Terminal data management method and system for medicine sales

Abstract

The invention provides a terminal data management method and system for medicine sales. According to the method, medicine purchasing historical data, electronic health record data and allergy taboo data of customers are integrated to construct a medicine adaptive sign map, and the map establishes a dynamic association relationship between medicine indications and sign parameters. And acquiring heart rate and respiratory rate parameters of the customer in real time, and matching the heart rate and respiratory rate parameters with the physical sign parameters in the map to generate a physical sign parameter matching result. And generating a personalized recommendation instruction containing an initial recommended drug list and taboo prompts in combination with taboo rules and curative effect data in the drug indication library. According to the real-time change trend of the heart rate and the respiratory rate, the drug priority of the recommendation list is dynamically adjusted, finally, an updated recommendation drug list is generated and sent to the sales terminal equipment, and accurate drug recommendation based on the real-time health state is achieved. According to the technical scheme provided by the invention, the security and accuracy of terminal data management can be improved.

Description

Technical Field

[0001] This application relates to the technical field of terminal data management, and particularly to a terminal data management method and system for pharmaceutical sales. Background Art

[0002] In the current pharmaceutical retail industry, pharmacy terminals are facing an increasing demand for personalized drug recommendations. With the improvement of consumers' health awareness and the development of big data technology, the traditional "one-size-fits-all" drug sales model can no longer meet customers' requirements for accurate medication guidance and health management services. In the application scenario, it is required that pharmacy terminals can realize intelligent and personalized drug recommendations based on multi-dimensional data such as customers' historical drug purchase records, disease characteristics, physical information, and medication habits. At the same time, this scenario also needs to support functions such as dynamic management of drug inventory, tracking and analysis of recommendation effects, and compliance audits, so as to improve the service level and operation efficiency of pharmacies.

[0003] In response to the above technical requirements, some current pharmacy terminal systems have introduced a recommendation mechanism based on collaborative filtering algorithms and combined with structured customer profiles for preliminary personalized recommendations. This solution collects customers' basic information and drug purchase behavior logs, constructs user portraits and product label systems, and uses similarity calculations to match the potential associations between users and drugs, thereby generating recommendation results. In addition, the system also integrates a simple data analysis module to assist pharmacists in optimizing drug displays and making replenishment decisions, forming a certain degree of intelligent sales closed-loop.

[0004] However, this existing solution still has obvious limitations. First, the collaborative filtering algorithm relies on a large amount of historical interaction data, and it is prone to the problem of recommendation cold start in the scenarios of new users or new drugs, resulting in a decrease in recommendation accuracy. Second, this solution fails to fully integrate dynamic factors such as the changing trends of patients' health status and doctors' suggestions, and it is difficult to provide personalized recommendations with medical basis. In addition, the system lacks the ability to deeply understand professional information such as drug indications and contraindications, and there are certain compliance risks in the recommendation process. Therefore, there is an urgent need for a more refined terminal data management method with medical knowledge support to improve the accuracy, safety, and service quality of drug recommendations. Summary of the Invention

[0005] This application provides a terminal data management method and system for pharmaceutical sales to solve the problems of poor security and poor accuracy in terminal data management in the prior art.

[0006] In a first aspect, this application provides a terminal data management method for pharmaceutical sales, including: Obtain the drug purchase history data, electronic health record data, and allergy and taboo data generated by the customer at the pharmaceutical sales terminal. The drug purchase history data includes the drug name, drug usage frequency, and drug indications purchased by the customer; Based on the cross-correlation relationship among the drug purchase history data, electronic health record data, and allergy and taboo data, construct a drug adaptation physical sign map, which includes physical sign parameters associated with the drug indications; Synchronously collect the customer's heart rate parameter and respiratory rate parameter, and match the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug adaptation physical sign map to obtain a physical sign parameter matching result; According to the physical sign parameter matching result, combined with the drug taboo rules and efficacy data in the drug indication library, generate a personalized recommendation instruction including an initial recommended drug list and a taboo reminder; Based on the real-time change trends of the personalized recommendation instruction, heart rate parameter, and respiratory rate parameter, dynamically adjust the priority order of the drugs in the initial recommended drug list to generate an updated recommended drug list, and send the updated recommended drug list to the pharmaceutical sales terminal.

[0007] Optionally, the step of synchronously collecting the customer's heart rate parameter and respiratory rate parameter, and matching the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug adaptation physical sign map to obtain a physical sign parameter matching result includes: Obtain the customer's body surface reflection signal, extract a periodic fluctuation signal containing cardiac pulsation and respiratory movement characteristics from the body surface reflection signal, and calculate the heart rate parameter and respiratory rate parameter according to the periodic fluctuation signal; Perform interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the drug indication in the drug adaptation physical sign map to generate a heart rate matching degree, and at the same time calculate the matching degree between the respiratory rate parameter and the preset respiratory rate threshold range corresponding to the drug indication in the drug adaptation physical sign map to obtain a respiratory rate matching degree; Adjust the weight ratio of the heart rate matching degree and the respiratory rate matching degree according to the instantaneous change amount of the heart rate parameter and respiratory rate parameter to obtain an adjusted weight ratio; Perform weighted calculation on the heart rate matching degree and the respiratory rate matching degree based on the adjusted weight ratio to generate a physical sign parameter matching result.

[0008] Optionally, the step of performing interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the drug indication in the drug adaptation physical sign map to generate a heart rate matching degree includes: Obtain the preset heart rate threshold range associated with the current drug indication in the drug-adapted physical sign atlas, where the preset heart rate threshold range includes an upper threshold and a lower threshold; Calculate a first deviation amount between the heart rate parameter and the upper threshold, and a second deviation amount between the heart rate parameter and the lower threshold, and superimpose the first deviation amount and the second deviation amount to determine the comprehensive deviation degree of the heart rate parameter relative to the preset heart rate threshold range; Query the preset correspondence between the deviation degree and the matching degree according to the comprehensive deviation degree to obtain a basic heart rate matching degree, and adjust the basic heart rate matching degree through the fluctuation characteristic parameter of the heart rate parameter to generate a heart rate matching degree.

[0009] Optionally, calculating the matching degree between the respiratory rate parameter and the preset respiratory rate threshold range corresponding to the drug indication in the drug-adapted physical sign atlas to obtain a respiratory rate matching degree includes: Extract the upper respiratory rate threshold and the lower respiratory rate threshold associated with the current drug indication from the drug-adapted physical sign atlas, and calculate a first distance difference between the respiratory rate parameter and the upper respiratory rate threshold, and a second distance difference between the respiratory rate parameter and the lower respiratory rate threshold; Superimpose the first distance difference and the second distance difference to determine the comprehensive deviation amount of the respiratory rate parameter relative to the preset respiratory rate threshold range; Based on the comprehensive deviation amount, look up the corresponding basic matching degree value in the preset respiratory rate matching degree conversion table, and correct the basic matching degree value by using the fluctuation characteristic data of the respiratory rate parameter to obtain a respiratory rate matching degree.

[0010] Optionally, based on the real-time change trends of the personalized recommendation instruction, the heart rate parameter, and the respiratory rate parameter, dynamically adjusting the priority order of the drugs in the initial recommended drug list to generate an updated recommended drug list includes: According to the heart rate parameter and the respiratory rate parameter, calculate the heart rate change trend value and the respiratory rate change trend value within a preset time window; According to the association relationship between the drug indication and the physical sign parameter in the drug-adapted physical sign atlas, determine the dynamic influence coefficients of the heart rate change trend value and the respiratory rate change trend value on the drug indication, and based on the dynamic influence coefficients, adjust the initial priority scores of the drugs in the initial recommended drug list; According to the contraindication prompt in the personalized recommendation instruction, adjust the initial priority scores of the drugs marked as contraindications in the initial recommended drug list, and comprehensively calculate the adjusted initial priority scores and the drug usage frequencies to generate the priority scores of the drugs; Re - sort the drugs in the initial recommended drug list according to the said priority scores to generate an updated recommended drug list.

[0011] Optionally, the determining of the dynamic influence coefficients of the heart rate change trend value and the respiratory rate change trend value on the drug indications according to the association relationship between the drug indications and the physical sign parameters in the drug - adapted physical sign map includes: Extract the heart rate - related parameters and respiratory rate - related parameters associated with the drug indications from the drug - adapted physical sign map; Obtain the heart rate influence component according to the degree of association between the heart rate change trend value and the heart rate - related parameters, and at the same time calculate the association strength between the respiratory rate change trend value and the respiratory rate - related parameters to obtain the respiratory rate influence component; Superimpose the heart rate influence component and the respiratory rate influence component to generate an initial influence coefficient, and dynamically correct the initial influence coefficient based on the historical association data between the drug indications and the physical sign parameters to obtain the dynamic influence coefficient.

[0012] Optionally, the generating of a personalized recommendation instruction including an initial recommended drug list and a contraindication prompt according to the physical sign parameter matching result, in combination with the drug contraindication rules and efficacy data in the drug indication library, includes: Determine the drug indication category adapted to the customer's current physical sign state based on the physical sign parameter matching result, and extract the candidate drug information associated with the drug indication category from the drug indication library; Compare the candidate drug information with the list of prohibited drugs in the drug contraindication rules in the drug indication library, and exclude the drug information included in the list of prohibited drugs to obtain the safe drug information; Rank the safe drug information according to the efficacy data in the drug indication library to obtain a drug ranking result, and associate the drug ranking result with the drug usage frequency in the drug purchase history data to obtain the initial recommended drug list; Add contraindication prompt information to the drugs in the initial recommended drug list according to the allergy contraindication data to generate a personalized recommendation instruction.

