Intelligent recommendation of herbal extraction methods and apparatus

Abstract

The application provides a kind of intelligent recommendation herbal extraction method and equipment, belong to intelligent recommendation technical field, its method includes: when user triggers extraction device, the facial image and scalp image of user are collected and image processing and identification are carried out, obtain the facial representation information and scalp representation information of user;Receive the questionnaire information related to health that user inputs in the interactive interface of extraction device, and carry out information analysis, obtain the present basic information;Preliminary estimate the present health condition of user, and extract several health strengthening indexes from the present health condition;Determine the conditioning direction of user in dependence on all health strengthening indexes, and the conditioning effect of traditional Chinese medicine herb and the various extraction methods of traditional Chinese medicine herb existing in extraction device are intelligently matched, output recommended mode for user to select.It is convenient for the required extraction drug to meet the actual needs of user's pathology, to maximize the efficiency of drug extraction and subsequent effective use of drug.

Description

Technical Field

[0001] The present invention relates to the field of intelligent recommendation technology, and in particular to an intelligent recommendation herbal extraction method and equipment. Background Art

[0002] Traditional Chinese medicine preparations are made under the guidance of traditional Chinese medicine theory, using Chinese herbal medicine as raw materials, and are processed into medicines with certain specifications that can be directly used to prevent and treat diseases. Since traditional pharmaceutical manufacturing methods require manual extraction, there may be unsatisfactory drug extraction in this process, resulting in waste of Chinese herbal medicines and reduced efficacy. Or, during the extraction process, general intelligent extraction equipment provides several known drug juices for users to choose from, and does not determine the user's actual needs based on the user themselves, further reducing the ineffective use of drugs.

[0003] Therefore, the present invention proposes an intelligent herbal extraction method and device. Summary of the Invention

[0004] The present invention provides an intelligent herbal extraction method and device for intelligently recommending herbal extraction, which is used to determine the user's health enhancement index through comprehensive analysis of the face, scalp and questionnaire survey, so that the extracted drugs can meet the user's actual pathological needs. The conditioning direction and extraction method are subsequently determined based on the health enhancement index to maximize the efficiency of drug extraction and the subsequent effective use of the drugs.

[0005] The present invention provides an intelligent recommendation herbal extraction method, comprising:

[0006] Step 1: When the user triggers the extraction device, the user's facial image and scalp image are collected and image processing and recognition are performed to obtain the user's facial representation information and scalp representation information;

[0007] Step 2: receiving health-related questionnaire information input by the user on the interactive interface of the extraction device, and parsing the information to obtain current basic information, wherein the questionnaire information includes: the actual pulse rate measured by the user using a pulse sensor on site and several related health indicator information;

[0008] Step 3: Comprehensively analyzing and processing the facial representation information, scalp representation information, and current basic information to preliminarily estimate the user's current health status and extract several health enhancement indicators from the current health status;

[0009] Step 4: Determine the conditioning direction of the user based on all health enhancement indicators, and intelligently match them with the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output a recommended method for the user to choose.

[0010] Preferably, obtaining the facial representation information of the user includes:

[0011] Extracting three-channel components of each pixel in the facial image, comparing the three-channel components with a component combination-skin color database, and matching skin color labels to corresponding pixels;

[0012] Clustering all skin color labels to obtain several skin color blocks, and determining the facial color features of each skin color block. Combined with the facial position of the corresponding skin color block, an initial sequence is constructed.

[0013] Performing low-saturation adjustment and high-saturation adjustment on the image block corresponding to each skin color block to obtain a low-saturation image block and a high-saturation image block respectively;

[0014] Extracting pixel values ​​of the same pixel from the low-saturation image and the high-saturation image, respectively, and combining the first skin color feature and the second skin color feature of the corresponding skin color block in the low-saturation image and the high-saturation image to obtain a reference pair of the corresponding pixel;

[0015] Perform a perimeter search on each pixel point and lock the fault boundary point based on the pixel value of the corresponding pixel point as a reference to obtain the number of fault locks for each pixel point;

[0016] According to the number of locked slices and in combination with reference pairs of corresponding pixels, the initial sequence is expanded to obtain a facial color sequence;

[0017] Inputting the facial color sequence into a skin color sequence analysis model to obtain skin color information corresponding to the skin color block;

[0018] Based on all skin color information and the facial occupancy size of the skin color block corresponding to each skin color information, facial representation information is obtained.

[0019] Preferably, the initial sequence is expanded to obtain a facial color sequence, including:

[0020] Performing a first mean processing on two pixel values ​​in a reference pair of the pixel points to obtain a first value;

[0021] Determine the absolute value of the difference between the pixel value of each locked fault boundary point in the fault locking quantity and the pixel value of the corresponding reference pixel point, and perform a second mean processing to obtain a second value;

[0022] Determine the auxiliary skin color information of the corresponding pixel point based on the first value, the second value, the number of fault locks, and the straight-line distance between each locked fault boundary point and the corresponding pixel point as a reference basis;

[0023] The auxiliary skin color information is added to the corresponding facial position in the initial sequence to obtain a facial color sequence.

