Material purchasing demand bank benefit decision generation method and device, and medium

Abstract

The invention belongs to the technical field of electric power material management, and relates to a material procurement demand bank benefit decision generation method and device, and a medium. The method comprises the steps of obtaining a geographic position and a procurement list of a procurement unit; obtaining the geographic position of each electric power material warehouse, an inventory data form and the sum of the ages of the electric power material warehouses; performing feature extraction on the purchase list and each inventory data form to obtain a feature matrix of the purchase list and a feature matrix of each inventory data form; calculating the cosine similarity between the feature matrix of the purchase list and the feature matrix of each inventory data form, and obtaining a precise benefit warehouse set based on the cosine similarity; based on the distance between each electric power material warehouse and the electric power material purchasing unit, obtaining a first sorting number; obtaining a second sorting number based on the sum of the storage ages of the electric power materials of the electric power material warehouses; based on the first sorting number and the second sorting number, obtaining a precise warehouse utilization coefficient of each electric power material warehouse; and utilizing the electric power material warehouse with the maximum accurate warehouse utilization coefficient to provide electric power materials.

Description

Technical Field

[0001] The present invention relates to the technical field of power material management, and in particular to a method, device and computer-readable storage medium for generating a profit-stock decision for material procurement demand. Background Art

[0002] With the advancement of large-scale construction of power projects, the surplus materials, project return materials, and emergency materials generated during the power project have led to a large backlog of power materials, which occupy a large amount of storage space. In order to improve the efficiency of the use of inventory materials and reduce the cost of purchasing power materials, it is necessary to actively carry out inventory utilization, that is, to allocate and use the inventory of power materials before purchasing them.

[0003] In the prior art, when performing inventory utilization work, the inventory power material information is often manually searched, checked and sorted from paper documents or electronic spreadsheets of various power material warehouses, and then the material information of each power material warehouse is compared with the purchase list of the purchasing unit, and the power material warehouse that can meet the procurement needs is selected to provide materials to the purchasing unit, thereby effectively utilizing the backlog of materials, while meeting the material needs of the purchasing unit, promoting the effective flow of inventory resources, and realizing the inventory utilization of power materials. However, when checking whether the quantity and specifications of inventory materials meet the purchasing needs of the purchasing unit, for each type of power material in the purchase list, the staff needs to search and compare one by one whether each power material warehouse has inventory that can meet the purchase quantity and specifications of this type of power material. Finally, by integrating the matching degree between the inventory of each power material warehouse and the purchase list, the power material warehouse that can best meet the purchasing needs is selected to provide power materials to the purchasing unit. This not only wastes a lot of human resources, but also often is affected by subjective factors when judging whether the inventory materials of each power material warehouse meet the purchasing needs. For example, for slight differences in the specifications of power materials, the staff may think that the difference can be ignored, or they may think that the difference cannot meet the purchasing needs, thereby affecting the final decision to use the warehouse and failing to select a truly matching power material warehouse.

[0004] In summary, the existing method of generating power material utilization decision based on manual comparison is not only inefficient and wastes a lot of human resources, but also fails to generate the optimal utilization decision, affecting the quality of utilization work. Summary of the invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the problems in the prior art of generating power material storage decisions based on manual comparison, which are inefficient, require a lot of human resources to waste, and cannot generate the optimal storage decision, thus affecting the quality of storage work.

[0006] In order to solve the above technical problems, the present invention provides a method for making a decision on the benefits of material procurement demand, comprising: Obtain the geographical location and purchase list of the power material purchasing unit; obtain the geographical location, inventory data form and the sum of the inventory ages of all power materials in the inventory data form of each power material warehouse; Extracting a target feature vector for each power material in the purchase list, and obtaining a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; Extracting the target feature vector of each power material in each inventory data form, and obtaining the feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; Calculate the cosine similarity of the feature matrix of the purchase list and the feature matrix of each inventory data sheet respectively, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; For the power material warehouses in the precision benefit warehouse concentration, based on the geographical location of each power material warehouse and the geographical location of the power material purchasing unit, the distance between each power material warehouse and the power material purchasing unit is calculated, and the distances are sorted from small to large to obtain the first sorting number of each power material warehouse; the sum of the storage ages of all power materials in the inventory data form of each power material warehouse is sorted from small to large to obtain the second sorting number of each power material warehouse; Based on the weighted sum of the first ranking number and the second ranking number of each power material warehouse in the precise profit warehouse set, the precise profit coefficient of the power material warehouse is obtained; the power material warehouse with the largest precise profit coefficient is taken as the target power material warehouse to provide power materials to the power material purchasing unit.

