Rule engine algorithm and system serving medical enterprise marketing policy

Abstract

The invention belongs to the technical field of evaluation and prediction. The rule engine algorithm serving the medical enterprise marketing policy comprises the steps of obtaining implementation and use conditions of an initial preferential policy and acceptance and repetition frequency of a customer to the initial preferential policy to obtain an initial preferential policy effect; according to the initial preferential policy effect, the cost price data, the market sales price data and the historical order data, obtaining an income condition; obtaining a market change trend, and obtaining a current preferential policy in combination with the income condition; and adjusting the current preferential policy according to the implementation and use conditions of the current preferential policy and the acceptance and repetition frequency of the client to the current preferential policy to obtain a target preferential policy. Through the method, the flexibility and effectiveness of the enterprise in the aspects of making and executing the preferential policy are realized, and the response speed of the enterprise to the market change and the timeliness of policy adjustment are solved.

Description

Technical Field

[0001] The present application belongs to the field of evaluation and prediction technology, and in particular, relates to a rule engine algorithm and system serving the marketing policies of medical enterprises. Background Art

[0002] In the field of medical device supply chain management, manufacturers or platform companies usually formulate and implement a variety of preferential policies, such as price discounts, rebate plans and promotional activities, in order to attract customers and increase sales. These policies are intended to stimulate market demand and improve the market competitiveness of products through economic incentives. However, the existing technology has some obvious deficiencies in the implementation and management of preferential policies.

[0003] First, the existing system lacks the ability to effectively monitor and analyze the use of preferential policies, making it difficult for companies to track the actual effects of policies in real time and evaluate their specific impact on sales. Second, companies lack the ability to evaluate costs and benefits, making it difficult to accurately calculate the costs and benefits of each preferential policy, and thus unable to determine whether the policy truly brings economic benefits to the company. In addition, the existing system has limited ability to recommend strategies, and is unable to automatically recommend the best policy based on historical order data, cost structure, and market conditions, making it difficult for companies to formulate dynamic, personalized policy strategies.

[0004] The existence of these problems limits the flexibility and effectiveness of enterprises in formulating preferential policies, and affects the speed of enterprises' response to market changes and the timeliness of policy adjustments. Therefore, it is urgent to develop a method that can automatically analyze the use of preferential policies, evaluate costs and benefits, and recommend the optimal strategy. Summary of the invention

[0005] Based on this, it is necessary to provide a rule engine algorithm that serves the marketing policies of medical enterprises to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for a rule engine algorithm serving a marketing policy of a medical enterprise, the method comprising: Obtain the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, and obtain the effect of the initial preferential policy; Obtaining the revenue situation based on the effects of the initial preferential policies, cost price data, market sales price data and historical order data; Obtain the market trend and, combined with the revenue situation, obtain the current preferential policies; According to the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, the current preferential policy is adjusted to obtain a target preferential policy.

[0007] In some practicable methods, the step of obtaining the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, and obtaining the effect of the initial preferential policy includes: Use the enterprise's system to obtain transaction records; Extracting features of the initial preferential policy to obtain features of the initial preferential policy; According to the characteristics of the initial preferential policy, feature matching is performed on the transaction records to obtain the implementation and use of the initial preferential policy; Constructing a questionnaire for the initial preferential policies; Obtaining the customer's feedback on the questionnaire to obtain the customer's acceptance; Acquire the transaction record of the customer during the execution period of the initial preferential policy to obtain the recurrence frequency of the customer; The effect of the initial preferential policy is obtained based on the implementation and use of the initial preferential policy, the acceptance of the customers, and the repetition frequency of the customers.

[0008] In some practicable methods, the step of obtaining the revenue situation according to the initial preferential policy effect, cost price data, market sales price data and historical order data includes: Using the enterprise's system to obtain the cost price data, the market sales price data and the historical order data; Use financial analysis methods to build a revenue analysis model; The cost price data, the market sales price data, the historical order data, and the effect of the initial preferential policy are respectively input into the profit analysis model to obtain the profit situation.

[0009] In some practicable methods, the step of inputting the cost price data, the market sales price data, the historical order data, and the effect of the initial preferential policy into the profit analysis model to obtain the profit situation includes: Decomposing the effect of the initial preferential policy to obtain the sales volume increased by the initial preferential policy, as well as the acceptance and the repetition frequency; The sales volume increased due to the initial preferential policy is used, together with the cost price data, the market selling price data and the historical order data, to be input into the revenue analysis model to obtain the revenue situation; Constructing an evaluation model, wherein the evaluation model represents an evaluation of the initial preferential policy to form a score; Inputting the customer's acceptance of the initial preferential policy, the repetition frequency, and the sales volume increased due to the initial preferential policy into the evaluation model, respectively, to obtain acceptance scores, repetition frequency scores, and sales volume increased due to the initial preferential policy scores; The evaluation model is then used to calculate the acceptance score, the repetition frequency score, and the sales volume score increased by the initial preferential policy to obtain the score of the initial preferential policy.