[0024] Preferably, information is parsed to obtain current basic information, including:

[0025] Retrieving several embedded points of the user's answers to each health question from the questionnaire information, and adjusting the initial weight of the embedded point based on the modal particle of each embedded point to obtain an embedded point vector;

[0026] Inputting the buried point vector into an answer parsing model matching the health question to obtain health symptoms;

[0027] Among them, all health conditions are taken as current basic information.

[0028] Preferably, the facial representation information, scalp representation information and current basic information are subjected to comprehensive analysis and processing, including:

[0029] performing a first extraction on the facial representation information according to a facial indicator set;

[0030] performing a second extraction on the scalp representation information according to the scalp indicator set;

[0031] Performing a third extraction of the current basic information according to the question-answer indicator set;

[0032] The first extraction result, the second extraction result, and the third extraction result are sequentially input into the result analysis table.

[0033] Preferably, several health enhancement indicators are extracted from the current health status, including:

[0034] Performing a combination analysis of all input results in the result analysis table according to the analysis standard to obtain a corresponding combination analysis result;

[0035] Extract non-healthy factors from each combined analysis result and use them as initial indicators;

[0036] All initial indicators are combined to obtain several health enhancement indicators.

[0037] Preferably, the user's conditioning direction is determined based on all health enhancement indicators, including:

[0038] The number of occurrences of each health enhancement indicator was determined from the combined analysis results of all times;

[0039] Determine the interaction relationship between the health enhancement indicator and each of the remaining indicators in the corresponding combined analysis results, and determine the preliminary radiation range based on the corresponding combined analysis results;

[0040] Determine all the interaction relationships involved in the corresponding combination analysis results for each health enhancement indicator, rank them in order of relationship strength, and calculate the first intensity difference between adjacent interaction relationships;

[0041] Locking the beating intensity difference from the first intensity difference, determining the optimized intensity based on the first intensity difference before the position where the beating intensity difference is located, and adjusting the interaction relationship before the position according to the optimized intensity to obtain the enhancement factor of the corresponding health enhancement indicator in the corresponding combination analysis result;

[0042] Obtaining an extended radiation range based on the preliminary radiation range and the enhancement factor, and constructing a correlation expression;

[0043] Based on the expression-attribute comparison table, the health attributes of each associated expression are obtained, and the attribute set of the corresponding health enhancement indicator is obtained by combining the number of occurrences;

[0044] Obtain the sub-direction and indicator weight that match the corresponding attribute set from the set-direction comparison table;

[0045] Based on all sub-directions and indicator weights, the adjustment direction is determined.

[0046] Preferably, intelligent matching is performed with the conditioning effects of the Chinese medicinal herbs present in the extraction device and the various extraction methods of the Chinese medicinal herbs, including:

[0047] Eliminate the conditioning conflicts of the sub-directions whose indicator weights are greater than the preset weights according to the TCM conditioning theory mechanism, and match the conditioning contents after conflict elimination with the functional effects of the Chinese medicinal herbs in the extraction device, screen out the first herbs with conditioning effects, and determine the herbal function and herbal dosage of each first herb;

[0048] Input the sub-directions and indicator weights of all health enhancement indicators into the user drug identification model to obtain the drug absorption effect of the user;

[0049] The herbal state of each first herb in the extraction device is determined respectively, and in combination with the drug absorption effect of the user, several recommended extraction methods are determined for the user to choose.

[0050] Preferably, the extraction method is related to ultra-pressure purification and filtration technology, release and equalization technology, micro-nano collision technology and intelligent automatic temperature and pressure technology.

[0051] The present invention provides an intelligent herbal extraction device, comprising:

[0052] An image acquisition module, configured to acquire a facial image and a scalp image of the user and perform image processing and recognition when the user triggers the extraction device, thereby obtaining facial representation information and scalp representation information of the user;

[0053] An information analysis module, configured to receive health-related questionnaire information input by the user on the interactive interface of the extraction device, and perform information analysis to obtain current basic information;

[0054] A health estimation module is used to comprehensively analyze and process the facial representation information, scalp representation information, and current basic information, preliminarily estimate the user's current health status, and extract a number of health enhancement indicators from the current health status;

[0055] The extraction recommendation module is used to determine the conditioning direction of the user based on all health enhancement indicators, and intelligently match the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output the recommended method for the user to choose.

[0056] Compared with the prior art, the present invention has the following advantages:

[0057] Through comprehensive analysis of the face, scalp and questionnaire surveys, the user's health enhancement indicators are determined, so that the drugs required for extraction can meet the user's actual pathological needs. Subsequently, the conditioning direction and extraction method are determined based on the health enhancement indicators to maximize the efficiency of drug extraction and the subsequent effective use of drugs.

[0058] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 This is a flow chart of an intelligent herbal extraction method according to an embodiment of the present invention;

[0062] Figure 2 This is a structural diagram of an intelligent herbal extraction device according to an embodiment of the present invention;

[0063] Figure 32 is a structural diagram of an extraction device in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] The present invention provides an intelligent recommendation herbal extraction method, such as Figure 1 Shown, including:

[0066] Step 1: When the user triggers the extraction device, the user's facial image and scalp image are collected and image processing and recognition are performed to obtain the user's facial representation information and scalp representation information;

[0067] Step 2: receiving health-related questionnaire information input by the user on the interactive interface of the extraction device, and parsing the information to obtain current basic information, wherein the questionnaire information includes: the actual pulse rate measured by the user using a pulse sensor on site and several related health indicator information;

[0068] Step 3: Comprehensively analyzing and processing the facial representation information, scalp representation information, and current basic information to preliminarily estimate the user's current health status and extract several health enhancement indicators from the current health status;

[0069] Step 4: Determine the conditioning direction of the user based on all health enhancement indicators, and intelligently match them with the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output a recommended method for the user to choose.