[0007] Preferably, extracting the target feature vector of each power material includes: The Word2Vec model is used to convert the name of the power material into a word vector to obtain the text feature vector of the power material; Normalizing various numerical parameters of the electric power material, and combining the normalized numerical parameters to obtain a numerical feature vector of the electric power material; Combining the text feature vector and the numerical feature vector of the electric power material to obtain a target feature vector of the electric power material; The numerical parameters of the electric power materials include quantity, specifications, price, electrical performance, power capacity, and performance indicators.

[0008] Preferably, the calculation formula for the precise warehouse profit coefficient of the power material warehouse is: , in, Indicates the precise profit coefficient of the power material warehouse; Indicates the weight of the first sort number; Indicates the first sorting number of the power material warehouse; Indicates the number of power material warehouses concentrated in the precise warehouse; Indicates the weight of the second sort number; Indicates the second sorting number of the power material warehouse; .

[0009] Preferably, if the precision profit coefficients of the multiple power material warehouses in the precision profit warehouse set are equal, A subset of accurate benefit warehouses is obtained based on multiple power material warehouses with equal accurate benefit coefficients in the accurate benefit warehouse set; For each power material warehouse in the precise profit warehouse subset, respectively calculate the difference between the purchase quantity of each power material in the purchase list and the inventory quantity of the same power material in the power material warehouse, and sum the absolute values ​​of all the calculated differences; The electric power material warehouse with the smallest sum of the absolute values ​​of the differences is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

[0010] Preferably, based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than the first preset threshold, obtaining the accurate warehouse set further includes: Based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is less than or equal to the first preset threshold and greater than the second preset threshold, a recommended warehouse set is obtained.

[0011] Preferably, when the sum of the inventory quantities of any one type of power material in all power material warehouses in the precise warehouse set is less than the purchase quantity of the same type of power material in the purchase list, Obtaining the precise profit coefficient of each power material warehouse in the recommended profit warehouse set; The electric power material warehouse with the largest precision profit coefficient is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

[0012] Preferably, before extracting features from each type of power material information in the purchase list and each inventory data form, the method further includes: preprocessing the data in the purchase list and each inventory data form.

[0013] Preferably, it also includes using the Quartz component to monitor the inventory quantity of each power material in each power material warehouse in real time, and updating the inventory data table of each power material warehouse.

[0014] The present invention also provides a device for generating a benefit-stock decision for material procurement demand, comprising: The data acquisition module is used to obtain the geographical location and purchase list of the power material purchasing unit; obtain the geographical location, inventory data form and the sum of the storage age of all power materials in the inventory data form of each power material warehouse; A first feature matrix acquisition module is used to extract a target feature vector for each power material in the purchase list, and obtain a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; A second feature matrix acquisition module is used to extract the target feature vector of each power material in each inventory data form, and obtain the feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; A similarity calculation module, used to calculate the cosine similarity between the feature matrix of the purchase list and the feature matrix of each inventory data sheet, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; A sorting module is used to calculate the distance between each power material warehouse and the power material procurement unit for the power material warehouses in the precision benefit warehouse concentration based on the geographical location of each power material warehouse and the geographical location of the power material procurement unit, and sort the distances from small to large to obtain a first sorting number for each power material warehouse; sort the sum of the storage ages of all power materials in the inventory data form of each power material warehouse from small to large to obtain a second sorting number for each power material warehouse; The profit decision generation module is used to obtain the precise profit coefficient of the power material warehouse based on the weighted sum of the first ranking number and the second ranking number of each power material warehouse in the precise profit warehouse set; the power material warehouse with the largest precise profit coefficient is taken as the target power material warehouse to provide power materials to the power material purchasing unit.

