Traditional Chinese medicine related biological characteristic data acquisition method and device, storage medium and electronic device

Abstract

The invention relates to the technical field of traditional Chinese medicine related biological data collection, and particularly provides a traditional Chinese medicine related biological characteristic data collection method and device, a storage medium and an electronic device.The method can comprise the steps that outer contour characteristic point positions of specific positions of collected objects are encoded, and specific position codes are obtained, the specific position comprises at least one of the following parts: a face part, a lingual surface, a lingual sole and a palm; comparing the specific position code with a preset acquisition frame code, and determining a feature acquisition frame; judging whether the feature points in the specific position meet shooting requirements or not by using the specific position code; and under the condition that the shooting requirement is met, obtaining a feature image under the feature acquisition frame. According to some embodiments of the invention, intelligent collection of biological characteristic data related to traditional Chinese medicine can be realized, and the collection efficiency and precision are high.

Description

Technical Field

[0001] The present application relates to the technical field of TCM-related biological data collection, and in particular, to a method, device, storage medium and electronic device for TCM-related biological feature data collection. Background Art

[0002] With the continuous popularization and development of the field of traditional Chinese medicine, how to link the field of traditional Chinese medicine with Internet data collection has become a current development goal.

[0003] At present, when collecting biometric data related to traditional Chinese medicine, different collection instruments are needed to independently collect the relevant biometric data of the tongue, face, pulse and palm of the collection object. However, the independent collection method using independent instruments not only consumes manpower costs, but also greatly reduces the efficiency of biometric data collection.

[0004] Therefore, how to provide a technical solution for an efficient method of collecting biometric data related to traditional Chinese medicine has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of some embodiments of the present application is to provide a method, device, storage medium and electronic device for collecting biometric data related to traditional Chinese medicine. Through the technical solutions of the embodiments of the present application, accurate and efficient collection of biometric data related to traditional Chinese medicine can be achieved with a high degree of intelligence.

[0006] In a first aspect, some embodiments of the present application provide a method for collecting biometric data related to traditional Chinese medicine, including: encoding the outer contour feature points of a specific position of a collection object to obtain a specific position code, wherein the specific position includes at least one of the following: face, tongue surface, tongue base and palm; comparing the specific position code with a preset collection frame code to determine a feature collection frame; using the specific position code to determine whether the feature points within the specific position meet the shooting requirements; and if the shooting requirements are met, obtaining a feature image under the feature collection frame.

[0007] Some embodiments of the present application determine a feature acquisition frame applicable to the acquisition object by using the specific position code corresponding to the outer contour feature point at a specific position of the acquisition object, and determine whether the feature points in the specific position meet the shooting requirements. If they meet the requirements, the feature acquisition frame is used to acquire the corresponding feature image. Some embodiments of the present application can adaptively select a feature acquisition frame applicable to different acquisition objects, thereby achieving accurate and efficient data collection of the feature points of the acquisition object, which is highly practical and intelligent.

[0008] In some embodiments, before encoding the outer contour feature points of a specific position of the acquisition object, the method includes: acquiring the specific position of the acquisition object to obtain an initial frame image; performing key point matching on the initial frame image to determine feature point information; and determining the outer contour feature points of the specific position through the feature point information.

[0009] Some embodiments of the present application perform key point matching to determine feature point information after preliminary acquisition of the acquisition object to obtain an initial frame image, and then determine the outer contour feature points corresponding to specific positions, thereby providing effective data support for the subsequent adaptive selection of a feature acquisition frame suitable for the acquisition object.

[0010] In some embodiments, comparing the specific position code with the preset collection frame code to determine the feature collection frame includes: solving the distance value between the specific position code and each collection frame corresponding to the preset collection frame code; and taking the collection frame corresponding to the minimum value of the distance values ​​of each collection frame as the feature collection frame.

[0011] Some embodiments of the present application determine a feature acquisition frame by comparing the distance between a specific position code and a preset acquisition frame code, and can implement adaptive selection and adjustment of the acquisition frame for different acquisition objects.

[0012] In some embodiments, the use of the specific position code to determine whether the feature points in the specific position meet the shooting requirements includes: based on the specific position code, obtaining a feature value list, wherein the value of each feature point in the feature value list represents whether the position of the feature point is correct; by analyzing the key feature point values ​​in the feature value list, determining a total feature recognition value, wherein the total feature recognition value is a True value, representing that the feature point meets the shooting requirements, and the total feature recognition value is a False value, representing that the feature point does not meet the shooting requirements.

[0013] Some embodiments of the present application determine a feature value list through specific position coding, and then determine a total feature recognition value based on the values ​​of key feature points in the feature value list. The total feature recognition value can be used to accurately determine whether the feature points meet the shooting requirements.

