Method for procurement source searching, electronic equipment, storage medium and program product

Abstract

The invention relates to the technical field of procurement source searching, in particular to a method for procurement source searching, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring a plurality of purchasing dimensions, a purchasing demand, a plurality of first to-be-selected suppliers and related data of each first to-be-selected supplier; determining a target weight corresponding to each purchasing dimension according to the related data of each first supplier to be selected; adding the target weight corresponding to each purchasing dimension as a constraint condition to a preset supplier selection model to obtain a target supplier selection model; corresponding purchasing characteristics in the purchasing demands are extracted; inputting the purchase features into a target supplier selection model, so as to determine a plurality of second to-be-selected suppliers through the target supplier selection model; acquiring state information of each second supplier to be selected; and converting each second to-be-selected supplier and the state information of each second to-be-selected supplier into a text format to obtain to-be-selected supplier options, and outputting the to-be-selected supplier options.

Description

Technical Field

[0001] The present application relates to the technical field of procurement and sourcing, and in particular to a method, electronic device, storage medium and computer program product for procurement and sourcing. Background Art

[0002] The traditional procurement sourcing process usually takes a lot of time and manpower. Business personnel obtain a list of suppliers based on procurement sourcing needs through industry knowledge, market research, supplier databases, or reference to other companies' experience, screen potential suppliers, and then manually evaluate the supplier's qualifications, experience, reputation, financial status, etc. by checking the supplier's official website, industry certification agency rating reports, and reference to the supplier's customer evaluations. Then, they contact the supplier by phone, email, or interview to understand its products, prices, delivery capabilities, after-sales service, etc., and further verify the supplier's reliability and adaptability, and make a quotation request to the potential supplier, negotiate with it on price and contract terms to obtain the most favorable procurement conditions, and finally make the final supplier selection decision based on comprehensive considerations such as supplier evaluation, quotation, and contract terms. Sourcing through business personnel has the disadvantages of large time consumption, incomplete information acquisition, subjectivity and bias, and low information processing efficiency. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, electronic device, storage medium and computer program product for procurement sourcing that replaces manual sourcing.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a method for sourcing, the method comprising:

[0005] Obtain multiple procurement dimensions, procurement requirements, multiple first-choice suppliers, and relevant data of each first-choice supplier. The supplier's relevant data includes enterprise ERP data and enterprise market data;

[0006] Determine the target weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier;

[0007] Add the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain a target supplier selection model;

[0008] Extract corresponding procurement features in procurement requirements based on multiple procurement dimensions;

[0009] Inputting the procurement characteristics into the target supplier selection model to determine a plurality of second candidate suppliers from a plurality of first candidate suppliers through the target supplier selection model;

[0010] Obtaining status information of each second candidate supplier, wherein the status information includes basic information and operating conditions of the supplier;

[0011] Each second supplier to be selected and the status information of each second supplier to be selected are converted into a text format to obtain supplier options to be selected and output.

[0012] In an embodiment of the present application, determining the target weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier; obtaining the first enterprise weight and the first user weight corresponding to each procurement dimension; obtaining the factor weight corresponding to each factor, wherein the factors include market, enterprise and user; determining the target weight of each procurement dimension based on each factor weight and the first market weight, the first enterprise weight and the first user weight of each procurement dimension.

[0013] In an embodiment of the present application, determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: for each procurement dimension, identifying the dimension term text related to the procurement dimension in the relevant data of all first candidate suppliers; for each procurement dimension, determining the proportion of the dimension term text related to the procurement dimension in all the dimension term texts corresponding to all the procurement dimensions, and determining the proportion as the first market weight of the procurement dimension.

[0014] In an embodiment of the present application, the method includes: before adding the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain the target supplier selection model, obtaining a preset number of historical procurement demands and the historical suppliers corresponding to each historical procurement demand; for each historical procurement demand, extracting at least one historical procurement feature corresponding to the historical procurement demand according to multiple procurement dimensions; for each historical procurement demand, determining the historical procurement dimension corresponding to each historical procurement feature of the historical procurement demand; for each historical procurement feature, determining the target weight corresponding to the historical procurement dimension corresponding to the historical procurement feature as the feature weight corresponding to the historical procurement feature; for each historical procurement demand, using each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature as input values, and the historical supplier corresponding to the historical procurement demand as the output value to train the preset supplier selection model to be trained; when the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy, determining that the training of the preset supplier selection model to be trained is completed.