[0013] In a second aspect, the present application provides a terminal data management system for pharmaceutical sales, including: An acquisition module, which acquires the drug purchase history data, electronic health record data and allergy contraindication data generated by a customer at a pharmaceutical sales terminal, and the drug purchase history data includes the drug names, drug usage frequencies and drug indications purchased by the customer; A construction module constructs a drug-adapted physical sign map based on the cross-correlation relationship among the drug purchase history data, the electronic health record data, and the allergy and taboo data. The drug-adapted physical sign map includes physical sign parameters associated with the indications of the drug. A matching module synchronously collects the heart rate parameter and the respiratory rate parameter of the customer, and matches the heart rate parameter and the respiratory rate parameter with the physical sign parameters in the drug-adapted physical sign map to obtain a physical sign parameter matching result. A generation module generates a personalized recommendation instruction including an initial recommended drug list and a taboo reminder according to the physical sign parameter matching result, in combination with the drug taboo rules and efficacy data in the drug indication library. An adjustment module dynamically adjusts the priority order of the drugs in the initial recommended drug list based on the real-time change trends of the personalized recommendation instruction, the heart rate parameter, and the respiratory rate parameter, generates an updated recommended drug list, and sends the updated recommended drug list to the pharmaceutical sales terminal.

[0014] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a terminal data management method for pharmaceutical sales as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements a terminal data management method for pharmaceutical sales as described in the first aspect.

[0016] In an embodiment of the present application, the drug purchase history data, the electronic health record data, and the allergy and taboo data generated by a customer at a pharmaceutical sales terminal are obtained. The drug purchase history data includes the drug name, drug usage frequency, and drug indications purchased by the customer; based on the cross-correlation relationship among the drug purchase history data, the electronic health record data, and the allergy and taboo data, a drug-adapted physical sign map is constructed. The drug-adapted physical sign map includes physical sign parameters associated with the indications of the drug; the heart rate parameter and the respiratory rate parameter of the customer are synchronously collected, and the heart rate parameter and the respiratory rate parameter are matched with the physical sign parameters in the drug-adapted physical sign map to obtain a physical sign parameter matching result; according to the physical sign parameter matching result, in combination with the drug taboo rules and efficacy data in the drug indication library, a personalized recommendation instruction including an initial recommended drug list and a taboo reminder is generated; based on the real-time change trends of the personalized recommendation instruction, the heart rate parameter, and the respiratory rate parameter, the priority order of the drugs in the initial recommended drug list is dynamically adjusted, an updated recommended drug list is generated, and the updated recommended drug list is sent to the pharmaceutical sales terminal.

[0017] The technical solution of this application has the following beneficial effects: By integrating multi-source data such as medication purchase history, health records, and allergy taboos, this application establishes a customer health profile in the pharmaceutical sales scenario, providing a structured data basis for subsequent analysis. By cross-correlating drug indications with physical sign parameters such as heart rate and respiratory rate thresholds, a dynamic and extensible drug-sign physical sign association rule library is formed to support real-time matching and decision-making. Through non-contact physical sign monitoring technology, customer health status data is obtained in real time, and dynamic matching is performed in combination with the preset thresholds in the atlas, realizing the instant association analysis of health status and drug indications. Based on the dual constraints of the physical sign matching results and the drug taboo efficacy rules, a recommended list that takes into account both safety and effectiveness is generated to avoid medication risks. According to the real-time changes of physical sign parameters, the recommended order is dynamically optimized to ensure that the recommendation strategy is adaptively adjusted according to the changes in the customer's health status, improving the timeliness of the recommendation.

[0018] Furthermore, by collecting the customer's body surface reflection signals to extract periodic fluctuation characteristics, the heart rate and respiratory rate parameters are calculated. The parameters are matched with the preset threshold intervals in the drug-adapted physical sign atlas to generate a matching degree, and the matching degree weight ratio is dynamically adjusted according to the instantaneous change amount of the parameters. Finally, the physical sign parameter matching result is calculated by weighted calculation. Breaking through the limitations of traditional static threshold matching, the sensitivity to abnormal physical sign fluctuations is enhanced through a dynamic weight adjustment mechanism, improving the matching accuracy and real-time response ability of health status and drug indications in the pharmaceutical recommendation scenario.

[0019] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 Shows a flowchart of a terminal data management method for pharmaceutical sales provided by this application; Figure 2 Shows a schematic structural diagram of a terminal data management system for pharmaceutical sales provided by this application; Figure 3 Shows a schematic structural diagram of a computing device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0023] In some processes described in the specification, claims and above-mentioned drawings of this application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish each different operation, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0024] Researchers found that traditional pharmaceutical sales terminals lack the ability to integrate multi-dimensional health data of customers, making it difficult to achieve precise drug recommendations based on real-time physical sign changes, resulting in lagging and insufficiently safe recommendation results. Based on this, a terminal data management method for pharmaceutical sales is provided. This method can construct a drug adaptation physical sign map by integrating the purchase history, electronic health records, and allergy taboos data, and dynamically adjust the recommendation list in combination with the heart rate and respiratory rate parameters collected in real time, so as to improve the accuracy and timeliness of personalized drug recommendations.

[0025] Throughout the research process, it was found that traditional pharmaceutical sales terminals are difficult to achieve personalized recommendations through static data and cannot respond to changes in customers' physiological states in real time, resulting in limited recommendation accuracy and safety. Therefore, a method for constructing a drug adaptation physical sign map by integrating the purchase history, health records, and allergy information was developed. By combining the heart rate and respiratory rate parameters collected in real time to dynamically match physical sign features, using drug taboo rules and efficacy data to generate a recommendation list, and continuously optimizing the drug priority according to the change trend of physical sign parameters, a personalized drug recommendation system that can accurately match customers' needs and dynamically adjust is finally realized.

[0026] The technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the scope of protection of this application.

[0027] Figure 1 A flowchart of a terminal data management method for pharmaceutical sales provided for the embodiments of this application is as Figure 1 shown, and this method includes: 101. Obtain the drug purchase history data, electronic health record data, and allergy and contraindication data generated by customers at the pharmaceutical sales terminal. The drug purchase history data includes the drug names, drug usage frequencies, and drug indications purchased by the customers. In this step, the pharmaceutical sales terminal refers to the channel where drugs are directly sold to consumers.

[0028] The drug purchase history data includes the drug names, usage frequencies, and indications purchased by the customers. The electronic health record data refers to the records covering chronic diseases and past diagnosis and treatment information.

[0029] The allergy and contraindication data refers to the records of customers' allergic reactions to specific drugs or ingredients. The drug name is the legal or commercial name used to identify the drug.

[0030] The drug usage frequency refers to the number of times a patient takes the drug within a certain period. The indication is the range of diseases or symptoms for which a drug or treatment method is applicable for diagnosis, treatment, or prevention.

[0031] In the embodiment of the present application, first, collect the drug purchase history data of customers from the pharmacy terminal system, including information such as drug names, usage frequencies, and corresponding indications. These data reflect the past medication behavior characteristics of customers. Then, access the electronic health record data of customers, covering basic diseases, diagnosis records, and doctor's suggestions, etc., to understand their overall health status. Subsequently, extract the allergy and contraindication data, including known drug allergy history and contraindication information, to ensure the safety of subsequent recommendations. Finally, standardize the three types of data and store them in a unified data management platform to provide complete information input for constructing the drug-adapted physical sign map.

[0032] A certain customer has purchased drugs for cardiovascular health many times at the pharmaceutical sales terminal. The drug purchase record shows that the customer has been taking a certain type of antihypertensive drug for a long time and the medication frequency is stable. The electronic health record records that the customer has been diagnosed with abnormal blood pressure and accompanied by mild respiratory sensitivity symptoms. The allergy and contraindication data clearly marks a severe allergic reaction to a certain common antibiotic. The system integrates the above information through a data interface to form the customer's health record, including medication preferences, physiological indicators, and contraindication restrictions.

[0033] 102. Based on the cross-correlation relationship of the drug purchase history data, electronic health record data, and allergy and contraindication data, construct a drug-adapted physical sign map, and the drug-adapted physical sign map includes physical sign parameters associated with the drug indications. In this step, the cross-correlation relationship refers to integrating the information in multiple data sources, such as the drug purchase history data, electronic health record data, and allergy and contraindication data, and analyzing the mutual relationships existing between these data.

[0034] Drug indication association refers to the relationship between diseases or symptoms that a certain drug can effectively treat or relieve, based on the results of medical research and clinical trials.

[0035] The drug-adapted physical sign map refers to the mapping of the association between drug indications and customer physical sign parameters. For example, an antipyretic drug may be associated with "elevated body temperature" and "increased heart rate".

[0036] Physical sign parameters refer to physiological indicators related to the mechanism of action of drugs, such as heart rate, respiratory rate, and blood pressure.

[0037] In the embodiments of the present application, based on the three types of data obtained in step 101, a knowledge graph modeling method is used to construct a drug-adapted physical sign map. First, natural language processing technology is used to semantically analyze the indication descriptions in the drug instructions to extract key physical sign parameters, such as blood pressure, blood glucose level, and inflammation indicators. Then, through rule matching and association analysis, the customer's drug purchase history and physical sign data in the health record are mapped to the corresponding drug nodes to form a multi-dimensional association relationship between drugs and physical signs. Finally, the map not only contains the static mapping of drugs and indications, but also integrates the dynamic changes in the customer's individual health status, providing accurate medical basis support for subsequent personalized recommendations.

