A procurement supply chain decision-making assistance method and system based on artificial intelligence

Abstract

The present invention provides a procurement supply chain decision-making assistance method and system based on artificial intelligence. The method obtains procurement requirements and bids provided by various suppliers, compares the procurement requirements with the matching data in the bids provided by various suppliers, and determines the first supplier. The method collects internal data, external data, and evaluation grade data of the first suppliers that have cooperated, as well as the external data of the first suppliers that have not cooperated. The internal data is the data generated during the transaction process, and the external data is public data. The internal data at least includes the communication data between the user and the supplier. The method determines the evaluation grade of the supplier based on the acquired data corresponding to each first supplier, and pushes the evaluation grade to the user, which can assist the user in making procurement supply chain decisions so that the decision results meet the user's needs.

Description

Technical Field

[0001] The present invention belongs to the technical field of procurement supply chain decision-making assistance, and in particular relates to a procurement supply chain decision-making assistance method and system based on artificial intelligence. Background Art

[0002] Supplier selection is a crucial step in procurement supply chain decision-making. Potential suppliers must be evaluated across multiple dimensions, including product quality, price, delivery capabilities, after-sales service, and reputation. By comprehensively considering these factors, the supplier that best suits your company's needs is selected to ensure a stable supply and a positive partnership.

[0003] Currently, decision-making is mainly done through organizational reviews, where suppliers with higher cost-performance are identified through experience. However, this method is relatively subjective and may not actually achieve the intended results. Summary of the Invention

[0004] Based on this, an embodiment of the present invention provides an artificial intelligence-based procurement supply chain decision-making assistance method and system, which aims to assist users in making procurement supply chain decisions so that the decision results meet user needs.

[0005] A first aspect of an embodiment of the present invention provides an artificial intelligence-based procurement supply chain decision-making assistance method, the method comprising:

[0006] Obtain the purchase requirements and the bids provided by each supplier, compare the purchase requirements with the matching data in the bids provided by each supplier, and determine the top supplier;

[0007] Collecting internal data, external data, and evaluation rating data of the first supplier with which the user has cooperated, and external data of the first supplier with which the user has not cooperated, wherein the internal data is data generated during the transaction process, and the external data is public data, wherein the internal data at least includes communication data between the user and the supplier;

[0008] Based on the acquired data corresponding to each first supplier, an evaluation grade of the supplier is determined, and the evaluation grade is pushed to the user.

[0009] Furthermore, the step of collecting the internal data, external data, and evaluation grade data of the first suppliers with which the cooperation has been established, and the external data of the first suppliers without which the cooperation has been established, further includes:

[0010] Evaluate the consistency of the first-party supplier's internal and external data, including evaluation of data matching, consistency based on time series, and consistency based on logical relationships;

[0011] Adjust the supplier's assessment level based on the consistency assessment results.

[0012] Furthermore, in the step of adjusting the supplier's evaluation level based on the consistency evaluation result, when the consistency evaluation result meets the requirements, the supplier's evaluation level is maintained; when the consistency evaluation result does not meet the requirements, the supplier's evaluation level is downgraded.

[0013] Furthermore, in the step of evaluating the consistency between the internal data and external data of the first supplier with whom we have cooperated,

[0014] Data matching includes key information matching and transaction data matching. The key information matching includes the matching of supplier basic information and product information. The transaction data matching includes the matching of order data and price data.

[0015] Time series-based consistency includes data update frequency consistency and historical data time series consistency;

[0016] Consistency based on logical relationships includes causal consistency and data association consistency.

[0017] Furthermore, the communication data includes at least email data, instant messaging data and meeting minutes data. The email data, instant messaging data and meeting minutes data are analyzed using natural language processing technology, and the communication heat is calculated based on the analysis results. The communication heat is used to determine the supplier's evaluation level.