[0015] In an embodiment of the present application, for each historical procurement demand, each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature are used as input values, and the historical suppliers corresponding to the historical procurement demand are used as output values ​​to train the preset supplier selection model to be trained, including: for a first preset proportion of historical procurement demands in a preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as training input values, and the historical suppliers corresponding to the first preset proportion of historical procurement demands are used as training output values ​​to train the preset supplier selection model to be trained; when the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy, for a second preset proportion of historical procurement demands in the preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as test input values, and the historical suppliers corresponding to the second preset proportion of historical procurement demands are used as test output values ​​to test the preset supplier selection model to be trained; when the test accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy.

[0016] In an embodiment of the present application, the method also includes: after converting each second supplier to be selected and the status information of each second supplier to be selected into a text format to obtain and output the supplier options to be selected, determining the target supplier corresponding to the procurement demand among the multiple suppliers to be selected according to the received selection instructions for the supplier options to be selected; and iteratively optimizing the preset supplier selection model through the target supplier.

[0017] In an embodiment of the present application, extracting corresponding procurement features in procurement requirements based on multiple procurement dimensions includes: for each procurement dimension, identifying text data related to the procurement dimension in the procurement requirements, determining the dimensional features corresponding to the procurement dimension based on the text data, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements; for each procurement dimension, when text data related to the procurement dimension in the procurement requirements is identified, but the dimensional features corresponding to the procurement dimension cannot be determined based on the text data, outputting an inquiry text for the dimensional features of the procurement dimension; when a reply text to the inquiry text is received, identifying the reply text to determine the dimensional features of the procurement dimension corresponding to the inquiry text, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements.

[0018] A second aspect of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0019] Memory stores computer-executable instructions;

[0020] The processor executes the computer-executable instructions stored in the memory to implement the method for procurement sourcing as described in any one of the above embodiments.

[0021] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute a method for procurement and sourcing according to any one of the above-mentioned embodiments.

[0022] A fourth aspect of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for procurement and sourcing according to any one of the above embodiments.

[0023] Through the above technical solution, the procurement dimensions, procurement requirements and multiple first candidates for selection in the same technical field as the procurement requirements are obtained. The processor can also obtain the relevant data of each first candidate for selection. The processor can determine the target weight corresponding to each procurement dimension through the relevant data of each first candidate for selection. The target weight is added as a constraint to the preset supplier selection model to obtain the target supplier selection model, and the procurement characteristics corresponding to the procurement requirements are obtained by identifying the procurement requirements. The procurement characteristics are input into the target supplier selection model to which the weight constraint has been added to output the corresponding second candidate for selection, which helps users quickly select suppliers that meet the procurement requirements from a large number of candidates for selection, and by determining the weight of each procurement dimension, the selected suppliers can be evaluated more comprehensively to improve the accuracy of supplier selection.

[0024] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0026] Figure 1 A schematic diagram of a process flow of a method for sourcing according to an embodiment of the present application is shown;

[0027] Figure 2 A structural block diagram of an electronic device according to an embodiment of the present application is schematically shown;

[0028] Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0030] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0031] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0032] Figure 1 The following schematically shows a flow chart of a method for sourcing according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for procurement sourcing, which may include the following steps.

[0033] Step 101: Acquire multiple procurement dimensions, procurement requirements, multiple first candidate suppliers, and relevant data of each first candidate supplier, wherein the supplier-related data includes enterprise ERP data and enterprise market data;

[0034] Step 102: Determine the target weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier;

[0035] Step 103: Add the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain a target supplier selection model;

[0036] Step 104: extracting corresponding procurement features in the procurement requirements according to multiple procurement dimensions;

[0037] Step 105: input the procurement characteristics into the target supplier selection model to determine a plurality of second candidate suppliers from a plurality of first candidate suppliers through the target supplier selection model;

[0038] Step 106: Obtain status information of each second candidate supplier, wherein the status information includes basic information and operating conditions of the supplier;

[0039] Step 107: Convert each second supplier to be selected and the status information of each second supplier to be selected into a text format to obtain supplier options to be selected and output them.