[0038] Regarding the customer's antihypertensive drug usage record, the system analyzes the physical sign data of similar patients and finds that the heart rate of most patients is within a specific safe range, and the respiratory rate needs to be maintained within a reasonable range to avoid inducing respiratory symptoms. Based on this, the system establishes an association rule between the antihypertensive drug indication and the heart rate and respiratory rate thresholds in the drug-adapted physical sign map, and marks the sensitivity level of the drug to physical sign changes. For example, a certain type of antihypertensive drug is highly sensitive to heart rate fluctuations.

[0039] 103. Simultaneously collect the customer's heart rate parameter and respiratory rate parameter, and match the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug-adapted physical sign map to obtain a physical sign parameter matching result; In this step, the heart rate parameter refers to the pulsation frequency measured by an optical sensor on the customer's wrist or carotid artery.

[0040] The respiratory rate parameter refers to the number of breaths obtained by monitoring chest movements or a nasal airflow sensor.

[0041] Physical sign parameter matching refers to comparing real-time physical sign data with the preset threshold in the map and calculating the matching degree.

[0042] The physical sign parameter matching result refers to a series of quantitative indicators or scores obtained after comparing the customer's physiological sign parameters such as heart rate and respiratory rate with the pre-constructed drug-adapted physical sign map.

[0043] In the embodiments of the present application, first, the millimeter-wave radar or infrared sensor built into the terminal is used to non-contact collect the micro-motion signals on the customer's body surface. The original signals are filtered and denoised, the heart rate parameters are extracted through the peak detection algorithm, and the respiratory rate parameters are calculated through amplitude integration. Secondly, the extracted heart rate parameters and respiratory rate parameter values are input into the drug-adapted physical sign atlas, and the nearest neighbor algorithm is used to match the preset physical sign threshold range in the drug-adapted physical sign atlas, and the matching degree score is calculated. The dynamic weight adjustment calculates the change rate through a sliding window according to the change trend of the physical sign parameters to obtain the physical sign parameter matching result.

[0044] When the customer visits the terminal again, the system monitors their physical signs in real time through a non-contact sensor and detects that the current heart rate is within the preset safe range, but the respiratory rate is slightly higher than the recommended range. The system compares the real-time data with the thresholds in the drug-adapted physical sign atlas and calculates that the heart rate matching degree is high and the respiratory rate matching degree is low, indicating that attention should be paid to the medication risks related to the respiratory tract.

[0045] 104. According to the physical sign parameter matching result, combined with the drug contraindication rules and efficacy data in the drug indication library, generate a personalized recommendation instruction including an initial recommended drug list and a contraindication reminder; In this step, the drug indication library refers to a systematic database that contains information on various drugs and their corresponding treatment conditions.

[0046] The drug contraindication rules are a series of guiding principles or specifications used to identify situations in which specific drugs should not be used.

[0047] The initial recommended drug list refers to the drugs that are preferentially recommended according to the matching degree, with high indication matching degree and low contraindication risk.

[0048] The efficacy data involves the evaluation of the effects of drugs under clinical conditions, including the cure rate of the target disease by the drugs, the degree of symptom improvement, and the side effect situation, etc.

[0049] The contraindication reminder refers to adding warning labels to the drugs in the list that may cause allergies or contraindications.

[0050] The personalized recommendation instruction is a specific medication suggestion generated based on a comprehensive analysis of factors such as the customer's individual drug purchase history, electronic health record, allergy and contraindication data, and real-time physical sign parameters.

[0051] In the embodiment of the present application, first, the physical sign parameter matching results are input into the drug indication library. The rule engine is then used to filter out drugs that conflict with the customer's allergy contraindications and health records, generating drug contraindication rules. Secondly, drugs with a matching degree above a threshold are extracted from the drug-compatible physical sign map. The remaining drugs are ranked based on the efficacy data to generate an initial list of recommended drugs. A weighted scoring algorithm is then used to comprehensively consider the matching degree and efficacy data. For drugs that do not trigger contraindication prompts but require attention, a template engine is used to generate personalized recommendation instructions.

[0052] Based on the matching results, the system selects antihypertensive drugs from the drug library that match cardiovascular indications and contain no allergenic ingredients, generating an initial list of recommendations. Furthermore, a warning label is added to certain medications that may increase respiratory burden, stating, "Risk of abnormal respiratory rate exists; consult a physician recommended." The drugs on the list are sorted by efficacy data and frequency of use, prioritizing those with long-term use and minimal side effects.

[0053] 105. Based on the real-time changing trends of the personalized recommendation instructions, heart rate parameters, and respiratory rate parameters, dynamically adjust the priority order of the drugs in the initial recommended drug list, generate an updated recommended drug list, and send the updated recommended drug list to the pharmaceutical sales terminal.

[0054] In this step, priority adjustment refers to increasing the recommendation weight of drugs with relevant indications based on real-time changes in physical signs.

[0055] Real-time change trends refer to the results of dynamic monitoring and analysis of short-term fluctuations in customers' physiological parameters.

[0056] The updated list of recommended drugs is the result of dynamically adjusted drug priority ranking based on real-time changing trends, drug adaptation signs map and contraindication rules.

[0057] Pharmaceutical sales terminals refer to entities or equipment that sell drugs directly to consumers, including first-terminal hospital pharmacies, second-terminal chain pharmacies and single-store pharmacies, and third-terminal community clinics, rural health centers, and individual pharmacies.

[0058] In an embodiment of the present application, based on the personalized recommendation instructions generated in step 104, the real-time change trends of the heart rate parameters and the respiratory rate parameters are further combined to use a time series prediction model to perform a short-term evolution analysis of the customer's health status. If a certain sign is found to have obvious fluctuations, the priority order of the relevant drugs in the personalized recommended drug list will be automatically adjusted. For example, when the heart rate continues to rise, the system will increase the recommendation weight of cardiovascular regulation drugs. Finally, the updated recommended drug list will be pushed to the pharmaceutical sales terminal interface for reference by customers or pharmacists, thereby realizing a dynamic recommendation closed-loop process based on real-time health status.

[0059] During the customer's viewing of the recommended list, the system continuously monitors that their breathing rate gradually increases and approaches the preset abnormal threshold. At this time, the system automatically reduces the priority of drugs that may affect respiratory function, promotes the ranking of another type of alternative drug that has no impact on the respiratory system, pushes the updated list to the terminal screen, and simultaneously issues a soft voice prompt: "Sign changes detected, and the recommendation has been optimized for you."

[0060] In summary, steps 101 to 105 construct a full-chain recommendation system from historical behavior to real-time physical signs through multi-source data fusion and real-time dynamic analysis. The cross-correlation of the purchase history and the health record ensures the comprehensiveness of the recommendation basis, the combination of physical sign parameter matching and taboo rules improves safety, and the dynamic adjustment based on trends enhances the timeliness and accuracy of the recommendation. Ultimately, it realizes the scientific, intelligent, and safe personalized drug recommendation, reduces the medication risk, and optimizes the customer experience.

[0061] To solve the problem of the accuracy of real-time physiological data matching in personalized drug recommendation, this method dynamically matches by synchronously collecting the customer's heart rate and breathing rate parameters and combining the preset threshold range in the drug-adapted physical sign map. The core of the research and development lies in using the surface reflection signal to extract the periodic fluctuation characteristics of the cardiac pulsation and respiratory movement, calculating the deviation amount and fluctuation trend, and dynamically adjusting the weight ratio of the heart rate and breathing rate matching degree, and finally generating a comprehensive matching result. This process improves the accuracy and adaptability of the matching by quantifying the deviation degree between the parameters and the threshold and introducing a weight correction mechanism for the real-time change amount. In some embodiments, in step 103, the synchronously collecting the customer's heart rate parameter and breathing rate parameter, and matching the heart rate parameter and breathing rate parameter with the physical sign parameter in the drug-adapted physical sign map to obtain a physical sign parameter matching result includes: 201. Obtain the customer's surface reflection signal, extract the periodic fluctuation signal containing the cardiac pulsation and respiratory movement characteristics from the surface reflection signal, and calculate the heart rate parameter and breathing rate parameter according to the periodic fluctuation signal; In step 201, the cardiac pulsation refers to the process in which the heart pumps blood through regular contraction and relaxation. The respiratory movement refers to the process of gas exchange achieved through the expansion and contraction of the lungs. The surface reflection signal refers to the weak fluctuation signal generated on the customer's skin surface due to the cardiac pulsation and respiratory movement collected by a non-contact sensor. The periodic fluctuation signal is the time-series signal corresponding to the cardiac pulsation and respiratory movement separated after filtering and feature extraction. The heart rate parameter is the number of heartbeats per minute calculated according to the cardiac pulsation cycle. The breathing rate parameter is the number of breaths per minute calculated according to the respiratory cycle.

[0062] In the embodiments of the present application, first, a non-contact sensor device is used to collect the body surface reflection signal of a customer, and this signal contains minute body surface vibration information caused by heartbeats and respiratory movements. Subsequently, signal filtering and feature extraction techniques are employed to separate the periodic fluctuation components from the original reflection signal, and waveform features related to heartbeats and respiration are extracted respectively. Then, Fourier transform or wavelet analysis methods are used to perform frequency domain conversion on the extracted waveforms to identify their main frequency components, thereby calculating the heart rate parameter and the respiratory rate parameter. Finally, these two parameters are used as the basic inputs for subsequent matching analysis to evaluate the degree of fit between the customer's current physiological state and the drug indications.