[0070] In this embodiment, the extraction device, such as Figure 3 As shown, it includes a shell part, a crushing part, an extraction part, a transmission part, a measuring part, a cooling part, a power part, an interactive part, a collection part and a data processing part. The interactive part is used to obtain user-triggered information, and then facial collection and scalp collection are realized based on the collection part. The interactive part is further used to display the questionnaire content for user input to obtain questionnaire information, and then the data processing part conducts a comprehensive analysis of the three aspects of the results to determine the health enhancement index, and then determines the conditioning direction to obtain an intelligent matching result (extraction method). After the user selects the recommended extraction method in the interactive part, the crushing part, extraction part, transmission part, measuring part, cooling part and power part are controlled to start working to realize the extraction operation.

[0071] In this embodiment, the facial image is acquired to determine the user's skin color, whether there are acne on the face, whether the face is oily, etc. The scalp image is acquired to determine whether the user's scalp is oily, the amount of hair, and the thickness of the hair.

[0072] In this embodiment, the questionnaire information includes: pulse information, drug allergy information, current physical discomfort information, recent food information, etc.

[0073] In this embodiment, the comprehensive analysis and processing is to determine the current health condition of the user. For example, if the user is generally healthy but has excessive moisture and liver fire, then the health enhancement indicators are: moisture elimination index, liver fire weakening index, etc.

[0074] In this embodiment, the adjustment direction is determined based on the individual direction of the corresponding indicator and the indicator weight, ensuring the priority of the adjustment.

[0075] In this embodiment, for example, the Chinese medicinal herbs used to reduce liver fire are: honeysuckle, astragalus, gardenia, raw rehmannia, rhubarb, moutan bark, oriental Chinese medicine, and anemarrhena. For example, the Chinese herbal medicine used to regulate dampness is Poria. At this time, the weight of the index corresponding to dampness accounts for 60%, and the weight of the index corresponding to liver fire accounts for 40%. At this time, the number of grams and auxiliary additions of other herbs are determined according to the conditioning effect of the formula, and the extraction method is recommended.

[0076] Among them, the extraction method is regarded as corresponding to one method as long as there is a difference in one parameter in the ultra-pressure purification and filtration technology, the release and equalization technology, the micro-nano collision technology and the intelligent automatic temperature and pressure technology.

[0077] The beneficial effects of the above technical solution are: determining the user's health enhancement indicators through comprehensive analysis of the face, scalp and questionnaire survey, so that the drugs required for extraction meet the user's actual pathological needs, and subsequently determining the conditioning direction and extraction method through the health enhancement indicators to maximize the efficiency of drug extraction and the subsequent effective use of drugs.

[0078] The present invention provides a method for intelligently recommending herbal extracts, which obtains facial representation information of a user, comprising:

[0079] Extracting three-channel components of each pixel in the facial image, comparing the three-channel components with a component combination-skin color database, and matching skin color labels to corresponding pixels;

[0080] Clustering all skin color labels to obtain several skin color blocks, and determining the facial color features of each skin color block. Combined with the facial position of the corresponding skin color block, an initial sequence is constructed.

[0081] Performing low-saturation adjustment and high-saturation adjustment on the image block corresponding to each skin color block to obtain a low-saturation image block and a high-saturation image block respectively;

[0082] Extracting pixel values ​​of the same pixel from the low-saturation image and the high-saturation image, respectively, and combining the first skin color feature and the second skin color feature of the corresponding skin color block in the low-saturation image and the high-saturation image to obtain a reference pair of the corresponding pixel;

[0083] Perform a perimeter search on each pixel point and lock the fault boundary point based on the pixel value of the corresponding pixel point as a reference to obtain the number of fault locks for each pixel point;

[0084] According to the number of locked slices and in combination with reference pairs of corresponding pixels, the initial sequence is expanded to obtain a facial color sequence;

[0085] Inputting the facial color sequence into a skin color sequence analysis model to obtain skin color information corresponding to the skin color block;

[0086] Based on all skin color information and the facial occupancy size of the skin color block corresponding to each skin color information, facial representation information is obtained.

[0087] In this embodiment, the three-channel components are: red channel component, blue channel component and green channel component. For example, the three-channel components of pixel A1 are: r1, b1, g1. At this time, the component combination-skin color database contains the three-channel components and the corresponding skin color labels, which are all pre-stored, such as: oily skin color, acne skin color, red-warm skin color, uneven skin color, etc., and then the skin color label of each pixel can be obtained.

[0088] In this embodiment, cluster analysis is implemented using the k-means algorithm, which belongs to the prior art.

[0089] In this embodiment, after clustering, the pixels involved in the same clustering result and the positions of the pixels on the face are regarded as a skin color block, that is, there are as many skin color blocks as there are clustering results.