[0040] The processor can obtain multiple procurement dimensions pre-configured when conducting procurement sourcing, the procurement requirements input by the user, multiple first selected suppliers related to the field corresponding to the procurement requirements, and the relevant data of each first selected supplier. The first selected supplier can be a supplier in the same field as the procurement requirements, and the relevant data of the supplier can include the enterprise ERP data and enterprise market data corresponding to the supplier. The processor can determine the target weight corresponding to each procurement dimension on the procurement requirements based on the relevant data of each first selected supplier. The processor can obtain a preset supplier selection model, and after the processor determines the target weight of each procurement dimension, the target weight corresponding to the procurement dimension can be added as a constraint to the preset supplier model to obtain the target supplier model. The processor can identify the corresponding procurement features in the procurement requirements according to multiple procurement dimensions. For example, assuming that the procurement dimensions include ten dimensions of price, quality, delivery, service, safety and environment, region, production capacity, evaluation, scale, and risk, the processor can identify the procurement requirements to determine the procurement features corresponding to the procurement requirements. For example, after identifying the procurement requirements according to the procurement dimensions, the processor can determine that the procurement features corresponding to the procurement requirements are high price, high quality, and good service. After the processor extracts the procurement features corresponding to the procurement requirements, the procurement features can be input into the target supplier selection model. Since the target supplier adds the target weight corresponding to each procurement dimension as a constraint condition, after the processor inputs the procurement features into the target supplier selection model, the target supplier selection model can use the target weight of the procurement dimension corresponding to the procurement features as the feature weight of the procurement features, and under the constraint of the feature weight, the target supplier selection model can output multiple second candidates according to the received procurement features, wherein the second candidates are determined from multiple first candidates. The processor can obtain the status information of each second candidate, which may include the basic information and operating conditions of the supplier. The processor can convert the status information of each second candidate and the second candidate into a text format, thereby obtaining the candidate supplier options corresponding to the procurement requirements, and output the candidate supplier options corresponding to the procurement requirements. For example, assuming that the method for procurement sourcing is applied to an interactive device, the interactive device includes an interactive interface, and the processor can output the generated candidate supplier options corresponding to the procurement requirements through the interactive interface.

[0041] In one embodiment, determining the target weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier; obtaining the first enterprise weight and the first user weight corresponding to each procurement dimension; obtaining the factor weight corresponding to each factor, wherein the factors include market, enterprise and user; determining the target weight of each procurement dimension based on each factor weight and the first market weight, the first enterprise weight and the first user weight of each procurement dimension.

[0042] The processor can determine the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier. The processor can also obtain the first enterprise weight and the first user weight corresponding to each procurement dimension based on the input configuration data or the preset configuration data. For example, the processor can determine that the first enterprise weight for the price procurement dimension is a1%, the first enterprise weight for the quality procurement dimension is a2%, etc. by obtaining the enterprise configuration. The processor can determine that the first user weight for the price procurement dimension is b1%, the first user weight for the quality procurement dimension is b2%, etc. by obtaining the user attention configuration. The processor can also obtain the factor weight corresponding to each factor through the input configuration data or the preset configuration data, wherein the factors include the market, the enterprise, and the user. That is to say, for example, after the first enterprise weight for each procurement dimension is determined through the enterprise configuration, the processor can obtain the factor weight of this factor for this configuration factor of the enterprise. For each dimension, the processor can determine the target weight of each procurement dimension based on the factor weight of each factor and the first market weight, first enterprise weight and first user weight of each procurement dimension. For example, assuming that the first market weight for the price procurement dimension is c1%, the first market weight for the quality procurement dimension is c2%, the factor weight for the enterprise factor is A%, the factor weight for the user factor is B%, and the factor weight for the market factor is C%, then the processor can determine the target weight for the price procurement dimension as a1%×A%+b1%×B%+c1%×C%. Similarly, the target weight for the quality procurement dimension can be a2%×A%+b2%×B%+c2%×C%, so as to determine the target weight for each procurement dimension.