[0014] In some embodiments, determining the total feature recognition value by analyzing the key feature point values ​​in the feature value list includes: obtaining a key feature point, wherein the key feature point is at least one of the feature points; if the key feature point values ​​corresponding to the key feature point are all True values, then determining the total feature recognition value to be a True value; if there is a False value in the key feature point values ​​corresponding to the key feature point, then determining the total feature recognition value to be a False value.

[0015] Some embodiments of the present application determine the total feature recognition value by taking the values ​​of key feature points, so as to accurately determine whether the feature points meet the shooting requirements, and the determination efficiency is high.

[0016] In some embodiments, the method further includes: confirming that the values ​​acquired by the plurality of pressure sensors on the wrist of the acquisition subject can generate a pulse diagnosis waveform; and determining a pulse diagnosis image of the acquisition subject from the pulse diagnosis waveform.

[0017] Some embodiments of the present application collect data on the wrist to determine the pulse diagnosis image, thereby achieving integrated collection with the above-mentioned characteristic data.

[0018] In some embodiments, the specific positions include: face, tongue surface, tongue base, palm and wrist; obtaining the feature image under the feature acquisition frame includes: using the feature acquisition frame to collect the face, tongue surface, tongue base and palm in turn to obtain the feature images corresponding to the face, tongue surface, tongue base and palm respectively; after obtaining the feature image, collecting data on the wrist to obtain the pulse diagnosis image.

[0019] Some embodiments of the present application improve data collection efficiency by achieving integrated collection of feature images and pulse diagnosis images of the collection object in the order of face, tongue surface, tongue base, palm and wrist.

[0020] In a second aspect, some embodiments of the present application provide a device for collecting biometric data related to traditional Chinese medicine, including: through any method embodiment in the first aspect, data is collected from the face, tongue surface, tongue base, palm and wrist of the collection object in sequence, and feature images corresponding to the face, tongue surface, tongue base and palm are obtained, respectively, as well as a pulse diagnosis image corresponding to the wrist.

[0021] In a third aspect, some embodiments of the present application provide a device for collecting biometric data related to traditional Chinese medicine, including: a coding module, used to encode the outer contour feature points of a specific position of a collection object to obtain a specific position code, wherein the specific position includes at least one of the following: face, tongue surface, tongue base and palm; a comparison module, used to compare the specific position code with a preset collection frame code to determine a feature collection frame; a judgment module, used to use the specific position code to judge whether the feature points within the specific position meet the shooting requirements; and a collection module, used to obtain the feature image under the feature collection frame if the shooting requirements are met.

[0022] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the method described in any embodiment of the first aspect.

[0023] In a fifth aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, can implement a method as described in any embodiment of the first aspect.

[0024] In a sixth aspect, some embodiments of the present application provide a computer program product, wherein the computer program product comprises a computer program, wherein the computer program, when executed by a processor, can implement the method described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 One of the flow charts of the method for collecting biometric data related to traditional Chinese medicine provided in some embodiments of the present application;

[0027] Figure 2 Flowchart 2 of a method for collecting biometric data related to traditional Chinese medicine provided in some embodiments of the present application;

[0028] Figure 3 A block diagram of a device for collecting biometric data related to traditional Chinese medicine provided in some embodiments of the present application;

[0029] Figure 4 A schematic diagram of an electronic device is provided for some embodiments of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0031] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0032] In the related technologies, tongue, face, pulse and palm data are relatively important basic information in the field of traditional Chinese medicine, which can provide important auxiliary information for traditional Chinese medicine. With the continuous development of artificial intelligence, combining traditional manual observation and measurement of tongue, face, pulse and palm data with artificial intelligence has become a hot topic in this field. Currently, when collecting tongue, face, pulse and palm data from users, users are usually required to manually select which data to measure, and intelligent collection cannot be achieved; and the size of the collection frame is fixed and cannot be intelligently adapted.

[0033] It can be seen from the above-mentioned related technologies that when collecting tongue, face, pulse and palm data related to traditional Chinese medicine, the existing technology is unable to adaptively adapt the collection object and continuously collect, and the degree of intelligence is low.

[0034] In view of this, some embodiments of the present application provide a method for collecting biometric data related to traditional Chinese medicine, which can automatically adapt to a feature collection frame suitable for the collection object by comparing the specific position code corresponding to the outer contour feature point of the characteristic position of the collection object with the preset collection frame code; the specific position code can also be used to confirm whether the feature point in the specific position meets the shooting requirements; if the shooting requirements are met, the specific position of the collection object is collected through the feature collection frame to obtain a feature image. It can be seen that some embodiments of the present application can realize the intelligent collection of biometric data and realize the intelligent adaptation of the collection frame.

