be matched based on the Euclidean distance. The material category identification module is used to determine the target matching material that matches the material to be identified based on each weight to be used, and to use the material category of the target matching material as the material category of the material to be identified; The feature value determination module includes: The unit for determining the impact factor to be used is used to determine the impact factor to be used for each material to be matched based on the historical scheduling data to be processed for each material to be matched in each historical period. The matching feature value determination unit is used to determine the matching feature value corresponding to each matching material based on the usage impact factor and objective function of each matching material. The material category identification device is used to perform the material category identification method according to any one of claims 1-5.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the material category identification method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for identifying the material category as described in any one of claims 1-5.

Images