[0063] 202. Perform interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the drug indication in the drug adaptation sign map to generate a heart rate matching degree. At the same time, calculate the matching degree between the respiratory rate parameter and the preset respiratory rate threshold range corresponding to the drug indication in the drug adaptation sign map to obtain a respiratory rate matching degree. In step 202, the preset heart rate threshold range refers to the heart rate safety interval associated with the indication defined in the drug adaptation sign map. The heart rate matching degree refers to the degree of compliance between the real-time heart rate and the threshold range. The preset respiratory rate threshold refers to the range of safe or ideal respiratory rates preset according to factors such as the individual's age and health status in a specific application or medical context. The respiratory rate matching degree refers to the degree of compliance between the actually measured respiratory rate and the preset standard or expected value.

[0064] In the embodiments of the present application, based on the heart rate parameter and the respiratory rate parameter calculated in step 201, interval matching analysis is performed between them and the heart rate threshold range and the respiratory rate threshold range set for the corresponding drug indication in the drug adaptation sign map respectively. Specifically, a numerical interval overlap degree calculation method is used to determine the degree to which the current parameter value falls within the preset threshold range, and then two quantitative indicators, namely the heart rate matching degree and the respiratory rate matching degree, are generated. These two indicators reflect the degree of fit between the customer's current physiological state and a specific drug indication, providing a basis for subsequent dynamic weight adjustment.

[0065] 203. Adjust the weight ratio of the heart rate matching degree and the respiratory rate matching degree according to the instantaneous change amount of the heart rate parameter and the respiratory rate parameter to obtain an adjusted weight ratio. In step 203, the instantaneous change amount refers to the fluctuation amplitude of the heart rate or respiratory rate within a preset time window. The weight ratio refers to the contribution ratio of different sign matching degrees in the final result. The heart rate matching degree refers to the degree of compliance between the actually measured heart rate and a preset standard or target heart rate. The respiratory rate matching degree refers to the degree of fit between the actually measured respiratory rate and the preset safe or ideal respiratory rate range.

[0066] In the embodiments of the present application, on the basis of obtaining the heart rate matching degree and the breathing rate matching degree, the instantaneous change trends of the heart rate parameters and the breathing rate parameters are further analyzed, that is, the fluctuation amplitude per unit time. If a certain parameter shows a significant fluctuation, it indicates that this physical sign has a more critical impact on the current health status. Accordingly, a sliding window statistical method is used to calculate the change amount, and the weight ratio of the heart rate matching degree and the breathing rate matching degree is dynamically adjusted based on the size of the change amount. For example, when the heart rate changes violently, the weight proportion of its matching degree is increased, and vice versa, the influence of the breathing rate is emphasized to ensure that the matching result is more in line with the real-time health status.

[0067] 204. Perform a weighted calculation on the heart rate matching degree and the breathing rate matching degree based on the adjusted weight ratio to generate a physical sign parameter matching result.

[0068] In step 204, the physical sign parameter matching result is the final matching score generated after comprehensively considering the heart rate matching degree, the breathing rate matching degree, and the adjusted weight ratio. The weighted calculation is a mathematical processing method that reflects the relative importance in the overall evaluation or calculation by assigning corresponding weights to different numerical values or variables.

[0069] In the embodiments of the present application, after the weight ratio is adjusted in step 203, a weighted summation operation is performed on the heart rate matching degree and the breathing rate matching degree according to the adjusted weights to generate a comprehensive physical sign parameter matching result. This result integrates the key indicators of the customer's current physiological state and their change trends, can more accurately reflect the adaptation relationship between the individual and the drug indication, provides a core decision-making basis for the generation of subsequent personalized recommendation instructions, and realizes a complete data conversion process from the original body surface signal to the input of the recommendation logic.

[0070] The following is a specific example: When a customer purchases medicine at a medical product sales terminal, a millimeter-wave radar collects the body surface reflection signals. After preprocessing, the system separates the heartbeat signal and the breathing signal from them, and calculates the real-time heart rate and breathing rate accordingly. The system compares the actual heart rate with the corresponding heart rate threshold range in the drug adaptation physical sign map to generate the heart rate matching degree. The same method is used for the breathing rate to obtain the breathing rate matching degree. Subsequently, the system analyzes the fluctuation trends of the heart rate and the breathing rate through a sliding window algorithm, calculates their instantaneous change amounts, and adjusts the weight ratio of the two in the final evaluation according to the change significance. Then, the system performs a weighted calculation on the matching degrees and the corresponding weights to obtain a comprehensive physical sign parameter matching result. Based on this result, the system determines that the current physical sign state is "highly matched", and sends an instruction to preferentially recommend a specific drug to the drug recommendation module, and the relevant information is synchronously displayed on the sales terminal screen.

[0071] In summary, steps 201 to 204 ensure the non-invasiveness and real-time nature of physiological parameter collection through millimeter-wave radar and signal processing technologies. By combining the interval matching and weight adjustment algorithms, the adaptability and sensitivity of the matching results are improved. The finally generated matching results of the physical sign parameters provide a scientific basis for personalized drug recommendation, effectively reducing the medication risk and optimizing the customer experience.

[0072] To solve the problem of how to quantitatively evaluate the matching degree between the customer's current heart rate status and the drug indication, by calculating the upper and lower deviation amounts of the heart rate parameter from the preset threshold range, and superimposing them to form a comprehensive deviation degree, and dynamically correcting the basic matching degree in combination with the heart rate fluctuation characteristics. This method breaks through the limitation of single-threshold matching, introduces the fluctuation characteristics as a correction factor, makes the matching result more conform to the complexity of individual physical signs, and thus improves the pertinence and safety of drug recommendation. In some embodiments, the step 202 of performing interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the drug indication in the drug adaptation physical sign map to generate a heart rate matching degree includes: 301. Obtain the preset heart rate threshold range associated with the current drug indication in the drug adaptation physical sign map, where the preset heart rate threshold range includes an upper threshold and a lower threshold; In step 301, the preset heart rate threshold range is a reasonable fluctuation range set according to the heart rate control target required for a specific indication in clinical research or the drug instruction manual. The upper threshold and the lower threshold respectively represent the maximum and minimum values of this range, and are used to define an acceptable heart rate range.

[0073] In the embodiments of the present application, first, extract the heart rate parameter constraint information related to the current drug indication from the drug adaptation physical sign map. This map stores the physiological conditions applicable to various drugs, including the corresponding upper and lower heart rate thresholds, which are used to define the heart rate range within which the drug has the best efficacy or safety guarantee. Through the data query interface, obtain the specific values of these thresholds to form a clear reference interval. This preset heart rate threshold range serves as the basic standard for subsequent deviation amount calculation, ensuring that the subsequent matching degree analysis can be carried out according to medical norms.

[0074] 302. Calculate the first deviation amount of the heart rate parameter from the upper threshold and the second deviation amount from the lower threshold, and superimpose the first deviation amount and the second deviation amount to determine the comprehensive deviation degree of the heart rate parameter relative to the preset heart rate threshold range; In step 302, the first deviation refers to the degree to which the actual heart rate exceeds the upper threshold; if not, it is zero. The second deviation refers to the degree to which the actual heart rate falls below the lower threshold; if not, it is zero. The combined deviation is the linear superposition of the deviations in these two directions, reflecting the overall severity of the deviation from the ideal range.

[0075] In an embodiment of the present application, first, after obtaining the customer's real-time heart rate value, the system compares it with the upper threshold and the lower threshold respectively. If the heart rate is higher than the upper threshold, the difference is calculated as the first deviation; if the heart rate is lower than the lower threshold, the difference is calculated as the second deviation. Secondly, the two deviations are superimposed using the absolute value weighting method or the Euclidean distance method to obtain the comprehensive deviation degree of the heart rate parameter relative to the ideal threshold range. The larger the deviation degree value, the less the customer's current heart rate meets the ideal applicable conditions of the drug, thereby affecting the subsequent matching score.

[0076] 303. Query a preset correspondence between the deviation degree and the matching degree according to the comprehensive deviation degree to obtain a basic heart rate matching degree, and adjust the basic heart rate matching degree according to the fluctuation characteristic parameter of the heart rate parameter to generate a heart rate matching degree.

[0077] In step 303, the correspondence between the degree of deviation and the degree of match is a pre-defined mapping function or table lookup rule, typically showing a decreasing trend in the degree of match as the degree of deviation increases. Fluctuation characteristic parameters refer to indicators of the heart rate's temporal changes, such as rate of change and amplitude of fluctuation, and are used to reflect heart rate stability. The basic heart rate match is the initial match score calculated solely based on the static degree of deviation. The heart rate match is the final match score, corrected for stability factors, and better reflects the dynamic changes in the patient's current physiological state and drug compatibility.

[0078] In the embodiment of the present application, the system first inputs the comprehensive deviation degree into the preset deviation degree and matching degree mapping module, and outputs a basic heart rate matching degree. Subsequently, the system analyzes the historical fluctuations of the heart rate parameters, uses a sliding window algorithm to calculate the heart rate change rate and fluctuation amplitude, and generates fluctuation characteristic parameters. If the fluctuation is large, the basic matching degree is appropriately reduced; if the fluctuation is small and tends to be stable, the matching degree is maintained or slightly increased. The final output adjusted heart rate matching degree is closer to the customer's actual physiological state and the dynamic changes in drug compatibility.