[0010] In some practicable methods, the step of obtaining the revenue situation according to the initial preferential policy effect, cost price data, market sales price data and historical order data further includes: Obtain expected returns; Compare the income situation with the expected income to obtain a comparison result; Score the comparison results to obtain a revenue score; A comprehensive score is performed based on the revenue situation score and the score of the initial preferential policy to obtain a target revenue score.

[0011] Some of the possible implementation methods include obtaining market change trends and combining the revenue situation to obtain the current preferential policies, including: Obtaining market change trends, wherein the market change trends represent changes in customer consumption behavior, competitor promotions, and industry trends; Obtain the revenue influencing factors based on the impact of the factors included in the initial preferential policy on the revenue situation; Preferential policies are formulated according to the market change trend and the profit influencing factors to obtain the current preferential policies.

[0012] In some practicable ways, the step of adjusting the current preferential policy according to the implementation of the current preferential policy and market feedback to obtain the target preferential policy includes: According to the implementation of the current preferential policy, the transaction records during the implementation of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, are obtained to obtain the effect of the current preferential policy; Obtain the market change trend during the implementation of the current preferential policy; According to the market change trend during the implementation of the current preferential policy and the effect of the current preferential policy, the current preferential policy is adjusted to obtain the target preferential policy.

[0013] In a second aspect, the present application provides a rule engine system serving the marketing policy of a medical enterprise, which is applied to the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise, and the system includes: An acquisition unit, used to acquire the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, to obtain the effect of the initial preferential policy; The revenue unit is used to obtain the revenue situation according to the effect of the initial preferential policy, cost price data, market sales price data and historical order data; The acquisition unit is also used to acquire the market change trend and obtain the current preferential policy in combination with the revenue situation; The result unit is used to adjust the current preferential policy according to the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, to obtain a target preferential policy.

[0014] In a third aspect, the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise.

[0016] Beneficial effects: This application provides a rule engine algorithm that serves the marketing policy of medical enterprises, obtains the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, and obtains the effect of the initial preferential policy; obtains the revenue situation based on the initial preferential policy effect, cost price data, market sales price data and historical order data; obtains the market change trend, and obtains the current preferential policy in combination with the revenue situation; adjusts the current preferential policy based on the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, and obtains the target preferential policy. Through the above method, the flexibility and effectiveness of the enterprise in the formulation of preferential policies are achieved, and the speed of the enterprise's response to market changes and the timeliness of policy adjustments are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1The present invention is a flowchart of a rule engine algorithm serving the marketing policy of a medical enterprise in one embodiment. DETAILED DESCRIPTION

[0019] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all couplings of one or more related listed items.

[0021] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0022] Some terms involved in this application are explained below to facilitate understanding of this application: ERP (Enterprise Resource Planning) refers to a system that includes multiple modules such as financial management, human resource management, supply chain management, customer relationship management, and production management.

[0023] CRM (Customer Relationship Management) refers to managing the interaction and relationship between enterprises and customers through technical means. CRM system can help enterprises collect, analyze and use customer data to improve customer satisfaction, increase customer loyalty and improve sales performance.

[0024] Point of Sale (POS) is a computer system used to process transactions in a retail environment, allowing merchants to quickly and accurately record transaction information when selling goods or services.

[0025] Natural Language Processing (NLP) is a branch of artificial intelligence and linguistics that can extract useful information from large amounts of text data.

[0026] Preferential policies refer to price discounts, rebates or promotional plans formulated by manufacturers or platforms to attract customers or increase sales.

[0027] Cost and benefit assessment refers to the process of systematically calculating the costs incurred during the implementation of a policy and the sales revenue it brings in order to determine its economic benefits.

[0028] Historical order data refers to a company's past sales order records, which serve as basic data for analyzing customer behavior, policy effects, and strategy adjustments.

[0029] Strategy recommendation means that the system proactively generates suggestions on the best price, promotion and rebate strategy for a company in its marketing activities based on data analysis results.

[0030] like Figure 1 As shown, in the first aspect, the present application provides a rule engine algorithm serving the marketing policy of a medical enterprise, and the method includes: S100, obtaining the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, to obtain the effect of the initial preferential policy.

[0031] Specifically, obtaining the initial preferential policy effect may include the following steps: S101, using the enterprise's system to obtain transaction records.