[0018] Furthermore, the step of analyzing the email data, the instant messaging data, and the meeting minutes data using natural language processing technology and calculating the communication heat according to the analysis results includes:

[0019] Analyzing the email data, the instant messaging data, and the meeting minutes data using natural language processing technology to determine the frequency of communication within a preset time period;

[0020] Determining whether the communication frequency is greater than a preset frequency;

[0021] If it is determined that the communication frequency is greater than the preset frequency, the content belonging to the same communication topic in the email data, the instant messaging data, and the meeting minutes data is extracted, and the sentiment analysis algorithm in the natural language processing technology is used to analyze the sentiment tendency of the content of the same communication topic;

[0022] Construct a communication heat calculation model based on the importance of the communication topic and the emotional tendency in the content of the same communication topic;

[0023] The communication heat is determined according to the communication heat calculation model.

[0024] Furthermore, in the step of determining the evaluation level of the supplier based on the data corresponding to each first supplier obtained, the internal data, external data and evaluation level data corresponding to each first supplier are input into the trained random forest model, and the evaluation level is output, wherein the internal data and evaluation level data of the non-cooperative first supplier are used as the benchmark value.

[0025] A second aspect of an embodiment of the present invention provides an artificial intelligence-based procurement supply chain decision-making support system, which is used to implement the artificial intelligence-based procurement supply chain decision-making support method described in the first aspect. The system includes:

[0026] The comparison module is used to obtain the purchase requirements and the bids provided by each supplier, compare the purchase requirements with the matching data in the bids provided by each supplier, and determine the first supplier;

[0027] a collection module, configured to collect internal data, external data, and evaluation grade data of the first supplier with which the user has cooperated, and external data of the first supplier with which the user has not cooperated, wherein the internal data is data generated during the transaction process, and the external data is public data, wherein the internal data at least includes communication data between the user and the supplier;

[0028] The determination module is used to determine the evaluation level of the supplier based on the acquired data corresponding to each first supplier, and push the evaluation level to the user.

[0029] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based procurement supply chain decision-making assistance method provided in the first aspect.

[0030] The fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the artificial intelligence-based procurement supply chain decision-making assistance method provided in the first aspect is implemented.

[0031] An artificial intelligence-based procurement supply chain decision-making support method and system provided in an embodiment of the present invention obtains procurement requirements and bids provided by each supplier, compares the procurement requirements with the matching data in the bids provided by each supplier, and determines the first supplier; collects internal data, external data and evaluation grade data of the first supplier that has cooperated, and external data of the first supplier that has not cooperated, wherein the internal data is the data generated during the transaction process, and the external data is public data, wherein the internal data at least includes the communication data between the user and the supplier; determines the evaluation grade of the supplier based on the acquired data corresponding to each first supplier, and pushes the evaluation grade to the user, which can assist the user in making procurement supply chain decisions so that the decision results meet the user's needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a flowchart of an implementation method for assisting decision-making in a procurement supply chain based on artificial intelligence provided in the first embodiment of the present invention;

[0033] Figure 2 This is a structural block diagram of an artificial intelligence-based procurement supply chain decision support system provided in Example 2 of the present invention;

[0034] Figure 3 This is a structural block diagram of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0035] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0036] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0038] Example 1

[0039] According to an embodiment of the present invention, an embodiment of a procurement supply chain decision-making assistance method based on artificial intelligence is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In this embodiment, a procurement supply chain decision-making assistance method based on artificial intelligence is provided, which can be used in electronic devices, such as computers. Figure 1 , Figure 1 The flowchart of an implementation of an artificial intelligence-based procurement supply chain decision-making assistance method provided in the first embodiment of the present invention is shown, which specifically includes steps S01 to S03.

[0041] Step S01: Obtain procurement requirements and bids provided by various suppliers, compare the procurement requirements with matching data in the bids provided by various suppliers, and determine a first supplier.

[0042] It is understandable that the procurement requirements are proposed by Party A, and each supplier submits a corresponding bid based on the procurement requirements. The procurement requirements are compared with the matching data in the bids provided by each supplier to determine the first supplier that meets the requirements. Among them, the matching data can be found through OCR (Optical Character Recognition) technology and then compared.