[0079] Here's a specific example: A customer is checking a medicine for regulating blood pressure in front of a self-service medical terminal. The system collects the reflected signals from the customer's body surface through millimeter-wave radar, and obtains the current heart rate value after processing. Subsequently, the system extracts the heart rate threshold range corresponding to the medicine from the medicine-adapted physical sign atlas. The actual heart rate value is compared with the upper and lower limits, the deviation degree is calculated, and the basic matching degree is obtained accordingly. At the same time, the system also analyzes the change trend of the customer's heart rate in the past period of time, and finds that the customer's heart rate shows an upward trend with enhanced volatility. Therefore, the basic matching degree is moderately adjusted downward to generate the final heart rate matching degree. This matching degree is used in the comprehensive evaluation link of the medicine recommendation system to determine whether to preferentially recommend this medicine and synchronously display the recommendation reason.

[0080] In summary, steps 301 to 303 realize a full-process evaluation mechanism from static threshold comparison to dynamic fluctuation adjustment through multi-level modeling of the matching relationship between heart rate and medicine indications. It not only considers whether the heart rate is within a reasonable range, but also introduces fluctuation characteristics to optimize the matching degree twice, improving the scientificity and personalization level of the recommendation result. This multi-dimensional evaluation method enhances the sensitivity of the medicine recommendation system to the user's current health status, and helps to achieve a safer and more accurate over-the-counter medicine guidance service.

[0081] To solve the problem of how to quantitatively evaluate the matching degree between the customer's current breathing frequency state and the medicine indications, the upper and lower distance differences between the calculated parameters and the preset threshold are calculated, and the comprehensive deviation amount is formed after superposition. The basic matching degree is corrected by combining the breathing frequency fluctuation characteristics. The research and development idea focuses on solving the matching deviation problem caused by individual differences or environmental interference of the breathing frequency. The robustness of the matching is improved through a dynamic correction mechanism to ensure that the recommendation result better meets the actual clinical needs. In some embodiments, step 202 of calculating the matching degree between the breathing frequency parameter and the preset breathing frequency threshold range corresponding to the medicine indication in the medicine-adapted physical sign atlas to obtain the breathing frequency matching degree includes: 401. Extract the upper breathing frequency threshold and the lower breathing frequency threshold associated with the current medicine indication from the medicine-adapted physical sign atlas, and calculate the first distance difference between the breathing frequency parameter and the upper breathing frequency threshold, and the second distance difference between the breathing frequency parameter and the lower breathing frequency threshold; In step 401, the upper breathing frequency threshold and the lower breathing frequency threshold are the boundary values of the ideal breathing frequency interval set according to clinical guidelines or medicine instructions. The first distance difference refers to the degree to which the actual breathing frequency value exceeds the upper threshold, and is zero if it does not exceed. The second distance difference refers to the degree to which the actual breathing frequency value is lower than the lower threshold, and is zero if it is not lower.

[0082] In the embodiments of the present application, first, the system first identifies the drug that the customer is currently querying or preparing to purchase, and extracts the heart rate threshold range data related to the indications of the drug from the drug-adapted physical sign atlas by calling the database interface. This process calls the database interface to find the upper limit threshold and lower limit threshold of the respiratory rate in the corresponding record according to the drug identifier. Subsequently, the system compares the real-time collected respiratory rate parameter with the upper limit threshold and lower limit threshold of the respiratory rate respectively. If the respiratory rate is higher than the upper limit, the difference is calculated as the first distance difference; if the respiratory rate is lower than the lower limit, the difference is calculated as the second distance difference. The absolute values of both are saved to provide input for subsequent calculations.

[0083] 402. Superimpose the first distance difference and the second distance difference to determine the comprehensive deviation amount of the respiratory rate parameter relative to the preset respiratory rate threshold range; In step 402, the first distance difference refers to the degree to which the actual respiratory rate value exceeds the upper limit threshold, and is zero if it does not exceed. The second distance difference refers to the degree to which the actual respiratory rate value is lower than the lower limit threshold, and is zero if it is not lower. The comprehensive deviation amount is the result of linearly superimposing the deviation situations in the above two directions, reflecting the severity of the overall deviation from the ideal interval.

[0084] In the embodiments of the present application, first, based on the first distance difference and the second distance difference obtained in the steps, they respectively represent the positive deviation between the current respiratory rate parameter and the upper limit of the preset respiratory rate threshold range and the negative deviation between the current respiratory rate parameter and the lower limit. These two differences are superimposed and calculated by a mathematical weighting method, usually using the method of absolute value summation or square root of the sum of squares, to eliminate the directional influence and retain the authenticity of the deviation degree. The superimposed result is the comprehensive deviation amount of the respiratory rate parameter relative to the standard range, which is used to measure the matching level between the customer's current respiratory state and the requirements of the drug indications. This comprehensive deviation amount is the key input for subsequent matching degree generation, directly affecting the safety and applicability evaluation of the recommended drugs.

[0085] 403. Based on the comprehensive deviation amount, find the corresponding basic matching degree value in the preset respiratory rate matching degree conversion table, and correct the basic matching degree value by using the fluctuation characteristic data of the respiratory rate parameter to obtain the respiratory rate matching degree.

[0086] In step 403, the respiratory rate matching degree conversion table refers to a pre-set mapping function or look-up table rule, usually showing that as the deviation amount increases, the matching degree shows a decreasing trend. The basic matching degree value refers to the initial matching score calculated only based on the static deviation amount. The respiratory rate matching degree refers to the final matching score corrected by combining stability factors, which can better reflect the dynamic changes in the current physiological state of the customer and the drug suitability.

[0087] In the embodiments of the present application, after obtaining the comprehensive deviation amount, it is used as an input parameter and mapped to a preset respiration frequency matching degree conversion table to find the corresponding initial basic matching degree value. This conversion table is set by medical experts according to clinical data to ensure that the basic matching degree conforms to the influence law of actual physiological changes on drug efficacy. Subsequently, the fluctuation characteristic data of the respiration frequency parameter, such as the short-term fluctuation amplitude or change rate, is introduced to evaluate the stability of this physical sign. If the fluctuation is large, it is considered that there is uncertainty in the current state, and the matching degree is correspondingly lowered; otherwise, the matching degree can be appropriately increased. Finally, the respiration frequency matching degree obtained after being corrected by the fluctuation characteristics is closer to the real-time health status of the customer, provides accurate data support for personalized recommendation, and lays a reliable basis for the dynamic adjustment of subsequent recommendation instructions.

[0088] The following is a specific example: A customer is viewing a drug for relieving asthma symptoms in front of a self-service medical terminal. The system collects the body surface reflection signal through a millimeter-wave radar, and obtains the current respiration frequency value after processing. Subsequently, the system extracts the respiration frequency threshold range corresponding to this drug from the drug adaptation physical sign map. The actual respiration frequency value is compared with the upper and lower limits to calculate the deviation amount, and the basic matching degree is obtained accordingly. At the same time, the system also analyzes the change trend of the customer's respiration frequency in the past period of time, and finds that the respiration frequency shows an upward trend and the volatility increases, so the basic matching degree is moderately lowered to generate the final respiration frequency matching degree. This matching degree is used in the comprehensive evaluation link of the drug recommendation system to determine whether to give priority to recommending this drug and synchronously display the recommendation reason.

[0089] In summary, steps 401 to 403 realize the whole-process evaluation mechanism from static threshold comparison to dynamic fluctuation adjustment through multi-level modeling of the matching relationship between respiration frequency and drug indications. It not only considers whether the respiration frequency is in a reasonable range, but also introduces fluctuation characteristics to optimize the matching degree twice, improving the scientificity and personalization level of the recommendation result. This multi-dimensional evaluation method enhances the sensitivity of the drug recommendation system to the user's current health status, and helps to achieve a safer and more accurate over-the-counter drug guidance service.

[0090] To solve the problem of real-time optimization of drug recommendation priorities, this solution dynamically adjusts drug recommendation priorities by monitoring the changing trends of heart rate and respiratory rate in real time, combines the correlation between the changing trends of physical sign parameters and drug indications, calculates the dynamic influence coefficient, and comprehensively adjusts the priority scores based on taboo rules and drug usage frequencies. This process realizes the dynamic response of the recommendation results, solves the defect that static recommendations cannot adapt to real-time changes in physical signs, and improves the timeliness and scientific nature of personalized recommendations. In some embodiments, in step 105, based on the real-time changing trends of the personalized recommendation instruction, heart rate parameters, and respiratory rate parameters, dynamically adjusting the priority order of drugs in the initial recommended drug list to generate an updated recommended drug list includes: 501. Calculate the heart rate change trend value and respiratory rate change trend value within a preset time window according to the heart rate parameters and respiratory rate parameters; In step 501, the preset time window refers to a fixed duration interval used to analyze the changes in physical sign parameters. The heart rate change trend value and respiratory rate change trend value respectively represent the fluctuation direction and amplitude of the heart rate and respiratory rate within this window.

[0091] In the embodiments of the present application, first, the customer's heart rate parameters and respiratory rate parameters are collected in real time through sensors, and continuous time series data is recorded within a preset time window. The linear regression algorithm is applied to the heart rate parameters to calculate its change slope as the trend value. The differential mean of adjacent time points of the respiratory rate parameters is calculated as the fluctuation amplitude index. Secondly, the collected time series data is input into the calculation module after filtering and denoising, and the heart rate change trend value and respiratory rate change trend value are output.