[0043] In one embodiment, determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: for each procurement dimension, identifying the dimension term text related to the procurement dimension in the relevant data of all first candidate suppliers; for each procurement dimension, determining the proportion of the dimension term text related to the procurement dimension in all the dimension term texts corresponding to all the procurement dimensions, and determining the proportion as the first market weight of the procurement dimension.

[0044] The processor can obtain relevant data of multiple first candidate suppliers. The first candidate suppliers can be suppliers in the same field as the procurement demand. The relevant data of the supplier can include the enterprise ERP data of the supplier, such as basic information of the supplier, historical procurement information, historical godfather information, supplier performance information and supplier contract information, etc., and enterprise market data, such as industry reports, annual reports, enterprise registration information, enterprise website information and social media information, etc. The processor can obtain the relevant data of each first candidate supplier through the enterprise ERP system or the market public data source. For each procurement dimension, the processor can identify the dimension entry text related to the procurement dimension in the relevant data of all first candidate suppliers. For example, the processor can retrieve and identify the dimension entry text related to the procurement dimension in the relevant data through vector indexing, web crawlers, etc., and the dimension entry text related to the procurement dimension can be a word with similar attributes to the noun corresponding to the procurement dimension. For example, assuming that the procurement dimension is price, the dimension entry text related to the procurement dimension can include: cost, holiday collection, investment, expense, etc., assuming that the procurement dimension is capacity, the dimension entry text related to the procurement dimension can include: capacity, output, productivity, production efficiency, etc. After determining the dimension term text of each purchasing dimension, the processor can determine the proportion of the dimension term text related to each purchasing dimension in the total dimension term text corresponding to all purchasing dimensions for each purchasing dimension, and determine the proportion of each purchasing dimension as the first market weight of each purchasing dimension. For example, as shown in Table 1: Assuming that the first line is the purchasing dimension, for each dimension, the processor can determine the commonly used terms corresponding to the dimension, that is, the dimension term text related to the purchasing dimension, and determine the market heat of the dimension through the proportion of commonly used terms. For example, as shown in Table 1, the market heat corresponding to the dimension price is c1%, and the processor can determine the market heat c1% of the dimension as the first market weight corresponding to the dimension.

[0045] Table 1

[0046]

[0047] In one embodiment, before adding the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain the target supplier selection model, a preset number of historical procurement demands and the historical suppliers corresponding to each historical procurement demand are obtained; for each historical procurement demand, at least one historical procurement feature corresponding to the historical procurement demand is extracted according to multiple procurement dimensions; for each historical procurement demand, the historical procurement dimension corresponding to each historical procurement feature of the historical procurement demand is determined; for each historical procurement feature, the target weight corresponding to the historical procurement dimension corresponding to the historical procurement feature is determined as the feature weight corresponding to the historical procurement feature; for each historical procurement demand, each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature are used as input values, and the historical suppliers corresponding to the historical procurement demand are used as output values ​​to train the preset supplier selection model to be trained; when the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the training of the preset supplier selection model to be trained is completed.

[0048] In one embodiment, for each historical procurement demand, each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature are used as input values, and the historical suppliers corresponding to the historical procurement demand are used as output values ​​to train the preset supplier selection model to be trained, including: for a first preset proportion of historical procurement demands in a preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as training input values, and the historical suppliers corresponding to the first preset proportion of historical procurement demands are used as training output values ​​to train the preset supplier selection model to be trained; when the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy, for a second preset proportion of historical procurement demands in the preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as test input values, and the historical suppliers corresponding to the second preset proportion of historical procurement demands are used as test output values ​​to test the preset supplier selection model to be trained; when the test accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy.