[0035] The following is combined with Figure 1 The implementation process of biometric data collection related to TCM provided by some embodiments of the present application is exemplified. It should be noted that the implementation process of biometric data collection related to TCM can be executed by a device for collecting biometric data related to TCM, and the device for collecting biometric data related to TCM is an integrated device for collecting multiple biometric data. Before executing the following method, you first need to turn on the point source switch of the device to enable the device. Under the condition of network connection, the user can open the software to enter the homepage, and by calling the hardware camera, the voice prompt "enter image acquisition" will be heard.

[0036] Please see attached Figure 1 , Figure 1 A flow chart of a method for collecting biometric data related to traditional Chinese medicine provided in some embodiments of the present application, the method for collecting biometric data related to traditional Chinese medicine may include:

[0037] S110, encoding the outer contour feature points of a specific position of the acquisition object to obtain a specific position code, wherein the specific position includes at least one of the following: face, tongue surface, tongue base and palm.

[0038] For example, in some embodiments of the present application, a data set encoding method is used for the outer contour feature points of a specific position of the collected user (as a specific example of the collection object) to obtain a characteristic position encoding. For example, when the specific position is the face, the facial outer contour feature points are extracted, and then encoded to obtain a facial encoding (as a specific example of a specific position encoding). When the specific position is the tongue surface, the tongue surface outer contour feature points are extracted, and then encoded to obtain a tongue surface encoding (as a specific example of a specific position encoding). When the specific position is the bottom of the tongue, the tongue bottom outer contour feature points are extracted, and then encoded to obtain a tongue bottom encoding (as a specific example of a specific position encoding). When the specific position is the palm, the palm outer contour feature points are extracted, and then encoded to obtain a palm encoding (as a specific example of a specific position encoding).

[0039] In some embodiments of the present application, S110 may include: capturing the specific position of the acquisition object to obtain an initial frame image; performing key point matching on the initial frame image to determine feature point information; and determining the outer contour feature point position of the specific position through the feature point information.

[0040] For example, in some embodiments of the present application, the user needs to put the head into the device according to the collection prompt on the left side of the homepage, and read each frame of the image information collected by the camera in real time (as a specific example of the initial frame image). Then call the Python-based specific location big data model to perform key point matching and output feature point information. After that, the corresponding outer contour feature points are extracted based on the feature point information.

[0041] The following is an exemplary description of different specific locations.

[0042] When the specific position is a face, each frame of the image information collected by the camera is read in real time, and the Python-based facial big data model is called to perform 855 key point matching processing, and the coordinates of the facial contour, eyebrows, eyes, nose, mouth, ears and other parts on the face (as a specific example of feature points) are returned (as a specific example of feature point information). After that, the facial contour feature points are obtained by extracting all or part of the information in the facial contour, eyebrows, eyes, nose, mouth, ears and other parts.

[0043] When the specific position is the tongue surface, the user needs to put the head into the device according to the collection prompts on the left side of the page, and extend the tongue flatly outward. Read each frame of the image information collected by the camera in real time, and call the Python-based tongue surface big data model to perform 288 key point matching processing, and return the feature point information on the tongue surface, such as tongue contour, tongue coating color, greasy coating, cracks, tooth marks (as a specific example of feature points) and other information. The feature points of the tongue surface outer contour are extracted by extracting all or part of the information such as tongue contour, tongue coating color, greasy coating, cracks, tooth marks, etc.

[0044] When the specific position is the tongue base, the user needs to put the head into the device according to the collection prompts on the left side of the page, and roll up the tongue, read each frame of the image information collected by the camera in real time, and call the Python-based tongue base big data model to perform 302 key point matching processing, and return the feature point information on the tongue base, such as tongue base contour, tongue color, sublingual collaterals (as a specific example of feature points), etc. The tongue base outer contour feature points are extracted by extracting all or part of the information such as tongue base contour, tongue color, sublingual collaterals, etc.

[0045] When the specific position is the palm, the user needs to put the palm into the device according to the collection prompts on the left side of the page, read each frame of the image information collected by the camera in real time, and call the Python-based palm big data model to perform 359 key point matching processing, and return information such as the palm contour, palm, and five fingers (as a specific example of feature point information). The palm outer contour feature points are extracted by extracting all or part of the information such as the palm contour, palm, and five fingers.