[0092] 502. Determine the dynamic influence coefficients of the heart rate change trend value and respiratory rate change trend value on the drug indications according to the correlation between the drug indications and physical sign parameters in the drug adaptation physical sign map, and adjust the initial priority scores of each drug in the initial recommended drug list based on the dynamic influence coefficients; In step 502, the correlation refers to the definition of the association between drug indications and physical sign parameters in the drug adaptation physical sign map. The dynamic influence coefficient represents the sensitivity of drug indications to physical sign changes and is determined by the association strength recorded in the drug adaptation physical sign map. The initial priority score refers to the original recommended weight generated according to drug efficacy and taboo rules.

[0093] In the embodiments of the present application, first, according to the correlation between the drug indications and the sign parameters in the drug adaptation sign atlas, the sensitive sign indicators corresponding to the currently recommended drugs are identified, and in combination with the real-time obtained heart rate change trend value and the respiratory rate change value, the influence intensity on the drug efficacy or applicability is calculated. This influence intensity is quantified through a regression analysis model or an expert rule base to form a dynamic influence coefficient. Subsequently, this coefficient is applied to each drug in the initial recommended drug list, and the initial priority score of the drug is weighted and adjusted according to its response characteristics to the sign changes. For example, if the efficacy of a certain drug is enhanced when the heart rate increases, its priority score is increased. This process realizes the dynamic mapping from the physiological state change to the drug recommendation ranking.

[0094] 503. According to the contraindication prompt in the personalized recommendation instruction, adjust the initial priority score of the drug marked as a contraindication in the initial recommended drug list, and comprehensively calculate the adjusted initial priority score and the drug usage frequency to generate the priority score of each drug; In step 503, the contraindication prompt refers to the warning sign of prohibition or cautious use for a specific drug. The drug usage frequency is the high-frequency degree of the drug in historical recommendations or actual uses, reflecting its generality. The comprehensive calculation refers to the weighted summation of the adjusted priority score and the usage frequency to generate the final priority score. The priority score is a specific value obtained by quantitatively evaluating the execution priority of a task, requirement, or operation, and is used to represent its relative rank in resource allocation, processing order, or importance.

[0095] In the embodiments of the present application, on the basis of obtaining the adjusted initial priority score in step 502, the contraindication prompt information in the personalized recommendation instruction is further introduced, and the drugs marked as contraindications are forced to be downgraded, usually by means of negative weight multiplication or directly setting them to the lowest score, to avoid unsafe recommendations. At the same time, in combination with the customer's historical drug usage frequency data, the acceptance and compliance of the drug at the individual level are evaluated by using a collaborative filtering algorithm or a frequency statistics method. Finally, the adjusted initial priority score and the usage frequency score are normalized and fused to generate the comprehensive priority score of the drug, which is used as the core basis for subsequent ranking.

[0096] 504. Reorder the drugs in the initial recommended drug list according to the priority score to generate an updated recommended drug list.

[0097] In step 504, the reordering is to arrange the drugs from high score to low score to generate the final recommendation order. The updated recommended drug list refers to the drug recommendation list generated by adjusting through algorithms or system logic based on dynamic factors such as the patient's real-time health data, personalized needs, drug adaptation rules, and contraindication prompts.

[0098] In the embodiments of the present application, after calculating the priority scores of all drugs, the drugs in the initial recommended drug list are rearranged according to the scores from high to low. During the sorting process, a stable sorting algorithm can be used to ensure that drugs with the same score maintain their original relative order. The updated recommended drug list not only reflects the changing trend of the customer's current physiological state, but also takes into account the safety constraints of drugs and individual medication habits, thus realizing the unity of personalization, safety and practicability of the recommendation results. Finally, this list will be pushed to the pharmaceutical sales terminal for customers or pharmacists to refer to and use, completing the closed-loop process of drug recommendation.

[0099] The following is a specific example: A customer goes to a pharmaceutical terminal to buy medicine due to hypertension. The system first analyzes the real-time monitoring data and finds that the customer's heart rate has risen significantly from a relatively low level to a relatively high level within a preset time window, while the respiratory rate remains stable. Based on this, the heart rate change trend value is calculated as a significant increase, and the respiratory rate trend value is calculated as stable. Subsequently, the drug adaptation sign map is queried to obtain that the sensitivity coefficient of antihypertensive drugs to heart rate fluctuations is medium to high, and the sensitivity coefficient to respiratory rate fluctuations is low, and a dynamic influence coefficient of moderate increase is generated in combination with the current trend value. During the priority adjustment stage, the priority score of a certain potent antihypertensive drug in the initial recommended list is significantly increased after being adjusted by the dynamic influence coefficient, but it is detected that the drug contains a substance that matches the customer's contraindicated ingredients, so its priority is greatly downgraded. Finally, a comprehensive score is generated in combination with the high-frequency use characteristics of the drug in the historical record. In the finally generated updated recommended list, the priority of this drug jumps from a medium position to a high position, and at the same time, another drug without contraindication matching is adjusted to the first place due to the score advantage. The updated list is presented in real time through the terminal interface.

[0100] To sum up, in steps 501 to 504, this solution realizes the real-time optimization of the drug recommendation priority by dynamically analyzing the changing trend of sign parameters, combining drug adaptation rules and contraindication prompts. By trend analysis, it captures the subtle signals of the disease change and improves the foresight of the recommendation. By quantifying the influence of sign changes on drug adaptability with the dynamic influence coefficient, it enhances the scientific nature. By balancing safety and generality through contraindication punishment and usage frequency weighting, it takes into account the user experience and medical norms. The finally generated recommended list has higher accuracy and clinical applicability in a dynamic scenario.

[0101] To solve the problem of comprehensively evaluating the correlation between drug indications and sign parameters, by extracting the correlation parameters of heart rate and respiratory rate, calculating the correlation degree and strength between the trend value and the parameters, and dynamically correcting them in combination with historical correlation data. This method solves the problem that traditional static correlation analysis cannot adapt to dynamic sign changes, making the influence coefficient more dynamic and clinically guiding. In some embodiments, determining the dynamic influence coefficient of the heart rate change trend value and the respiratory rate change trend value on the drug indication according to the correlation between the drug indication and the sign parameters in the drug adaptation sign map in step 502 includes: 601. Extract the heart rate correlation parameter and the respiratory rate correlation parameter associated with the drug indication from the drug adaptation sign map; In step 601, the heart rate correlation parameter represents the sensitivity of the drug indication to heart rate changes, and the respiratory rate correlation parameter represents the sensitivity of the drug indication to respiratory rate changes. Both are extracted from the drug adaptation sign map, and the higher the value, the more significant the influence.

[0102] In the embodiments of the present application, first, based on the knowledge structure in the drug adaptation sign map, locate the indication entry corresponding to the currently recommended drug, and extract the heart rate correlation parameter and the respiratory rate correlation parameter related to this indication therefrom. These parameters are set by medical experts according to clinical research and represent the range of key physiological indicators that affect the drug efficacy in a specific disease state. For example, the efficacy of certain cardiovascular drugs may be closely related to the patient's resting heart rate, while respiratory system drugs may be more dependent on the change trend of the respiratory rate. Through the map query mechanism, these parameters are extracted in a structured form as an important reference basis for subsequent dynamically evaluating the drug recommendation priority, ensuring that the recommendation logic has medical professional support.

[0103] 602. Obtain the heart rate influence component according to the correlation degree between the heart rate change trend value and the heart rate correlation parameter, and at the same time calculate the correlation strength between the respiratory rate change trend value and the respiratory rate correlation parameter to obtain the respiratory rate influence component; In step 602, the correlation strength is an index in statistics to measure the degree of closeness of the relationship between two or more variables. The heart rate influence component is the product of the heart rate change trend value and the heart rate correlation parameter, which is used to quantify the influence intensity of heart rate fluctuations on drug recommendation. The respiratory rate influence component is the product of the respiratory rate change trend value and the respiratory rate correlation parameter, which quantifies the influence intensity of respiratory fluctuations.

[0104] In the embodiments of the present application, on the basis of obtaining the heart rate correlation parameter and the respiratory rate correlation parameter, the matching degree between the current heart rate change trend value of the customer and its corresponding heart rate correlation parameter is further analyzed, and the similarity calculation or regression model is used to evaluate the correlation degree to generate the heart rate influence component. At the same time, for the relationship between the respiratory rate change trend value and the respiratory rate correlation parameter, the correlation strength is calculated by using the correlation coefficient analysis or the dynamic time warping algorithm to obtain the respiratory rate influence component.

[0105] 603. Superimpose the heart rate influence component and the respiratory rate influence component to generate an initial influence coefficient, and dynamically correct the initial influence coefficient based on the historical association data between the drug indication and the sign parameter to obtain a dynamic influence coefficient.

[0106] In step 603, the initial influence coefficient refers to the weighted sum of the heart rate influence component and the respiratory rate influence component. Dynamic correction is a method of continuously adjusting and optimizing strategies, models or systems according to environmental changes, data updates or feedback information. Historical association data refers to a data set that reveals the interrelationships between historical events, phenomena, objects or variables through data mining, statistical analysis or system records within a specific time range. The dynamic influence coefficient refers to the final value obtained by correcting the initial influence coefficient based on the historical association data.