[0090] In this embodiment, facial color features refer to those obtained by inputting all skin color labels related to the corresponding skin color blocks into the facial analysis model, and the facial analysis model is obtained by training a neural network model based on samples of different combinations of skin color conditions and the expert's diagnosis results of the combined skin color conditions. Therefore, the facial features of different skin color blocks can be directly obtained.

[0091] In this embodiment, the facial position is the position of the corresponding facial feature on the face, that is, it is related to the position of the pixel corresponding to the label.

[0092] In this embodiment, the initial sequence = {face position - facial color features}.

[0093] In this embodiment, low saturation adjustment and high saturation adjustment are for more obvious analysis of facial features, and the setting value of low saturation adjustment can be -100, and the setting value of high saturation adjustment can be +100. A saturated image block can be obtained by directly adjusting the setting.

[0094] In this embodiment, the information of the reference pair includes: the pixel value of the same pixel in the low-saturation image and the high-saturation image, and the skin color features corresponding to the low-saturation image and the high-saturation image.

[0095] In this embodiment, the principles for obtaining the first skin color feature, the second skin color feature, and the facial color feature are similar and will not be described in detail here.

[0096] In this embodiment, the peripheral search refers to a layer-by-layer search of neighboring pixel points until a fault boundary point is determined, that is, the difference between the pixel value of the fault boundary point and the pixel value of the corresponding pixel point is suddenly too large. For example, the original pixel value is a1, and the pixel value of the determined fault boundary point is b1. At this time, the absolute value of the difference between b1 and a1 is greater than the set value. It should be noted that in the layer-by-layer search process, the pixel point that first appears to meet the absolute value of the difference greater than the set value is regarded as the fault boundary point.

[0097] In this embodiment, since a surrounding search is performed on each pixel point, each pixel point may serve as a fault boundary point. Even if it is not the fault boundary point of pixel point B1, it may serve as the fault boundary point of pixel point B2. Therefore, a quantitative statistics is required to determine the number of pixel points serving as fault boundary points, that is, the number of fault locks.

[0098] In this embodiment, the facial color sequence = initial sequence + expanded sequence.

[0099] In this embodiment, the skin color sequence analysis model is obtained by training a neural network model based on different skin color sequences and expert judgment results on different skin color sequences as samples. Therefore, skin color information can be obtained, further ensuring the accuracy of skin color information determination.

[0100] In this embodiment, the facial representation information is: the skin color information of each skin color block, the position of the skin color block on the face, and the size of the skin color block on the face.

[0101] The beneficial effects of the above technical solution are: directly setting skin color labels for the captured images to achieve preliminary clustering analysis and sequence construction, and subsequently adjusting the image blocks to low saturation and high saturation to further enrich the facial information and combine fault locking to expand the sequence, ensuring the effective and reasonable acquisition of facial representation information, providing a basis for subsequent analysis.

[0102] The present invention provides an intelligent herbal extraction recommendation method, which expands the initial sequence to obtain a complexion sequence, comprising:

[0103] Performing a first mean processing on two pixel values ​​in a reference pair of the pixel points to obtain a first value;

[0104] Determine the absolute value of the difference between the pixel value of each locked fault boundary point in the fault locking quantity and the pixel value of the corresponding reference pixel point, and perform a second mean processing to obtain a second value;

[0105] Determine the auxiliary skin color information of the corresponding pixel point based on the first value, the second value, the number of fault locks, and the straight-line distance between each locked fault boundary point and the corresponding pixel point as a reference basis;

[0106] The auxiliary skin color information is added to the corresponding facial position in the initial sequence to obtain a facial color sequence.

[0107] In this embodiment, the first value=the sum of two pixel values / 2.

[0108] In this embodiment, the second value=the sum of all absolute values ​​of differences involving pixels on the same reference basis / the number of slice locks.

[0109] In this embodiment, the auxiliary skin color information corresponds to Among them, L i1 L represents the straight-line distance between the i1th locked fault boundary point and the corresponding pixel point as the reference basis; max The maximum value of the distance between any two cluster centers in all clustering results; ln represents the sign of the logarithmic function; n1 represents the number of fault locks, and a1+a2 represents the sum of the feature differences between the first skin color feature and the second skin color feature of the skin color block where the corresponding pixel point is located and the corresponding facial color feature.

[0110] It should be noted that the auxiliary skin color information is the calculated pixel value.

[0111] In this embodiment, the facial color sequence = {auxiliary skin color information of the pixels corresponding to the initial sequence}.

[0112] The beneficial effects of the above technical solution are: by averaging the pixel values ​​in the reference pair, and

[0113] The present invention provides an intelligent herbal extraction recommendation method, which performs information analysis to obtain current basic information, including:

[0114] Retrieving several embedded points of the user's answers to each health question from the questionnaire information, and adjusting the initial weight of the embedded point based on the modal particle of each embedded point to obtain an embedded point vector;

[0115] Inputting the buried point vector into an answer parsing model matching the health question to obtain health symptoms;

[0116] Among them, all health conditions are taken as current basic information.

[0117] In this embodiment, the answer point refers to the information that needs to be captured after the user answers the corresponding health question. For example, what is the pulse frequency? The user's answer is: currently it is 120 times / min. At this time, the answer point only needs to capture 120.