[0046] It should be noted that the above-mentioned Python-based facial big data model, tongue surface big data model, tongue base big data model and palm big data model are all obtained by training with relevant data sets. In addition to using Python's big data model, other machine language models or other biometric recognition algorithms can also be used to achieve data recognition and matching, and the embodiments of the present application are not limited to this.

[0047] S120, comparing the specific position code with a preset collection frame code to determine a feature collection frame.

[0048] For example, in some embodiments of the present application, multiple collection frames corresponding to the preset collection frame code may be set. For example, the collection frames include three types in the range of "large, medium, and small", and each collection frame corresponds to its own collection frame code. For example, by comparing the facial code with each preset collection frame code of the corresponding face, a facial collection frame suitable for the collection object is selected (as a specific example of a feature collection frame), thereby achieving the purpose of adaptive collection frame adjustment. For another example, by comparing the tongue surface code with each preset collection frame code of the corresponding tongue surface, a tongue surface collection frame suitable for the collection object is selected (as a specific example of a feature collection frame). Based on the same principle, the tongue base collection frame and the palm collection frame are obtained.

[0049] In some embodiments of the present application, S120 may include: solving the distance value between the specific position code and each corresponding collection frame in the preset collection frame code; and taking the collection frame corresponding to the minimum value of the distance values ​​of each collection frame as the feature collection frame.

[0050] For example, in some embodiments of the present application, taking the face as an example, the face code and the three known "large, medium, and small" range collection frame codes are calculated respectively to obtain the Euclidean distance under the three ranges. Then, the minimum value is taken out through np.argmin(), that is, the face collection frame corresponding to the closest (i.e., the closest distance) collection frame code is displayed on the software interface. Based on the same principle of close distance, the tongue surface collection frame, the tongue bottom collection frame, and the palm collection frame can be selected.

[0051] S130: Use the specific position code to determine whether the feature points in the specific position meet the shooting requirements.

[0052] For example, in some embodiments of the present application, feature points in different specific positions are analyzed respectively to determine whether they meet the shooting requirements.

[0053] In some embodiments of the present application, S130 may include: obtaining a feature value list based on the specific position code, wherein the value of each feature point in the feature value list represents whether the position of the feature point is correct; determining a total feature recognition value by analyzing the key feature point values ​​in the feature value list, wherein the total feature recognition value is a True value, representing that the feature point meets the shooting requirements, and the total feature recognition value is a False value, representing that the feature point does not meet the shooting requirements.

[0054] For example, in some embodiments of the present application, for the face, the facial code is compared with the default value in the device to confirm whether the feature points in the facial code meet the default value, and a face list is obtained (as a specific example of a feature value list). If it meets the value of True, it means that the position of the feature point is correct, otherwise it is False, which means that the position of the feature point is wrong. For example, if the eye coordinates do not meet the default value, the value corresponding to the eye in the feature value list is False. Correspondingly, for the tongue surface, the tongue surface code is compared with the preset default value related to the tongue surface to obtain a tongue surface list (as a specific example of a feature value list). For example, if the tongue surface contour information does not meet the default value, the contour value in the tongue surface list is False. The method of obtaining the palm list and the palm list is similar to the above principle. To avoid repetition, it will not be repeated here.

[0055] After obtaining a list of feature values ​​corresponding to different specific positions, the key feature point values ​​corresponding to the key feature points in the list can be confirmed to determine the total feature recognition value, and then determine whether the current shooting requirements are met.

[0056] In some embodiments of the present application, S130 may include: obtaining a key feature point, wherein the key feature point is at least one of the feature points; if the key feature point values ​​corresponding to the key feature point are all True values, then determining that the total feature recognition value is a True value; if there is a False value among the key feature point values ​​corresponding to the key feature point, then determining that the total feature recognition value is a False value.

[0057] S140, when the shooting requirements are met, obtaining a feature image under the feature acquisition frame.

[0058] For example, in some embodiments of the present application, key feature points are first selected from each specific position. Then, the total feature recognition value is determined to be True (value) or False (value) by the key feature point value. When it is confirmed that the shooting requirements are met (i.e., the total feature recognition value is True), a feature image under the above-selected feature acquisition frame is obtained. In addition, if the shooting requirements are not met, the feature positioning of the acquisition object can be re-captured, the feature acquisition frame can be adjusted, and the acquisition object can be prompted to make adjustments until the shooting requirements are met.

[0059] For example, for the collection of facial images (as a specific example of feature images), the eyes are set as the key feature points. If the value corresponding to the eyes is False, the total value of facial recognition (as a specific example of the total value of feature recognition) is False. At this time, when the user clicks the "shoot" button, the software page will display "Face not recognized" and the voice prompt "Face not recognized". If the value corresponding to the eyes is True, the total value of facial recognition is True. At this time, the verification is passed, and the "Upload Image" button may appear on the page. In response to the user's operation instruction on the button, through S140 and the voice prompt "Facial image saved successfully", the page appears "Facial image saved successfully, about to enter the tongue image collection", and the facial image collection is completed. At this time, it automatically jumps to the tongue image collection module.