[0032] Specifically, the enterprise's system may be a sales system, such as ERP, CRM, and point of sale systems, which may be used alone or in combination. Detailed transaction records containing the application of preferential policies may be obtained through the existing enterprise system, and the transaction records may include transaction time, customer information, purchased products, applied preferential policies, etc. It should be noted that the enterprise's system is a conventional system, and this application does not improve the structure of the system.

[0033] S102, extracting features of the initial preferential policy to obtain features of the initial preferential policy.

[0034] Specifically, natural language processing (NLP) can be used to extract features of the initial preferential policies to obtain keywords and named entities, such as "discount", "specific model", "validity period", etc.

[0035] S103, performing feature matching on the transaction records according to the features of the initial preferential policy to obtain the implementation and use of the initial preferential policy.

[0036] Specifically, the features of the initial preferential policy are vectorized, that is, the extracted features are converted into numerical form to create a feature vector. For example, the discount rate can be expressed as a percentage value, and the applicable products can be expressed as the code of the product category. Similarly, the transaction records are feature extracted to obtain the features of the transaction records. The feature extraction of the transaction records can be a conventional feature extraction method, which is not limited in this application. Similarly, the features of the transaction records are vectorized. Then, the feature vector of the initial preferential policy and the similarity between the feature vectors of the transaction records are compared using a similarity calculation method (such as cosine similarity) to determine whether the transaction record meets the characteristics of the preferential policy.

[0037] For example, a medical device company launched a preferential policy: "For the purchase of model X100 pacemakers, a 10% discount is provided, valid from January 1, 2024 to March 31, 2024." Feature extraction: Use NLP technology to extract keywords: "model X100", "pacemaker", "10% discount", "validity period".

[0038] Feature matching: Quantize the features of the initial preferential policy. For example, encode the model X100 as 1 and convert the validity period into a date format.

[0039] In the transaction record database, logical rules are used to match transaction records that match the model and validity period (feature extraction of transaction records is omitted here. If the transaction records are complex, feature extraction can be performed on the transaction records and then converted into feature vectors for matching).

[0040] For each matching transaction record, check whether the discount rate is applied correctly, for example, by calculating the ratio of the actual payment amount to the original price to see if it is close to 90% (i.e. the price after a 10% discount).

[0041] Through this method, the characteristics of preferential policies can be accurately extracted and matched from transaction records, providing accurate data support for subsequent preferential policy evaluations.

[0042] S104, constructing a questionnaire for the initial preferential policy.

[0043] Specifically, a questionnaire is constructed for the initial preferential policy. The purpose of the questionnaire is to obtain the customer's acceptance (acceptance refers to whether the customer is satisfied with the initial preferential policy when there is demand, thus forming the acceptance). Therefore, the core idea of ​​the survey document is to raise questions around acceptance, and expand them to form multiple questions for customers to answer.

[0044] S105, obtaining the customer's feedback result on the questionnaire to obtain the customer's acceptance degree.

[0045] Specifically, the survey file can be sent to the customer through a mobile phone, computer, etc., and after receiving the feedback results of the questionnaire, the customer's acceptance can be formed according to the feedback results. For example, a score can be set for each question in the questionnaire, and the score of each question is accumulated according to the customer's feedback to obtain a total score, and then the total score is matched with a pre-constructed acceptance evaluation level (the score range is set according to the evaluation level, and the score falling within the score range is the corresponding evaluation level), so as to obtain the customer's acceptance.

[0046] S106, obtaining the transaction record of the customer during the execution period of the initial preferential policy, and obtaining the repetition frequency of the customer.

[0047] Specifically, based on the aforementioned transaction records, the transaction records of the same customer can be obtained, and based on the number of transaction records of the same customer, the customer's repetition frequency can be obtained, and the repetition frequency indicates how many times the initial preferential policy has been used. A unique ID can be constructed for each customer, and the unique ID can be used to count the number of transaction records of the customer.

[0048] S107, obtaining the effect of the initial preferential policy according to the implementation and use of the initial preferential policy, the acceptance of the customers, and the repetition frequency of the customers.

[0049] By utilizing the implementation and use of the initial preferential policy obtained in the above steps, the customer's acceptance, and the customer's repetition frequency, a comprehensive evaluation of the initial preferential policy can be achieved, thereby obtaining the effect achieved during the implementation of the initial preferential policy.

[0050] For example, a medical device company launched a 10% discount policy for a specific model of pacemaker. Through the company's system, the company obtained transaction records containing the application of the policy. Then, the company extracted the key features of the policy, such as the discount rate and applicable products. Through feature matching, the company identified the transactions to which the policy was applied and counted the use of the policy. At the same time, the company designed and distributed questionnaires to collect customer feedback on the policy and evaluate customer acceptance. By analyzing the customer's consumption records during the policy implementation period, the company obtained the customer's repetition frequency. Finally, the company combined these data to evaluate the effectiveness of the preferential policy and found that the policy increased sales and customer acceptance was high, but the repetition frequency was lower than expected. Based on these evaluation results, the company can make adjustments in subsequent preferential policies to address the problem of low repetition frequency.