[0049] Before the processor adds the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain the target supplier selection model, the processor may obtain a preset number of historical procurement requirements and the historical suppliers corresponding to each historical procurement requirement. For each historical procurement requirement, the processor may extract at least one historical procurement feature corresponding to each historical procurement requirement based on multiple procurement dimensions. For each historical procurement requirement, the processor may determine the historical procurement dimension corresponding to each historical procurement feature of the historical procurement requirement, and for each historical procurement feature, the processor may determine the target weight corresponding to the historical procurement dimension corresponding to the historical procurement feature as the feature weight corresponding to the historical procurement feature. For each historical procurement requirement, the processor may use each historical procurement feature of the historical procurement requirement and the feature weight corresponding to each historical procurement feature as input values, and use the historical supplier corresponding to the historical procurement requirement as an output value to train the preset supplier selection model to be trained. The processor may divide a preset number of historical procurement demands to obtain a first preset ratio of historical procurement demands and a second preset ratio of historical procurement demands. For the first preset ratio of historical procurement demands in the preset number, each historical procurement feature corresponding to each historical procurement demand and a feature weight corresponding to each historical procurement feature are used as training input values, and the historical suppliers corresponding to the first preset ratio of historical procurement demands are used as training output values ​​to train the preset supplier selection model to be trained. Specifically, the processor may input each historical procurement feature corresponding to each historical procurement demand and a feature weight corresponding to each historical procurement feature into the preset supplier selection model to be trained. The preset supplier selection model may be a neural network model established by a neural network algorithm. The corresponding supplier is output by the preset supplier selection model to be trained. The parameters in the preset supplier selection model to be trained are adjusted so that the preset supplier selection model to be trained is Assume that the overlap between the suppliers output by the supplier selection model and the historical suppliers corresponding to the first preset proportion of historical procurement demands reaches the preset overlap, that is, the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy. When the processor determines that the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy, each historical procurement feature corresponding to each historical procurement demand in the second preset proportion of historical procurement demands in the preset quantity, and the feature weight corresponding to each historical procurement feature can be used as a test input value, and the historical suppliers corresponding to the second preset proportion of historical procurement demands are used as test output values ​​to test the preset supplier selection model to be trained. When the test accuracy of the preset supplier selection model to be trained reaches the preset accuracy, the processor can determine that the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy. At this time, the processor can determine that the training of the preset supplier selection model to be trained is completed.

[0050] In one embodiment, the method also includes: after converting each second supplier to be selected and the status information of each second supplier to be selected into a text format to obtain and output the supplier options to be selected, determining the target supplier corresponding to the procurement demand among the multiple suppliers to be selected according to the received selection instructions for the supplier options to be selected; and iteratively optimizing the preset supplier selection model through the target supplier.

[0051] The processor selects multiple second suppliers to be selected through the target supplier selection model, and converts each second supplier to be selected and the status information of each second supplier to be selected into text format to obtain and output the supplier options to be selected. Then, according to the selection instructions received for the supplier options to be selected, the processor can determine the selected supplier option according to the selection instructions, and determine the selected supplier option as the target supplier corresponding to the procurement demand. After determining the target supplier corresponding to the procurement demand, the processor can use the target supplier that already corresponds to the current procurement demand as sample data to iteratively optimize the preset supplier selection model, so as to continuously tune and train the preset supplier selection model.

[0052] In one embodiment, extracting corresponding procurement features in procurement requirements based on multiple procurement dimensions includes: for each procurement dimension, identifying text data related to the procurement dimension in the procurement requirements, determining the dimensional features corresponding to the procurement dimension based on the text data, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements; for each procurement dimension, when text data related to the procurement dimension in the procurement requirements is identified, but the dimensional features corresponding to the procurement dimension cannot be determined based on the text data, outputting an inquiry text for the dimensional features of the procurement dimension; when a reply text to the inquiry text is received, identifying the reply text to determine the dimensional features of the procurement dimension corresponding to the inquiry text, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements.