[0043] Step S02, collecting the internal data, external data and evaluation grade data of the first supplier with which the user has cooperated, and the external data of the first supplier with which the user has not cooperated, wherein the internal data is the data generated during the transaction process, and the external data is the public data, wherein the internal data at least includes the communication data between the user and the supplier.

[0044] It should be noted that the first suppliers that meet the requirements may include suppliers that have been cooperated with and suppliers that have not been cooperated with. Users need to select suitable suppliers based on their own needs. They may continue to choose the original supplier because the previous cooperation was relatively smooth, or they may change suppliers because the previous cooperation was not pleasant. As for whether to choose the original supplier or change the supplier, the embodiment of the present invention evaluates it through data analysis rather than subjective selection.

[0045] Specifically, internal data refers to detailed data on past supplier transactions extracted from a company's procurement management system, including purchase order numbers, order dates, product names, quantities, prices, delivery dates, actual arrival dates, and acceptance results. By writing specialized database query scripts, this data is regularly extracted into a temporary storage area for preliminary data cleansing to remove duplicate records and obvious errors.

[0046] It is understood that when a supplier and an enterprise have collaborated, internal data may also include communication data, which includes at least email data, instant messaging data, and meeting minutes. Natural language processing techniques are used to analyze these email data, instant messaging data, and meeting minutes data, and the communication intensity is calculated based on the analysis results. This communication intensity is used to determine the supplier's evaluation level. For example, a data collection program is developed using the POP3 or IMAP protocol of the enterprise email system to regularly download email exchanges between the enterprise and the supplier. These emails are parsed to extract information such as the subject line, sender, recipient, send time, and email content, and stored in a dedicated email database. For communications using instant messaging tools (such as WeChat and QQ), screenshot recognition technology or third-party data collection services are used to regularly collect key communication records, with the authorization of both parties. Meeting minutes are stored electronically to facilitate the retrieval of communication records.

[0047] External data refers to information collected about suppliers using web crawlers from authoritative industry websites, commercial databases, and government open data platforms. For example, information such as company profiles, product awards, and market share can be captured from industry websites. Financial statements, including balance sheets, income statements, and cash flow statements, can be obtained from commercial databases to assess the supplier's financial health. Discussions and reviews about suppliers on social media platforms and professional forums are also monitored. Natural language processing-based text crawling tools are used to collect user feedback on supplier product quality, service attitude, and other aspects. Keywords and filtering rules are used to filter out irrelevant information, ensuring the relevance and validity of the collected data.

[0048] Since the supplier has been evaluated when the cooperation was first decided, the supplier's evaluation level can be adjusted by evaluating the consistency of the internal data and external data of the first supplier. When the evaluation is conducted again, the accuracy of the supplier's evaluation can be improved.

[0049] It should be noted that the consistency evaluation between internal data and external data includes the evaluation of data matching, consistency based on time series, and consistency based on logical relationships. Specifically, data matching includes key information matching and transaction data matching. The key information matching includes the matching of supplier basic information and product information. The transaction data matching includes order data matching and price data matching. More specifically, for key information matching, for example, for text information such as supplier name, address, contact information, etc., an edit distance algorithm (such as Levenshtein Distance) can be used to calculate consistency. Assume that the supplier address recorded internally is string A, and the address in the external data is string B. The Levenshtein distance d(A,B) represents the minimum number of single-character editing operations (insertion, deletion, replacement) required to convert character A to string B. The matching degree M can be defined as , where |A| and |B| are the lengths of strings A and B respectively. The closer the matching degree is to 1, the higher the consistency between the two.

[0050] For example, for information such as product models and specifications, if they are numerical or have clear coding rules, you can directly compare whether the numerical values or codes are consistent. For complex text descriptions, such as product technical parameter descriptions, you can first vectorize the text (such as using the word vector model Word2Vec) to convert the text into a vector in the vector space. and Then calculate the cosine similarity of the vectors To measure consistency.