[0015] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for generating a benefit inventory decision for material procurement needs are implemented.

[0016] The method for generating a profit-stock decision for material procurement demand provided in the present application performs feature matching on the procurement list and the inventory data of each power material warehouse, and obtains a precise profit-stock warehouse set based on the power material warehouses with a high matching degree; since the closer the distance between the power material warehouse and the procurement unit, the lower the cost in the material supply process and the higher the material supply efficiency, the closer the power material warehouse can provide power materials to the procurement unit more quickly; at the same time, the younger the storage age of the power material, the shorter the storage time of the power material, and the smaller the risk of performance degradation or damage caused by excessive storage time, therefore, the power material warehouse with a smaller sum of the power material storage age provides better quality of power materials, and the present application obtains the first ranking number of each power material warehouse by sorting the distance between the power material warehouses in the precise profit-stock warehouse set and the procurement unit, and obtains the second ranking number of each power material warehouse by sorting the sum of the power material storage ages of each power material warehouse, and calculates the precise profit coefficient of each power material warehouse in combination with the first ranking number and the second ranking number, so that among the power material warehouses with a high feature matching degree, the power material warehouses that can ensure the quality and efficiency of power material supply are preferentially selected to provide power materials to the procurement unit. The solution provided in this application, based on feature matching, comprehensively considers the cost, efficiency and quality issues in the process of power material supply, so as to generate the optimal inventory decision, which not only reduces labor costs, but also improves the utilization rate of inventory materials, alleviates the inventory pressure of power materials, and takes into account the quality and efficiency of power material supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein: Figure 1 Flowchart of the method for generating profit-stock decision for the material procurement demand provided for this application; Figure 2 A schematic diagram of the interface of the Liku system designed for the Liku decision-making generation method based on the material procurement demand provided in this application; Figure 3 A schematic diagram of a library system designed for a library decision generation method based on the material procurement needs provided in this application; Figure 4 Schematic diagram of the structure of the resource utilization decision-making device for the material procurement needs provided for this application. DETAILED DESCRIPTION

[0018] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0019] See also Figure 1 , Figure 1 The figure shows a flow chart of a method for generating a profit decision for material procurement demand provided in this application, which specifically includes: S10: Obtain the geographical location and purchase list of the power material purchasing unit; obtain the geographical location, inventory data form and the sum of the inventory ages of all power materials in the inventory data form of each power material warehouse; Specifically, the purchase list includes the names of the power materials to be purchased, the purchase quantity, price and specifications of each power material; the inventory data form of the power material warehouse includes the names of the power materials in stock in the power material warehouse, the inventory quantity, price and specifications of each power material.

[0020] Optionally, in the prior art, the inventory data of each power material warehouse is obtained manually offline, and in the present application, an http protocol interface can be used to obtain the inventory data form of each power material warehouse in real time.

[0021] S20: extracting the target feature vector of each power material in the purchase list, and obtaining a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; S30: extracting a target feature vector of each power material in each inventory data form, and obtaining a feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; S40: Calculate the cosine similarity of the feature matrix of the purchase list and the feature matrix of each inventory data sheet respectively, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; S50: For the power material warehouses where the precise warehouse is concentrated, based on the geographical location of each power material warehouse and the geographical location of the power material purchasing unit, the distance between each power material warehouse and the power material purchasing unit is calculated, and the distances are sorted from small to large to obtain the first sorting number of each power material warehouse; the sum of the storage ages of all power materials in the inventory data form of each power material warehouse is sorted from small to large to obtain the second sorting number of each power material warehouse; S60: Obtain the precise profit coefficient of the power material warehouse based on the weighted sum of the first ranking number and the second ranking number of each power material warehouse in the precise profit warehouse set; select the power material warehouse with the largest precise profit coefficient as the target power material warehouse to provide power materials to the power material purchasing unit.