[0118] In this embodiment, the modal particles can be: maybe, probably, often, occasionally, etc. For example, the questionnaire question is: Do you suffer from insomnia? At this time, the user's reply is: I suffer from insomnia occasionally. For example, the weight originally set for insomnia is c1. At this time, the modal particle is occasionally, which means it is not serious. c1 can be reduced by r01, where r01 is the reduced weight for the corresponding modal particle.

[0119] In this embodiment, the embedding point vector = {the extraction results of the answer embedding points involved in the same question and the adjustment weights of the embedding points}.

[0120] In this embodiment, the answer analysis model includes the same questionnaire question and the answer result for the question, and the expert's judgment on the answer result is obtained by training the neural network model with samples, so health symptoms can be directly obtained.

[0121] The beneficial effect of the above technical solution is: by performing buried point retrieval and weight adjustment, it is ensured that the obtained vector is more in line with the user's own symptoms, thereby providing a data basis for subsequent analysis.

[0122] The present invention provides an intelligent herbal extraction recommendation method, which comprehensively analyzes and processes the facial representation information, scalp representation information, and current basic information, including:

[0123] performing a first extraction on the facial representation information according to a facial indicator set;

[0124] performing a second extraction on the scalp representation information according to the scalp indicator set;

[0125] Performing a third extraction of the current basic information according to the question-answer indicator set;

[0126] The first extraction result, the second extraction result, and the third extraction result are sequentially input into the result analysis table.

[0127] In this embodiment, the facial indicator set includes: facial oiliness indicator, facial yellowness indicator, facial redness and temperature indicator, facial acne indicator, etc.

[0128] In this embodiment, the scalp index set includes: scalp oiliness index, hair quality index, etc.

[0129] In this embodiment, the question-and-answer indicator set includes: pulse rate indicator, allergy indicator, most recent food indicator, etc.

[0130] The purpose of extraction is to analyze relevant results.

[0131] In this embodiment, the result analysis representation includes indicator descriptions of various indicators and blank placement locations corresponding to the results of the corresponding indicators. It is only necessary to place the extracted results in the corresponding blank locations.

[0132] The beneficial effect of the above technical solution is: through facial indicators, scalp indicators and question-and-answer indicators, corresponding information is extracted in sequence, effectively ensuring the reliability of the results.

[0133] The present invention provides an intelligently recommended herbal extraction method, which extracts several health enhancement indicators from the current health status, including:

[0134] Performing a combination analysis of all input results in the result analysis table according to the analysis standard to obtain a corresponding combination analysis result;

[0135] Extract non-healthy factors from each combined analysis result and use them as initial indicators;

[0136] All initial indicators are combined to obtain several health enhancement indicators.

[0137] In this embodiment, the full-time combination analysis refers to randomly combining the results of the three aspects, and it is required that all indicators have been combined. For example, there are results corresponding to indicator 1, indicator 2, and indicator 3 respectively. At this time, indicator 1, indicator 2, indicator 2, indicator 3, and indicator 1, indicator 2, and indicator 3 are combined respectively, that is, 3 combination analysis results are obtained.

[0138] In this embodiment, non-health factors refer to factors that affect physical health, such as heavy dampness, excessive liver fire, etc.

[0139] For example, the combination analysis result 01 contains initial indicators u1 and initial indicators u2, and the combination analysis result 02 contains initial indicators u3 and initial indicators u1. At this time, the health enhancement indicators obtained after the union processing are: initial indicator u1, initial indicator u2, and initial indicator u3.

[0140] The beneficial effect of the above technical solution is that all possibilities can be included by conducting a full range of combined analyses, ensuring the comprehensiveness of the acquisition of health enhancement indicators and providing a reliable basis for subsequent determination of the conditioning direction.

[0141] The present invention provides an intelligent herbal extraction recommendation method, which relies on all health enhancement indicators to determine the user's conditioning direction, including:

[0142] The number of occurrences of each health enhancement indicator was determined from the combined analysis results of all times;

[0143] Determine the interaction relationship between the health enhancement indicator and each of the remaining indicators in the corresponding combined analysis results, and determine the preliminary radiation range based on the corresponding combined analysis results;

[0144] Determine all the interaction relationships involved in the corresponding combination analysis results for each health enhancement indicator, rank them in order of relationship strength, and calculate the first intensity difference between adjacent interaction relationships;

[0145] Locking the beating intensity difference from the first intensity difference, determining the optimized intensity based on the first intensity difference before the position where the beating intensity difference is located, and adjusting the interaction relationship before the position according to the optimized intensity to obtain the enhancement factor of the corresponding health enhancement indicator in the corresponding combination analysis result;

[0146] Obtaining an extended radiation range based on the preliminary radiation range and the enhancement factor, and constructing a correlation expression;

[0147] Based on the expression-attribute comparison table, the health attributes of each associated expression are obtained, and the attribute set of the corresponding health enhancement indicator is obtained by combining the number of occurrences;

[0148] Obtain the sub-direction and indicator weight that match the corresponding attribute set from the set-direction comparison table;

[0149] Based on all sub-directions and indicator weights, the adjustment direction is determined.