[0051] For order data matching, for example, the internal purchase order number, order date, product name, and quantity information are constructed into a multi-tuple set I, and the externally acquired related transaction information is constructed into a set E. The consistency can be evaluated by calculating the Jaccard similarity of the two sets. Let the intersection of sets I and E be I∩E, and the union be I∪E. The Jaccard similarity is ,The higher the Jaccard similarity is, the better the order data consistency is.

[0052] For price data matching, for example, for internal procurement prices and the market price of similar products obtained from external sources , the price difference rate can be calculated If there are multiple price data points (such as the comparison of different batch purchase prices with different channel market prices), the average price difference rate can be calculated. , where n is the number of data points. The lower the average price difference rate, the higher the consistency of internal and external price data;

[0053] Time series consistency includes data update frequency consistency and historical data time series consistency. Specifically, for data update frequency consistency, let the number of updates of internal data in the time period [t1, t2] be n i , the number of updates of external data in the same time period is n e The update frequency difference rate can be calculated by To measure the consistency of update frequency, the lower the update frequency difference rate, the closer the update frequencies of the two are. For the key time node, let the internal data be at the key time node t k The state value is x ik , the state value of external data at the same time node is x ek If the status value is discrete (such as order status: not shipped, shipped, arrived), you can directly compare whether they are the same; if it is numerical (such as logistics transportation distance), you can calculate the absolute error e k =|x ik −x ek ∣, and calculate the mean absolute error (m is the number of key time nodes) to evaluate consistency. The smaller the mean absolute error, the higher the data consistency at the key time nodes.

[0054] For the consistency of historical data time series, specifically, for time series data such as historical transaction data and product quality data, let the internal time series data be y i (t), the external time series data is y e (t). The consistency can be measured by calculating the root mean square error (RMSE), , where T is the number of time points. The smaller the RMSE value, the closer the internal and external time series data are in terms of value. In order to evaluate the consistency of time series trends, the Pearson correlation coefficient r can be used. The Pearson correlation coefficient is used to measure the degree of linear correlation between two variables. For internal time series data y i (t) and external time series data y e (t), ,in, and are the averages of internal and external time series data, respectively;

[0055] Consistency based on logical relationships includes causal consistency and data association consistency. Specifically, for causal consistency, for example, the causal relationship between external industry news reports and internal purchase order arrival data can be analyzed using conditional probability. Suppose event A is an external report that a supplier is short of raw materials (or other reasons), and event B is that the internal purchase order has a delivery delay. Then the conditional probability . By counting the number of times events A and B occur at the same time in historical data and the number of times event A occurs, the conditional probability is calculated. For the logical relationship between internal quality inspection results and external market feedback, a confusion matrix can be constructed. Let the internal inspection pass as a positive sample, the unqualified as a negative sample, the external market feedback is good as a positive sample, and the feedback quality problem as a negative sample. By counting the actual situation of internal inspection results and external market feedback, fill in the confusion matrix. For example, the number of samples that pass the internal inspection and have good external feedback is a The number of samples that passed the internal test but had quality problems in external feedback is b, the number of samples that failed the internal test but had good external feedback is c, and the number of samples that failed the internal test and had quality problems in external feedback is d. The accuracy can be calculated The higher the accuracy, the better the consistency between internal and external quality logic relationships.

[0056] For example, the consistency of data association between the internal procurement management system and the quality inspection department database and the supplier product quality certification information obtained externally can be evaluated by constructing association rules and calculating support and confidence. Suppose the rule is "If a product is purchased internally (condition), then the product quality inspection is qualified and the external industry platform shows that it has passed the quality certification (result)." Support

[0057] , confidence , the higher the support and confidence, the better the data association consistency. In the supply chain, suppose the internal record of raw material procurement time t r , quantity q r , supplier production planning time t p , product delivery time t d (If relevant information is obtained from the outside). The consistency of association can be evaluated by calculating the production cycle difference rate. Assuming the theoretical production cycle T theory Determined based on industry data or experience, the actual production cycle T actual =t d −t r (Considering the time from raw material procurement to product delivery). Production cycle variance rate , the lower the production cycle difference rate, the higher the consistency of data association in the supply chain.