[0022] Furthermore, in order to improve data quality and thus make the ultimately generated inventory utilization decision optimal, step S10 also includes preprocessing the data in the purchase list and each inventory data form.

[0023] Specifically, the preprocessing steps include: 1. Clarifying and unifying the information contained in the purchase list and each inventory data form for each type of power material; 2. Clarifying the definition, data type and value range of each field in the information contained in each type of power material; 3. Removing duplicate data and abnormal data in the purchase list and each inventory data form to ensure data quality.

[0024] Specifically, since the purchase list and the inventory data form contain both text information such as the names of electric power materials and parameter information such as the quantity and specifications of each electric power material, when judging whether the inventory data form matches the purchase list, it is necessary to judge the consistency of the names of the electric power materials and the consistency of the quantity, specifications and other information of the electric power materials with the same name. Therefore, it is necessary to extract the text features and data features of each electric power material in the purchase list and the inventory data form, and then calculate the similarity between the purchase list and the inventory data form based on the text features and data features of the electric power materials, so as to judge whether the electric power material warehouse corresponding to the inventory data form can meet the procurement needs of the purchasing unit.

[0025] Specifically, in some embodiments of the present application, extracting the target feature vector of each power material includes: The Word2Vec model is used to convert the name of the power material into a word vector to obtain the text feature vector of the power material; Normalizing various numerical parameters of the electric power material, and combining the normalized numerical parameters to obtain a numerical feature vector of the electric power material; The text feature vector and the numerical feature vector of the electric power material are combined to obtain the target feature vector of the electric power material.

[0026] Specifically, by normalizing the numerical parameters of power materials, various numerical parameters can be adjusted to the same level. The numerical parameters of power materials include quantity, specification, price, electrical performance, power capacity, and performance indicators.

[0027] By using cosine similarity to match text features and data features, for example, the purchase quantity of cables in the purchase list is 10 and the length is 1000m, and the inventory quantity of cables in an electric power material warehouse is 10 and the length is 1000m, then the inventory quantity and specifications of cables in the electric power material warehouse match the purchase list 100%; if the purchase list contains multiple electric power materials, the feature matrix of the purchase list is constructed based on the target feature vector of each electric power material, and the feature matrix of the electric power material warehouse is constructed based on the target feature vector of each electric power material in the electric power material warehouse. The matching degree between the electric power material inventory of the electric power material warehouse and the purchase list is determined by calculating the cosine similarity of the two feature matrices.

[0028] Further, based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than the first preset threshold, obtaining the accurate warehouse set further includes: Based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is less than or equal to the first preset threshold and greater than the second preset threshold, a recommended warehouse set is obtained.

[0029] When the sum of the inventory quantities of any one type of power material in all power material warehouses in the precise warehouse set is less than the purchase quantity of the same type of power material in the purchase list, Obtain the precise profit coefficient of each power material warehouse in the recommended profit warehouse concentration; The power material warehouse with the largest precision warehouse utilization coefficient is selected as the target power material warehouse to provide power materials to the power material purchasing units.

[0030] In a specific example of the present application, the first preset threshold is 80%, and the second preset threshold is 70%. If the purchase quantity of cables in the purchase list is 50, and the sum of the inventory quantities of cables in all power material warehouses in the precise benefit warehouse set is less than 50, then the power material warehouse with the highest match to the purchase list can be selected from the recommended benefit warehouse set as the target power material warehouse to supplement the missing power materials, thereby utilizing the precise benefit warehouse set and the recommended benefit warehouse set to jointly meet procurement needs and maximize the effective utilization of the backlog of power materials.