[0150] In this embodiment, for example, the health enhancement indicator u1 appears in both the combined analysis result 01 and the combined analysis result 02. In this case, it is considered that the number of appearances is 2.

[0151] In this embodiment, the interaction relationship is obtained by inputting all health enhancement indicators in the combined analysis results into a mutual analysis model, which is obtained by training a neural network model based on samples of the interaction between the health enhancement indicators, and can therefore be obtained directly.

[0152] In this embodiment, for example, the health enhancement index u1 has no relationship with the health enhancement index u2, and has an intensity relationship of 0.2 with the health enhancement index u3. At this time, the results corresponding to the health enhancement index u2 are not associated with the health enhancement index u1, and 20% of the results associated with the health enhancement index u3 are associated with the health enhancement index u1. At this time, the preliminary radiation range for the health enhancement index u1 will be obtained, that is, the content that has a relationship with other health enhancement indicators.

[0153] In this embodiment, the interaction relationship and the relationship strength are realized by comparing with each other. For example, if the interaction relationship does not exist, the relationship strength is 0; if the interaction relationship is a close relationship, the relationship strength is 1. Both are realized based on a relationship-strength comparison table, which includes different interaction relationships and the relationship strengths that match them.

[0154] In this embodiment, the first intensity difference is the intensity difference between adjacent action relationships after sorting.

[0155] In this embodiment, the beating intensity difference refers to an intensity having a value greater than r01 (a set value) in the first intensity difference.

[0156] In this embodiment, the positions locked by the beating intensity difference correspond to adjacent action relationships, that is, there are two positions, and the front one of the two positions is regarded as the current position.

[0157] In this embodiment, Where floor(m1 / 2) is m1 / 2 rounded down, and m1 is the number of all first intensity differences before the current position;

[0158] In this embodiment, the adjustment result of the strength of each interaction relationship corresponding to the position is:

[0159]

[0160] Among them, wx represents the position number of the corresponding interaction relationship strength before the position, and the value of the position number is 1, 2, 3, ..., m1.

[0161] In this embodiment, the enhancement factor=(the sum of all adjustment results−the sum of the intensities before adjustment) / (m1+1).

[0162] In this embodiment, the enhancement factor is regarded as an extension of the association results corresponding to the other enhancement indicators whose relationship strength is not 1. If the value of the original strength + the enhancement factor is greater than 1, the full association extension is performed. If it is still less than 1, the relevant association extension is performed according to the newly added value actually obtained.

[0163] In this embodiment, the association expression is a combination of the representative symbols of the association results with each other health indicator after actual expansion, and each association is unique, and thus the representative symbol is unique.

[0164] In this embodiment, the expression-attribute comparison table includes different symbol combinations and health attributes matching the symbol combinations, and the health attributes are related to dampness, phlegm, cold, liver fire, lung fire, etc.

[0165] In this embodiment, the attribute set = {health attributes of health enhancement indicators at different occurrence times}.

[0166] In this embodiment, the set-direction comparison table includes attribute sets of different combinations and conditioning sub-directions matching the sets and indicator weights, thereby obtaining the conditioning direction.

[0167] The beneficial effects of the above technical solution are: determining the preliminary radiation range through the interaction relationship, and then obtaining the enhancement factor by sorting the intensity, determining the intensity difference, and adjusting the relationship, so as to ensure the comprehensiveness of the association to achieve the reasonable acquisition of the expression, and provide convenience for the subsequent acquisition of sub-directions and weights of different health enhancement indicators.

[0168] The present invention provides an intelligently recommended herbal extraction method that intelligently matches the conditioning effects of the Chinese medicinal herbs present in the extraction device and the various extraction methods of the Chinese medicinal herbs, including:

[0169] Eliminate the conditioning conflicts of the sub-directions whose indicator weights are greater than the preset weights according to the TCM conditioning theory mechanism, and match the conditioning contents after conflict elimination with the functional effects of the Chinese medicinal herbs in the extraction device, screen out the first herbs with conditioning effects, and determine the herbal function and herbal dosage of each first herb;

[0170] Input the sub-directions and indicator weights of all health enhancement indicators into the user drug identification model to obtain the drug absorption effect of the user;

[0171] The herbal state of each first herb in the extraction device is determined respectively, and in combination with the drug absorption effect of the user, several recommended extraction methods are determined for the user to choose.

[0172] Among them, after the user makes a selection, all the required first herbs are stirred and extracted according to the extraction method, and the user is reminded to take the traditional Chinese medicine based on the extraction device. Among them, the reminder can be an interface reminder based on the interactive part, or a broadcast reminder, etc.

[0173] Preferably, the extraction method is related to ultra-pressure purification and filtration technology, release and equalization technology, micro-nano collision technology and intelligent automatic temperature and pressure technology.

[0174] In this embodiment, the TCM conditioning theory mechanism is pre-established and is based on TCM theory based on observation, auscultation, hearing, questioning and palpation, etc., providing the most basic and comprehensive relationship between TCM herbal information and medication conditions.

[0175] In this embodiment, the preset weight value is 0.1.

[0176] In this embodiment, the purpose of regulating conflict is to avoid the situation where the herbs e1 and e2 can regulate the health problems in the corresponding directions y1 and y2 respectively, but the herbs e1 and e2 cannot be used at the same time.