[0060] For the collection of tongue surface images (as a specific example of feature images), the tongue surface contour information is set as the key feature point. If the tongue surface contour information does not meet the default value, the tongue surface contour value in the tongue surface list is False; and because the tongue surface contour value is a key value (that is, a key feature point value), it is judged to be non-compliant, and the total tongue surface recognition value (as a specific example of the total feature recognition value) returns False. At this time, when the user clicks the "shoot" button, the software page will display "tongue surface not recognized" and the voice prompt "tongue surface not recognized"; if the tongue surface recognition meets the standard, the total tongue surface recognition value returns True, the verification is passed, and the "upload image" button appears on the page. After clicking the button, S140 is executed internally, and the voice prompt "tongue surface image saved successfully" appears on the page "tongue surface image saved successfully, about to enter the tongue base image collection", and the tongue surface image collection is completed. At this time, it automatically jumps to the tongue base image collection module.

[0061] For the collection of tongue base images (as a specific example of feature images), the tongue base contour information is set as the key feature point. If the tongue base contour information does not meet the default value, the tongue base contour value in the tongue base list is False; and because the tongue base contour value is a key value (that is, a key feature point value), it is judged to be non-compliant, and the total tongue base recognition value (as a specific example of the total feature recognition value) returns False. At this time, when the user clicks the "shoot" button, the software page will display "tongue base not recognized" and the voice prompt "tongue base not recognized"; if the tongue base recognition meets the standard, the total value returns True, the verification is passed, and the "upload image" button appears on the page. After clicking the button, S140 is executed internally, and the voice prompt "tongue base image saved successfully" appears on the page. "Tongue base image saved successfully, about to enter palm image collection", so far the tongue base image collection is completed. At this time, it automatically jumps to the palm image collection module.

[0062] For the palm image (as a specific example of a feature image) collection, the palm contour information is set as the key feature point. If the palm contour information does not meet the default value, the palm contour value in the palm list is False; and because the palm contour value is a key value (that is, a key feature point value), it is determined to be non-compliant, and the total palm recognition value (as a specific example of the total feature recognition value) returns False. At this time, when the user clicks the "shoot" button, the software page will display "The palm is not recognized" and the voice prompt "The palm is not recognized"; if the palm recognition meets the standard, the total value returns True, the verification is passed, and the "upload image" button appears on the page. After clicking the button, S140 is executed internally, and the voice prompt "The palm image is saved successfully" appears on the page. "The palm image is saved successfully, and the left hand (or right hand) pulse diagnosis collection is about to begin", and the palm image collection is completed. At this time, it automatically jumps to the left hand (or right hand) pulse diagnosis image acquisition module.

[0063] Therefore, in some embodiments of the present application, the method for collecting biometric data related to traditional Chinese medicine also includes: confirming that the values ​​obtained by multiple pressure sensors on the wrist of the collection object can generate a pulse diagnosis waveform; and determining the pulse diagnosis image of the collection object from the pulse diagnosis waveform.

[0064] For example, in some embodiments of the present application, after completing the acquisition of the above-mentioned facial, tongue surface, tongue base and palm images, it automatically jumps to the left hand pulse diagnosis acquisition module (that is, the left hand pulse diagnosis image acquisition module). Specifically, the user needs to put the left wrist into the hardware device according to the acquisition prompt on the left side of the page, click the "Start Acquisition" button on the interface, and the three pressure sensors on the hardware (as a specific example of multiple pressure sensors) will return corresponding values ​​for the three pulse waves of Cun, Guan and Chi respectively, which correspond to the three pulse waves of Cun, Guan and Chi on the software. When the user's wrist position is inaccurate or the pulse is very weak, the pressure sensor cannot obtain the waveform, and the value False is returned. At this time, the software interface displays "No pulse diagnosis is recognized", and the voice prompts "No pulse diagnosis is recognized" and the pulse diagnosis acquisition process ends, and the "Start Acquisition" button reappears on the interface. If the pulse diagnosis collection complies with the rules and the pulse diagnosis waveform can be obtained, the user can click the "Capture" button on the page to fix the pulse diagnosis image. Then the "Upload Image" button will appear on the page. Click the button and the voice prompt "Left hand pulse diagnosis image saved successfully" will appear on the page "Left hand pulse diagnosis image saved successfully, about to enter the right hand pulse diagnosis collection". The left hand pulse diagnosis collection is now completed. At this time, it will automatically jump to the right hand pulse diagnosis image collection module.