[0031] Specifically, the lower the age of electric power materials, the shorter the storage time of the electric power materials, and the more their quality and performance meet the use requirements. Therefore, giving priority to the use of electric power materials with a short storage age can reduce the risks of damage and expiration of inventory materials due to long-term storage, thereby ensuring the quality of electric power materials. At the same time, the distance between the electric power material warehouse and the purchasing unit affects both the supply speed and the transportation cost of the electric power materials. Therefore, the present application comprehensively considers the storage age of each electric power material warehouse and the distance from the purchasing unit in the precise warehouse, which can not only ensure the quality of the electric power materials provided, but also minimize the supply cost of the electric power materials and improve the supply efficiency of the electric power materials.

[0032] In some embodiments of the present application, the calculation formula for the precise warehouse profit coefficient of the power material warehouse is: , in, Indicates the precise profit coefficient of the power material warehouse; Indicates the weight of the first sort number; Indicates the first sorting number of the power material warehouse; Indicates the number of power material warehouses concentrated in the precise warehouse; Indicates the weight of the second sort number; Indicates the second sorting number of the power material warehouse; .

[0033] Furthermore, if the precision profit coefficients of multiple power material warehouses in the precision profit warehouse concentration are equal, Based on the multiple power material warehouses with equal precision benefit coefficients in the precision benefit warehouse set, a precision benefit warehouse subset is obtained; For each power material warehouse in the precise profit warehouse subset, the difference between the purchase quantity of each power material in the purchase list and the inventory quantity of the same power material in the power material warehouse is calculated respectively, and the absolute values ​​of all the calculated differences are summed; The electric power material warehouse with the smallest sum of the absolute values ​​of the differences is selected as the target electric power material warehouse to provide electric power material to the electric power material purchasing unit.

[0034] When the age of an electric power material warehouse and the distance to a purchasing unit are equal, the difference between the inventory of each electric power material and the purchase demand can be calculated, and the sum of the absolute values ​​of all the differences can be calculated. For example, the electric power materials that need to be purchased in the purchase list include cables with a purchase quantity of 100, voltmeters with a purchase quantity of 50, and transformers with a purchase quantity of 130. The inventory quantity of cables in the first electric power material warehouse is 80, the inventory quantity of voltmeters is 50, and the inventory quantity of transformers is 100. The sum of the absolute values ​​of the differences is 50; the inventory quantity of cables in the second electric power material warehouse is 95, the inventory quantity of voltmeters is 60, and the inventory quantity of transformers is 150. The sum of the absolute values ​​of the differences is 35. The second electric power material warehouse is selected as the target electric power material warehouse to provide electric power materials for the purchasing unit.

[0035] Furthermore, in some embodiments of the present application, the Quartz component can also be used to monitor the inventory quantity of each power material in each power material warehouse in real time, and update the inventory data form of each power material warehouse to ensure the real-time and effectiveness of the inventory data form of each power material warehouse, and improve the accuracy of the generated warehouse utilization decision.

[0036] It is worth noting that the present application has designed a material procurement demand benefit decision generation system based on the material procurement demand benefit decision generation method provided in the above embodiment, such as Figure 2 The following is a schematic diagram of the system interface. Figure 3The figure shows the principle diagram of the system's warehouse utilization. The data acquisition module in the RSP platform obtains the inventory data of each power material warehouse in real time through the http protocol interface, and uses the Quarta component to monitor and update the inventory data of each power material warehouse in real time. At the same time, the designer writes the warehouse utilization decision generation method provided in the above embodiment into the RSP platform. When in use, it is only necessary to upload the purchase list of the purchasing unit to the RSP platform. The warehouse utilization decision generation module in the RSP platform can use the warehouse utilization decision generation method of the material procurement demand provided in the above embodiment to select the power material warehouse that best matches the procurement demand from each power material warehouse, and output the warehouse utilization decision. In addition, the project personnel can also approve the warehouse utilization decision output by the RSP platform.