[0177] In this embodiment, the functional effect is the effect of each herb, which is known.

[0178] In this embodiment, the function and usage can be directly output after matching.

[0179] In this embodiment, the drug recognition model is obtained by training a neural network model based on different directions and weight combinations, and the absorption effect estimation results based on the combinations are samples. Therefore, the drug absorption effect can be directly obtained.

[0180] In this embodiment, the herbal state refers to the solid block state, powder state, etc.

[0181] In this embodiment, the extraction method is obtained by matching from a state-effect-method comparison table, which includes different herbal states, drug absorption effects and matching extraction methods.

[0182] The beneficial effect of the above technical solution is that by eliminating drug conflicts and matching functional effects, reasonable herbs can be screened, and then combined with the drug absorption effect, extraction methods can be recommended to achieve intelligent extraction.

[0183] The present invention provides an intelligent recommendation herbal extraction device, such as Figure 2 Shown, including:

[0184] An image acquisition module, configured to acquire a facial image and a scalp image of the user and perform image processing and recognition when the user triggers the extraction device, thereby obtaining facial representation information and scalp representation information of the user;

[0185] An information analysis module, configured to receive health-related questionnaire information input by the user on the interactive interface of the extraction device, and perform information analysis to obtain current basic information;

[0186] A health estimation module is used to comprehensively analyze and process the facial representation information, scalp representation information, and current basic information, preliminarily estimate the user's current health status, and extract a number of health enhancement indicators from the current health status;

[0187] The extraction recommendation module is used to determine the conditioning direction of the user based on all health enhancement indicators, and intelligently match the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output the recommended method for the user to choose.

[0188] The beneficial effects of the above technical solution are: determining the user's health enhancement indicators through comprehensive analysis of the face, scalp and questionnaire survey, so that the drugs required for extraction meet the user's actual pathological needs, and subsequently determining the conditioning direction and extraction method through the health enhancement indicators to maximize the efficiency of drug extraction and the subsequent effective use of drugs.

[0189] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for intelligently recommending herbal extraction, characterized in that: include: Step 1: When the user triggers the extraction device, the user's facial image and scalp image are collected and image processing and recognition are performed to obtain the user's facial representation information and scalp representation information; Step 2: receiving health-related questionnaire information input by the user on the interactive interface of the extraction device, and parsing the information to obtain current basic information, wherein the questionnaire information includes: the actual pulse rate measured by the user using a pulse sensor on site and several related health indicator information; Step 3: Comprehensively analyzing and processing the facial representation information, scalp representation information, and current basic information to preliminarily estimate the user's current health status and extract several health enhancement indicators from the current health status; Step 4: Determine the user's conditioning direction based on all health enhancement indicators, intelligently match the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output a recommended method for the user to choose; Obtaining the user's facial representation information includes: Extracting three-channel components of each pixel in the facial image, comparing the three-channel components with a component combination-skin color database, and matching skin color labels to corresponding pixels; Clustering all skin color labels to obtain several skin color blocks, and determining the facial color features of each skin color block. Combined with the facial position of the corresponding skin color block, an initial sequence is constructed. Performing low-saturation adjustment and high-saturation adjustment on the image block corresponding to each skin color block to obtain a low-saturation image block and a high-saturation image block respectively; Extracting pixel values ​​of the same pixel from the low-saturation image and the high-saturation image, respectively, and combining the first skin color feature and the second skin color feature of the corresponding skin color block in the low-saturation image and the high-saturation image to obtain a reference pair of the corresponding pixel; Perform a perimeter search on each pixel point and lock the fault boundary point based on the pixel value of the corresponding pixel point as a reference to obtain the number of fault locks for each pixel point; According to the number of locked slices and in combination with reference pairs of corresponding pixels, the initial sequence is expanded to obtain a facial color sequence; Inputting the facial color sequence into a skin color sequence analysis model to obtain skin color information corresponding to the skin color block; Based on all skin color information and the facial occupancy size of the skin color block corresponding to each skin color information, facial representation information is obtained.

2. The intelligent herbal extraction method according to claim 1, characterized in that: The initial sequence is expanded to obtain a facial color sequence, including: Performing a first mean processing on two pixel values ​​in a reference pair of the pixel points to obtain a first value; Determine the absolute value of the difference between the pixel value of each locked fault boundary point in the fault locking quantity and the pixel value of the corresponding reference pixel point, and perform a second mean processing to obtain a second value; Determine the auxiliary skin color information of the corresponding pixel point based on the first value, the second value, the number of fault locks, and the straight-line distance between each locked fault boundary point and the corresponding pixel point as a reference basis; The auxiliary skin color information is added to the corresponding facial position in the initial sequence to obtain a facial color sequence.

3. The intelligent recommendation herbal extraction method according to claim 1, characterized in that: Perform information analysis to obtain current basic information, including: Retrieving several embedded points of the user's answers to each health question from the questionnaire information, and adjusting the initial weight of the embedded point based on the modal particle of each embedded point to obtain an embedded point vector; Inputting the buried point vector into an answer parsing model matching the health question to obtain health symptoms; Among them, all health conditions are taken as current basic information.