[0065] Enter the right hand pulse acquisition module (that is, the right hand pulse image acquisition module) from the left hand pulse acquisition module. The user needs to put the right wrist into the hardware device according to the acquisition prompt on the left side of the page, click the "Start Acquisition" button on the interface, and the three pressure sensors on the device will return the values ​​corresponding to the three pulse waves of Cun, Guan, and Chi on the software. When the user's wrist position is not accurate or the pulse is very weak, the pressure sensor cannot obtain the waveform and returns the value False. At this time, the software interface displays "No pulse diagnosis was identified", and the voice prompt "No pulse diagnosis was identified" and the pulse acquisition process ends. The "Start Acquisition" button reappears on the interface; if the pulse diagnosis acquisition meets the rules, you can click the "Intercept" button on the page, the pulse diagnosis image is fixed, and then the "Upload Image" button appears on the page. Click the button, the voice prompt "The right hand pulse diagnosis image is saved successfully", and the page appears "The right hand pulse diagnosis image is saved successfully, please fill in the patient's mobile phone number", and the right hand pulse acquisition is completed.

[0066] In some embodiments of the present application, specific positions include: face, tongue surface, tongue base, palm and wrist; S140 may include: using a feature acquisition frame to sequentially acquire data from the face, tongue surface, tongue base and palm to obtain feature images corresponding to the face, tongue surface, tongue base and palm respectively; after obtaining the feature image, performing data acquisition on the wrist to obtain a pulse diagnosis image.

[0067] For example, in some embodiments of the present application, the specific position may include the four parts of the tongue, face, pulse and palm, and it may also include some of the parts. Regardless of how many parts the specific position includes, the collection of relevant image data of these parts is implemented on an integrated TCM-related biometric data collection device. For example, taking the facial, tongue, tongue base, palm and wrist data collection as an example, after completing the facial image collection in the manner provided above, it automatically jumps to the tongue image collection; after completing the tongue image collection, it automatically jumps to the tongue base image collection; after completing the tongue base image collection, it automatically jumps to the palm image collection; after completing the palm image collection, it automatically jumps to the pulse diagnosis image collection of the left wrist, and finally jumps to the pulse diagnosis image collection of the right wrist. During the entire collection process, the specific position of the collection object can be intelligently adapted to realize intelligent data collection with high efficiency. Moreover, after completing the pulse diagnosis image acquisition of the right wrist, the user can click on the mobile phone number text box to enter the mobile phone number and other basic information, and then click the "Complete Collection" button on the software interface. Alternatively, after the user completes the input, "This collection has been completed" will automatically appear on the page, and a voice prompt "This collection has been completed" will be given. At this point, the data collection of the tongue, face, pulse and palm can be completed at one time.

[0068] In other embodiments, the specific position may include the face, tongue surface, tongue bottom, palm; or may include the face, tongue surface, tongue bottom. The specific position may be determined according to the actual application scenario, and the embodiments of the present application are not specifically limited here.

[0069] It should be noted that S120 and S130 may be executed simultaneously or separately, and this embodiment of the present application does not specifically limit this.

[0070] Based on the above method, some embodiments of the present application also provide a device for collecting biometric data related to traditional Chinese medicine, including: Figure 1 In any embodiment of the method, data is collected from the face, tongue surface, tongue base, palm and wrist of the collection object in sequence to obtain feature images corresponding to the face, tongue surface, tongue base and palm, respectively, and a pulse diagnosis image corresponding to the wrist. The device can realize the integrated intelligent collection of TCM-related data, improving the collection efficiency and accuracy.

[0071] The following is combined with Figure 2 The specific process of collecting biometric data related to traditional Chinese medicine provided by some embodiments of the present application is exemplified.

[0072] Please see attached Figure 2 , Figure 2 A flow chart of a method for collecting biometric data related to Traditional Chinese Medicine provided for some embodiments of the present application.

[0073] The above process is explained below as an example.

[0074] S201, after performing key point matching on the facial image information of the collected object, obtain the facial contour feature points.

[0075] S202, encoding facial contour feature points to obtain facial encoding.

[0076] S203, comparing the facial code with the preset acquisition frame code to determine a feature acquisition frame, and using the facial code to determine facial feature points that meet the shooting requirements to obtain a facial image.

[0077] After completing facial image acquisition, it automatically jumps to tongue image acquisition.

[0078] S204, after performing key point matching on the collected tongue surface image information, obtain the tongue surface outer contour feature points.