[0107] In the embodiments of the present application, first, the heart rate influence component and the respiratory rate influence component are added according to a preset weight to generate an initial influence coefficient. Secondly, historical association data is queried. For example, the actual use effect of the drug under similar sign parameters in the past three months is used, and the mean value of the historical association data is calculated by using the moving window average algorithm. Finally, the initial influence coefficient and the historical mean value are weighted and fused to obtain a dynamic influence coefficient. For example, if the initial influence coefficient is a high value, but the historical data shows that there is an increased risk of side effects of the drug in a similar scenario, the dynamic influence coefficient is reduced by the correction ratio.

[0108] The following is a specific example: When a customer selects cardiovascular drugs at the medical terminal, the system first queries the drug adaptation sign atlas and obtains that the sensitivity coefficient of antihypertensive drugs to heart rate changes is moderately high, and the sensitivity coefficient to respiratory rate changes is low. Subsequently, it is monitored that the customer's heart rate shows a significant upward trend and the respiratory rate shows a slight downward trend. According to the change amplitude of the heart rate and the sensitivity coefficient, the calculated heart rate impact component is high, and according to the change amplitude of the respiratory rate and the sensitivity coefficient, the calculated respiratory rate impact component is low. Then, the two are superimposed to generate a relatively high initial impact coefficient. However, it is found from the historical data that there is a characteristic of an increased risk of side effects of this drug in the scenario of too fast heart rate. Therefore, the initial impact coefficient is moderately adjusted downward to generate the final dynamic impact coefficient. The system evaluates according to the corrected dynamic impact coefficient and determines that the adaptability of the strong antihypertensive drug is reduced, so it adjusts its priority and preferentially recommends alternative drugs with less side effects.

[0109] In summary, steps 601 to 603 achieve the accurate calculation of the dynamic impact coefficient by structurally extracting the correlation parameters between drugs and signs, and combining the quantitative matching of trend values and parameters. At the same time, the initial value is corrected using historical data to improve the stability and adaptability of the recommendation results, thereby optimizing the accuracy and safety of drug recommendations in complex sign change scenarios.

[0110] To solve the problem of potential medication safety hazards in personalized drug recommendations caused by inaccurate sign parameter matching, uncoverage of contraindication risks, and unreasonable recommendation priorities, this solution extracts candidate drugs from the indication library and excludes contraindicated drugs, optimizes the ranking by combining efficacy scores and usage frequencies, and finally adds allergy warning information. This method realizes safe, accurate, and personalized drug recommendations, and solves the problems of ignoring contraindication risks and historical medication preferences in traditional recommendations. In some embodiments, in step 104, according to the sign parameter matching result, combined with the drug contraindication rules and efficacy data in the drug indication library, a personalized recommendation instruction including an initial recommended drug list and contraindication warnings is generated, including: 701. Determine the drug indication category suitable for the customer's current sign state based on the sign parameter matching result, and extract candidate drug information associated with the drug indication category from the drug indication library; In step 701, the sign parameter matching result includes the customer's physiological indicators, symptom descriptions, and disease diagnosis records. The drug indication category refers to the medical classification corresponding to these signs. The candidate drug information includes drug names, ingredients, indication labels, and efficacy scores. The drug indication category refers to the disease or symptom treatment classification that matches the customer's current sign state. The drug indication library is a systematic database that centrally stores, manages, and dynamically updates drug indication-related data. Its core function is to provide standardized and structured indication information support for drug research and development, clinical decision-making, medication safety, and personalized recommendations.

[0111] In the embodiments of the present application, first, the symptom description of the customer is parsed through natural language processing technology, keywords are extracted and mapped to standard medical terms. Subsequently, using a rule-based classification model or a machine learning classifier, the physical sign parameters are matched with the preset drug indication categories to determine the currently applicable drug indication category. For example, if the customer's blood pressure value is higher than the threshold and the symptoms include dizziness, it is matched to the "hypertensive" category. After the matching is completed, all drug information of this category is retrieved from the drug indication library to form candidate drug information.

[0112] 702. Compare the candidate drug information with the list of prohibited drugs in the drug contraindication rules in the drug indication library, exclude the drug information included in the list of prohibited drugs, and obtain safe drug information; In step 702, the drug contraindication rules include a list of prohibited drugs and patient condition restrictions. Safe drug information refers to the remaining drugs after excluding taboos. The list of prohibited drugs refers to the set of drugs prohibited under specific diseases marked in the drug indication library. Safe drug information refers to the subset of candidate drugs after excluding prohibited drugs.

[0113] In the embodiments of the present application, first, the ingredients in the candidate drug information, the drug indication library, and the prohibited conditions in the drug contraindication rules are compared item by item. For example, if a certain drug ingredient matches the customer's allergen, it is removed. The comparison process uses rule engine technology and is screened through preset logical rules. If there are complex conditions, the decision tree algorithm is combined to determine whether the prohibited rule is triggered. The finally generated safe drug information only includes drugs that meet the current customer conditions.

[0114] 703. Prioritize the safe drug information according to the efficacy data in the drug indication library to obtain a drug ranking result, and associate the drug ranking result with the drug usage frequency in the drug purchase history data to obtain an initial recommended drug list; In step 703, the efficacy data includes the clinical trial result scores of drugs, the doctor recommendation frequency, and the patient feedback scores. The drug purchase history data includes the drugs purchased by the customer in the past and their frequencies. The drug ranking result refers to the priority list calculated comprehensively based on efficacy and historical data. The initial recommended drug list refers to the preliminary drug recommendation list generated according to the patient's physical sign parameters, the indication classification in the drug indication library, and the contraindication rules, combined with the efficacy data, historical medication records, and personalized needs.

[0115] In the embodiments of the present application, first, drug information that matches the current customer's health status is extracted from the drug indication library, and these drugs are preliminarily evaluated in combination with the efficacy data stored therein. The efficacy data includes dimensions such as the clinical effectiveness ranking of the drug in the same type of indication, the onset time of action, and the incidence rate of side effects. Through a multi-criteria decision analysis algorithm or a weighted scoring model, the drugs are sorted by priority to obtain the drug sorting result. Subsequently, the sorting result is correlated with the customer's drug purchase history data to extract the names and usage frequencies of the drugs used in the past, and collaborative filtering or frequency statistics methods are used to evaluate the customer's acceptance and compliance with different drugs. Finally, by integrating the efficacy priority and usage frequency information, an initial recommended drug list is generated, providing a basic recommended set for subsequent safety verification and personalized prompt addition.

[0116] 704. Add taboo prompt information to the drugs in the initial recommended drug list according to the allergy taboo data to generate a personalized recommendation instruction.

[0117] In step 704, the allergy taboo data refers to the known allergens of the customer and their corresponding drugs, and the taboo prompt information refers to the warning instructions for the drug ingredients or indications. The taboo prompt information refers to the text warning for the potential risks of the drug. The personalized recommendation instruction refers to a structured instruction containing the initial recommended list and taboo prompts for the terminal device to parse and display.

[0118] In the embodiments of the present application, after obtaining the initial recommended drug list, allergy taboo data is further introduced, and the drug ingredients, action mechanisms, and their corresponding contraindication information in the list are compared one by one. Through a rule matching engine, drugs with potential allergy risks or taboo conflicts are identified, and corresponding taboo prompt information is automatically generated, such as instructions like "contraindicated for those allergic to this ingredient" or "use with caution in patients with abnormal liver function". Subsequently, the taboo prompt information is embedded in the display item of the corresponding drug in the recommendation list to form a personalized recommendation instruction with safety reminders. This instruction not only includes the sorting result of the recommended drugs but also integrates individual health constraints, ensuring that the recommended content has safety guarantees while meeting the efficacy requirements, and improving the intelligence and compliance level of the pharmacy terminal recommendation system.

[0119] The following is a specific example: When a certain customer purchases medicine at a medical terminal due to hypertension, the physical sign monitoring shows a high heart rate. The system first matches the cardiovascular indication category and extracts all antihypertensive drugs as candidate drugs. Subsequently, it filters out the drugs containing ephedrine through the contraindication rules and retains the remaining candidate drugs. Then, by combining the efficacy data with the customer's high-frequency usage records, it ranks the drug with the highest comprehensive weight first. In view of the customer's allergy record, after adding a "use with caution" reminder to the drugs containing caffeine, the system generates a recommended list including the priority ranking and contraindication reminders and pushes it to the terminal screen. The customer finally selects an alternative drug without caffeine to complete the purchase of medicine.

[0120] In summary, steps 701 to 704 ensure the safety of the recommended drugs and improve the personalized matching degree through the physical sign parameters, contraindication rules, efficacy scores, and historical behaviors in the multi-dimensional data fusion. The dynamic exclusion of contraindicated drugs and the priority ranking mechanism effectively reduce the medication risk, and the accurate generation of contraindication reminders further guarantees the safety of patients, thus realizing scientific, safe, and personalized drug recommendations.

[0121] Figure 2 The following is a schematic structural diagram of a terminal data management system for pharmaceutical sales provided by an embodiment of the present application, as Figure 2 shown. The system includes: An acquisition module 21, which acquires the purchase history data, electronic health record data, and allergy contraindication data generated by the customer at the pharmaceutical sales terminal. The purchase history data includes the drug names, drug usage frequencies, and drug indications purchased by the customer; A construction module 22, which constructs a drug-adapted physical sign map based on the cross-correlation relationship of the purchase history data, electronic health record data, and allergy contraindication data. The drug-adapted physical sign map contains physical sign parameters associated with the drug indications; A matching module 23, which synchronously acquires the customer's heart rate parameter and respiratory rate parameter, and matches the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug-adapted physical sign map to obtain a physical sign parameter matching result; A generation module 24, which generates a personalized recommendation instruction including an initial recommended drug list and a contraindication reminder according to the physical sign parameter matching result, in combination with the drug contraindication rules and efficacy data in the drug indication library; An adjustment module 25, which dynamically adjusts the priority order of the drugs in the initial recommended drug list based on the real-time change trends of the personalized recommendation instruction, heart rate parameter, and respiratory rate parameter, generates an updated recommended drug list, and sends the updated recommended drug list to the pharmaceutical sales terminal.