4. The intelligent herbal extraction method according to claim 1, characterized in that: Comprehensively analyzing and processing the facial representation information, scalp representation information, and current basic information, including: performing a first extraction on the facial representation information according to a facial indicator set; performing a second extraction on the scalp representation information according to the scalp indicator set; Performing a third extraction of the current basic information according to the question-answer indicator set; The first extraction result, the second extraction result, and the third extraction result are sequentially input into the result analysis table.

5. The intelligent recommendation herbal extraction method according to claim 4, characterized in that: Several health-enhancing indicators are extracted from the current health status, including: Performing a combination analysis of all input results in the result analysis table according to the analysis standard to obtain a corresponding combination analysis result; Extract non-healthy factors from each combined analysis result and use them as initial indicators; All initial indicators are combined to obtain several health enhancement indicators.

6. The intelligent herbal extraction method according to claim 5, characterized in that: All health enhancement indicators are relied upon to determine the direction of conditioning for the user, including: The number of occurrences of each health enhancement indicator was determined from the combined analysis results of all times; Determine the interaction relationship between the health enhancement indicator and each of the remaining indicators in the corresponding combined analysis results, and determine the preliminary radiation range based on the corresponding combined analysis results; Determine all the interaction relationships involved in the corresponding combination analysis results for each health enhancement indicator, rank them in order of relationship strength, and calculate the first intensity difference between adjacent interaction relationships; Locking the beating intensity difference from the first intensity difference, determining the optimized intensity based on the first intensity difference before the position where the beating intensity difference is located, and adjusting the interaction relationship before the position according to the optimized intensity to obtain the enhancement factor of the corresponding health enhancement indicator in the corresponding combination analysis result; Obtaining an extended radiation range based on the preliminary radiation range and the enhancement factor, and constructing a correlation expression; Based on the expression-attribute comparison table, the health attributes of each associated expression are obtained, and the attribute set of the corresponding health enhancement indicator is obtained by combining the number of occurrences; Obtain the sub-direction and indicator weight that match the corresponding attribute set from the set-direction comparison table; Based on all sub-directions and indicator weights, the adjustment direction is determined.

7. The intelligent recommendation herbal extraction method according to claim 6, characterized in that: Intelligently match the conditioning effects of Chinese herbs in the extraction device and the various extraction methods of Chinese herbs, including: Eliminate the conditioning conflicts of the sub-directions whose indicator weights are greater than the preset weights according to the TCM conditioning theory mechanism, and match the conditioning contents after conflict elimination with the functional effects of the Chinese medicinal herbs in the extraction device, screen out the first herbs with conditioning effects, and determine the herbal function and herbal dosage of each first herb; Input the sub-directions and indicator weights of all health enhancement indicators into the user drug identification model to obtain the drug absorption effect of the user; The herbal state of each first herb in the extraction device is determined respectively, and in combination with the drug absorption effect of the user, several recommended extraction methods are determined for the user to choose.

8. The intelligent herbal extraction method according to claim 7, characterized in that: The extraction method is related to ultra-pressure purification and filtration technology, release and equalization technology, micro-nano collision technology and intelligent automatic temperature and pressure technology.

9. An intelligent herbal extraction device, characterized in that: include: An image acquisition module, configured to acquire a facial image and a scalp image of the user and perform image processing and recognition when the user triggers the extraction device, thereby obtaining facial representation information and scalp representation information of the user; An information analysis module, configured to receive health-related questionnaire information input by the user on the interactive interface of the extraction device, and perform information analysis to obtain current basic information; A health estimation module is used to comprehensively analyze and process the facial representation information, scalp representation information, and current basic information, preliminarily estimate the user's current health status, and extract a number of health enhancement indicators from the current health status; An extraction recommendation module is used to determine the conditioning direction of the user based on all health enhancement indicators, and intelligently match the conditioning effects of the Chinese medicinal herbs in the extraction device and the various extraction methods of the Chinese medicinal herbs, and output a recommended method for the user to choose; Obtaining the user's facial representation information includes: Extracting three-channel components of each pixel in the facial image, comparing the three-channel components with a component combination-skin color database, and matching skin color labels to corresponding pixels; Clustering all skin color labels to obtain several skin color blocks, and determining the facial color features of each skin color block. Combined with the facial position of the corresponding skin color block, an initial sequence is constructed. Performing low-saturation adjustment and high-saturation adjustment on the image block corresponding to each skin color block to obtain a low-saturation image block and a high-saturation image block respectively; Extracting pixel values ​​of the same pixel from the low-saturation image and the high-saturation image, respectively, and combining the first skin color feature and the second skin color feature of the corresponding skin color block in the low-saturation image and the high-saturation image to obtain a reference pair of the corresponding pixel; Perform a perimeter search on each pixel point and lock the fault boundary point based on the pixel value of the corresponding pixel point as a reference to obtain the number of fault locks for each pixel point; According to the number of locked slices and in combination with reference pairs of corresponding pixels, the initial sequence is expanded to obtain a facial color sequence; Inputting the facial color sequence into a skin color sequence analysis model to obtain skin color information corresponding to the skin color block; Based on all skin color information and the facial occupancy size of the skin color block corresponding to each skin color information, facial representation information is obtained.

Images