[0051] In addition, transaction records can be used to check whether the store has promoted the initial preferential policy, because if there is an initial preferential policy promotion, there is a high probability that transaction records will be generated. In other words, the working conditions of the store can be discovered through transaction records, so that problems in the store can be understood and improvements can be made, such as training on the initial preferential policy and increasing publicity. This can avoid, to a certain extent, the problem of inaccurate initial preferential policy effects due to negligence of store staff.

[0052] S200, obtaining revenue status according to the initial preferential policy effect, cost price data, market sales price data and historical order data.

[0053] Specifically, obtaining the income situation may include the following steps: S201, using the enterprise's system to obtain the cost price data, the market sales price data and the historical order data.

[0054] Specifically, the cost price data of products can be extracted from the enterprise's ERP system, including raw material costs, production costs, transportation costs, etc. The sales price data of products can be obtained from the CRM system or point of sale system, including sales prices for different customers and at different time points. Historical order data can be extracted from the enterprise's database, including order date, product details, sales quantity, discount information, etc.

[0055] S202, using financial analysis methods to construct a revenue analysis model.

[0056] Specifically, a revenue analysis model is constructed, which can comprehensively consider the cost price, market sales price, historical order data, and the effects of preferential policies to evaluate the revenue. Among them, the financial analysis method and the revenue analysis model are conventional methods and models, and this application does not improve or adjust them.

[0057] It should be noted that the benefit analysis model may include the following formula: Profit situation = ((market price × price adjustment factor − cost price × cost adjustment factor) × (baseline sales volume + increased sales volume due to initial preferential policy − normal sales volume lost due to initial preferential policy) ) − preferential policy cost × policy adjustment factor.

[0058] Among them, factors represent parameters, which are used to quantify and adjust basic data to reflect the actual market and operating conditions. Each factor is a multiplier, which is used to adjust basic data to more accurately predict revenue. Specifically, the price adjustment factor can represent the impact of market fluctuations and seasonal factors on sales prices; the cost adjustment factor can represent the impact of backlog products on costs, such as possible discount processing costs; the sales adjustment factor can represent the impact of backlogs and seasonal factors on sales volume; the policy adjustment factor can represent the impact of market fluctuations on the cost of preferential policies, such as the marketing expenses that may need to be increased; the baseline sales volume can represent the sales volume when there is no preferential policy. The baseline sales volume can be obtained by taking the average of the sales volume formed outside the initial preferential policy within the historical time range, such as the historical monthly average sales volume, which is the baseline sales volume. It should be noted that market fluctuations and seasonal factors are only part of the adjustment factors, which can be adjusted according to actual conditions. It should be explained that the initial preferential policy cost can refer to the promotion cost, employee training and other costs, indicating the expenses required for the introduction of the preferential policy.

[0059] For example, the basic data of a product is as follows: Cost price (C): 100 yuan; Market price (S): 200 yuan; Baseline sales (B): 1,000 units; Initial preferential policy cost (P): 5,000 yuan; Consider the following adjustment factors: Price adjustment factor (Fp): Taking into account market fluctuations and seasonal factors, it is assumed to be 1.05 (indicating a 5% increase in the market selling price).

[0060] Cost adjustment factor (Fc): Consider that overstocked products may need to be discounted, assuming it is 0.95 (indicating a 5% cost reduction).

[0061] Sales adjustment factor (Fs): takes into account the impact of overstock and seasonal factors on sales, assumed to be 1.10 (indicating a 10% increase in sales).

[0062] Policy adjustment factor (Fp): Considers the impact of market fluctuations on the cost of preferential policies, assumed to be 1.20 (indicating a 20% increase in the cost of preferential policies).

[0063] Based on these data and factors, we can calculate the return: Adjusted market price: S × Fp = 200 × 1.05 = 210 yuan; Adjusted cost price: C × Fc = 100 × 0.95 = 95 yuan; Adjusted baseline sales volume: B × Fs = 1000 × 1.10 = 1100 units; The adjusted preferential policy cost: P × Fp = 5000 × 1.20 = 6000 yuan; Substituting these data into the profit analysis model formula: Profit = ((210−95)×(1100−0))−6000=120500; Therefore, according to the profit analysis model, it can be estimated that the profit will be 120,500 yuan after considering all adjustment factors.

[0064] Through the above method, not only the cost price data, the market sales price data and the historical order data are taken into consideration, but also the impact of the silent cost, that is, the adjustment factor, on the revenue is taken into consideration. In this way, the calculation of the revenue situation is more accurate.