[0079] S205, encoding the tongue surface outer contour feature points to obtain the tongue surface code.

[0080] S206, comparing the tongue surface code with the preset acquisition frame code to determine the feature acquisition frame, and using the tongue surface code to determine that the tongue surface feature points meet the shooting requirements to obtain the tongue surface image.

[0081] After completing the tongue surface image acquisition, it automatically jumps to the tongue base image acquisition.

[0082] S207, after performing key point matching on the collected tongue base image information, obtain the tongue base outer contour feature points.

[0083] S208, encoding the feature points of the tongue bottom outer contour to obtain the tongue bottom code.

[0084] S209, comparing the tongue bottom code with the preset acquisition frame code to determine the feature acquisition frame, and using the tongue bottom code to determine that the tongue bottom feature points meet the shooting requirements to obtain the tongue bottom image.

[0085] After completing the tongue base image acquisition, it automatically jumps to the palm image acquisition.

[0086] S210, after performing key point matching on the collected palm image information, obtain the palm outer contour feature points.

[0087] S211, encoding the feature points of the palm outer contour to obtain a palm code.

[0088] S212, comparing the palm code with the preset acquisition frame code to determine the feature acquisition frame, and using the palm code to determine that the palm feature points meet the shooting requirements to obtain a palm image.

[0089] After completing the palm image acquisition, it automatically jumps to the pulse diagnosis image acquisition.

[0090] S213, confirming that the values ​​collected by the multiple pressure sensors on the wrist can generate a pulse diagnosis waveform, and capturing a corresponding pulse diagnosis image from the pulse diagnosis waveform.

[0091] It should be understood that although the above embodiment collects images in the order of face, tongue surface, tongue base, palm and wrist, in actual application, the data collection order of face, tongue surface, tongue base, palm and wrist can be adjusted, and the pulse diagnosis image can be collected on the left wrist and / or right wrist, and the embodiment of the present application is not limited to this. In addition, the specific implementation process of S201 to S213 can refer to the method embodiment provided above, and the detailed description is appropriately omitted here to avoid repetition.

[0092] Please refer to Figure 3 , Figure 3 The block diagram of the composition of the device for collecting biometric data related to traditional Chinese medicine provided by some embodiments of the present application is shown. It should be understood that the device for collecting biometric data related to traditional Chinese medicine corresponds to the above method embodiment and can perform each step involved in the above method embodiment. The specific functions of the device for collecting biometric data related to traditional Chinese medicine can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here.

[0093] Figure 3The device for collecting biometric data related to traditional Chinese medicine includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the device for collecting biometric data related to traditional Chinese medicine. The device for collecting biometric data related to traditional Chinese medicine includes: an encoding module 310, which is used to encode the outer contour feature points of a specific position of the collection object to obtain a specific position code, wherein the specific position includes at least one of the following: face, tongue surface, tongue base and palm; a comparison module 320, which is used to compare the specific position code with a preset collection frame code to determine a feature collection frame; a judgment module 330, which is used to use the specific position code to determine whether the feature points in the specific position meet the shooting requirements; a collection module 340, which is used to obtain the feature image under the feature collection frame when the shooting requirements are met.

[0094] In some embodiments of the present application, the encoding module 310 is used to capture the specific position of the acquisition object to obtain an initial frame image; perform key point matching on the initial frame image to determine feature point information; and determine the outer contour feature point position of the specific position through the feature point information.

[0095] In some embodiments of the present application, the comparison module 320 is used to solve the distance value between the specific position code and each corresponding collection frame in the preset collection frame code; and take the collection frame corresponding to the minimum value of the distance values ​​of each collection frame as the feature collection frame.

[0096] In some embodiments of the present application, the judgment module 330 is used to obtain a feature value list based on the specific position code, wherein the value of each feature point in the feature value list represents whether the position of the feature point is correct; by analyzing the key feature point values ​​in the feature value list, the total feature recognition value is determined, wherein the total feature recognition value is a True value, representing that the feature point meets the shooting requirements, and the total feature recognition value is a False value, representing that the feature point does not meet the shooting requirements.

[0097] In some embodiments of the present application, the judgment module 330 is used to obtain a key feature point, wherein the key feature point is at least one of the feature points; if the key feature point values ​​corresponding to the key feature point are all True values, then the total feature recognition value is determined to be a True value; if there is a False value in the key feature point values ​​corresponding to the key feature point, then the total feature recognition value is determined to be a False value.

[0098] In some embodiments of the present application, the device for collecting biometric data related to traditional Chinese medicine also includes a pulse diagnosis collection module (not shown in the figure), which is used to confirm that the numerical values ​​obtained by multiple pressure sensors on the wrist of the collection object can generate a pulse diagnosis waveform; and determine the pulse diagnosis image of the collection object from the pulse diagnosis waveform.