[0058] In an embodiment of the present invention, when the consistency assessment result meets the requirements, that is, all calculated parameters meet the preset values, which may be artificially determined values, the supplier's assessment level is maintained; when the consistency assessment result does not meet the requirements, that is, there is a parameter in the above-mentioned consistency assessment that does not meet the preset value, it can be regarded as the consistency assessment result does not meet the requirements, indicating that there is a problem with the authenticity of the data, and the supplier's assessment level is downgraded.

[0059] In addition, the step of analyzing the email data, the instant messaging data, and the meeting minutes data using natural language processing technology and calculating the communication heat according to the analysis results includes:

[0060] Analyzing the email data, instant messaging data, and meeting minutes data using natural language processing (NLP) technology to determine the frequency of communication within a preset time period. For example, the frequency of mutual communication within a month is determined. A communication session is considered one session when a certain number of communication records or a certain duration of voice calls between the two parties are reached in a day.

[0061] Determining whether the communication frequency is greater than a preset frequency;

[0062] If it is determined that the communication frequency is greater than the preset frequency, it indicates that the two parties maintain close communication and that there is sufficient communication data for analysis. Then, the content belonging to the same communication topic in all the email data, instant messaging data, and meeting minutes data during the cooperation period is extracted using a text classification algorithm in natural language processing technology. Then, the sentiment analysis algorithm in natural language processing technology is used to analyze the sentiment tendencies in the content of the same communication topic. Among them, the sentiment tendencies of the two parties in the communication are determined to be positive, neutral, or negative, and the number of occurrences of positive, neutral, and negative sentiment tendencies under the same topic is counted respectively;

[0063] Based on the importance of the communication topic and the emotional tendency in the content of the same communication topic, a communication heat calculation model is constructed. This communication heat calculation model adopts a weighted average method, comprehensively considering factors such as the importance of the communication topic and the emotional tendency in the content of the same communication topic;

[0064] The communication heat is determined according to the communication heat calculation model, wherein the communication heat calculation model can be expressed as , n represents the number of communication topics, i Indicates the i communication topics, and determine the weights according to the importance of different communication topics w i , and satisfies , each communication topic has a basic value b i The basic value can be set according to historical data, business rules, etc. For the i-th communication topic, the number of positive times is p i , the number of neutral times is n i , the number of negative q i Assuming that positive emotional tendency is scored 3 points each time, neutral emotional tendency is scored 0 points each time, and negative emotional tendency is scored -3 points each time (the specific score can be adjusted according to the actual situation), then i The sentiment tendency score of each communication topic .

[0065] Step S03: Determine the evaluation level of the supplier based on the acquired data corresponding to each first supplier, and push the evaluation level to the user.

[0066] Specifically, the internal data, external data and evaluation grade data corresponding to each first supplier are input into the trained random forest model, and the evaluation grade is output, wherein the internal data and evaluation grade data of the first supplier that has not cooperated are given benchmark values. In addition, when the evaluation grade of the supplier that has cooperated is adjusted after consistency comparison, the adjusted evaluation grade is used as the evaluation grade of the supplier and input into the trained random forest model.

[0067] It should be noted that random forest is an ensemble learning algorithm based on decision trees, with good noise immunity and generalization performance. The random forest model was trained on the training set, with initial model parameters set, such as 100 trees, a maximum depth of 10, and a minimum number of sample splits of 5. Through repeated training, the model parameters were adjusted, and changes in evaluation metrics such as precision, recall, and F1 score on the validation set were observed. A grid search technique was used to comprehensively search and optimize the model parameters. For example, a combination search was conducted for the number of trees within the range [50, 100, 150], the maximum depth within the range [5, 10, 15], and the minimum number of sample splits within the range [3, 5, 7]. The parameter combination that achieved the best performance on the validation set was selected as the final model parameter combination.