[0065] S203, inputting the cost price data, the market sales price data, the historical order data, and the effect of the initial preferential policy into the profit analysis model respectively to obtain the profit situation.

[0066] Next, the relevant data collected so far is input into the benefit analysis model to obtain the benefit situation. In other words, the benefit analysis model will process these data and calculate the actual benefit situation under the initial preferential policy.

[0067] It should be noted that step S203, inputting the cost price data, the market sales price data, the historical order data, and the initial preferential policy effect into the profit analysis model to obtain the profit situation, may include the following steps: S2031, splitting the effect of the initial preferential policy to obtain the sales volume increased by the initial preferential policy, as well as the acceptance and the repetition frequency.

[0068] Among them, the sales volume increased by the initial preferential policy can be obtained through the transaction records in the aforementioned steps. In this way, the effect of the initial preferential policy is split so that the acceptance and repetition frequency can be determined in subsequent steps to score the initial preferential policy.

[0069] S2032, using the sales volume increased by the initial preferential policy, the cost price data, the market sales price data and the historical order data, and inputting them into the profit analysis model to obtain the profit situation.

[0070] As in the formula in the aforementioned step S202, the sales volume increased due to the initial preferential policy is substituted into the formula and calculated together with the relevant data, and the revenue situation can be obtained through the revenue analysis model.

[0071] S2033, construct an evaluation model.

[0072] The evaluation model represents the evaluation of the initial preferential policy to form a score.

[0073] Specifically, the evaluation model can set the score corresponding to the scoring criteria, and use the scoring criteria to score and obtain the score of each item. The scoring criteria of the evaluation model can be a conventional scoring method, for example, setting a scoring standard for acceptance, setting a scoring standard for repetition frequency, and setting a scoring standard for sales volume increased by the initial preferential policy. Finally, the total score is obtained according to the scoring criteria.

[0074] S2034, inputting the customer's acceptance of the initial preferential policy, the repetition frequency, and the sales volume increased due to the initial preferential policy into the evaluation model, respectively, to obtain an acceptance score, a repetition frequency score, and a sales volume increased due to the initial preferential policy score, respectively.

[0075] S2035, using the evaluation model again, calculating the acceptance score, the repetition frequency score, and the sales volume score increased by the initial preferential policy to obtain the score of the initial preferential policy.

[0076] Specifically, weights may be set for acceptance, repetition frequency, and sales volume increased by the initial preferential policy, and weighted calculations may be performed in the evaluation model based on the weights and the scores obtained to ultimately determine the score of the initial preferential policy.

[0077] In summary, the above methods provide a structured and systematic way to evaluate the effects of preferential policies, making the decision-making process more data-driven and objective. By breaking down the policy effects and evaluating each factor separately, the advantages and disadvantages of the policy can be more accurately identified, so that targeted adjustments can be made.

[0078] It should be noted that step S200, obtaining the revenue situation according to the initial preferential policy effect, cost price data, market sales price data and historical order data, also includes the following steps: S204, obtaining expected benefits.

[0079] S205, comparing the revenue situation with the expected revenue to obtain a comparison result.

[0080] S206, scoring the comparison result to obtain a revenue score.

[0081] S207, performing a comprehensive score based on the revenue situation score and the score of the initial preferential policy to obtain a target revenue score.

[0082] It should be noted that when some companies implement preferential policies, they not only aim to generate revenue, but also to enhance brand value. Therefore, the company's profit situation is scored, and then combined with the score of the initial preferential policy to obtain a comprehensive score. This comprehensive score is the target profit score.

[0083] It should also be noted that the expected benefit is the actual benefit that is intended to be achieved when the initial preferential policy is introduced. The expected benefit is compared with the current benefit situation to form a comparison result. By comparing the comparison, you can know whether the current benefit exceeds or does not exceed the expected benefit. By comparing the comparison result with the preset scoring criteria, you can get the score of the current benefit situation. Next, after giving weights to the benefit situation and the initial preferential policy, the benefit situation score and the initial preferential policy score are comprehensively scored, that is, weighted calculation, to obtain the target benefit score.

[0084] It is understandable that the score of the initial preferential policy includes the acceptance score, the repetition frequency score, and the sales volume score increased by the initial preferential policy. All of these aspects express the customer's recognition of the corporate brand to a certain extent, which invisibly enhances the brand value of the company. Therefore, it is necessary to calculate the target revenue score.

[0085] S300, obtaining the market change trend, and combining the initial preferential policy effect and the revenue situation to obtain the current preferential policy.

[0086] Specifically, obtaining the current preferential policies may include the following steps: S301, obtaining market change trends.

[0087] Among them, the market change trend represents changes in customer consumption behavior, competitor promotions and industry trends.