[0053] When the processor identifies the purchasing features corresponding to the purchasing requirements according to multiple purchasing dimensions, the processor can identify the text data related to the purchasing dimension in the purchasing requirements for each purchasing dimension. For example, the processor can identify the purchasing requirements based on a large language model, an AIGC model, or other models with text recognition functions to determine the text data related to the purchasing dimensions, and determine the dimensional features corresponding to the purchasing dimensions included in the text data based on the text data. After determining the purchasing dimensions and the corresponding dimensional features included in the purchasing requirements, the processor can determine the purchasing dimensions and the dimensional features of the purchasing dimensions as the purchasing features corresponding to the purchasing requirements. For example, assuming that the processor identifies the text data related to the purchasing dimensions in the purchasing requirements as "the price of the item is high", the purchasing dimension corresponding to the text data is "price", and the dimensional feature corresponding to the purchasing dimension is "high". The processor can use the purchasing dimension "price" and the dimensional feature "high" as the purchasing features corresponding to the purchasing requirements. For example, the purchasing feature can be "high price". For each procurement dimension, when the processor recognizes text data related to the procurement dimension in the procurement demand, but cannot determine the dimensional feature corresponding to the procurement dimension included in the text data according to the text data, the processor can output an inquiry text for the dimensional feature of the procurement dimension. For example, assuming that the processor recognizes that the text data related to the procurement dimension is "item price", the procurement dimension corresponding to the text data is "price", but the current processor cannot determine the feature of the procurement dimension "price" according to the text data. At this time, the processor can generate an inquiry text for the dimensional feature. For example, the processor can generate an inquiry text of "What conditions must the item price meet?" When the processor receives a reply text for the inquiry text, the reply text can be identified in the same way to determine the dimensional feature of the procurement dimension corresponding to the inquiry text. For example, assuming that the reply text received by the processor is "high price", the processor can determine that the dimensional feature of the procurement dimension "price" corresponding to the inquiry text is "high" by identifying the reply text. The procurement dimension and the dimensional feature determined by the reply text are determined as the procurement feature corresponding to the procurement demand.

[0054] In one embodiment, Figure 2 As shown, an electronic device 200 is provided, including: a processor 201, and a memory 202 communicatively connected to the processor 201; the memory 202 stores computer execution instructions; the processor 201 executes the computer execution instructions stored in the memory 202 to implement a method for procurement and sourcing as in any one of the above embodiments.

[0055] In the above technical solution, the procurement dimension, procurement demand and multiple first selected suppliers in the same technical field as the procurement demand are obtained, and the processor can also obtain the relevant data of each first selected supplier. The processor can determine the target weight corresponding to each procurement dimension through the relevant data of each first selected supplier. The processor can train the preset supplier selection model through a preset number of historical procurement demands and historical suppliers corresponding to the historical procurement demands, and add the target weight corresponding to each procurement dimension as a constraint condition to the trained preset supplier selection model to obtain the target supplier selection model, and then obtain the procurement characteristics corresponding to the procurement requirements by identifying the procurement requirements, and input the procurement characteristics into the target supplier selection model to which the weight constraint condition has been added, and determine the multiple second selected suppliers corresponding to the procurement characteristics through the target supplier selection model. The user can select the final target supplier corresponding to the procurement demand from the multiple second selected suppliers selected by the target supplier selection model through the selection instruction. Through the target supplier selection model, it helps users quickly select suppliers that meet the procurement requirements from a large number of selected suppliers, and by determining the weight of each procurement dimension, it can more comprehensively evaluate the selected suppliers to improve the accuracy of supplier selection.

[0056] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0057] In one embodiment, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute a method for procurement sourcing according to any one of the above embodiments.

[0058] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for procurement sourcing according to any one of the above embodiments.

[0059] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store procurement dimensions and relevant data of suppliers. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for procurement sourcing is implemented.

[0060] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining multiple procurement dimensions, procurement requirements, multiple first candidate suppliers, and relevant data of each first candidate supplier, wherein the supplier's relevant data includes enterprise ERP data and enterprise market data; determining the target weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier; adding the target weight corresponding to each procurement dimension as a constraint condition to a preset supplier selection model to obtain a target supplier selection model; extracting corresponding procurement features in the procurement requirements according to the multiple procurement dimensions; inputting the procurement features into the target supplier selection model to determine multiple second candidate suppliers among the multiple first candidate suppliers through the target supplier selection model; obtaining status information of each second candidate supplier, wherein the status information includes basic information and operating conditions of the supplier; converting each second candidate supplier and the status information of each second candidate supplier into text format to obtain candidate supplier options and output them.

[0061] In one embodiment, determining the target weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier; obtaining the first enterprise weight and the first user weight corresponding to each procurement dimension; obtaining the factor weight corresponding to each factor, wherein the factors include market, enterprise and user; determining the target weight of each procurement dimension based on each factor weight and the first market weight, the first enterprise weight and the first user weight of each procurement dimension.