[0037] Based on the method for generating a benefit-stock decision of material procurement demand provided in the above embodiment, the embodiment of the present application also provides a device for generating a benefit-stock decision of material procurement demand, such as Figure 4 As shown, the device specifically includes: The data acquisition module 10 is used to obtain the geographical location and purchase list of the power material purchasing unit; obtain the geographical location, inventory data form and the sum of the storage ages of all power materials in the inventory data form of each power material warehouse; A first feature matrix acquisition module 20 is used to extract a target feature vector for each power material in the purchase list, and obtain a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; The second feature matrix acquisition module 30 is used to extract the target feature vector of each power material in each inventory data form, and obtain the feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; A similarity calculation module 40 is used to calculate the cosine similarity between the feature matrix of the purchase list and the feature matrix of each inventory data sheet, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; The sorting module 50 is used to calculate the distance between each power material warehouse and the power material purchasing unit for the power material warehouses in the precision warehouse, based on the geographical location of each power material warehouse and the geographical location of the power material purchasing unit, and sort the distances from small to large to obtain the first sorting number of each power material warehouse; sort the sum of the storage ages of all power materials in the inventory data form of each power material warehouse from small to large to obtain the second sorting number of each power material warehouse; The profit decision generation module 60 is used to obtain the precise profit coefficient of the power material warehouse based on the weighted sum of the first ranking number and the second ranking number of each power material warehouse in the precise profit warehouse set; the power material warehouse with the largest precise profit coefficient is used as the target power material warehouse to provide power materials to the power material purchasing unit.

[0038] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for generating a benefit inventory decision for material procurement needs are implemented.

[0039] The method for generating a utilization decision for material procurement needs provided in the present application performs feature matching on the procurement list and inventory data, obtains an accurate utilization warehouse set based on the power material warehouses with a high degree of matching, and then combines the cost and efficiency issues in the actual supply scenario of power materials, comprehensively considers the actual distance between each power material warehouse and the procurement unit in the accurate utilization warehouse set, and the warehouse age of the power materials, so as to give priority to the power material warehouses that can ensure the quality and efficiency of power material supply to provide power materials to the procurement unit, and combines the procurement needs of the procurement unit with the power material utilization plan, on the basis of text and data feature matching, comprehensively considers the cost, efficiency and quality issues in the power material supply process, and generates the optimal utilization decision, which greatly improves the utilization rate of inventory materials, alleviates the inventory pressure of power materials, and effectively reduces the phenomenon of repeated procurement of power materials.

[0040] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0041] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0043] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0044] Obviously, the above embodiments are merely examples for the purpose of clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. A method for generating a profit-stock decision for material procurement demand, characterized in that: include: Obtain the geographical location and purchase list of power material purchasing units; Obtaining the geographical location of each power material warehouse, the inventory data form, and the sum of the storage ages of all power materials in the inventory data form; Extracting a target feature vector for each power material in the purchase list, and obtaining a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; Extracting the target feature vector of each power material in each inventory data form, and obtaining the feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; Calculate the cosine similarity of the feature matrix of the purchase list and the feature matrix of each inventory data sheet respectively, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; For the power material warehouses in the precision benefit warehouse concentration, based on the geographical location of each power material warehouse and the geographical location of the power material procurement unit, the distance between each power material warehouse and the power material procurement unit is calculated, and the distances are sorted from small to large to obtain the first sorting number of each power material warehouse; Sort the sum of the storage ages of all power materials in the inventory data form of each power material warehouse from small to large to obtain the second sorting number of each power material warehouse; Based on the weighted sum of the first ranking number and the second ranking number of each power material warehouse in the precise profit warehouse set, a precise profit coefficient of the power material warehouse is obtained; The electric power material warehouse with the largest precision profit coefficient is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

2. The method for generating benefit-stock decision of material procurement demand according to claim 1, characterized in that: The target feature vectors extracted for each power material include: The Word2Vec model is used to convert the name of the power material into a word vector to obtain the text feature vector of the power material; Normalizing various numerical parameters of the electric power material, and combining the normalized numerical parameters to obtain a numerical feature vector of the electric power material; Combining the text feature vector and the numerical feature vector of the electric power material to obtain a target feature vector of the electric power material; The numerical parameters of the electric power materials include quantity, specifications, price, electrical performance, power capacity, and performance indicators.