[0088] Specifically, based on public information, such as the Internet and news, conventional big data analysis tools are used to analyze and obtain market change trends. The change trends can be obtained by drawing charts.

[0089] S302, obtaining revenue influencing factors according to the impact of factors included in the initial preferential policy on the revenue situation.

[0090] Specifically, the factors included in the initial preferential policy are split to form different factor labels. For example, the key factors in the initial preferential policy are analyzed, such as discount strength label, promotion scope label, duration label, promotion channel label, etc. The attractiveness and market response of the initial preferential policy are understood through market research and customer feedback, such as questionnaires, online reviews and customer service feedback. In this way, customer feedback is marked and matched with existing factor labels. Finally, the factors are sorted according to the number of matching factor labels, so as to obtain the factors that have the greatest impact on the revenue situation, that is, the revenue influencing factors.

[0091] S303: Formulate preferential policies according to the market change trend and the profit influencing factors to obtain the current preferential policies.

[0092] Specifically, according to the factor ranking obtained in the above steps, formulating preferential policies may include adding factors with the greatest impact on the revenue situation in the factor ranking, and / or adjusting factors with the least impact on the revenue situation in the factor ranking, thereby obtaining the current preferential policies.

[0093] For example, a medical device company that produces pacemakers wants to adjust its market preferential policies. By analyzing public information such as social media discussions, industry reports, and competitors' marketing activities, it is found that customers are paying more and more attention to remote monitoring functions, and competitors are launching new pacemakers with remote monitoring functions. Using big data analysis tools, the company draws a chart showing the growth in market demand for remote monitoring pacemakers, confirming this market change trend. The company splits the key factors of the initial preferential policy (such as discount strength, promotion scope, duration, and promotion channels) and forms labels. Through market research and customer feedback, the company learned that customers pay the most attention to discount strength and new technology (remote monitoring function). By analyzing questionnaires, online reviews, and customer service feedback, the company matches customer feedback with factor labels and sorts factors according to the number of matches, and finds that discount strength and remote monitoring function are the main factors affecting revenue. Based on the growing market demand for remote monitoring pacemakers and customers' high attention to discount strength and new technologies, the company launches a new preferential policy. The new policy includes providing additional discounts on pacemakers with remote monitoring functions, extending the duration of promotional activities, and increasing investment in online marketing channels to attract more customers who pay attention to new technologies.

[0094] To sum up, through this process, enterprises can more accurately grasp market demands and changes, optimize preferential policies, thereby improving market response speed and customer satisfaction, increasing sales and market share, and ultimately improving overall business performance and brand competitiveness.

[0095] S400: According to the implementation of the current preferential policy and market feedback, the current preferential policy is adjusted to obtain a target preferential policy.

[0096] Specifically, obtaining the target preferential policy may include the following steps: S401, based on the implementation of the current preferential policy, obtain the transaction records during the implementation period of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, and obtain the effect of the current preferential policy.

[0097] Specifically, the transaction data during the implementation of the current preferential policy is collected through the enterprise's system (ERP, CRM, etc.), and the transaction data may include sales volume, sales revenue, customer information, etc. As in the above method, evaluate customer acceptance and repetition frequency, for example, collect customer acceptance and repetition frequency data on preferential policies through questionnaires, online reviews, customer service feedback and other channels.

[0098] S402, obtaining the market change trend during the implementation of the current preferential policy.

[0099] Specifically, use big data analysis tools to analyze public information, such as online discussions, news reports, industry reports, etc., to obtain market trends during the implementation of the current preferential policies. In addition, monitor competitors, pay attention to their preferential activities and market performance, and understand changes in the industry's competitive landscape.

[0100] S403, adjusting the current preferential policy according to the market change trend during the implementation of the current preferential policy and the effect of the current preferential policy to obtain a target preferential policy.

[0101] Specifically, the effect of the current preferential policy can refer to the calculation method of the effect of the initial preferential policy.

[0102] Construct a preferential policy template, which includes each factor of the current preferential policy, sets a floating range for each factor, and sets an adjustment step and cycle. For example, the discount time range is one quarter, the discount is between 30% and 10%, the adjustment step is one week, and the adjustment cycle is one month.

[0103] According to the market trend during the implementation of the current preferential policy and the effect of the current preferential policy, each factor is automatically adjusted within the set floating range according to the adjustment step and cycle, so as to obtain the target preferential policy. Whether to adjust upward or downward, this application does not limit this, and can be set according to actual conditions. For example, if the competitor's price is 100, the preset adjustment direction is downward, and the price of the same product will be reduced according to the preset step and cycle.