[0122] Figure 2 The described terminal data management system for pharmaceutical sales can execute Figure 1The implementation principles and technical effects of the terminal data management method for pharmaceutical sales described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the terminal data management system for pharmaceutical sales described in the above embodiment has been described in detail in the related embodiments of the method and will not be further elaborated here.

[0123] In one possible design, Figure 2 The terminal data management system for pharmaceutical sales of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0124] The processing component 32 is used for the above Figure 1 The embodiment provides a terminal data management method for pharmaceutical sales.

[0125] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0126] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0127] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0128] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0129] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0130] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server. The above processing components, storage components, etc. can be basic server resources rented or purchased from a cloud computing platform.

[0131] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 terminal data management method for pharmaceutical sales shown in the embodiment.

[0132] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A terminal data management method for pharmaceutical sales, characterized in that, Including: Obtaining the drug purchase history data, electronic health record data, and allergy and taboo data generated by the customer at the pharmaceutical sales terminal. The drug purchase history data includes the drug names purchased by the customer, the drug usage frequency, and the drug indications; Based on the cross - correlation relationship of the drug purchase history data, electronic health record data, and allergy and taboo data, constructing a drug - adapted physical sign map, which contains physical sign parameters associated with the drug indications; Simultaneously collecting the customer's heart rate parameter and respiratory rate parameter, and matching the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug - adapted physical sign map to obtain a physical sign parameter matching result; According to the physical sign parameter matching result, combining the drug taboo rules and efficacy data in the drug indication library, generating a personalized recommendation instruction including an initial recommended drug list and a taboo reminder; Based on the real - time change trends of the personalized recommendation instruction, heart rate parameter, and respiratory rate parameter, dynamically adjusting the priority order of the drugs in the initial recommended drug list, generating an updated recommended drug list, and sending the updated recommended drug list to the pharmaceutical sales terminal.

2. The method according to claim 1, characterized in that, The simultaneously collecting the customer's heart rate parameter and respiratory rate parameter, and matching the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug - adapted physical sign map to obtain a physical sign parameter matching result includes: Obtaining the customer's body surface reflection signal, extracting a periodic fluctuation signal containing cardiac pulsation and respiratory movement characteristics from the body surface reflection signal, and calculating the heart rate parameter and respiratory rate parameter according to the periodic fluctuation signal; Performing interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the current drug indication in the drug - adapted physical sign map to generate a heart rate matching degree, and at the same time calculating the matching degree between the respiratory rate parameter and the preset respiratory rate threshold range corresponding to the current drug indication in the drug - adapted physical sign map to obtain a respiratory rate matching degree; Adjusting the weight ratio of the heart rate matching degree and the respiratory rate matching degree according to the instantaneous change amount of the heart rate parameter and respiratory rate parameter to obtain an adjusted weight ratio; Based on the adjusted weight ratio, performing weighted calculation on the heart rate matching degree and the respiratory rate matching degree to generate a physical sign parameter matching result.

3. The method according to claim 2, characterized in that The performing interval matching between the heart rate parameter and the preset heart rate threshold range corresponding to the current drug indication in the drug - adapted physical sign map to generate a heart rate matching degree includes: Obtaining the preset heart rate threshold range associated with the current drug indication in the drug - adapted physical sign map, where the preset heart rate threshold range includes an upper threshold and a lower threshold; Calculating the first deviation amount between the heart rate parameter and the upper threshold, and the second deviation amount between the heart rate parameter and the lower threshold, and superimposing the first deviation amount and the second deviation amount to determine the comprehensive deviation degree of the heart rate parameter relative to the preset heart rate threshold range; Query the preset correspondence between the deviation degree and the matching degree according to the comprehensive deviation degree to obtain the basic heart rate matching degree, and adjust the basic heart rate matching degree through the fluctuation characteristic parameters of the heart rate parameters to generate the heart rate matching degree.

4. The method according to claim 2, wherein Calculating the matching degree between the respiratory rate parameter and the preset respiratory rate threshold range corresponding to the drug indication in the drug adaptation sign map to obtain the respiratory rate matching degree, including: Extract the upper respiratory rate threshold and the lower respiratory rate threshold associated with the current drug indication from the drug adaptation sign map, and calculate the first distance difference between the respiratory rate parameter and the upper respiratory rate threshold, and the second distance difference between the respiratory rate parameter and the lower respiratory rate threshold; Superimpose the first distance difference and the second distance difference to determine the comprehensive deviation amount of the respiratory rate parameter relative to the preset respiratory rate threshold range; Based on the comprehensive deviation amount, look up the corresponding basic matching degree value in the preset respiratory rate matching degree conversion table, and correct the basic matching degree value by using the fluctuation characteristic data of the respiratory rate parameter to obtain the respiratory rate matching degree.

5. The method according to claim 1, characterized in that Based on the real-time change trends of the personalized recommendation instruction, the heart rate parameter, and the respiratory rate parameter, dynamically adjust the priority order of the drugs in the initial recommended drug list to generate an updated recommended drug list, including: According to the heart rate parameter and the respiratory rate parameter, calculate the heart rate change trend value and the respiratory rate change trend value within a preset time window; According to the association relationship between the drug indication and the sign parameter in the drug adaptation sign map, determine the dynamic influence coefficients of the heart rate change trend value and the respiratory rate change trend value on the drug indication, and based on the dynamic influence coefficients, adjust the initial priority scores of the drugs in the initial recommended drug list; According to the taboo prompt in the personalized recommendation instruction, adjust the initial priority scores of the drugs marked as taboo in the initial recommended drug list, and comprehensively calculate the adjusted initial priority scores and the drug usage frequencies to generate the priority scores of the drugs; Reorder the drugs in the initial recommended drug list according to the priority scores to generate an updated recommended drug list.

6. The method according to claim 5, characterized in that The determining the dynamic influence coefficients of the heart rate change trend value and the respiratory rate change trend value on the drug indication according to the association relationship between the drug indication and the sign parameter in the drug adaptation sign map includes: Extract the heart rate association parameter and the respiratory rate association parameter associated with the drug indication from the drug adaptation sign map; According to the correlation degree between the heart rate change trend value and the heart rate association parameter, obtain the heart rate influence component, and at the same time calculate the correlation strength between the respiratory rate change trend value and the respiratory rate association parameter to obtain the respiratory rate influence component; Superimpose the heart rate influence component and the respiratory rate influence component to generate an initial influence coefficient, and dynamically correct the initial influence coefficient based on the historical association data between the drug indication and the sign parameter to obtain the dynamic influence coefficient.

7. The method according to claim 1, wherein Generating a personalized recommendation instruction including an initial recommended drug list and a contraindication reminder by combining the drug contraindication rules and efficacy data in the drug indication library according to the physical sign parameter matching result, including: Determining a drug indication category adapted to the current physical sign state of the customer based on the physical sign parameter matching result, and extracting candidate drug information associated with the drug indication category from the drug indication library; Comparing the candidate drug information with the list of prohibited drugs in the drug contraindication rules in the drug indication library, excluding the drug information included in the list of prohibited drugs, and obtaining safe drug information; Performing a priority ranking on the safe drug information according to the efficacy data in the drug indication library to obtain a drug ranking result, and associating the drug ranking result with the drug usage frequency in the drug purchase history data to obtain an initial recommended drug list; Adding contraindication reminder information to the drugs in the initial recommended drug list according to the allergy contraindication data to generate a personalized recommendation instruction.

8. A terminal data management system for pharmaceutical sales, characterized in that, Including: An acquisition module that acquires the drug purchase history data, electronic health record data, and allergy contraindication data generated by the customer at the pharmaceutical sales terminal, where the drug purchase history data includes the drug names, drug usage frequencies, and drug indications purchased by the customer; A construction module that constructs a drug-adapted physical sign map based on the cross-correlation relationship among the drug purchase history data, electronic health record data, and allergy contraindication data, and the drug-adapted physical sign map includes physical sign parameters associated with the drug indications; A matching module that synchronously collects the customer's heart rate parameter and respiratory rate parameter, and matches the heart rate parameter and respiratory rate parameter with the physical sign parameters in the drug-adapted physical sign map to obtain a physical sign parameter matching result; A generation module that generates a personalized recommendation instruction including an initial recommended drug list and a contraindication reminder according to the physical sign parameter matching result, in combination with the drug contraindication rules and efficacy data in the drug indication library; An adjustment module that dynamically adjusts the priority order of the drugs in the initial recommended drug list based on the real-time change trends of the personalized recommendation instruction, heart rate parameter, and respiratory rate parameter, generates an updated recommended drug list, and sends the updated recommended drug list to the pharmaceutical sales terminal.

9. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a terminal data management method for pharmaceutical sales as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored, and when the computer program is executed by the computer, it implements a terminal data management method for pharmaceutical sales as described in any one of claims 1 to 7.

Images