[0062] In one embodiment, determining the first market weight corresponding to each procurement dimension based on the relevant data of each first candidate supplier includes: for each procurement dimension, identifying the dimension term text related to the procurement dimension in the relevant data of all first candidate suppliers; for each procurement dimension, determining the proportion of the dimension term text related to the procurement dimension in all the dimension term texts corresponding to all the procurement dimensions, and determining the proportion as the first market weight of the procurement dimension.

[0063] In one embodiment, the method includes: before adding the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain the target supplier selection model, obtaining a preset number of historical procurement demands and the historical suppliers corresponding to each historical procurement demand; for each historical procurement demand, extracting at least one historical procurement feature corresponding to the historical procurement demand according to multiple procurement dimensions; for each historical procurement demand, determining the historical procurement dimension corresponding to each historical procurement feature of the historical procurement demand; for each historical procurement feature, determining the target weight corresponding to the historical procurement dimension corresponding to the historical procurement feature as the feature weight corresponding to the historical procurement feature; for each historical procurement demand, using each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature as input values, and the historical suppliers corresponding to the historical procurement demand as output values ​​to train the preset supplier selection model to be trained; when the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy, determining that the training of the preset supplier selection model to be trained is completed.

[0064] In one embodiment, for each historical procurement demand, each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature are used as input values, and the historical suppliers corresponding to the historical procurement demand are used as output values ​​to train the preset supplier selection model to be trained, including: for a first preset proportion of historical procurement demands in a preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as training input values, and the historical suppliers corresponding to the first preset proportion of historical procurement demands are used as training output values ​​to train the preset supplier selection model to be trained; when the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy, for a second preset proportion of historical procurement demands in the preset number, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as test input values, and the historical suppliers corresponding to the second preset proportion of historical procurement demands are used as test output values ​​to test the preset supplier selection model to be trained; when the test accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy.

[0065] In one embodiment, the method also includes: after converting each second supplier to be selected and the status information of each second supplier to be selected into a text format to obtain and output the supplier options to be selected, determining the target supplier corresponding to the procurement demand among the multiple suppliers to be selected according to the received selection instructions for the supplier options to be selected; and iteratively optimizing the preset supplier selection model through the target supplier.

[0066] In one embodiment, extracting corresponding procurement features in procurement requirements based on multiple procurement dimensions includes: for each procurement dimension, identifying text data related to the procurement dimension in the procurement requirements, determining the dimensional features corresponding to the procurement dimension based on the text data, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements; for each procurement dimension, when text data related to the procurement dimension in the procurement requirements is identified, but the dimensional features corresponding to the procurement dimension cannot be determined based on the text data, outputting an inquiry text for the dimensional features of the procurement dimension; when a reply text to the inquiry text is received, identifying the reply text to determine the dimensional features of the procurement dimension corresponding to the inquiry text, and determining the procurement dimension and the dimensional features of the procurement dimension as procurement features corresponding to the procurement requirements.

[0067] 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 in combination with 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.) that contain computer-usable program code.

[0068] 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.

[0069] 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.

[0070] 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 The steps for the functions specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0073] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0075] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for sourcing, characterized in that: The method comprises: Acquire multiple procurement dimensions, procurement requirements, multiple first candidate suppliers, and relevant data of each first candidate supplier, wherein the supplier-related data includes enterprise ERP data and enterprise market data; Determine the target weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier; Add the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain a target supplier selection model; Extracting corresponding procurement features in the procurement requirements according to the multiple procurement dimensions; Inputting the procurement characteristics into a target supplier selection model to determine a plurality of second candidate suppliers from a plurality of first candidate suppliers through the target supplier selection model; Acquire status information of each second supplier to be selected, wherein the status information includes basic information and operating conditions of the supplier; Each of the second suppliers to be selected and the status information of each of the second suppliers to be selected are converted into a text format to obtain supplier options to be selected and output.

2. The method for sourcing according to claim 1, characterized in that: Determining the target weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier includes: Determine a first market weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier; Obtain the first enterprise weight and the first user weight corresponding to each procurement dimension; Obtain the factor weight corresponding to each factor, where the factors include market, enterprise, and user; The target weight of each procurement dimension is determined according to each factor weight and the first market weight, the first enterprise weight and the first user weight of each procurement dimension.