3. The method for generating benefit-stock decision of material procurement demand according to claim 1, characterized in that: The calculation formula for the precise utilization coefficient of the power material warehouse is: ， in, Indicates the precise profit coefficient of the power material warehouse; Indicates the weight of the first sort number; Indicates the first sorting number of the power material warehouse; Indicates the number of power material warehouses concentrated in the precise warehouse; Indicates the weight of the second sort number; Indicates the second sorting number of the power material warehouse; .

4. The method for generating benefit-stock decision of material procurement demand according to claim 1, characterized in that: If the precision profit coefficients of multiple power material warehouses in the precision profit warehouse concentration are equal, A subset of accurate benefit warehouses is obtained based on multiple power material warehouses with equal accurate benefit coefficients in the accurate benefit warehouse set; For each power material warehouse in the precise profit warehouse subset, respectively calculate the difference between the purchase quantity of each power material in the purchase list and the inventory quantity of the same power material in the power material warehouse, and sum the absolute values ​​of all the calculated differences; The electric power material warehouse with the smallest sum of the absolute values ​​of the differences is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

5. The method for generating benefit-stock decision of material procurement demand according to claim 1, characterized in that: Based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than the first preset threshold, obtaining the accurate warehouse set further includes: Based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is less than or equal to the first preset threshold and greater than the second preset threshold, a recommended warehouse set is obtained.

6. The method for generating benefit-stock decision of material procurement demand according to claim 5, characterized in that: When the sum of the inventory quantities of any one type of power material in all power material warehouses in the precise warehouse set is less than the purchase quantity of the same type of power material in the purchase list, Obtaining the precise profit coefficient of each power material warehouse in the recommended profit warehouse set; The electric power material warehouse with the largest precision profit coefficient is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

7. The method for generating profit-stock decision of material procurement demand according to claim 1, characterized in that: Before extracting features from each type of power material information in the purchase list and each inventory data form, the method further includes: preprocessing the data in the purchase list and each inventory data form.

8. The method for generating benefit-stock decision of material procurement demand according to claim 1, characterized in that: It also includes using Quartz components to monitor the inventory quantity of each power material in each power material warehouse in real time, and updating the inventory data form of each power material warehouse.

9. A device for generating a benefit-stock decision for material procurement demand, characterized in that: include: The data acquisition module is used to obtain the geographical location and purchase list of the power material purchasing unit; Obtaining the geographical location of each power material warehouse, the inventory data form, and the sum of the storage ages of all power materials in the inventory data form; A first feature matrix acquisition module is used to extract a target feature vector for each power material in the purchase list, and obtain a feature matrix of the purchase list based on the target feature vectors of all power materials in the purchase list; A second feature matrix acquisition module is used to extract the target feature vector of each power material in each inventory data form, and obtain the feature matrix of each inventory data form based on the target feature vectors of all power materials in each inventory data form; A similarity calculation module, used to calculate the cosine similarity between the feature matrix of the purchase list and the feature matrix of each inventory data sheet, and obtain an accurate warehouse set based on the power material warehouses corresponding to the inventory data sheets whose cosine similarity is greater than a first preset threshold; A sorting module is used to calculate the distance between each power material warehouse and the power material procurement unit for the power material warehouses in the precision benefit warehouse concentration based on the geographical location of each power material warehouse and the geographical location of the power material procurement unit, and sort the distances from small to large to obtain a first sorting number for each power material warehouse; sort the sum of the storage ages of all power materials in the inventory data form of each power material warehouse from small to large to obtain a second sorting number for each power material warehouse; A profit-making decision generation module, configured to obtain a precise profit coefficient of the power material warehouse based on a weighted sum of a first ranking number and a second ranking number of each power material warehouse in the precise profit warehouse set; The electric power material warehouse with the largest precision profit coefficient is taken as the target electric power material warehouse to provide electric power materials to the electric power material purchasing unit.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating a benefit inventory decision for material procurement needs according to any one of claims 1 to 8 are implemented.

Images