[0104] Through the above method, the target preferential policy can be automatically adjusted. For example, if a product has the same price and the competitor is offering a 20% discount, and public information is used to obtain that the competitor is selling the product at a 20% discount, a discount below 20% can be offered, such as 25% discount. When the competitor's preferential period ends, if the product is still sold at a 25% discount, it will obviously reduce the company's profits. Therefore, the 25% discount is automatically increased to ensure the maximum profit of the company.

[0105] It should be noted that the automatic adjustment of the target preferential policy may also include the following steps: In the constructed preferential policy template, each factor is assigned a weight.

[0106] Obtain the preferential policies of competitors, extract factor features, and match the factor features with the corresponding factors in the preferential policy template to obtain the matching result with the highest similarity for each factor; wherein each factor feature of the competitor is matched to the corresponding factor in the preferential policy template, and the similarity matching can use a conventional similarity algorithm, which is not limited in this application.

[0107] Based on the matching result with the highest similarity of each factor and the weight of each factor in the preferential policy template, the preferential policies of competitors are weightedly calculated to obtain the preferential policy scores of competitors; According to the preferential policy scores of competitors, as well as the floating range, adjustment step and cycle set for each factor in the preferential policy template, the current preferential policy is adjusted to obtain the score of the current preferential policy; wherein, the score of the current preferential policy is greater than the score of the preferential policy of competitors, so that even if the competitor is preferential in price, the current preferential policy in this application can adjust factors other than price so that the score of the current preferential policy is still greater than the score of the preferential policy of competitors, or, adjust the price slightly, and adjust other factors so that the total score of the current preferential policy is still greater than the score of the preferential policy of competitors. This method can ensure a high score while not being limited to the adjustment of a single factor, but can improve the total score by adjusting multiple factors.

[0108] In summary, the above methods enable enterprises to quickly respond to market changes and improve the adaptability and flexibility of preferential policies through automatic adjustment mechanisms. Adjustments based on data analysis ensure scientific and accurate decision-making. By automatically adjusting preferential policy factors, enterprises can allocate marketing resources and budgets more effectively.

[0109] For example, a medical device company launched a discount policy. The company collected transaction data during the policy implementation period through the ERP and CRM systems and found that sales increased, but did not meet expectations. Through customer surveys, the company learned that customers had a high acceptance of the discount policy, but the repetition frequency was low, mainly because the product price was still higher than that of competitors. Next, market analysis showed that competitors were launching more attractive preferential policies, and the market had increasingly higher technical requirements for medical devices. Based on this information, the company pre-built a preferential policy template, including factors such as discount intensity, promotion scope, duration, and promotion channels, and set a floating range and adjustment cycle for each factor. For example, the discount intensity can be adjusted once a quarter according to market demand, and the promotion scope can be adjusted according to seasonal factors. The company automatically adjusts these factors according to market trends and policy effects to form a new target preferential policy. In this way, the medical device company is able to optimize its preferential policies based on market changes and customer feedback, thereby increasing market share and customer satisfaction. The automatic adjustment mechanism enables the company to respond quickly to market changes and ensure that the preferential policies always remain competitive.

[0110] In summary, the present application provides a rule engine algorithm for serving the marketing policy of medical enterprises, which has the following beneficial effects: 1. Efficient data analysis and evaluation: The system can analyze the implementation effects of various preferential policies in real time, reducing the time cost of manual evaluation and improving the accuracy of evaluation.

[0111] 2. Dynamic strategy recommendation: Through the analysis of historical data, the system can proactively recommend the best policy options to help companies flexibly respond to market changes.

[0112] 3. Maximizing benefits: By accurately evaluating the costs and benefits of various policies, companies can maximize the benefits of preferential policies and optimize business strategies.

[0113] 4. Intelligent management: Enterprises can use this system to automatically adjust preferential policies to prevent outdated or invalid policies from continuing to affect corporate profits.

[0114] In a second aspect, the present application provides a rule engine system serving the marketing policy of a medical enterprise, which is applied to the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise, and the system includes: An acquisition unit, used to acquire the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, to obtain the effect of the initial preferential policy; The revenue unit is used to obtain the revenue situation according to the effect of the initial preferential policy, cost price data, market sales price data and historical order data; The acquisition unit is also used to acquire the market change trend and obtain the current preferential policy in combination with the revenue situation; The result unit is used to adjust the current preferential policy according to the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, to obtain a target preferential policy.

[0115] In a third aspect, the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise when executing the computer program.

[0116] In a fourth aspect, the present application provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned rule engine algorithm serving the marketing policy of a medical enterprise.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0119] The protection scope of the present disclosure is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. A rule engine algorithm serving the marketing policy of medical enterprises, characterized in that the method include: Obtain the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, and obtain the effect of the initial preferential policy; Obtaining the revenue situation based on the effects of the initial preferential policies, cost price data, market sales price data and historical order data; Obtain the market trend and, combined with the revenue situation, obtain the current preferential policies; According to the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, the current preferential policy is adjusted to obtain a target preferential policy.

2. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 1, characterized in that: The step of obtaining the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, and obtaining the effect of the initial preferential policy includes: Use the enterprise's system to obtain transaction records; Extracting features of the initial preferential policy to obtain features of the initial preferential policy; According to the characteristics of the initial preferential policy, feature matching is performed on the transaction records to obtain the implementation and use of the initial preferential policy; Constructing a questionnaire for the initial preferential policies; Obtaining the customer's feedback on the questionnaire to obtain the customer's acceptance; Acquire the transaction record of the customer during the execution period of the initial preferential policy to obtain the recurrence frequency of the customer; The effect of the initial preferential policy is obtained based on the implementation and use of the initial preferential policy, the acceptance of the customers, and the repetition frequency of the customers.

3. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 1, characterized in that: The step of obtaining the revenue situation according to the initial preferential policy effect, cost price data, market sales price data and historical order data includes: Using the enterprise's system to obtain the cost price data, the market sales price data and the historical order data; Use financial analysis methods to build a revenue analysis model; The cost price data, the market sales price data, the historical order data, and the effect of the initial preferential policy are respectively input into the profit analysis model to obtain the profit situation.

4. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 3, characterized in that: The step of inputting the cost price data, the market sales price data, the historical order data, and the effect of the initial preferential policy into the profit analysis model to obtain the profit situation includes: Decomposing the effect of the initial preferential policy to obtain the sales volume increased by the initial preferential policy, as well as the acceptance and the repetition frequency; The sales volume increased due to the initial preferential policy is used, together with the cost price data, the market selling price data and the historical order data, to be input into the revenue analysis model to obtain the revenue situation; Constructing an evaluation model, wherein the evaluation model represents an evaluation of the initial preferential policy to form a score; Inputting the customer's acceptance of the initial preferential policy, the repetition frequency, and the sales volume increased due to the initial preferential policy into the evaluation model, respectively, to obtain acceptance scores, repetition frequency scores, and sales volume increased due to the initial preferential policy scores; The evaluation model is then used to calculate the acceptance score, the repetition frequency score, and the sales volume score increased by the initial preferential policy to obtain the score of the initial preferential policy.

5. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 4, characterized in that: The step of obtaining the revenue situation according to the effect of the initial preferential policy, cost price data, market sales price data and historical order data also includes: Obtain expected returns; Compare the income situation with the expected income to obtain a comparison result; Score the comparison results to obtain a revenue score; A comprehensive score is performed based on the revenue situation score and the score of the initial preferential policy to obtain a target revenue score.

6. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 1, characterized in that: The steps of obtaining the market trend and combining it with the revenue to obtain the current preferential policies include: Obtaining market change trends, wherein the market change trends represent changes in customer consumption behavior, competitor promotions, and industry trends; Obtain the revenue influencing factors based on the impact of the factors included in the initial preferential policy on the revenue situation; Preferential policies are formulated according to the market change trend and the profit influencing factors to obtain the current preferential policies.

7. The rule engine algorithm serving the marketing policy of medical enterprises according to claim 1, characterized in that: The step of adjusting the current preferential policy according to the implementation of the current preferential policy and market feedback to obtain the target preferential policy includes: According to the implementation of the current preferential policy, the transaction records during the implementation of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, are obtained to obtain the effect of the current preferential policy; Obtain the market change trend during the implementation of the current preferential policy; According to the market change trend during the implementation of the current preferential policy and the effect of the current preferential policy, the current preferential policy is adjusted to obtain the target preferential policy.

8. A rule engine system serving the marketing policy of medical enterprises, characterized in that: A rule engine algorithm for serving a medical enterprise marketing policy applied to any one of claims 1-7, the system comprising: An acquisition unit, used to acquire the implementation and use of the initial preferential policy, as well as the customer's acceptance and repetition frequency of the initial preferential policy, to obtain the effect of the initial preferential policy; The revenue unit is used to obtain the revenue situation according to the effect of the initial preferential policy, cost price data, market sales price data and historical order data; The acquisition unit is also used to acquire the market change trend and obtain the current preferential policy in combination with the revenue situation; The result unit is used to adjust the current preferential policy according to the implementation and use of the current preferential policy, as well as the customer's acceptance and repetition frequency of the current preferential policy, to obtain a target preferential policy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the rule engine algorithm for serving the marketing policy of a medical enterprise according to any one of claims 1 to 7 are implemented.

10. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the rule engine algorithm for serving the marketing policy of a medical enterprise according to any one of claims 1 to 7 are implemented.

Images