[0068] In summary, the artificial intelligence-based procurement supply chain decision-making assistance method in the above-mentioned embodiments of the present invention obtains procurement requirements and bids provided by each supplier, compares the procurement requirements with the matching data in the bids provided by each supplier, and determines the first supplier; collects internal data, external data and evaluation grade data of the first supplier that has cooperated, and external data of the first supplier that has not cooperated, the internal data is the data generated during the transaction process, and the external data is public data, wherein the internal data at least includes the communication data between the user and the supplier; determines the evaluation grade of the supplier based on the acquired data corresponding to each first supplier, and pushes the evaluation grade to the user, which can assist the user in making procurement supply chain decisions so that the decision results meet the user's needs.

[0069] Example 2

[0070] See also Figure 2 , Figure 2 This is a structural block diagram of an artificial intelligence-based procurement supply chain decision support system provided in Example 2 of the present invention. The artificial intelligence-based procurement supply chain decision support system 200 is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been explained will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0071] Specifically, the artificial intelligence-based procurement supply chain decision support system 200 includes: a comparison module 21, a collection module 22, and a determination module 23, wherein:

[0072] A comparison module 21 is used to obtain the purchase requirements and the bids provided by each supplier, compare the purchase requirements with the matching data in the bids provided by each supplier, and determine the first supplier;

[0073] A collection module 22 is configured to collect internal data, external data, and evaluation grade data of the first supplier with which the user has cooperated, as well as external data of the first supplier with which the user has not cooperated, wherein the internal data is data generated during the transaction process, and the external data is public data, wherein the internal data at least includes communication data between the user and the supplier, and the communication data at least includes email data, instant messaging data, and meeting minutes data; analyze the email data, instant messaging data, and meeting minutes data using natural language processing technology; and calculate communication heat based on the analysis results. The communication heat is used to determine the supplier's evaluation grade;

[0074] The determination module 23 is used to determine the evaluation level of the supplier based on the data corresponding to each first supplier obtained, and push the evaluation level to the user. Specifically, the internal data, external data and evaluation level data corresponding to each first supplier are input into the trained random forest model, and the evaluation level is output, wherein the internal data and evaluation level data of the non-cooperative first supplier are used as the benchmark value.

[0075] Furthermore, in some optional embodiments of the present invention, the artificial intelligence-based procurement supply chain decision support system 200 further includes:

[0076] An evaluation module is used to evaluate the consistency of the internal data and external data of the first supplier with which the supplier has cooperated, including evaluations of data matching, consistency based on time series, and consistency based on logical relationships. In addition, data matching includes key information matching and transaction data matching. The key information matching includes matching of basic supplier information and product information, and the transaction data matching includes matching of order data and price data.

[0077] Time series-based consistency includes data update frequency consistency and historical data time series consistency;

[0078] Consistency based on logical relationships includes causal consistency and data association consistency;

[0079] The adjustment module is used to adjust the supplier's assessment level according to the consistency assessment results. When the consistency assessment results meet the requirements, the supplier's assessment level is maintained; when the consistency assessment results do not meet the requirements, the supplier's assessment level is downgraded.

[0080] Furthermore, in some optional embodiments of the present invention, the collection module 22 includes:

[0081] A first determining unit is configured to analyze the email data, the instant messaging data, and the meeting minutes data using natural language processing technology to determine the communication frequency within a preset time period;

[0082] a judging unit, configured to judge whether the communication frequency is greater than a preset frequency;

[0083] an analysis unit configured to extract content belonging to the same communication topic from the email data, the instant messaging data, and the meeting minutes data if it is determined that the communication frequency is greater than a preset frequency, and analyze the emotional tendency of the content of the same communication topic using a sentiment analysis algorithm in natural language processing technology;

[0084] A construction unit is used to construct a communication heat calculation model based on the importance of the communication topic and the emotional tendency existing in the content of the same communication topic;

[0085] The second determining unit is configured to determine the communication heat according to the communication heat calculation model.

[0086] Example 3

[0087] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in embodiment three of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the procurement supply chain decision-making assistance method based on artificial intelligence as described above is implemented.

[0088] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0089] The memory 20 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 may be an internal storage unit of the electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 20 may include both an internal storage unit of the electronic device and an external storage device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is about to be output.