3. The method for sourcing according to claim 2, characterized in that: Determining the first market weight corresponding to each procurement dimension according to the relevant data of each first candidate supplier includes: For each procurement dimension, identifying dimension term texts related to the procurement dimension in the relevant data of all first candidate suppliers; For each procurement dimension, the proportion of the dimensional term text related to the procurement dimension in all the dimensional term texts corresponding to all the procurement dimensions is determined, and the proportion is determined as the first market weight of the procurement dimension.

4. The method for sourcing according to claim 1, characterized in that: The method comprises: Before adding the target weight corresponding to each procurement dimension as a constraint condition to the preset supplier selection model to obtain the target supplier selection model, obtaining a preset number of historical procurement demands and a historical supplier corresponding to each historical procurement demand; For each historical procurement demand, extracting at least one historical procurement feature corresponding to the historical procurement demand according to the multiple procurement dimensions; For each historical procurement demand, determining a historical procurement dimension corresponding to each historical procurement feature of the historical procurement demand; For each historical purchase feature, determining the target weight corresponding to the historical purchase dimension corresponding to the historical purchase feature as the feature weight corresponding to the historical purchase feature; For each historical procurement demand, each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature are used as input values, and the historical suppliers corresponding to the historical procurement demand are used as output values ​​to train the preset supplier selection model to be trained; When the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the training of the preset supplier selection model to be trained is completed.

5. The method for sourcing according to claim 4, characterized in that: The step of training the preset supplier selection model to be trained by taking each historical procurement feature of the historical procurement demand and the feature weight corresponding to each historical procurement feature as input values ​​and the historical supplier corresponding to the historical procurement demand as output values ​​for each historical procurement demand includes: For a first preset proportion of the historical procurement demands in the preset quantity, each historical procurement feature corresponding to each historical procurement demand and a feature weight corresponding to each historical procurement feature are used as training input values, and the historical suppliers corresponding to the first preset proportion of the historical procurement demands are used as training output values ​​to train the preset supplier selection model to be trained; When the training accuracy of the preset supplier selection model to be trained reaches the preset accuracy, for the historical procurement demands of the second preset proportion in the preset quantity, each historical procurement feature corresponding to each historical procurement demand and the feature weight corresponding to each historical procurement feature are used as test input values, and the historical suppliers corresponding to the historical procurement demands of the second preset proportion are used as test output values ​​to test the preset supplier selection model to be trained; When the test accuracy of the preset supplier selection model to be trained reaches the preset accuracy, it is determined that the selection accuracy of the preset supplier selection model to be trained reaches the preset accuracy.

6. The method for sourcing according to claim 1, characterized in that: The method further comprises: After converting each of the second suppliers to be selected and the status information of each of the second suppliers to be selected into a text format to obtain and output supplier options to be selected, determining a target supplier corresponding to the procurement demand among the multiple suppliers to be selected according to the received selection instruction for the supplier options to be selected; The preset supplier selection model is iteratively optimized through the target supplier.

7. The method for sourcing according to claim 1, characterized in that: The extracting corresponding procurement features in the procurement requirements according to the multiple procurement dimensions includes: For each procurement dimension, identifying text data related to the procurement dimension in the procurement requirement, determining a dimensional feature corresponding to the procurement dimension according to the text data, and determining the procurement dimension and the dimensional feature of the procurement dimension as the procurement feature corresponding to the procurement requirement; For each procurement dimension, when text data related to the procurement dimension in the procurement requirement is identified but the dimensional feature corresponding to the procurement dimension cannot be determined based on the text data, outputting a query text for the dimensional feature of the procurement dimension; When a reply text is received to the inquiry text, the reply text is identified to determine the dimensional characteristics of the procurement dimension corresponding to the inquiry text, and the procurement dimension and the dimensional characteristics of the procurement dimension are determined as procurement characteristics corresponding to the procurement demand.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for procurement sourcing according to any one of claims 1 to 7.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for sourcing according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for sourcing according to any one of claims 1 to 7.

Images