[0099] In some embodiments of the present application, the specific positions include: face, tongue surface, tongue base, palm and wrist; the acquisition module 340 is used to use the feature acquisition frame to collect the face, tongue surface, tongue base and palm in sequence to obtain feature images corresponding to the face, tongue surface, tongue base and palm respectively; after obtaining the feature image, data is collected on the wrist to obtain the pulse diagnosis image.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0101] Some embodiments of the present application further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the operations of the method corresponding to any of the above methods provided in the above embodiments.

[0102] Some embodiments of the present application further provide a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to any of the above methods provided in the above embodiments.

[0103] like Figure 4 As shown, some embodiments of the present application provide an electronic device 400, which includes: a memory 410, a processor 420, and a computer program stored in the memory 410 and executable on the processor 420, wherein the processor 420 can implement a method as described in any of the above embodiments when reading the program from the memory 410 through a bus 430 and executing the program.

[0104] Processor 420 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 420 can be a microprocessor.

[0105] The memory 410 may be used to store instructions executed by the processor 420 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 420 of the disclosed embodiment may be used to execute instructions in the memory 410 to implement the method shown above. The memory 410 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0106] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for collecting biometric data related to traditional Chinese medicine, characterized in that: include: Encoding the outer contour feature points of a specific position of the acquisition object to obtain a specific position code, wherein the specific position includes at least one of the following: face, tongue surface, tongue bottom and palm; Compare the specific position code with the preset acquisition frame code to determine the feature acquisition frame; Using the specific position code to determine whether the feature point in the specific position meets the shooting requirements; When the shooting requirements are met, the feature image under the feature acquisition frame is acquired.

2. The method according to claim 1, characterized in that Before encoding the outer contour feature points at specific positions of the acquisition object, the method includes: Capturing the specific position of the acquisition object to obtain an initial frame image; Performing key point matching on the initial frame image to determine feature point information; The outer contour feature point position of the specific position is determined through the feature point information.

3. The method according to claim 1 or 2, characterized in that The step of comparing the specific position code with the preset acquisition frame code to determine the feature acquisition frame includes: Solving the distance value between the specific position code and each corresponding acquisition frame in the preset acquisition frame code; The collection frame corresponding to the minimum value among the distance values ​​of the collection frames is used as the feature collection frame.

4. The method according to claim 1 or 2, characterized in that: The using the specific position code to determine whether the feature point in the specific position meets the shooting requirements includes: Based on the specific position code, a feature value list is obtained, wherein the value of each feature point in the feature value list represents whether the position of the feature point is correct; The total feature recognition value is determined by analyzing the key feature point values ​​in the feature value list, wherein the total feature recognition value is a True value, indicating that the feature point meets the shooting requirements, and the total feature recognition value is a False value, indicating that the feature point does not meet the shooting requirements.

5. The method according to claim 4, characterized in that Determining the total feature recognition value by analyzing the key feature point values ​​in the feature value list includes: Acquire a key feature point, wherein the key feature point is at least one of the feature points; If the key feature point values ​​corresponding to the key feature points are all True values, determining the total feature recognition value to be a True value; If there is a False value in the key feature point values ​​corresponding to the key feature point, the total feature recognition value is determined to be a False value.

6. The method according to any one of claims 1 to 2 and 5, characterized in that: The method further comprises: Confirming that the values ​​obtained by the plurality of pressure sensors from the wrist of the subject can generate a pulse diagnosis waveform; A pulse diagnosis image of the acquisition object is determined from the pulse diagnosis waveform.

7. The method according to claim 6, characterized in that The specific positions include: face, tongue surface, tongue bottom, palm and wrist; the acquiring of the feature image under the feature acquisition frame includes: Use the feature collection frame to collect the face, the tongue surface, the tongue bottom and the palm in sequence to obtain feature images corresponding to the face, the tongue surface, the tongue bottom and the palm respectively; After obtaining the characteristic image, data collection is performed on the wrist to obtain the pulse diagnosis image.

8. A device for collecting biometric data related to traditional Chinese medicine, characterized in that: include: By using the method described in any one of claims 1 to 7, data is collected on the face, tongue surface, tongue base, palm and wrist of the collection object in turn to obtain feature images corresponding to the face, tongue surface, tongue base and palm respectively, and a pulse diagnosis image corresponding to the wrist.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program executes the method according to any one of claims 1 to 7 when executed by a processor.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the computer program executes the method according to any one of claims 1 to 7 when being run by the processor.

Images