[0090] It should be pointed out that Figure 3 The structure shown does not constitute a limitation to the electronic device. In other embodiments, the electronic device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0091] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned artificial intelligence-based procurement supply chain decision-making assistance method.

[0092] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0093] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0094] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0095] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0096] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A procurement supply chain decision-making assistance method based on artificial intelligence, characterized in that: The method comprises: Obtain the purchase requirements and the bids provided by each supplier, compare the purchase requirements with the matching data in the bids provided by each supplier, and determine the top supplier; Collecting internal data, external data, and evaluation rating data of the first supplier with which the user has cooperated, and external data of the first supplier with which the user has not cooperated, wherein the internal data is data generated during the transaction process, and the external data is public data, wherein the internal data at least includes communication data between the user and the supplier; Evaluate the consistency of the first-party supplier's internal and external data, including evaluation of data matching, consistency based on time series, and consistency based on logical relationships; Adjust the supplier's assessment level based on the consistency assessment results. If the consistency assessment results meet the requirements, the supplier's assessment level will be maintained; if the consistency assessment results do not meet the requirements, the supplier's assessment level will be downgraded. Determine the evaluation level of the supplier based on the acquired data corresponding to each first supplier, and push the evaluation level to the user; The communication data includes at least email data, instant messaging data, and meeting minutes data. The email data, instant messaging data, and meeting minutes data are analyzed using natural language processing technology, and communication heat is calculated based on the analysis results. The communication heat is used to determine the supplier's evaluation level; The step of analyzing the email data, the instant messaging data, and the meeting minutes data using natural language processing technology and calculating the communication heat according to the analysis results includes: Analyzing the email data, the instant messaging data, and the meeting minutes data using natural language processing technology to determine the frequency of communication within a preset time period; Determining whether the communication frequency is greater than a preset frequency; If it is determined that the communication frequency is greater than the preset frequency, the content belonging to the same communication topic in the email data, the instant messaging data, and the meeting minutes data is extracted, and the sentiment analysis algorithm in the natural language processing technology is used to analyze the sentiment tendency of the content of the same communication topic; Construct a communication heat calculation model based on the importance of the communication topic and the emotional tendency in the content of the same communication topic; Determining communication heat according to the communication heat calculation model; In the step of determining the evaluation level of the supplier based on the data corresponding to each first supplier obtained, the internal data, external data and evaluation level data corresponding to each first supplier are input into the trained random forest model, and the evaluation level is output, wherein the internal data and evaluation level data of the non-cooperative first supplier are used as the benchmark value.

2. The artificial intelligence-based procurement supply chain decision-making assistance method according to claim 1 is characterized in that: In the step of evaluating the consistency between the internal data and external data of the first supplier with whom the cooperation has been established, Data matching includes key information matching and transaction data matching. The key information matching includes the matching of supplier basic information and product information. The transaction data matching includes the matching of order data and price data. Time series-based consistency includes data update frequency consistency and historical data time series consistency; Consistency based on logical relationships includes causal consistency and data association consistency.

3. A procurement supply chain decision support system based on artificial intelligence, characterized by: For implementing the artificial intelligence-based procurement supply chain decision-making assistance method according to any one of claims 1-2, the system comprises: The comparison module is used to obtain the purchase requirements and the bids provided by each supplier, compare the purchase requirements with the matching data in the bids provided by each supplier, and determine the first supplier; a collection module, configured to collect internal data, external data, and evaluation grade data of the first supplier with which the user has cooperated, and external data of the first supplier with which the user has not cooperated, wherein the internal data is data generated during the transaction process, and the external data is public data, wherein the internal data at least includes communication data between the user and the supplier; The determination module is used to determine the evaluation level of the supplier based on the acquired data corresponding to each first supplier, and push the evaluation level to the user.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the procurement supply chain decision-making assistance method based on artificial intelligence as described in any one of claims 1-2 is implemented.

5. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the artificial intelligence-based procurement supply chain decision-making assistance method as described in any one of claims 1 to 2.

Images